Compare commits

...

486 Commits

Author SHA1 Message Date
a205922d06 Update Calico from v3.24.5 to v3.25.0
* https://github.com/poseidon/terraform-render-bootstrap/pull/342
2023-01-24 08:29:08 -08:00
b5ba65d4c2 Update etcd from v3.5.6 to v3.5.7
* https://github.com/etcd-io/etcd/releases/tag/v3.5.7
2023-01-24 08:29:08 -08:00
e696fd2b22 Bump mkdocs-material from 9.0.5 to 9.0.6
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 9.0.5 to 9.0.6.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/9.0.5...9.0.6)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-23 09:08:20 -08:00
3ff9b792ca Bump pymdown-extensions from 9.9.1 to 9.9.2
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.9.1 to 9.9.2.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.9.1...9.9.2)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-23 09:02:30 -08:00
c4f1d2d1c8 Bump pymdown-extensions from 9.9 to 9.9.1
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.9 to 9.9.1.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.9...9.9.1)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-19 08:54:46 -08:00
a1d7b5cd1e Bump mkdocs-material from 9.0.3 to 9.0.5
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 9.0.3 to 9.0.5.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/9.0.3...9.0.5)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-19 08:51:56 -08:00
e7591030e0 Remove Twitter badge from README, we're on the Fediverse now 2023-01-19 08:43:49 -08:00
f2bf5ac3fb Update Kubernetes from v1.26.0 to v1.26.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1261
2023-01-19 08:27:56 -08:00
9cd1c5b17a Bump mkdocs-material from 9.0.0 to 9.0.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 9.0.0 to 9.0.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/9.0.0...9.0.3)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-11 20:48:11 -08:00
d6f739dedb Bump mkdocs-material from 8.5.11 to 9.0.0
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.11 to 9.0.0.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Upgrade guide](https://github.com/squidfunk/mkdocs-material/blob/master/docs/upgrade.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.11...9.0.0)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-02 22:29:06 -08:00
6bb7a36cf2 Bump pygments from 2.13.0 to 2.14.0
Bumps [pygments](https://github.com/pygments/pygments) from 2.13.0 to 2.14.0.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.13.0...2.14.0)

---
updated-dependencies:
- dependency-name: pygments
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2023-01-02 22:20:59 -08:00
0afe9d65ed Update Cilium from v1.12.4 to v1.12.5
* https://github.com/cilium/cilium/releases/tag/v1.12.5
2022-12-21 08:13:35 -08:00
11e540000f Update CHANGES to reiterate Terraform Module Registry deprecation
* Terraform supports sourcing modules from either Git repos or from
their own hosted Terraform Module Registry, introduced a few years ago
* Typhoon docs have always shown using Git-based module sources, not
the Terraform Module Registry. For example, module usage should be
`source = "git::https://github.com/poseidon/typhoon/...` not
`source = poseidon/kubernetes/...`
* Typhoon published Flatcar Linux modules (CoreOS Container Linux at the time)
to Terraform Module Registry, but the approach has a number of drawbacks
for publishers and for users.
  * Terraform's Module Registry requires subtree mirroring Typhoon to special
  terraform-platform-kubernetes repos. This distorts Git history,
  requires special automation, and the registry's naming requirements
  don't allow us to publish our full matrix of modules (Fedora CoreOS
  and Flatcar Linux, across AWS, Azure, GCP, on-prem, and DigitalOcean)
  * Terraform's Module Registry only supports release versions (no commit SHAs
  or forks)
* Ultimately, the Terraform Module Registry limits user flexibility, has
tedious publishing constraints, and introduces centralization where the
current decentralized Git-based approach is simpler and more featureful

Note: This does not affect Terraform _Providers_ like `poseidon/matchbox`
or `poseidon/ct`. For Terraform providers, Terraform's centralized
platform eases provider plugin installation and provides value
2022-12-10 10:00:22 -08:00
d6cbcf9f96 Update Kubernetes from v1.26.0-rc.1 to v1.26.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1260
2022-12-08 08:47:24 -08:00
ce52a2cd35 Update Nginx Ingress and monitoring addon components
* Update ingress-nginx, Prometheus, node-exporter, and
  kube-state-metrics
2022-12-05 09:38:38 -08:00
bd9a908125 Bump mkdocs-material from 8.5.10 to 8.5.11
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.10 to 8.5.11.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.10...8.5.11)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-12-05 09:35:43 -08:00
0dc8740c77 Update Kubernetes from v1.26.0-rc.0 to v1.26.0-rc.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1260-rc1
2022-12-05 09:31:45 -08:00
a9b12b6bca Update Kubernetes from v1.25.4 to v1.26.0-rc.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1260-rc0
2022-11-30 08:47:40 -08:00
d419c58ab1 Add Equinix to the sponsors list
* Thank you Equinix!
2022-11-30 00:30:39 -08:00
da76d32aba Migrate AWS launch configurations to launch templates
* Same features, but AWS will soon require launch templates
* Starting Dec 31, 2022 AWS will not add new instance types
(e.g. graviton 4) to launch configuration support

Rel: https://aws.amazon.com/blogs/compute/amazon-ec2-auto-scaling-will-no-longer-add-support-for-new-ec2-features-to-launch-configurations/
2022-11-30 00:26:03 -08:00
f0e5982b3c Bump pymdown-extensions from 9.8 to 9.9
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.8 to 9.9.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.8...9.9)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-11-29 08:43:17 -08:00
a8990b3045 Fix flannel container image registry location
* https://github.com/poseidon/terraform-render-bootstrap/pull/336
2022-11-23 16:18:30 -08:00
f597f7cda3 Update Prometheus and Grafana addons 2022-11-23 11:06:03 -08:00
b4857c123e Update flannel from v0.15.1 to v0.20.1
* https://github.com/flannel-io/flannel/releases/tag/v0.20.1
2022-11-23 11:03:29 -08:00
50bffaae8f Update etcd from v3.5.5 to v3.5.6 in CHANGES.md 2022-11-23 11:01:24 -08:00
a193762eed Update etcd from v3.5.5 to v3.5.6
* https://github.com/etcd-io/etcd/releases/tag/v3.5.6
2022-11-23 10:59:17 -08:00
adf33df99b Update Cilium from v1.12.3 to v1.12.4
* https://github.com/cilium/cilium/releases/tag/v1.12.4
2022-11-23 10:58:27 -08:00
29a005b7b4 Update CHANGELOG links 2022-11-17 07:55:58 -08:00
ccebc2313d Bump mkdocs-material from 8.5.8 to 8.5.10
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.8 to 8.5.10.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.8...8.5.10)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-11-14 18:29:11 -08:00
1f86592d13 Bump pymdown-extensions from 9.7 to 9.8
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.7 to 9.8.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.7...9.8)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-11-14 18:26:34 -08:00
6a521257d0 Link to new Mastodon accounts
* @typhoon@fosstodon.org will announce Typhoon releases, like the
@typhoon8s Twitter account does today
* @poseidon@fosstodon.org will announce Poseidon Labs news and
general projects, like the @poseidonlabs Twitter account does today
2022-11-10 09:48:30 -08:00
26dbc7e91d Update Kubernetes from v1.25.3 to v1.25.4
* Update Calico from v3.24.3 to v3.24.5
* Update Prometheus and Grafana addons
2022-11-10 09:42:21 -08:00
de668e696a Bump mkdocs-material from 8.5.7 to 8.5.8
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.7 to 8.5.8.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.7...8.5.8)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-11-07 09:45:38 -08:00
d3b2217444 Bump mkdocs from 1.4.1 to 1.4.2
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.4.1 to 1.4.2.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.4.1...1.4.2)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-11-07 09:36:20 -08:00
937acc4b5a Re-enable Graceful Node Shutdown feature
* Kubelet GracefulNodeShutdown works, but only partially handles
gracefully stopping the Kubelet. The most noticeable drawback
is that Completed Pods are left around
* Use a project like poseidon/scuttle or a similar systemd unit
as a snippet to add drain and/or delete behaviors if desired
* This reverts commit 1786e34f33.

Rel:

* https://www.psdn.io/posts/kubelet-graceful-shutdown/
* https://github.com/poseidon/scuttle
2022-11-02 20:49:01 -07:00
b0a6dc8115 Bump mkdocs-material from 8.5.6 to 8.5.7
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.6 to 8.5.7.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.6...8.5.7)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-10-25 19:27:41 -07:00
420ff6ff04 Bump pymdown-extensions from 9.6 to 9.7
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.6 to 9.7.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.6...9.7)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-10-25 17:50:48 -07:00
9b733d79c7 Update Calico v3.24.2 to v3.24.3
* https://github.com/projectcalico/calico/releases/tag/v3.24.3
* Add patch to allow Kubelet kubeconfig to drain nodes if desired
in addition to just deleting them in shutdown integrations. See
https://github.com/poseidon/terraform-render-bootstrap/pull/330
2022-10-23 22:00:15 -07:00
35a9e22b1f Update Calico from v3.24.1 to v3.24.2
* https://github.com/projectcalico/calico/releases/tag/v3.24.2
2022-10-20 09:28:19 -07:00
0f38a6d405 Remove defunct delete-node.service from worker nodes
* delete-node.service used to be used to remove nodes from the
cluster on shutdown, but its long since it last worked properly
* If there is still a desire for this concept, it can be added
with a custom snippet and with a better systemd unit
2022-10-20 08:43:48 -07:00
a535581ef2 Remove unused Wants=network.target from etcd-member
* network.target is a passive unit that's not actually pulled
in by units requiring or wanting it, its only used for shutdown
ordering
> "Services using the network should ... avoid any Wants=network.target or even Requires=network.target"

Rel: https://www.freedesktop.org/wiki/Software/systemd/NetworkTarget/
2022-10-20 08:32:55 -07:00
08d13e7215 Improve release notes slightly with links 2022-10-20 08:30:30 -07:00
3ff2d38fa5 Update Cilium from v1.12.2 to v1.12.3
* https://github.com/cilium/cilium/releases/tag/v1.12.3
2022-10-17 17:25:23 -07:00
d6d8eb8d79 Bump mkdocs from 1.4.0 to 1.4.1
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.4.0 to 1.4.1.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.4.0...1.4.1)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-10-17 16:56:19 -07:00
f04e1d25a8 Add Flatcar Linux ARM64 support on Azure
* Kinvolk now publishes Flatcar Linux images for ARM64
* For now, amd64 image must specify a plan while arm64 images
must NOT specify a plan due to how Kinvolk publishes.

Rel: https://github.com/flatcar/Flatcar/issues/872
2022-10-17 08:36:57 -07:00
b68f8bb2a9 Switch Azure Fedora CoreOS default worker type
* Change default Azure worker_type from Standard_DS1_v2 to Standard_D2as_v5
  * Get 2 VCPU, 7 GiB, 12500Mbps (vs 1 VCPU, 3.5GiB, 750 Mbps)
  * Small increase in pay-as-you-go price ($53.29 -> $62.78)
  * Small increase in spot price ($5.64/mo -> $7.37/mo)
  * Change from Intel to AMD EPYC (`D2as_v5` cheaper than `D2s_v5`)

Rel:

* https://github.com/poseidon/typhoon/pull/1248
* https://learn.microsoft.com/en-us/azure/virtual-machines/dasv5-dadsv5-series#dasv5-series
* https://learn.microsoft.com/en-us/azure/virtual-machines/dv2-dsv2-series#dsv2-series
2022-10-13 21:23:57 -07:00
651151805d Update Kubernetes v1.25.2 to v1.25.3
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1253
2022-10-13 21:02:39 -07:00
8d2c8b8db6 Switch to Flatcar Azure gen2 images and change worker type
* Switch from Azure Hypervisor generation 1 to generation 2
* Change default Azure `worker_type` from Standard_DS1_v2 to Standard_D2as_v5
  * Get 2 VCPU, 7 GiB, 12500Mbps (vs 1 VCPU, 3.5GiB, 750 Mbps)
  * Small increase in pay-as-you-go price ($53.29 -> $62.78)
  * Small increase in spot price ($5.64/mo -> $7.37/mo)
  * Change from Intel to AMD EPYC (`D2as_v5` cheaper than `D2s_v5`)

Notes: Azure makes you accept terms for each plan:

```
az vm image terms accept --publish kinvolk --offer flatcar-container-linux-free --plan stable-gen2
```

Rel:

* https://learn.microsoft.com/en-us/azure/virtual-machines/dasv5-dadsv5-series#dasv5-series
* https://learn.microsoft.com/en-us/azure/virtual-machines/dv2-dsv2-series#dsv2-series
2022-10-13 09:57:52 -07:00
675ac63159 Remove note about not supporting ARM64 with Calico CNI
* Calico v3.22.0 introduced multi-arch container images so Typhoon's
ARM64 support has allowed choosing Calico CNI since Typhoon v1.23.5
2022-10-11 23:21:02 -07:00
b4c8b1729c Switch addons images from k8s.gcr.io to registry.k8s.io
* Switch addon manifests to use the new Kubernetes image registry

Rel:

* https://github.com/poseidon/typhoon/pull/1206
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#moved-container-registry-service-from-k8sgcrio-to-registryk8sio
2022-10-09 16:14:28 -07:00
e82241169a Update Prometheus from v2.38.0 to v2.39.1
* https://github.com/prometheus/prometheus/releases/tag/v2.39.1
2022-10-09 16:12:35 -07:00
ffe4929ff6 Bump mkdocs-material from 8.5.3 to 8.5.6
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.3 to 8.5.6.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.3...8.5.6)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-10-09 14:44:06 -07:00
88b3925318 Bump pymdown-extensions from 9.5 to 9.6
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.5 to 9.6.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.5...9.6)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-10-03 15:34:37 -07:00
29876dc85a Bump mkdocs from 1.3.1 to 1.4.0
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.3.1 to 1.4.0.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.3.1...1.4.0)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-10-03 14:49:24 -07:00
7e29e35457 Bump mkdocs-material from 8.5.2 to 8.5.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.5.2 to 8.5.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.5.2...8.5.3)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-09-28 08:57:03 -07:00
3ee462a24c Update Kubernetes from v1.25.1 to v1.25.2
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1252
2022-09-22 08:15:30 -07:00
f833b7205d Sync recommended Terraform providers in docs 2022-09-20 08:30:15 -07:00
558e293f78 Update Nginx Ingress and Grafana addons 2022-09-20 08:28:30 -07:00
90782ea820 Remove workaround for preventing search . propagation
* Kubelet v1.25.1 has the fix https://github.com/kubernetes/kubernetes/pull/112157
2022-09-19 22:37:02 -07:00
8dc7cc614c Bump mkdocs-material from 8.4.4 to 8.5.2
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.4.4 to 8.5.2.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.4.4...8.5.2)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-09-19 22:16:32 -07:00
74d4d56dbd Remove workaround for v1.25.0 ConfigMap rendering issue
* LocalStorageCapacityIsolationFSQuotaMonitoring was reverted back to
alpha in v1.25.1, so we don't need to explicitly disable it anymore

Rel: https://github.com/kubernetes/kubernetes/issues/112081
2022-09-19 09:10:24 -07:00
5abe84b520 Update etcd from v3.5.4 to v3.5.5
* https://github.com/etcd-io/etcd/blob/main/CHANGELOG/CHANGELOG-3.5.md#v355
2022-09-15 09:01:45 -07:00
951209d113 Update Cilium from v1.12.1 to v1.12.2
* https://github.com/cilium/cilium/releases/tag/v1.12.2
2022-09-15 08:28:37 -07:00
09751cc0e8 Update Kubernetes from v1.25.0 to v1.25.1
* https://github.com/kubernetes/kubernetes/releases/tag/v1.25.1
2022-09-15 08:23:22 -07:00
c14300f0be Update Calico from v3.23.3 to v3.24.1
* https://github.com/projectcalico/calico/releases/tag/v3.24.1
2022-09-14 08:09:38 -07:00
37de9ca2ae Bump mkdocs-material from 8.4.2 to 8.4.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.4.2 to 8.4.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.4.2...8.4.4)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-09-14 07:42:59 -07:00
1786e34f33 Revert Graceful Node Shutdown feature
* Disable Kubelet Graceful Node Shutdown on worker nodes (enabled in
Kubernetes v1.25.0 https://github.com/poseidon/typhoon/pull/1222)
* Graceful node shutdown shutdown allows 30s for critical pods to
shutdown and 15s for regular pods to shutdown before releasing the
inhibitor lock to allow the host to shutdown
* Unfortunately, both pods and the node are shutdown at the same
time at the end of the 45s period without further configuration
options. As a result, regular pods and the node are shutdown at the
same time. In practice, enabling this feature leaves Error or Completed
pods in kube-apiserver state until manually cleaned up. This feature
is not ready for general use
* Fix issue where Error/Completed pods are accumulating whenever any
node restarts (or auto-updates), visible in kubectl get pods
* This issue wasn't apparent in initial testing and seems to only
affect non-critical pods (due to critical pods being killed earlier)
But its very apparent on our real clusters

Rel: https://github.com/kubernetes/kubernetes/issues/110755
2022-09-10 14:58:44 -07:00
5f612c82e2 Update kube-state-metrics and Grafana addons 2022-09-01 08:58:32 -07:00
e60a321185 Sync Terraform providers shown in docs 2022-09-01 08:07:15 -07:00
5ad74883fe Bump mkdocs-material from 8.4.1 to 8.4.2
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.4.1 to 8.4.2.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.4.1...8.4.2)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-09-01 08:06:34 -07:00
4ad473cd3c Add workaround patch to strip "search ." from resolv.conf
* systemd adds "search ." to hosts /run/systemd/resolve/resolv.conf
on hosts with a fqdn hostname
* Kubelet v1.25 began propagating "search ." from the host node
into containers' `/etc/resolv.conf`
* musl-based DNS resolvers don't behave correctly when `search .`
is used in their `/etc/resolv.conf`. This breaks Alpine images
* Adapt the same workaround used by Openshift to strip the "search ."
* This only applies to bare-metal Typhoon nodes (where hostnames are
set to fqdn's), nodes on cloud platforms aren't affected in the
Typhoon configuration

Kubernetes tracking issue: https://github.com/kubernetes/kubernetes/issues/112135

Rel:

* https://github.com/systemd/systemd/pull/17201
* https://github.com/kubernetes/kubernetes/pull/109441
* https://github.com/coreos/fedora-coreos-tracker/issues/1287
* https://github.com/openshift/okd-machine-os/pull/159
2022-08-31 08:05:45 -07:00
393a38deff Configure Graceful Node Shutdown and lengthen max inhibitor delay
* Configure Kubelet Graceful Node Shutdown to detect system shutdown
events and stop running containers gracefully when possible
* Allow up to 30s for critical pods to gracefully shutdown
* Allow up to 15s for regular pods to gracefully shutdown
* Node will be marked as NotReady promptly, instead of having to
wait for health checks
* Kubelet uses systemd inhibitor locks to delay shutdown for a limited
number of seconds
* Raise the default max inhibitor time from 5s to 45s

Verify systemd inhibitor locks are present:

```
sudo systemd-inhibit --list
WHO     UID USER PID  COMM    WHAT     WHY                                        MODE
kubelet 0   root 4581 kubelet shutdown Kubelet needs time to handle node shutdown delay
```

Tail journal logs and then shutdown a node via systemctl reboot
or via the cloud console to watch container shutdown

Rel:

* https://kubernetes.io/blog/2021/04/21/graceful-node-shutdown-beta/
* https://kubernetes.io/docs/reference/config-api/kubelet-config.v1beta1/
* https://github.com/kubernetes/kubernetes/issues/107043
* https://github.com/coreos/fedora-coreos-tracker/issues/821
* https://www.freedesktop.org/software/systemd/man/systemd-inhibit.html
* https://github.com/kubernetes/kubernetes/blob/release-1.24/pkg/kubelet/nodeshutdown/nodeshutdown_manager_linux.go
* https://github.com/godbus/dbus/blob/master/conn.go
2022-08-28 10:37:33 -07:00
76d92e9c2d Change podman log-driver from journald to k8s-file
* When podman runs the Kubelet container, logging to journald means
log lines are duplicated in the journal. journalctl -u kubelet shows
Kubelet's logs and the same log messages from podman. Using the
k8s-file driver alleviates this problem
* Fix Kubelet and etcd-member logs to be more readable and reduce
unneccessary Kubelet log volume
2022-08-27 17:15:22 -07:00
275fc0f9e8 Disable LocalStorageCapacityIsolationFSQuotaMonitoring feature
* Kubernetes v1.25.0 moved the LocalStorageCapacityIsolationFSQuotaMonitoring
feature from alpha to beta, but it breaks Kubelet updating ConfigMaps in
Pods, as shown by conformance tests
* Kubernetes is rolling LocalStorageCapacityIsolationFSQuotaMonitoring back
to alpha so its not enabled by default, but that will require a release
* Disable the feature gate directly as a workaround for now to make
Kubernetes v1.25.0 usable

```
FailedMount: MountVolume.SetUp failed for volume "configmap-volume" : requesting quota on existing directory /var/lib/kubelet/pods/f09fae17-ff16-4a05-aab3-7b897cb5b732/volumes/kubernetes.io~configmap/configmap-volume but different pod 673ad247-abf0-434e-99eb-1c3f57d7fdaa a4568e94-2b2d-438f-a4bd-c9edc814e478
```

Rel:

* https://github.com/kubernetes/kubernetes/pull/112076
* https://github.com/kubernetes/kubernetes/pull/107329
2022-08-27 09:49:35 -07:00
3fb59a3289 Migrate most Kubelet flags to KubeletConfiguration file
* Add a KubeletConfiguration file to replace most Kubelet
flags, to prepare for upcoming changes
* Pass Kubelet the --config flag to specify the location of
the KubeletConfiguration
* Remove flsgs / configuration where it matches the defaults
  * Remove --cgroups-per-qos, defaults to true
  * Remove --container-runtime, defaults to remote
  * Remove enforce-node-allocatable=pods, defaults to pods

Rel:

* https://kubernetes.io/docs/reference/command-line-tools-reference/kubelet/
* https://kubernetes.io/docs/reference/config-api/kubelet-config.v1beta1/
2022-08-27 09:28:15 -07:00
a31dbceac6 Update Kubernetes from v1.24.4 to v1.25.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md
2022-08-25 09:18:14 -07:00
1dcf56127b Bump mkdocs-material from 8.4.0 to 8.4.1
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.4.0 to 8.4.1.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.4.0...8.4.1)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-08-23 08:53:12 -07:00
bf06412dfd Update Prometheus and Grafana addons 2022-08-21 08:56:00 -07:00
505818b7d5 Update docs showing the terraform plan resources count
* Although I don't plan to keep these in sync, some users are
confused when the docs don't match the actual resource count
2022-08-21 08:52:35 -07:00
0d27811265 Update recommended Terraform provider versions 2022-08-18 09:08:55 -07:00
c13d060b38 Add docs for GCP MIG update and AWS instance refresh
* Document that worker instances are rolling replaced when
changes to their configuration are applied
2022-08-18 09:02:38 -07:00
e87d5aabc3 Adjust Google Cloud worker health checks to use kube-proxy healthz
* Change the workers managed instance group to health check nodes
via HTTP probe of the kube-proxy port 10256 /healthz endpoints
* Advantages: kube-proxy is a lower value target (in case there
were bugs in firewalls) that Kubelet, its more representative than
health checking Kubelet (Kubelet must run AND kube-proxy Daemonset
must be healthy), and its already used by kube-proxy liveness probes
(better discoverability via kubectl or alerts on pods crashlooping)
* Another motivator is that GKE clusters also use kube-proxy port
10256 checks to assess node health
2022-08-17 20:50:52 -07:00
760b4cd5ee Update Kubernetes from v1.24.3 to v1.24.4
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1244
2022-08-17 20:09:30 -07:00
fcd8ff2b17 Update Cilium from v1.12.0 to v1.12.1
* https://github.com/cilium/cilium/releases/tag/v1.12.1
2022-08-17 08:53:56 -07:00
ef2d2af0c7 Bump mkdocs-material from 8.3.9 to 8.4.0
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.3.9 to 8.4.0.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.3.9...8.4.0)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-08-16 08:29:51 -07:00
8e2027ed2d Bump pygments from 2.12.0 to 2.13.0
Bumps [pygments](https://github.com/pygments/pygments) from 2.12.0 to 2.13.0.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.12.0...2.13.0)

---
updated-dependencies:
- dependency-name: pygments
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-08-16 08:26:45 -07:00
52427a4271 Refresh instances in autoscaling group when launch configuration changes
* Changes to worker launch configurations start an autoscaling group instance
refresh to replace instances
* Instance refresh creates surge instances, waits for a warm-up period, then
deletes old instances
* Changing worker_type, disk_*, worker_price, worker_target_groups, or Butane
worker_snippets on existing worker nodes will replace instances
* New AMIs or changing `os_stream` will be ignored, to allow Fedora CoreOS or
Flatcar Linux to keep themselves updated
* Previously, new launch configurations were made in the same way, but not
applied to instances unless manually replaced
2022-08-14 21:43:49 -07:00
20b76d6e00 Roll instance template changes to worker managed instance groups
* When a worker managed instance group's (MIG) instance template
changes (including machine type, disk size, or Butane snippets
but excluding new AMIs), use Google Cloud's rolling update features
to ensure instances match declared state
* Ignore new AMIs since Fedora CoreOS and Flatcar Linux nodes
already auto-update and reboot themselves
* Rolling updates will create surge instances, wait for health
checks, then delete old instances (0 unavilable instances)
* Instances are replaced to ensure new Ignition/Butane snippets
are respected
* Add managed instance group autohealing (i.e. health checks) to
ensure new instances' Kubelet is running

Renames

* Name apiserver and kubelet health checks consistently
* Rename MIG from `${var.name}-worker-group` to `${var.name}-worker`

Rel: https://cloud.google.com/compute/docs/instance-groups/rolling-out-updates-to-managed-instance-groups
2022-08-14 13:06:53 -07:00
6facfca4ed Switch Kubernetes image registry from k8s.gcr.io to registry.k8s.io
* Announce: https://groups.google.com/g/kubernetes-sig-testing/c/U7b_im9vRrM

Rel: https://github.com/poseidon/terraform-render-bootstrap/pull/319
2022-08-13 16:16:21 -07:00
ed8c6a5aeb Upgrade CoreDNS from v1.8.5 to v1.9.3
Rel: https://github.com/poseidon/terraform-render-bootstrap/pull/318
2022-08-13 15:43:03 -07:00
003af72cc8 Rename google-cloud/fedora-coreos/kubernetes/workers fcc to butane
* Should have been part of https://github.com/poseidon/typhoon/pull/1203
2022-08-13 15:40:16 -07:00
b321b90a4f Update Grafana from v9.0.6 to v9.0.7 2022-08-13 15:39:44 -07:00
e5d0e2d48b Rename Fedora CoreOS fcc directory to butane
* Align both Fedora CoreOS and Flatcar Linux keeping Butane
Configs in a directory called butane
2022-08-10 09:10:18 -07:00
679f8b878f Update Grafana from v9.0.5 to v9.0.6 2022-08-10 08:23:04 -07:00
87a8278c9d Improve AWS autoscaling group and launch config names
* Rename launch configuration to use a name_prefix named after the
cluster and worker to improve identifiability
* Shorten AWS autoscaling group name to not include the launch config
id. Years ago this used to be needed to update the ASG but the AWS
provider detects changes to the launch configuration just fine
2022-08-08 20:46:08 -07:00
93b7f2554e Remove ineffective iptables-legacy.stamp
* Typhoon Fedora CoreOS is already using iptables nf_tables since
F36. The file to pin to legacy iptables was renamed to
/etc/coreos/iptables-legacy.stamp
2022-08-08 20:27:21 -07:00
62d47ad3f0 Update Cilium from v1.11.7 to v1.12.0
* https://github.com/cilium/cilium/releases/tag/v1.12.0
2022-08-08 19:59:03 -07:00
6eb7861f96 Update Grafana liveness and readiness probes
* Use the liveness and readiness probes that Grafana recommends
* Update Grafana from v9.0.3 to v9.0.5
2022-08-08 09:22:44 -07:00
ffbacbccf7 Update node-exporter DaemonSet to fix permission denied
* Add toleration to run node-exporter on controller nodes
* Add HostToContainer mount propagation and security context group
settings from upstream
* Fix SELinux denied accessing /host/proc/1/mounts. The mounts file
is has an SELinux type attribute init_t, but that won't allow running
the node-exporter binary so we have to use spc_t. This should be more
targeted at just the SELinux issue than making the Pod privileged
* Remove excluded mount points and filesystem types, the defaults are
https://github.com/prometheus/node_exporter/blob/v1.3.1/collector/filesystem_linux.go#L35

```
caller=collector.go:169 level=error msg="collector failed" name=filesystem duration_seconds=0.000666766 err="open /host/proc/1/mounts: permission denied"
```

```
[ 3664.880899] audit: type=1400 audit(1659639161.568:4400): avc:  denied  { search } for  pid=28325 comm="node_exporter" name="1" dev="proc" ino=22542 scontext=system_u:system_r:container_t:s0 tcontext=system_u:system_r:init_t:s0 tclass=dir permissive=0
```
2022-08-08 09:19:46 -07:00
16c2785878 Update docs on using Butane snippets for customization
* Typhoon now consistently uses Butane Configs for snippets
(variant `fcos` or `flatcar`). Previously snippets were either
Butane Configs (on FCOS) or Container Linux Configs (on Flatcar)
* Update docs on uploading Flatcar Linux DigitalOcean images
* Update docs on uploading Fedora CoreOS Azure images
2022-08-03 20:28:53 -07:00
4a469513dd Migrate Flatcar Linux from Ignition spec v2.3.0 to v3.3.0
* Requires poseidon v0.11+ and Flatcar Linux 3185.0.0+ (action required)
* Previously, Flatcar Linux configs have been parsed as Container
Linux Configs to Ignition v2.2.0 specs by poseidon/ct
* Flatcar Linux starting in 3185.0.0 now supports Ignition v3.x specs
(which are rendered from Butane Configs, like Fedora CoreOS)
* poseidon/ct v0.11.0 adds support for the flatcar Butane Config
variant so that Flatcar Linux can use Ignition v3.x

Rel:

* [Flatcar Support](https://flatcar-linux.org/docs/latest/provisioning/ignition/specification/#ignition-v3)
* [poseidon/ct support](https://github.com/poseidon/terraform-provider-ct/pull/131)
2022-08-03 08:32:52 -07:00
47d8431fe0 Fix bug provisioning multi-controller clusters on Google Cloud
* Google Cloud Terraform provider resource google_dns_record_set's
name field provides the full domain name with a trailing ".". This
isn't a new behavior, Google has behaved this way as long as I can
remember
* etcd domain names are passed to the bootstrap module to generate
TLS certificates. What seems to be new(ish?) is that etcd peers
see example.foo and example.foo. as different domains during TLS
SANs validation. As a result, clusters with multiple controller
nodes fail to run etcd-member, which manifests as cluster provisioning
hanging. Single controller/master clusters (default) are unaffected
* Fix etcd-member.service error in multi-controller clusters:

```
"error":"x509: certificate is valid for conformance-etcd0.redacted.,
conform-etcd1.redacted., conform-etcd2.redacted., not conform-etcd1.redacted"}
```
2022-08-02 20:21:02 -07:00
256b87812e Remove Terraform template provider dependency
* Use Terraform builtin templatefile functionality
* Remove dependency on deprecated Terraform template provider

Rel:

* https://registry.terraform.io/providers/hashicorp/template/2.2.0
* https://github.com/poseidon/terraform-render-bootstrap/pull/293
2022-08-02 18:15:03 -07:00
ca6eef365f Add badges to README 2022-07-31 18:03:09 -07:00
c6794f1007 Update Calico from v3.23.1 to v3.23.3
* https://github.com/projectcalico/calico/releases/tag/v3.23.3
2022-07-30 18:15:33 -07:00
de6f27e119 Update FCOS iPXE initrd and kernel arg settings
* Add initrd=main kernel argument for UEFI
* Switch to using the coreos.live.rootfs_url kernel argument
instead of passing the rootfs as an appended initrd
* Remove coreos.inst.image_url kernel argument since coreos-installer
now defaults to installing from the embedded live system
* Remove rd.neednet=1 and dhcp=ip kernel args that aren't needed
* Remove serial console kernel args by default (these can be
added via var.kernel_args if needed)

Rel:
* https://github.com/poseidon/matchbox/pull/972 (thank you @bgilbert)
* https://github.com/poseidon/matchbox/pull/978
2022-07-30 16:27:08 -07:00
6a9c32d3a9 Migrate from internal hosting to GitHub pages
* Add Twitter card customizations that have been kept in
an internal fork
* Add CNAME needed for GitHub pages
2022-07-27 21:56:42 -07:00
a7e9e423f5 Bump mkdocs from 1.3.0 to 1.3.1
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.3.0 to 1.3.1.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.3.0...1.3.1)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-07-21 09:07:21 -07:00
83236eab57 Add table of details about static Pods
* Also remote outdated mentions of rkt-fly
2022-07-21 09:03:27 -07:00
7f445b0dba Add release note about master to main branch rename
* Update Terraform provider versions
2022-07-19 18:12:37 -07:00
f42b45451b Update Cilium from v1.11.6 to v1.11.7
* https://github.com/cilium/cilium/releases/tag/v1.11.7
2022-07-19 09:06:15 -07:00
767a653baa Update Prometheus, Grafana, and ingress-nginx addons
* Update ingress-nginx RBAC Role to include coordination.k8s.io leases
permissions that are required with ingress-nginx v1.3.0
2022-07-15 20:19:12 -07:00
0db5f86110 Update Kubernetes from v1.24.2 to v1.24.3
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1243
2022-07-13 20:59:15 -07:00
4908fdd247 Bump mkdocs-material from 8.3.8 to 8.3.9
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.3.8 to 8.3.9.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.3.8...8.3.9)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-07-05 17:54:48 -07:00
42bf82b325 Update Prometheus and Grafana addons
* Bump recommended Terraform provider versions
2022-07-02 11:28:34 -07:00
61cbfc044d Bump mkdocs-material from 8.3.6 to 8.3.8
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.3.6 to 8.3.8.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.3.6...8.3.8)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-06-29 08:11:42 -07:00
07df0c2552 Add warning about Terraform AWS provider version
* Sync Terraform provider versions with those used internally
2022-06-23 21:31:20 -07:00
45d6ff2e38 Bump mkdocs-material from 8.3.4 to 8.3.6
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.3.4 to 8.3.6.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.3.4...8.3.6)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-06-20 11:46:24 -07:00
8398182956 Update Cilium and Calico CNI providers
* Update Cilium from v1.11.5 to v1.11.6
* Update Calico from v3.22.2 to v3.23.1
2022-06-18 19:29:01 -07:00
6d6b48b201 Update Kubernetes from v1.24.1 to v1.24.2
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1242
2022-06-18 18:35:42 -07:00
2a8915fee9 Update Prometheus, kube-state-metrics, and Grafana addons
* Update monitoring addons
2022-06-18 18:32:17 -07:00
337b1eef3a Bump mkdocs-material from 8.3.2 to 8.3.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.3.2 to 8.3.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.3.2...8.3.4)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-06-15 22:01:42 -07:00
fe28bd0783 Bump pymdown-extensions from 9.3 to 9.5
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.3 to 9.5.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.3...9.5)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-06-07 08:56:22 -07:00
5e2f9a5c44 Bump mkdocs-material from 8.2.16 to 8.3.2
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.16 to 8.3.2.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.16...8.3.2)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-06-07 08:52:40 -07:00
31c7f0ba0e Update nginx-ingress addon from v1.2.0 to v1.2.1
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.2.1
2022-05-31 16:37:57 +01:00
b8549a1e32 Update Cilium from v1.11.4 to v1.11.5
* https://github.com/poseidon/terraform-render-bootstrap/pull/309
2022-05-31 15:23:07 +01:00
8e8bf305c3 Update Prometheus and Grafana addons 2022-05-31 14:29:55 +01:00
a447494ccd Bump mkdocs-material from 8.2.15 to 8.2.16
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.15 to 8.2.16.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.15...8.2.16)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-05-31 10:30:34 +01:00
c5573199db Update Kubernetes from v1.24.0 to v1.24.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1241
2022-05-28 09:39:14 +01:00
0be171cde7 Bump mkdocs-material from 8.2.14 to 8.2.15
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.14 to 8.2.15.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.14...8.2.15)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-05-27 10:02:31 +01:00
e3b1e6c52e Bump mkdocs-material from 8.2.13 to 8.2.14
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.13 to 8.2.14.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.13...8.2.14)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-05-09 18:48:45 -07:00
b0e0b132e4 Update Kubernetes from v1.23.6 to v1.24.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1240
2022-05-04 08:27:14 -07:00
4fba09e8f8 Bump mkdocs-material from 8.2.11 to 8.2.13
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.11 to 8.2.13.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.11...8.2.13)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-05-03 07:42:29 -07:00
02f78fbd1a Update Grafana from v8.4.5 to v8.5.1 2022-05-02 08:19:41 -07:00
a122867748 Update nginx-ingress, Prometheus, and Grafana addons
* Sync addons with versions used in Poseidon
2022-04-27 21:02:32 -07:00
91b38bf3fd Update etcd from v3.5.2 to v3.5.4
* https://github.com/etcd-io/etcd/releases/tag/v3.5.4
2022-04-27 20:57:02 -07:00
9a4887d028 Add bind mounts for selinux to fcos kubelets
fixes #1123

Enables the use of CSI drivers with a StorageClass that lacks an explicit context mount option. In cases where the kubelet lacks mounts for `/etc/selinux` and `/sys/fs/selinux`, it is unable to set the `:Z` option for the CRI volume definition automatically. See [KEP 1710](https://github.com/kubernetes/enhancements/blob/master/keps/sig-storage/1710-selinux-relabeling/README.md#volume-mounting) for more information on how SELinux is passed to the CRI by Kubelet.

Prior to this change, a not-explicitly-labelled mount would have an `unlabeled_t` SELinux type on the host. Following this change, the Kubelet and CRI work together to dynamically relabel mounts that lack an explicit context specification every time it is rebound to a pod with SELinux type `container_file_t` and appropriate context labels to match the specifics for the pod it is bound to. This enables applications running in containers to consume dynamically provisioned storage on SELinux enforcing systems without explicitly setting the context on the StorageClass or PersistentVolume.
2022-04-26 21:33:26 -07:00
35bca6df90 Bump mkdocs-material from 8.2.9 to 8.2.11
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.9 to 8.2.11.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.9...8.2.11)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-04-25 19:02:15 -07:00
d7f55c4e46 Remove use of deprecated key_algorithm field in TLS assets
* Fixes warning about use of deprecated field `key_algorithm` in
the `hashicorp/tls` provider. The key algorithm can now be inferred
directly from the private key so resources don't have to output
and pass around the algorithm
2022-04-20 19:52:03 -07:00
80c6e2e7e6 Update Kubernetes from v1.23.5 to v1.23.6
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1236
2022-04-20 19:39:05 -07:00
fddd8ac69d Fix Flatcar Linux nodes on Google Cloud not ignoring image changes
* Add `boot_disk[0].initialize_params` to the ignored fields for the
controller nodes
* Nodes will auto-update, Terraform should not attempt to delete and
recreate nodes (especially controllers!). Lack of this ignore causes
Terraform to propose deleting controller nodes when Flatcar Linux
releases new images
* Matches the configuration on Typhoon Fedora CoreOS (which does not
have the issue)
2022-04-20 18:53:00 -07:00
2f7d2a92e0 Update Cilium and Calico CNI providers
* Update Cilium from v1.11.3 to v1.11.4
* Update Calico from v3.22.1 to v3.22.2
2022-04-19 08:28:52 -07:00
6cd6bb38de Bump mkdocs-material from 8.2.8 to 8.2.9
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.8 to 8.2.9.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.8...8.2.9)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-04-12 07:53:43 -07:00
d91408258b Update nginx-ingress, Prometheus, and Grafana addons 2022-04-04 08:53:29 -07:00
2df1873b7f Update Cilium from v1.11.2 to v1.11.3
* https://github.com/cilium/cilium/releases/tag/v1.11.3
2022-04-01 16:44:30 -07:00
93ebfc7dd0 Allow upgrading Azure Terraform Provider to v3.x
* Change subnet references to source and destinations prefixes
(plural)
* Remove references to a resource group in some load balancing
components, which no longer require it (inferred)
* Rename `worker_address_prefix` output to `worker_address_prefixes`
2022-04-01 16:36:53 -07:00
5365ce8204 Mount /etc/machine-id from host into Kubelet
* Kubelet node's System UUID can be detected from the sysfs
filesystem without a host mount, but if you need to distinguish
between the host's machine-id and SystemUUID
* On cloud platforms, MachineID and SystemUUID are identical,
but on bare-metal the two differ
2022-04-01 16:32:06 -07:00
2ad33cebaf Bump mkdocs-material from 8.2.5 to 8.2.8
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.5 to 8.2.8.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.5...8.2.8)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-03-28 10:20:10 -07:00
a26abcf5b1 Bump mkdocs from 1.2.3 to 1.3.0
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.2.3 to 1.3.0.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.2.3...1.3.0)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-03-28 10:07:34 -07:00
b8c4629548 Bump pymdown-extensions from 9.2 to 9.3
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.2 to 9.3.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.2...9.3)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-03-21 10:35:37 -07:00
c5814308ab Refresh Terraform providers shown in docs
* Update a few OS component details
2022-03-19 19:30:43 -07:00
b47edca6be Refresh Prometheus rules and Grafana dashboards
* Update Prometheus rules and Grafana dashboards
* Add new networking dashboards
2022-03-19 17:08:00 -07:00
e61d4b92da Update Kubernetes from v1.23.4 to v1.23.5
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1235
2022-03-16 21:01:41 -07:00
dca745fa4a Update monitoring addon components
* Update Prometheus, kube-state-metrics, and Grafana
2022-03-11 11:50:16 -08:00
661347fa71 Update nginx-ingress from v1.1.1 to v1.1.2
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.1.2
2022-03-11 11:42:33 -08:00
69770b4827 Update Calico from v3.21.2 to v3.22.1
* https://github.com/projectcalico/calico/releases/tag/v3.22.1
* Fix https://github.com/projectcalico/calico/issues/5011
2022-03-11 11:22:29 -08:00
f797f97675 Update Cilium from v1.11.1 to v1.11.2
* https://github.com/cilium/cilium/releases/tag/v1.11.2
2022-03-11 10:08:24 -08:00
9fe0f2fa6c Bump mkdocs-material from 8.2.3 to 8.2.5
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.3 to 8.2.5.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.3...8.2.5)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-03-11 09:57:31 -08:00
268648c146 Bump mkdocs-material from 8.2.1 to 8.2.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.2.1 to 8.2.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.2.1...8.2.3)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-02-28 09:36:48 -08:00
6cf40722de Revert kube-state-metrics upgrade
* kube-state-metrics:v2.4.0 isn't published, skip it
2022-02-21 19:57:47 -08:00
c230cdec46 Update Grafana and kube-state-metrics addons 2022-02-21 19:36:16 -08:00
cabf5b2c34 Update recommended Terraform provider versions
* Update poseidon/ct version from v0.9.1 to v0.10.0
* Update aws provider to v4.x series
2022-02-21 19:27:54 -08:00
ba8a951863 Bump mkdocs-material from 8.1.11 to 8.2.1
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.11 to 8.2.1.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.11...8.2.1)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-02-21 09:53:27 -08:00
9aa99f1996 Allow upgrading AWS Terraform provider to v4.x
* https://github.com/hashicorp/terraform-provider-aws/releases/tag/v4.0.0
2022-02-17 09:35:15 -08:00
fc38ba45b1 Update Kubernetes from v1.23.3 to v1.23.4
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1234
2022-02-17 09:00:31 -08:00
28a42238c4 Update nginx-ingress, Prometheus, and Grafana addons
* Align `nginx-ingress` `--controller-class` with `IngressClass`
to provide a better example (e.g. if extended to multiple ingress
controllers)
2022-02-17 08:58:29 -08:00
de9b30a587 Bump mkdocs-material from 8.1.10 to 8.1.11
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.10 to 8.1.11.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.10...8.1.11)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-02-14 11:11:06 -08:00
affb40d59b Bump pymdown-extensions from 9.1 to 9.2
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.1 to 9.2.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.1...9.2)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-02-14 11:10:56 -08:00
15ac49b34d Bump mkdocs-material from 8.1.9 to 8.1.10
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.9 to 8.1.10.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.9...8.1.10)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-02-07 09:49:24 -08:00
6c70d06937 Update etcd from v3.5.1 to v3.5.2
* https://github.com/etcd-io/etcd/releases/tag/v3.5.2
2022-02-07 08:10:17 -08:00
cf4beeba34 Change default CNI provider from Calico to Cilium
* Cilium (v1.8) was added to Typhoon in v1.18.5 in June 2020
and its become more impressive since then. Its currently the
leading CNI provider choice.
* Calico has grown complex, has lots of CRDs, masks its
management complexity with an operator (which we won't use),
doesn't provide multi-arch images, and hasn't been compatible
with Kubernetes v1.23 (with ipvs) for several releases.
* Both have CNCF conformance quirks (flannel used for conformance),
but that's not the main factor in choosing the default
2022-02-07 08:07:00 -08:00
10b4ba14b6 Bump mkdocs-material from 8.1.8 to 8.1.9
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.8 to 8.1.9.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.8...8.1.9)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-02-01 10:26:39 -08:00
e06ee042ee Switch to using Flatcar Linux images on Google Cloud
* Use the official Kinvolk Flatcar Linux image on Google Cloud
* Change `os_image` from a custom image name to `flatcar-stable`
(default), `flatcar-beta`, or `flatcar-alpha` (**action required**)
* Change `os_image` from a required to an optional variable
* Promote Typhoon on Flatcar Linux / Google Cloud to stable
* Remove docs about needing to upload a Flatcar Linux image
manually on Google Cloud and drop support for custom images
2022-01-28 21:04:10 -08:00
a527f73f5a Update Kubernetes from v1.23.2 to v1.23.3
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1233
2022-01-27 09:23:37 -08:00
c21a0479c0 Bump mkdocs-material from 8.1.7 to 8.1.8
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.7 to 8.1.8.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.7...8.1.8)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-01-27 09:02:30 -08:00
f614c538cf Update Terraform provider recommendations in docs 2022-01-19 21:16:37 -08:00
3da8c1575c Update nginx-ingress and Grafana addons 2022-01-19 21:09:21 -08:00
dedd17d085 Upgrade to DigitalOcean Terraform provider v2.x
* Remove deprecated `private_networking` parameter
2022-01-19 18:32:17 -08:00
e274a451ff Update Kubernetes from v1.23.1 to v1.23.2
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1232
2022-01-19 17:59:49 -08:00
b2e36947ab Bump mkdocs-material from 8.1.5 to 8.1.7
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.5 to 8.1.7.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.5...8.1.7)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-01-19 16:42:21 -08:00
5af0a5c5b9 Add Flatcar Linux ARM64 examples
* Fix content tabs format for switching between example
code blocks
2022-01-14 12:52:45 -08:00
2265ab5375 Remove Kubelet --network-plugin=cni flag
* Now that `docker-shim` is no longer used, the Kubelet flag
is no longer needed and will be removed in v1.24
2022-01-14 10:43:07 -08:00
08ea9776f3 Mask docker.service to prevent socket activation
* Kubelet now uses `containerd` as the container runtime, but
`docker.service` still starts when `docker.sock` is probed bc
the service is socket activated. Prevent this by masking the
`docker.service` unit
2022-01-14 10:31:47 -08:00
2e8bc99164 Remove template provider usage from terraform-render-bootstrap 2022-01-14 10:27:24 -08:00
b18b0a9f3d Remove unused ETCD_UNSUPPORTED_ARCH variable
* etcd used to require a special variable to use the arm64
container image, but this is no longer required
2022-01-14 10:25:45 -08:00
beb9f1477a Add experimental Flatcar Linux arm64 support on AWS
* Add `arch` variable to Flatcar Linux AWS `kubernetes` and
`workers` modules. Accept `amd64` (default) or `arm64` to support
native arm64/aarch64 clusters or mixed/hybrid clusters with arm64
workers
* Requires `flannel` or `cilium` CNI

Similar to https://github.com/poseidon/typhoon/pull/875
2022-01-14 10:24:48 -08:00
f544a9c71f Switch Fedora CoreOS from docker-shim to containerd
* Migrate from `docker-shim` to `containerd` in preparation
for Kubernetes v1.24.0 dropping `docker-shim` support
* Much consideration was given to the container runtime
choice. https://github.com/poseidon/typhoon/issues/899
provides relevant rationales
2022-01-13 09:17:29 -08:00
415b7fa19a Bump pygments from 2.11.1 to 2.11.2
Bumps [pygments](https://github.com/pygments/pygments) from 2.11.1 to 2.11.2.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.11.1...2.11.2)

---
updated-dependencies:
- dependency-name: pygments
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-01-13 09:03:25 -08:00
d0c29099ba Bump mkdocs-material from 8.1.4 to 8.1.5
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.4 to 8.1.5.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.4...8.1.5)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-01-11 20:42:31 -08:00
30e4070474 Bump mkdocs-material from 8.1.3 to 8.1.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.3 to 8.1.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.3...8.1.4)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-01-03 10:53:23 -08:00
43f6a19060 Bump pygments from 2.10.0 to 2.11.1
Bumps [pygments](https://github.com/pygments/pygments) from 2.10.0 to 2.11.1.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.10.0...2.11.1)

---
updated-dependencies:
- dependency-name: pygments
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2022-01-03 10:48:25 -08:00
50215e373b Add Prometheus config for monitoring Kubernetes Ingress
* Allow Kubernetes Ingress resources to be probed via Blackbox
Exporter (if present) if annotated `prometheus.io/probe: "true"`
* Fix probes of Services via Blackbox Exporter. Require Blackbox
Exporter to be deployed in the same `monitoring` namespace, be
named `blackbox-exporter`, and use port 8080
2021-12-29 11:57:50 -08:00
a9f9c59b91 Configure Prometheus to allow a custom scrape query param
* Set `prometheus.io/param` on a Kubernetes Service to scrape
the service endpoints and pass a custom query parameter
* For example, scrape Consul with `?format=prometheus`

```yaml
kind: Service
metadata:
  annotations:
    prometheus.io/scrape: 'true'
    prometheus.io/port: '8500'
    prometheus.io/path: /v1/agent/metrics
    prometheus.io/param: format=prometheus
```
2021-12-29 11:47:10 -08:00
6ed048eb65 Workaround Terraform v1.1 file provisioner regression
* Terraform v1.1 changed the behavior of provisioners and
`remote-exec` in a way that breaks support for expansions
in commands (including file provisioner, where `destination`
is part of an `scp` command)
* Terraform will likely revert the change eventually, but I
suspect it will take a while
* Instead, we can stop relying on Terraform's expansion
behavior. `/home/core` is a suitable choice for `$HOME` on
both Flatcar Linux and Fedora CoreOS (harldink `/var/home/core`)

Rel: https://github.com/hashicorp/terraform/issues/30243
2021-12-28 13:25:23 -08:00
ce7b2fa21f Bump mkdocs-material from 8.1.1 to 8.1.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.1.1 to 8.1.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.1.1...8.1.3)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-12-23 14:33:26 -08:00
9e3807798f Update Kubernetes from v1.23.0 to v1.23.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1231
2021-12-20 08:36:19 -08:00
ef9c6aa423 Switch Flatcar Linux to using containerd CRI
* Use containerd as the Kubernetes Container Runtime
2021-12-15 08:42:13 -08:00
bb5e5811ec Update Prometheus and Grafana addons 2021-12-15 08:16:46 -08:00
16aa997604 Fix Azure backend_address_pool_id deprecation warning
* Change to `backend_address_pool_ids` list
2021-12-14 10:26:08 -08:00
fb6650b06b Bump mkdocs-material from 8.0.4 to 8.1.1
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.0.4 to 8.1.1.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.0.4...8.1.1)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-12-13 17:44:02 -08:00
43c6558aaf Update nginx-ingress and monitoring addons 2021-12-10 11:29:49 -08:00
125008fbb3 Update Cilium from v1.10.5 to v1.11.0
* https://github.com/cilium/cilium/releases/tag/v1.11.0
2021-12-10 11:26:05 -08:00
136107b448 Set Kubelet resolver config to /run/systemd/resolve/resolv.conf
* Both Flatcar Linux and Fedora CoreOS use systemd-resolved,
but they setup /etc/resolv.conf symlinks differently
* Prefer using /run/systemd/resolve/resolv.conf directly, which
also updates to reflect runtime changes (e.g. resolvectl)
2021-12-10 08:22:30 -08:00
e97c1cc9e5 Enable Kubernetes aggregation by default
* Change `enable_aggregation` default from false to true
* These days, Kubernetes control plane components emit annoying
messages related to assumptions baked into the Kubernetes API
Aggregation Layer if you don't enable it. Further the conformance
tests force you to remember to enable it if you care about passing
those
* This change is motivated by eliminating annoyances, rather than
any enthusiasm for Kubernetes' aggregation features

Rel: https://kubernetes.io/docs/concepts/extend-kubernetes/api-extension/apiserver-aggregation/
2021-12-09 17:30:35 -08:00
39da5b53f5 Update operating system notes in architecture docs 2021-12-09 17:21:24 -08:00
41f739891b Normalize CA certs mounts in static Pods and kube-proxy
* Mount both /etc/ssl/certs and /etc/pki into control plane static
pods and kube-proxy, rather than choosing one based a variable
(set based on Flatcar Linux or Fedora CoreOS)
* Remove deprecated `--port` from `kube-scheduler` static Pod
2021-12-09 09:56:37 -08:00
861021ee98 Update Kubernetes from v1.22.4 to v1.23.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1230
* With Calico, add missing caliconodestatuses CRD added in v3.21.0
https://github.com/poseidon/terraform-render-bootstrap/pull/289
2021-12-09 09:28:41 -08:00
9d583ab377 Fix null provider version constraint on Google Cloud
* Part of https://github.com/poseidon/typhoon/pull/1074
2021-12-08 14:06:38 -08:00
c1d28e6f61 Change default disk_iops on Flatcar Linux
* Same as #1073, but for Flatcar Linux on AWS as well
2021-12-07 16:52:55 -08:00
a8fd21d250 Update minimum Terraform provider versions
* Update `null` provider to allow use of v3.1.x releases,
instead of being stuck on v2.1.2
* Update min versions in terraform-render-boostrap
https://github.com/poseidon/terraform-render-bootstrap/pull/287
* Document the recommended versions of Terraform cloud providers
2021-12-07 16:26:34 -08:00
9c626c9dbd Change default disk_iops from unset to 3000
* Since v1.21.3 switched controllers default disk type from
`gp2` to `gp3`, an iops diff has been shown (harmless, but
annoying)
* Controller nodes default to a 30GB `gp3` disk. `gp3` disks
do respect `iops` and the corresponding default is 3000
2021-12-07 15:44:09 -08:00
85252dec6e Switch FCOS workers to official Fedora CoreOS AMIs
* Fix worker nodes to use official Fedora CoreOS AMIs,
instead of the older Poseidon built AMIs (now removed).
This should have been part of #1038, but was missed in
code review
* Poseidon build AMIs have been deleted (so I don't have
to keep paying to host them for people)
2021-12-07 15:31:47 -08:00
298ea65d3e Bump mkdocs-material from 8.0.3 to 8.0.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 8.0.3 to 8.0.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/8.0.3...8.0.4)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-12-07 15:29:00 -08:00
c0ab15ba22 Bump mkdocs-material from 7.3.6 to 8.0.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.3.6 to 8.0.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Upgrade guide](https://github.com/squidfunk/mkdocs-material/blob/master/docs/upgrade.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.3.6...8.0.3)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-12-02 15:25:40 -08:00
5d7b6f611e Update nginx-ingess and Prometheus exporter addons 2021-11-21 09:28:17 -08:00
93594292eb Update Kubernetes from v1.22.3 to v1.22.4
* Update flannel from v0.15.0 to v0.15.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1224
2021-11-17 19:53:32 -08:00
0546608e77 Bump pymdown-extensions from 9.0 to 9.1
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 9.0 to 9.1.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/9.0...9.1)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-11-17 18:41:22 -08:00
94b2793e40 Update CoreDNS from v1.8.4 to v1.8.6
* https://coredns.io/2021/10/07/coredns-1.8.6-release/
2021-11-12 21:09:04 -08:00
4fd43b39ad Fix Flatcar Linux docker driver and add cgroups v2
* Remove `/sys/fs/cgroup/systemd` mount since Flatcar Linux
uses cgroups v2
* Flatcar Linux's `docker` switched from the `cgroupfs` to
`systemd` driver without notice
2021-11-12 21:07:20 -08:00
65083aca7d Update Calico and Flannel CNI providers
* Update Calico from v3.20.2 to v3.21.0
* Update Flannel from v0.14.0 to v0.15.0
2021-11-12 11:03:39 -08:00
07db4c1143 Allow use of google Terraform provider v4.0+
* https://github.com/hashicorp/terraform-provider-google/releases/tag/v4.0.0
2021-11-11 10:17:58 -08:00
e5d0ce5fd7 Bump mkdocs-material from 7.3.4 to 7.3.6
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.3.4 to 7.3.6.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.3.4...7.3.6)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-11-07 17:01:41 -08:00
b934a13605 Update Prometheus and Grafana addons 2021-11-07 17:00:40 -08:00
cd005a0b27 Prepare for v1.22.3 release 2021-10-28 11:58:55 -07:00
dd4a5a4e7e Update Kubernetes from v1.22.2 to v1.22.3
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1223
2021-10-28 10:11:06 -07:00
af835f976f Update flannel from v0.13.0 to v0.14.0
* https://github.com/flannel-io/flannel/releases/tag/v0.14.0
2021-10-28 10:09:06 -07:00
9e4a369f76 Bump mkdocs-material from 7.3.3 to 7.3.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.3.3 to 7.3.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.3.3...7.3.4)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-10-23 10:45:49 -07:00
831d897533 Bump mkdocs from 1.2.2 to 1.2.3
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.2.2 to 1.2.3.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.2.2...1.2.3)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-10-23 10:31:55 -07:00
17dce49982 Update etcd from v3.5.0 to v3.5.1
* https://github.com/etcd-io/etcd/releases/tag/v3.5.1
2021-10-17 11:28:27 -07:00
5744e10329 Update Cilium from v1.0.4 to v1.0.5
* https://github.com/cilium/cilium/releases/tag/v1.10.5
2021-10-17 11:26:59 -07:00
20748536df Update nginx-ingress from v1.0.2 to v1.0.4
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.0.4
2021-10-17 11:17:43 -07:00
f2e6256dd9 Update Prometheus, kube-state-metrics, and Grafana
* Update monitoring addons
2021-10-17 11:15:39 -07:00
443bd5a26b Add file to hold nodes on iptables-legacy
* Add `/etc/fedora-coreos/iptables-legacy.stamp` to declare
that `iptables-legacy` should be used instead of `iptables-nft`
(until support is added in future releases)
* https://github.com/coreos/fedora-coreos-tracker/issues/676
2021-10-11 20:30:49 -07:00
f8162b9be3 Update Calico from v3.20.1 to v3.20.2
* Use Calico's iptables legacy vs nft auto-detection
2021-10-11 20:28:48 -07:00
20ffbba4bf Bump mkdocs-material from 7.3.1 to 7.3.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.3.1 to 7.3.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/CHANGELOG)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.3.1...7.3.3)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-10-11 19:31:10 -07:00
15117fb95b Update Prometheus and nginx-ingress 2021-10-05 19:15:58 -07:00
10af8b4120 Bump mkdocs-material from 7.3.0 to 7.3.1
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.3.0 to 7.3.1.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.3.0...7.3.1)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-10-04 20:39:01 -07:00
e51b2903c1 Bump pymdown-extensions from 8.2 to 9.0
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 8.2 to 9.0.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/8.2...9.0)

---
updated-dependencies:
- dependency-name: pymdown-extensions
  dependency-type: direct:production
  update-type: version-update:semver-major
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-10-04 20:38:46 -07:00
cb72b261c7 Update Terraform provider poseidon/matchbox to v0.5+
* Relax version constraint to allow future minor version
releases to be used without a corresponding Typhoon change
2021-09-29 23:41:44 -07:00
209efd2f5b Update Prometheus, Grafana, and kube-state-metrics 2021-09-29 23:39:10 -07:00
388b1238bc Bump mkdocs-material from 7.2.8 to 7.3.0
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.2.8 to 7.3.0.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.2.8...7.3.0)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-09-27 20:40:44 -07:00
5a1e455220 Update nginx-ingress from v1.0.0 to v1.0.1 2021-09-24 09:38:18 -07:00
69f37c8b17 Update Prometheus from v2.29.2 to v2.30.0 2021-09-24 09:34:00 -07:00
b30de949b8 Update Calico and Cilium CNI
* Update Calico from v3.20.0 to v3.20.1
* Update Cilium from v1.10.3 to v1.10.4
2021-09-22 22:18:16 -07:00
4973178750 Bump mkdocs-material from 7.2.6 to 7.2.8
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.2.6 to 7.2.8.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.2.6...7.2.8)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-09-21 08:59:11 -07:00
bb7f31822e Update Kubernetes from v1.22.1 to v1.22.2
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1222
2021-09-15 19:56:24 -07:00
c6923b9ef3 Switch Fedora CoreOS to new ARM64 AMIs (#1038)
* Fedora CoreOS now publishes ARM64 AMIs
2021-09-12 11:49:13 -07:00
dae79d5916 Remove mention of freenode IRC
See #995
2021-09-12 10:10:49 -07:00
f4d5ac0ca7 Bump mkdocs-material from 7.2.5 to 7.2.6
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.2.5 to 7.2.6.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.2.5...7.2.6)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-09-11 12:49:06 -07:00
7e1b2cdba1 Discontinue Docker automated build publishing
* Poseidon infra publishes official multi-arch container
images for Kubelet to both Quay and Dockerhub (fallback).
There is no change here
* Automated builds by Quay and Dockerhub added separately
tagged images for those not able to trust our images and
preferring to trust Quay/Dockerhub. Going forward, we're
ending the use of Dockerhub automated builds. Docker has
moved automated builds to paid plans, even for open source
projects (we're not petitioning for a special exemption
given these are our unofficial images). Those still needing
Kubelet images built externally (i.e. not Poseidon Labs)
would still be able to use the Quay images tagged `build-SHA`
2021-09-01 11:52:57 -07:00
3bb20ce083 Bump mkdocs-material from 7.2.4 to 7.2.5
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.2.4 to 7.2.5.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.2.4...7.2.5)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-08-31 17:34:24 -07:00
eb29fb639b Update nginx-ingress, Prometheus, and Grafana addons 2021-08-24 22:14:57 -07:00
fcbdb50d93 Update Kubernetes from v1.22.0 to v1.22.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1221
2021-08-19 21:12:02 -07:00
efac611e9c Bump mkdocs-material from 7.2.2 to 7.2.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.2.2 to 7.2.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.2.2...7.2.4)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-08-16 11:51:08 -07:00
87ff431b80 Bump pygments from 2.9.0 to 2.10.0
Bumps [pygments](https://github.com/pygments/pygments) from 2.9.0 to 2.10.0.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.9.0...2.10.0)

---
updated-dependencies:
- dependency-name: pygments
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-08-16 11:40:09 -07:00
0d8ceae1d9 Add etcd v3.5.0 note to CHANGES 2021-08-11 09:24:43 -07:00
c5cf803634 Update Grafana and kube-state-metrics addons 2021-08-10 22:17:16 -07:00
61ee01f462 Show SSH keys with ssh-ed25519 instead of sha-rsa in docs
* For Fedora CoreOS, users should not be using sha-rsa public
keys anymore, so make sure the docs examples reflect this
* https://github.com/poseidon/typhoon/issues/915
2021-08-10 21:48:18 -07:00
cbef202eec Update Prometheus discovery of kube components
* Kubernetes v1.22.0 disabled kube-controller-manager insecure
port, which was used internally for Prometheus metrics scraping
* Configure Prometheus to discover and scrape endpoints for
kube-scheduler and kube-controller-manager via the authenticated
https ports, via bearer token
* Change firewall ports to allow Prometheus (on worker nodes)
to scrape kube-scheduler and kube-controller-manager targets
that run on controller(s) with hostNetwork
* Disable the insecure port on kube-scheduler
2021-08-10 21:25:19 -07:00
0c99b909a9 Update nginx-ingress from v0.47.0 to v1.0.0-beta.1
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.0.0-beta.1
2021-08-07 12:46:00 -07:00
739db3b35f Update Grafana and node-exporter addons
* https://github.com/grafana/grafana/releases/tag/v8.1.0
* https://github.com/prometheus/node_exporter/releases/tag/v1.2.1
2021-08-05 23:24:57 -07:00
c68b035a63 Update Flatcar Linux and Fedora CoreOS notes 2021-08-05 23:22:45 -07:00
1a5949824c Update etcd from v3.4.16 to v3.5.0
* Use multi-arch container image instead of a special
"-arm64" suffix on arm64
* https://github.com/etcd-io/etcd/releases/tag/v3.5.0
2021-08-04 22:10:07 -07:00
9bac641511 Update Kubernetes from v1.21.3 to v1.22.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1220
2021-08-04 22:09:19 -07:00
37ff3c28eb Bump mkdocs-material from 7.1.11 to 7.2.2
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.11 to 7.2.2.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.11...7.2.2)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-08-02 19:22:58 -07:00
f03045f0dc Update Cilium for cgroups v2 support
* On Fedora CoreOS, Cilium cross-node service IP load balancing
stopped working for a time (first observable as CoreDNS pods
located on worker nodes not being able to reach the kubernetes
API service 10.3.0.1). This turned out to have two parts:
* Fedora CoreOS switched to cgroups v2 by default. In our early
testing with cgroups v2, Calico (default) was used. With the
cgroups v2 change, SELinux policy denied some eBPF operations.
Since fixed in all Fedora CoreOS channels
* Cilium requires new mounts to support cgroups v2, which are
added here

* https://github.com/coreos/fedora-coreos-tracker/issues/292
* https://github.com/coreos/fedora-coreos-tracker/issues/881
* https://github.com/cilium/cilium/pull/16259
2021-07-24 10:36:47 -07:00
b603bbde3d Update Butane Config from v1.2.0 to v1.4.0
* Rename Fedora CoreOS Config (FCC) to Butane Config
* Require any snippets customizations use version v1.4.0

* https://typhoon.psdn.io/advanced/customization/#hosts
2021-07-19 23:53:51 -07:00
810236f6df Bump mkdocs-material from 7.1.10 to 7.1.11
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.10 to 7.1.11.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.10...7.1.11)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-07-19 10:38:59 -07:00
3c3d3a2473 Bump mkdocs from 1.2.1 to 1.2.2
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.2.1 to 1.2.2.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.2.1...1.2.2)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-07-19 10:06:13 -07:00
1af9fd8094 Remove outdated Terraform migration docs
* Terraform v0.12.x and v0.13.x are now quite outdated,
remove the migration docs
2021-07-19 08:36:59 -07:00
c734fa7b84 Update node-exporter from v1.1.2 to v1.2.0
* https://github.com/prometheus/node_exporter/releases/tag/v1.2.0
2021-07-18 15:26:44 -07:00
fdade5b40c Update poseidon/ct provider from v0.8.0 to v0.9.0
* Continue targeting Ignition v3.2.0 for some time
2021-07-18 09:05:02 -07:00
171fd2c998 Update Kubernetes from v1.21.2 to v1.21.3
* https://github.com/kubernetes/kubernetes/releases/tag/v1.21.3
2021-07-17 18:22:24 -07:00
545bd79624 Update Grafana from v8.0.4 to v8.0.6
* https://github.com/grafana/grafana/releases/tag/v8.0.6
2021-07-16 12:02:36 -07:00
12b825c78f Bump mkdocs-material from 7.1.9 to 7.1.10
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.9 to 7.1.10.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.9...7.1.10)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-07-12 19:10:52 -07:00
66e7354c8a Change AWS default disk type from gp2 to gp3
* https://aws.amazon.com/about-aws/whats-new/2020/12/introducing-new-amazon-ebs-general-purpose-volumes-gp3/
2021-07-04 10:43:05 -07:00
3a71b2ccb1 Update Cilium from v1.10.1 to v1.10.2
* https://github.com/cilium/cilium/releases/tag/v1.10.2
2021-07-04 10:11:21 -07:00
c7e327417b Update Prometheus and Grafana addons 2021-07-04 10:02:44 -07:00
e313e733ab Bump mkdocs-material from 7.1.8 to 7.1.9
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.8 to 7.1.9.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.8...7.1.9)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-06-29 22:23:36 -07:00
d0e73b8174 Bump terraform-render-bootstrap 2021-06-27 18:11:43 -07:00
65ddd2419c Add Known Issues with FCOS to CHANGES 2021-06-27 16:51:59 -07:00
b0e9b1fa60 Update Prometheus and Grafana addons
* https://github.com/prometheus/prometheus/releases/tag/v2.28.0
* https://github.com/grafana/grafana/releases/tag/v8.0.3
2021-06-27 14:46:43 -07:00
485feb82c4 Update CoreDNS from v1.8.0 to v1.8.4
* https://coredns.io/2021/01/20/coredns-1.8.1-release/
* https://coredns.io/2021/02/23/coredns-1.8.2-release/
* https://coredns.io/2021/02/24/coredns-1.8.3-release/
* https://coredns.io/2021/05/28/coredns-1.8.4-release/
2021-06-23 23:31:25 -07:00
0b276b6b7e Update Kubernetes from v1.21.1 to v1.21.2
* https://github.com/kubernetes/kubernetes/releases/tag/v1.21.2
2021-06-17 16:15:20 -07:00
e8513e58bb Add support for Terraform v1.0.0
* https://github.com/hashicorp/terraform/releases/tag/v1.0.0
2021-06-17 13:32:56 -07:00
d77343be3a Workaround systemd 248 path units not working reliably
* On FCOS 34 / systemd 248, `kubelet.path` won't activate (stuck
waiting) when `/etc/kubernetes/kubeconfig` exists, even with
manual prodding of the file. The root cause isn't known, but
a workaround is to delay `/etc/kubernetes` directory creation
or to touch the directory later
* Fix DigitalOcean worker node kubelet.service being enabled
immediately. On bare-metal and DigitalOcean, the kubeconfig
should activate the Kubelet, so it doesn't crashloop needlessly
(nice to have, not required)
2021-06-16 10:19:39 -07:00
f2b01e1d75 Bump mkdocs-material from 7.1.7 to 7.1.8
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.7 to 7.1.8.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.7...7.1.8)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-06-14 15:06:18 -07:00
60c2107d7f Bump mkdocs from 1.1.2 to 1.2.1
Bumps [mkdocs](https://github.com/mkdocs/mkdocs) from 1.1.2 to 1.2.1.
- [Release notes](https://github.com/mkdocs/mkdocs/releases)
- [Commits](https://github.com/mkdocs/mkdocs/compare/1.1.2...1.2.1)

---
updated-dependencies:
- dependency-name: mkdocs
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-06-14 15:01:52 -07:00
30cfeec6c1 Update nginx-ingress from v0.46.0 to v0.47.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.47.0
2021-06-07 10:11:07 -07:00
ba8774ee0d Bump mkdocs-material from 7.1.6 to 7.1.7
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.6 to 7.1.7.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.6...7.1.7)

---
updated-dependencies:
- dependency-name: mkdocs-material
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2021-06-07 09:43:23 -07:00
24e63bd134 Update Prometheus, Grafana, kube-state-metrics addons 2021-06-07 09:40:06 -07:00
996bdd9112 Update Calico from v3.19.0 to v3.19.1
* https://docs.projectcalico.org/archive/v3.19/release-notes/
2021-06-02 14:51:15 -07:00
a34d78f55d Bump mkdocs-material from 7.1.5 to 7.1.6
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.5 to 7.1.6.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.5...7.1.6)

Signed-off-by: dependabot[bot] <support@github.com>
2021-05-31 14:39:01 -07:00
04b2e149ba Remove freenode IRC from help section
* Due to the takeover of freenode.net IRC, the channel
there should no longer be used
2021-05-26 11:31:25 -07:00
9f0126a410 Fix typo in CHANGES.md 2021-05-25 21:16:53 -07:00
a1bab9c96e Bump mkdocs-material from 7.1.4 to 7.1.5
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.4 to 7.1.5.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.4...7.1.5)

Signed-off-by: dependabot[bot] <support@github.com>
2021-05-24 11:39:13 -07:00
966fd280b0 Update Cilium from v0.10.0-rc1 to v0.10.0
* https://github.com/cilium/cilium/releases/tag/v1.10.0
2021-05-24 11:16:51 -07:00
e4e074c894 Update Cilium from v1.9.6 to v1.10.0-rc1
* Add multi-arch container images and arm64 support
* https://github.com/cilium/cilium/releases/tag/v1.10.0-rc1
2021-05-14 14:24:52 -07:00
d51da49925 Update docs for Kubernetes v1.21.1 and Terraform v0.15.x 2021-05-13 11:34:01 -07:00
2076a779a3 Update Kubernetes from v1.21.0 to v1.21.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1211
2021-05-13 11:23:26 -07:00
048094b256 Update etcd from v3.4.15 to v3.4.16
* https://github.com/etcd-io/etcd/blob/main/CHANGELOG-3.4.md
2021-05-13 10:53:04 -07:00
75b063c586 Update Prometheus from v2.25.2 to v2.27.0
* Update Grafana from v7.5.4 to v7.5.6
* https://github.com/prometheus/prometheus/releases/tag/v2.27.0
* https://github.com/grafana/grafana/releases/tag/v7.5.6
2021-05-12 11:47:07 -07:00
1620d1e456 Bump mkdocs-material from 7.1.3 to 7.1.4
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.3 to 7.1.4.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.3...7.1.4)

Signed-off-by: dependabot[bot] <support@github.com>
2021-05-10 14:53:17 -07:00
939bffbf98 Bump pymdown-extensions from 8.1.1 to 8.2
Bumps [pymdown-extensions](https://github.com/facelessuser/pymdown-extensions) from 8.1.1 to 8.2.
- [Release notes](https://github.com/facelessuser/pymdown-extensions/releases)
- [Commits](https://github.com/facelessuser/pymdown-extensions/compare/8.1.1...8.2)

Signed-off-by: dependabot[bot] <support@github.com>
2021-05-10 14:52:58 -07:00
bc96443710 Update nginx-ingress from v0.45.0 to v0.46.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.46.0
2021-05-05 12:06:20 -07:00
82a7422b3d Change Dependabot pip watcher to check weekly 2021-05-05 11:34:57 -07:00
132ab395a5 Bump pygments from 2.8.1 to 2.9.0
Bumps [pygments](https://github.com/pygments/pygments) from 2.8.1 to 2.9.0.
- [Release notes](https://github.com/pygments/pygments/releases)
- [Changelog](https://github.com/pygments/pygments/blob/master/CHANGES)
- [Commits](https://github.com/pygments/pygments/compare/2.8.1...2.9.0)

Signed-off-by: dependabot[bot] <support@github.com>
2021-05-05 11:32:02 -07:00
5f87eb3ec9 Update Fedora CoreOS Kubelet for cgroups v2
* Fedora CoreOS is beginning to switch from cgroups v1 to
cgroups v2 by default, which changes the sysfs hierarchy
* This will be needed when using a Fedora Coreos OS image
that enables cgroups v2 (`next` stream as of this writing)

Rel: https://github.com/coreos/fedora-coreos-tracker/issues/292
2021-04-26 11:48:58 -07:00
b152b9f973 Reduce the default disk_size from 40GB to 30GB
* We're typically reducing the `disk_size` in real clusters
since the space is under used. The default should be lower.
2021-04-26 11:43:26 -07:00
9c842395a8 Update Cilium from v1.9.5 to v1.9.6
* https://github.com/cilium/cilium/releases/tag/v1.9.6
2021-04-26 10:55:23 -07:00
6cb9c0341b Bump mkdocs-material from 7.1.2 to 7.1.3
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.2 to 7.1.3.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.2...7.1.3)

Signed-off-by: dependabot[bot] <support@github.com>
2021-04-26 10:35:00 -07:00
d4fd6d4adb Bump mkdocs-material from 7.1.1 to 7.1.2
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.1 to 7.1.2.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.1...7.1.2)

Signed-off-by: dependabot[bot] <support@github.com>
2021-04-23 14:26:27 -07:00
3664dfafc2 Update docs with video meetings and referral links
* Use our DigitalOcean referral code for new DigitalOcean
users. This gives new accounts free cloud credits and
provides a smaller cloud credit back to the project
* Link to the new video meeting via one-time Github Sponsor
feature that we're trying out
* List Fedora CoreOS ARM64 as a supported platform (alpha).
Before this was only mentioned in docs and on the blog.
2021-04-17 19:15:51 -07:00
e535ddd15a Update Grafana from v7.5.3 to v7.5.4
* https://github.com/grafana/grafana/releases/tag/v7.5.4
2021-04-17 11:38:14 -07:00
5752a8f041 Update kube-state-metrics from v2.0.0-rc.1 to v2.0.0
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0
2021-04-17 11:34:52 -07:00
68abbf7b0d Fix docs link on index page (#975)
* Fix Fedora CoreOS Google Cloud tutorial link
2021-04-17 10:52:59 -07:00
67047ead08 Update Terraform version to allow v0.15.0
* Require Terraform version v0.13 <= x < v0.16
2021-04-16 09:46:01 -07:00
c11e23fc50 Fix minor docs issues and missing changelog links 2021-04-13 09:35:11 -07:00
b647ad8806 Bump mkdocs-material from 7.1.0 to 7.1.1
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.1.0 to 7.1.1.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.1.0...7.1.1)

Signed-off-by: dependabot[bot] <support@github.com>
2021-04-12 20:29:01 -07:00
2eb1ac1b4d Update nginx-ingress from v0.44.0 to v0.45.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.45.0
2021-04-12 00:18:47 -07:00
cb2721ef7d Update Grafana from v7.5.2 to v7.5.3
* https://github.com/grafana/grafana/releases/tag/v7.5.3
2021-04-12 00:17:22 -07:00
fc06d28e13 Remove deprecated field on azurerm_lb_backend_address_pool
* Remove the deprecated `resource_group_name` field from Azure
`azurerm_lb_backend_address_pool` resources
2021-04-11 23:59:17 -07:00
a9078cb52b Add sponsorship badge to Github repo 2021-04-11 16:00:16 -07:00
ebd9570ede Update Fedora CoreOS Config version from v1.1.0 to v1.2.0
* Require [poseidon/ct](https://github.com/poseidon/terraform-provider-ct)
Terraform provider v0.8+
* Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts)
customizations to update to v1.2.0

See upgrade [notes](https://typhoon.psdn.io/topics/maintenance/#upgrade-terraform-provider-ct)
2021-04-11 15:26:54 -07:00
34e8db7aae Update static Pod manifests for Kubernetes v1.21.0
* https://github.com/poseidon/terraform-render-bootstrap/pull/257
2021-04-11 15:05:46 -07:00
084e8bea49 Allow custom initial node taints on worker pool nodes
* Add `node_taints` variable to worker modules to set custom
initial node taints on cloud platforms that support auto-scaling
worker pools of heterogeneous nodes (i.e. AWS, Azure, GCP)
* Worker pools could use custom `node_labels` to allowed workloads
to select among differentiated nodes, while custom `node_taints`
allows a worker pool's nodes to be tainted as special to prevent
scheduling, except by workloads that explicitly tolerate the
taint
* Expose `daemonset_tolerations` in AWS, Azure, and GCP kubernetes
cluster modules, to determine whether `kube-system` components
should tolerate the custom taint (advanced use covered in docs)

Rel: #550, #663
Closes #429
2021-04-11 15:00:11 -07:00
d73621c838 Update Kubernetes from v1.20.5 to v1.21.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1210
2021-04-08 21:44:31 -07:00
1a6481df04 Update Grafana from v7.5.1 to v7.5.2
* https://github.com/grafana/grafana/releases/tag/v7.5.2
2021-04-04 18:20:02 -07:00
798ec9a92f Change CNI config directory to /etc/cni/net.d
* Change CNI config directory from `/etc/kubernetes/cni/net.d`
to `/etc/cni/net.d` (Kubelet default)
* https://github.com/poseidon/terraform-render-bootstrap/pull/255
2021-04-02 00:03:48 -07:00
96aed4c3c3 Bump mkdocs-material from 7.0.6 to 7.1.0
Bumps [mkdocs-material](https://github.com/squidfunk/mkdocs-material) from 7.0.6 to 7.1.0.
- [Release notes](https://github.com/squidfunk/mkdocs-material/releases)
- [Changelog](https://github.com/squidfunk/mkdocs-material/blob/master/docs/changelog.md)
- [Commits](https://github.com/squidfunk/mkdocs-material/compare/7.0.6...7.1.0)

Signed-off-by: dependabot[bot] <support@github.com>
2021-04-02 00:01:44 -07:00
7372d33af8 Update kube-state-metrics and Grafana
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-rc.1
* https://github.com/grafana/grafana/releases/tag/v7.5.1
2021-03-28 10:53:52 -07:00
451ec771a8 Update Terraform providers and CHANGES for release 2021-03-23 08:45:57 -07:00
4d9846b83e Add DigitalOcean as a OSS sponsorship partner
* Include DigitalOcean logo and link on repo and site
2021-03-21 11:34:36 -07:00
597ca4acce Update CoreDNS from v1.7.0 to v1.8.0
* https://github.com/poseidon/terraform-render-bootstrap/pull/254
2021-03-20 16:47:25 -07:00
507c646e8b Add Kubelet provider-id on AWS
* Set the Kubelet `--provider-id` on AWS based on metadata from
Fedora CoreOS afterburn or Flatcar Linux coreos-metadata
* Based on https://github.com/poseidon/typhoon/pull/951
2021-03-19 12:43:37 -07:00
d8f7da6873 Add dependabot update watcher for docs pypi packages
* Update requirements.txt packages for mkdocs
2021-03-19 11:55:54 -07:00
048f1f514e Update Grafana from v7.4.3 to v7.4.5
* https://github.com/grafana/grafana/releases/tag/v7.4.5
2021-03-19 11:51:52 -07:00
b825cd9afe Update Prometheus from v2.25.1 to v2.25.2
* https://github.com/prometheus/prometheus/releases/tag/v2.25.2
2021-03-19 11:49:38 -07:00
796149d122 Update Kubernetes from v1.20.4 to v1.20.5
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1205
2021-03-19 11:27:31 -07:00
a66bccd590 Update Cilium from v1.9.4 to v1.9.5
* https://github.com/cilium/cilium/releases/tag/v1.9.5
2021-03-14 11:48:22 -07:00
30b1edfcc6 Mark bootstrap token as sensitive in plan/apply
* Mark the bootstrap token as sensitive, which is useful when
Terraform is run in automated CI/CD systems to avoid showing
the token
* https://github.com/poseidon/terraform-render-bootstrap/pull/251
2021-03-14 11:32:35 -07:00
a4afe06b64 Update Calico from v3.17.3 to v3.18.1
* https://docs.projectcalico.org/archive/v3.18/release-notes/
2021-03-14 10:35:24 -07:00
4d58be0816 Update Prometheus from v2.25.0 to v2.25.1
* https://github.com/prometheus/prometheus/releases/tag/v2.25.1
2021-03-14 09:43:15 -07:00
170b768ad8 Add KUBELET_IMAGE to Fedora CoreOS bootstrap.service (#945)
* Align with Flatcar Linux `bootstrap.service`
2021-03-14 09:35:42 -07:00
5bc1cd28c3 Switch kube-state-metrics image from quay to k8s.gcr.io
* kube-state-metrics is continuing publishing container images
to `k8s.gcr.io` instead of `quay.io`

Rel: https://github.com/kubernetes/kube-state-metrics/issues/1409
2021-03-11 10:56:18 -08:00
13fbac6c79 Update Grafana from v7.4.2 to v7.4.3
* https://github.com/grafana/grafana/releases/tag/v7.4.3
2021-03-05 17:19:54 -08:00
a8fa4a9a06 Update node-exporter and kube-state-metrics
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-rc.0
* https://github.com/prometheus/node_exporter/releases/tag/v1.1.2
2021-03-05 17:13:45 -08:00
a5c1a96df1 Update etcd from v3.4.14 to v3.4.15
* https://github.com/etcd-io/etcd/releases/tag/v3.4.15
2021-03-05 17:02:57 -08:00
6a091e245e Remove Flatcar Linux Edge os_image option
* Flatcar Linux has not published an Edge channel image since
April 2020 and recently removed mention of the channel from
their documentation https://github.com/kinvolk/Flatcar/pull/345
* Users of Flatcar Linux Edge should move to the stable, beta, or
alpha channel, barring any alternate advice from upstream Flatcar
Linux
2021-02-20 16:09:54 -08:00
590796ee62 Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2021-02-19 00:24:07 -08:00
ec389295fe Update Grafana from v7.4.0 to v7.4.2
* https://github.com/grafana/grafana/releases/tag/v7.4.2
2021-02-19 00:18:39 -08:00
3c807f3478 Update Prometheus from v2.24.1 to v2.25.0
* https://github.com/prometheus/prometheus/releases/tag/v2.25.0
2021-02-19 00:16:35 -08:00
e76fe80b45 Update Kubernetes from v1.20.3 to v1.20.4
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1204
2021-02-19 00:02:07 -08:00
32853aaa7b Update Kubernetes from v1.20.2 to v1.20.3
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1203
2021-02-17 22:29:33 -08:00
c32a54db40 Update node-exporter from v1.0.1 to v1.1.1
* https://github.com/prometheus/node_exporter/releases/tag/v1.1.1
2021-02-14 14:30:28 -08:00
9671b1c734 Update flannel-cni from v0.4.1 to v0.4.2
* https://github.com/poseidon/flannel-cni/releases/tag/v0.4.2
2021-02-14 12:04:59 -08:00
3b933e1ab3 Update Grafana from v7.3.7 to v7.4.0
* https://github.com/grafana/grafana/releases/tag/v7.4.0
2021-02-07 21:42:18 -08:00
58d8f6f505 Update Prometheus from v2.24.0 to v2.24.1
* https://github.com/prometheus/prometheus/releases/tag/v2.24.1
2021-02-04 22:28:32 -08:00
56853fe222 Update nginx-ingress from v0.43.0 to v0.44.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.44.0
2021-02-04 22:19:58 -08:00
18165d8076 Update Calico from v3.17.1 to v3.17.2
* https://github.com/projectcalico/calico/releases/tag/v3.17.2
2021-02-04 22:03:51 -08:00
50acf28ce5 Update Cilium from v1.9.3 to v1.9.4
* https://github.com/cilium/cilium/releases/tag/v1.9.4
2021-02-03 23:08:22 -08:00
ab793eb842 Update Cilium from v1.9.2 to v1.9.3
* https://github.com/cilium/cilium/releases/tag/v1.9.3
2021-01-26 17:13:52 -08:00
b74c958524 Update Cilium from v1.9.1 to v1.9.2
* https://github.com/cilium/cilium/releases/tag/v1.9.2
2021-01-20 22:06:45 -08:00
2024d3c32e Link to Github Sponsors in README and docs
* Update the Social Contract and Sponsors
2021-01-16 12:56:59 -08:00
11c434915f Update Grafana from v7.3.6 to v7.3.7
* https://github.com/grafana/grafana/releases/tag/v7.3.7
2021-01-16 10:46:56 -08:00
05f7df9e80 Update Kubernetes from v1.20.1 to v1.20.2
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1202
2021-01-13 17:46:51 -08:00
4220b9ce18 Add support for Terraform v0.14.4+
* Support Terraform v0.13.x and v0.14.4+
2021-01-12 21:43:12 -08:00
6a6af4aa16 Update Prometheus from v2.24.0-rc.0 to v2.24.0
* https://github.com/prometheus/prometheus/releases/tag/v2.24.0
2021-01-12 20:49:18 -08:00
3dcd10f3b8 Update Prometheus v2.23.0 to v2.24.0-rc.0
* https://github.com/prometheus/prometheus/releases/tag/v2.24.0-rc.0
2021-01-01 13:49:28 -08:00
22503993b9 Update nginx-ingress from v0.41.2 to v0.43.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.43.0
* https://github.com/kubernetes/ingress-nginx/issues/6696
2021-01-01 13:44:45 -08:00
cf3aa8885b Update Prometheus rules and Grafana dashboards
* Update Grafana from v7.3.5 to v7.3.6
2020-12-19 14:56:42 -08:00
ba61a137db Add notice about upstream Fedora CoreOS changes
* Highlight that short-term, use of Fedora CoreOS will
require non-RSA SSH keys or a workaround snippet
2020-12-19 14:10:42 -08:00
646bdd78e4 Update Kubernetes from v1.20.0 to v1.20.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1201
2020-12-19 12:56:28 -08:00
c163fbbbcd Update docs and README for release 2020-12-12 12:31:35 -08:00
dc7be431e0 Remove iSCSI mounts from Kubelet
* Remove Kubelet `/etc/iscsi` and `iscsiadm` host mounts that
were added on bare-metal, since these no longer work on either
Fedora CoreOS or Flatcar Linux with newer `iscsiadm`
* These special mounts on bare-metal date back to #350 which
added them to provide a way to use iSCSI in Kubernetes v1.10
* Today, storage should be handled by external CSI providers
which handle different storage systems, which doesn't rely
on Kubelet storage utils

Close #907
2020-12-12 11:41:02 -08:00
86e0f806b3 Revert "Add support for Terraform v0.14.x"
This reverts commit 968febb050.
2020-12-11 00:47:57 -08:00
96172ad269 Update Grafana from v7.3.4 to v7.3.5
* https://github.com/grafana/grafana/releases/tag/v7.3.5
2020-12-11 00:24:43 -08:00
3eb20a1f4b Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2020-12-11 00:15:29 -08:00
ee9ce3d0ab Update Calico from v3.17.0 to v3.17.1
* https://github.com/projectcalico/calico/releases/tag/v3.17.1
2020-12-10 22:48:38 -08:00
a8b8a9b454 Update Kubernetes from v1.20.0-rc.0 to v1.20.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1200
2020-12-08 18:28:13 -08:00
968febb050 Add support for Terraform v0.14.x
* Support Terraform v0.13.x and v0.14.x
2020-12-07 00:22:38 -08:00
bee455f83a Update Cilium from v1.9.0 to v1.9.1
* https://github.com/cilium/cilium/releases/tag/v1.9.1
2020-12-04 14:14:18 -08:00
3e89ea1b4a Promote Fedora CoreOS bare-metal to stable
* Fedora CoreOS is a good choice for use on bare-metal
2020-12-04 14:02:55 -08:00
e77dd6ecd4 Update Kubernetes from v1.19.4 to v1.20.0-rc.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1200-rc0
2020-12-03 16:01:28 -08:00
4fd4a0f540 Move control plane static pod TLS assets to /etc/kubernetes/pki
* Change control plane static pods to mount `/etc/kubernetes/pki`,
instead of `/etc/kubernetes/bootstrap-secrets` to better reflect
their purpose and match some loose conventions upstream
* Place control plane and bootstrap TLS assets and kubeconfig's
in `/etc/kubernetes/pki`
* Mount to `/etc/kubernetes/pki` (rather than `/etc/kubernetes/secrets`)
to match the host location (less surprise)

Rel: https://github.com/poseidon/terraform-render-bootstrap/pull/233
2020-12-02 23:26:42 -08:00
804dfea0f9 Add kubeconfig's for kube-scheduler and kube-controller-manager
* Generate TLS client certificates for `kube-scheduler` and
`kube-controller-manager` with `system:kube-scheduler` and
`system:kube-controller-manager` CNs
* Template separate kubeconfigs for kube-scheduler and
kube-controller manager (`scheduler.conf` and
`controller-manager.conf`). Rename admin for clarity
* Before v1.16.0, Typhoon scheduled a self-hosted control
plane, which allowed the steady-state kube-scheduler and
kube-controller-manager to use a scoped ServiceAccount.
With a static pod control plane, separate CN TLS client
certificates are the nearest equiv.
* https://kubernetes.io/docs/setup/best-practices/certificates/
* Remove unused Kubelet certificate, TLS bootstrap is used
instead
2020-12-01 22:02:15 -08:00
8ba23f364c Add TokenReview and TokenRequestProjection flags
* Add kube-apiserver flags for TokenReview and TokenRequestProjection
(beta, defaults on) to allow using Service Account Token Volume
Projection to create and mount service account tokens tied to a Pod's
lifecycle

Rel:

* https://github.com/poseidon/terraform-render-bootstrap/pull/231
* https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/#service-account-token-volume-projection
2020-12-01 20:02:33 -08:00
f6025666eb Update etcd from v3.4.12 to v3.4.14
* https://github.com/etcd-io/etcd/releases/tag/v3.4.14
2020-11-29 20:04:25 -08:00
85eb502f19 Update Prometheus from v2.23.0-rc.0 to v2.23.0
* https://github.com/prometheus/prometheus/releases/tag/v2.23.0
2020-11-29 19:59:27 -08:00
fa3184fb9c Relax terraform-provider-ct version constraint
* Allow terraform-provider-ct versions v0.6+ (e.g. v0.7.1)
Before, only v0.6.x point updates were allowed
* Update terraform-provider-ct to v0.7.1 in docs
* READ the docs before updating terraform-provider-ct,
as changing worker user-data is handled differently
by different cloud platforms
2020-11-29 19:51:26 -08:00
22565e57e0 Update kube-state-metrics from v2.0.0-alpha.2 to v2.0.0-alpha.3
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.3
2020-11-25 14:30:11 -08:00
026e1f3648 Update Grafana from v7.3.3 to v7.3.4
* https://github.com/grafana/grafana/releases/tag/v7.3.4
2020-11-25 14:25:15 -08:00
ae548ce213 Update Calico from v3.16.5 to v3.17.0
* Enable Calico MTU auto-detection
* Remove [workaround](https://github.com/poseidon/typhoon/pull/724) to
Calico cni-plugin [issue](https://github.com/projectcalico/cni-plugin/issues/874)

Rel: https://github.com/poseidon/terraform-render-bootstrap/pull/230
2020-11-25 14:22:58 -08:00
e826b49648 Update Matchbox profile to use initramfs and rootfs images
* Fedora CoreOS stable (after Oct 6) ships separate initramfs
and rootfs images, used as initrd's
* Update profiles to match the Matchbox examples, which have
already switched to the new profile and to remove the unused
kernel args
* Requires Fedora CoreOS version which ships rootfs images
(e.g. stable 32.20200923.3.0 or later)

Rel:

* https://github.com/coreos/fedora-coreos-tracker/issues/390#issuecomment-661986987
* da0df01763 (diff-4541f7b7c174f6ae6270135942c1c65ed9e09ebe81239709f5a9fb34e858ddcf)

Supercedes https://github.com/poseidon/typhoon/pull/888
2020-11-25 14:13:39 -08:00
fa8f68f50e Fix Fedora CoreOS AWS AMI query in non-US regions
* A `aws_ami` data source will fail a Terraform plan
if no matching AMI is found, even if the AMI is not
used. ARM64 images are only published to a few US
regions, so the `aws_ami` data query could fail when
creating Fedora CoreOS AWS clusters in non-US regions
* Condition `aws_ami` on whether experimental arch
`arm64` is chosen
* Recent regression introduced in v1.19.4
https://github.com/poseidon/typhoon/pull/875

Closes https://github.com/poseidon/typhoon/issues/886
2020-11-25 11:32:05 -08:00
ba8d972c76 Update Prometheus from v2.22.2 to v2.23.0-rc.0
* https://github.com/prometheus/prometheus/releases/tag/v2.23.0-rc.0
2020-11-24 10:54:42 -08:00
c0347ca0c6 Set kubeconfig and asset_dist as sensitive
* Mark `kubeconfig` and `asset_dist` as `sensitive` to
prevent the Terraform CLI displaying these values, esp.
for CI systems
* In particular, external tools or tfvars style uses (not
recommended) reportedly display all outputs and are improved
by setting sensitive
* For Terraform v0.14, outputs referencing sensitive fields
must also be annotated as sensitive

Closes https://github.com/poseidon/typhoon/issues/884
2020-11-23 11:41:55 -08:00
9f94ab6bcc Rerun terraform fmt for recent variables 2020-11-21 14:20:36 -08:00
5e4f5de271 Enable Network Load Balancer (NLB) dualstack
* NLB subnets assigned both IPv4 and IPv6 addresses
* NLB DNS name has both A and AAAA records
* NLB to target node traffic is IPv4 (no change),
no change to security groups needed
* Ingresses exposed through the recommended Nginx
Ingress Controller addon will be accessible via
IPv4 or IPv6. No change is needed to the app's
CNAME to NLB record

Related: https://aws.amazon.com/about-aws/whats-new/2020/11/network-load-balancer-supports-ipv6/
2020-11-21 14:16:24 -08:00
be28495d79 Update Prometheus from v2.22.1 to v2.22.2
* https://github.com/prometheus/prometheus/releases/tag/v2.22.2
2020-11-19 21:50:48 -08:00
f1356fec24 Update Grafana from v7.3.2 to v7.3.3
* https://github.com/grafana/grafana/releases/tag/v7.3.3
2020-11-19 21:49:11 -08:00
cc00afa4e1 Add Terraform v0.13 input variable validations
* Support for migrating from Terraform v0.12.x to v0.13.x
was added in v1.18.8
* Require Terraform v0.13+. Drop support for Terraform v0.12
2020-11-17 12:02:34 -08:00
5c3b5a20de Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2020-11-14 13:32:04 -08:00
f5a83667e8 Update Grafana from v7.3.1 to v7.3.2
* https://github.com/grafana/grafana/releases/tag/v7.3.2
2020-11-14 13:30:30 -08:00
a911367c2e Update nginx-ingress from v0.41.0 to v0.41.2
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.41.2
2020-11-14 13:27:06 -08:00
f884de847e Discard Prometheus etcd gRPC failure alert
* Kubernetes watch expiry is not a gRPC code we care about
* Background: This rule is typically removed, but was added back in
2020-11-14 13:17:56 -08:00
1b3a0f6ebc Add experimental Fedora CoreOS arm64 support on AWS
* Add experimental `arch` variable to Fedora CoreOS AWS,
accepting amd64 (default) or arm64 to support native
arm64/aarch64 clusters or mixed/hybrid clusters with
a worker pool of arm64 workers
* Add `daemonset_tolerations` variable to cluster module
(experimental)
* Add `node_taints` variable to workers module
* Requires flannel CNI and experimental Poseidon-built
arm64 Fedora CoreOS AMIs (published to us-east-1, us-east-2,
and us-west-1)

WARN:

* Our AMIs are experimental, may be removed at any time, and
will be removed when Fedora CoreOS publishes official arm64
AMIs. Do NOT use in production

Related:

* https://github.com/poseidon/typhoon/pull/682
2020-11-14 13:09:24 -08:00
1113a22f61 Update Kubernetes from v1.19.3 to v1.19.4
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1194
2020-11-11 22:56:27 -08:00
152c7d86bd Change bootstrap.service container from rkt to docker
* Use docker to run `bootstrap.service` container
* Background https://github.com/poseidon/typhoon/pull/855
2020-11-11 22:26:05 -08:00
79deb8a967 Update Cilium from v1.9.0-rc3 to v1.9.0
* https://github.com/cilium/cilium/releases/tag/v1.9.0
2020-11-10 23:42:41 -08:00
f412f0d9f2 Update Calico from v3.16.4 to v3.16.5
* https://github.com/projectcalico/calico/releases/tag/v3.16.5
2020-11-10 22:58:19 -08:00
eca6c4a1a1 Fix broken flatcar linux documentation links (#870)
* Fix old documentation links
2020-11-10 18:30:30 -08:00
133d325013 Update nginx-ingress from v0.40.2 to v0.41.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.41.0
2020-11-08 14:34:52 -08:00
4b05c0180e Update Grafana from v7.3.0 to v7.3.1
* https://github.com/grafana/grafana/releases/tag/v7.3.1
2020-11-08 14:13:39 -08:00
f49ab3a6ee Update Prometheus from v2.22.0 to v2.22.1
* https://github.com/prometheus/prometheus/releases/tag/v2.22.1
2020-11-08 14:12:24 -08:00
0eef16b274 Improve and tidy Fedora CoreOS etcd-member.service
* Allow a snippet with a systemd dropin to set an alternate
image via `ETCD_IMAGE`, for consistency across Fedora CoreOS
and Flatcar Linux
* Drop comments about integrating system containers with
systemd-notify
2020-11-08 11:49:56 -08:00
ad1f59ce91 Change Flatcar etcd-member.service container from rkt to docker
* Use docker to run the `etcd-member.service` container
* Use env-file `/etc/etcd/etcd.env` like podman on FCOS
* Background: https://github.com/poseidon/typhoon/pull/855
2020-11-03 16:42:18 -08:00
82e5ac3e7c Update Cilium from v1.8.5 to v1.9.0-rc3
* https://github.com/poseidon/terraform-render-bootstrap/pull/224
2020-11-03 10:29:07 -08:00
a8f7880511 Update Cilium from v1.8.4 to v1.8.5
* https://github.com/cilium/cilium/releases/tag/v1.8.5
2020-10-29 00:50:18 -07:00
cda5b93b09 Update kube-state-metrics from v2.0.0-alpha.1 to v2.0.0-alpha.2
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.2
2020-10-28 18:49:40 -07:00
3e9f5f34de Update Grafana from v7.2.2 to v7.3.0
* https://github.com/grafana/grafana/releases/tag/v7.3.0
2020-10-28 17:46:26 -07:00
893d139590 Update Calico from v3.16.3 to v3.16.4
* https://github.com/projectcalico/calico/releases/tag/v3.16.4
2020-10-26 00:50:40 -07:00
fc62e51b2a Update Grafana from v7.2.1 to v7.2.2
* https://github.com/grafana/grafana/releases/tag/v7.2.2
2020-10-22 00:14:04 -07:00
e5ba3329eb Remove bare-metal CoreOS Container Linux profiles
* Remove Matchbox profiles for CoreOS Container Linux
* Simplify the remaining Flatcat Linux profiles
2020-10-21 00:25:10 -07:00
7c3f3ab6d0 Rename container-linux modules to flatcar-linux
* CoreOS Container Linux was deprecated in v1.18.3
* Continue transitioning docs and modules from supporting
both CoreOS and Flatcar "variants" of Container Linux to
now supporting Flatcar Linux and equivalents

Action Required: Update the Flatcar Linux modules `source`
to replace `s/container-linux/flatcar-linux`. See docs for
examples
2020-10-20 22:47:19 -07:00
a99a990d49 Remove unused Kubelet tls mounts
* Kubelet trusts only the cluster CA certificate (and
certificates in the Kubelet debian base image), there
is no longer a need to mount the host's trusted certs
* Similar change on Flatcar Linux in
https://github.com/poseidon/typhoon/pull/855

Rel: https://github.com/poseidon/typhoon/pull/810
2020-10-18 23:48:21 -07:00
df17253e72 Fix delete node permission on Fedora CoreOS node shutdown
* On cloud platforms, `delete-node.service` tries to delete the
local node (not always possible depending on preemption time)
* Since v1.18.3, kubelet TLS bootstrap generates a kubeconfig
in `/var/lib/kubelet` which should be used with kubectl in
the delete-node oneshot
2020-10-18 23:38:11 -07:00
eda78db08e Change Flatcar kubelet.service container from rkt to docker
* Use docker to run the `kubelet.service` container
* Update Kubelet mounts to match Fedora CoreOS
* Remove unused `/etc/ssl/certs` mount (see
https://github.com/poseidon/typhoon/pull/810)
* Remove unused `/usr/share/ca-certificates` mount
* Remove `/etc/resolv.conf` mount, Docker default is ok
* Change `delete-node.service` to use docker instead of rkt
and inline ExecStart, as was done on Fedora CoreOS
* Fix permission denied on shutdown `delete-node`, caused
by the kubeconfig mount changing with the introduction of
node TLS bootstrap

Background

* podmand, rkt, and runc daemonless container process runners
provide advantages over the docker daemon for system containers.
Docker requires workarounds for use in systemd units where the
ExecStart must tail logs so systemd can monitor the daemonized
container. https://github.com/moby/moby/issues/6791
* Why switch then? On Flatcar Linux, podman isn't shipped. rkt
works, but isn't developing while container standards continue
to move forward. Typhoon has used runc for the Kubelet runner
before in Fedora Atomic, but its more low-level. So we're left
with Docker, which is less than ideal, but shipped in Flatcar
* Flatcar Linux appears to be shifting system components to
use docker, which does provide some limited guards against
breakages (e.g. Flatcar cannot enable docker live restore)
2020-10-18 23:24:45 -07:00
afac46e39a Remove asset_dir variable and optional asset writes
* Originally, poseidon/terraform-render-bootstrap generated
TLS certificates, manifests, and cluster "assets" written
to local disk (`asset_dir`) during terraform apply cluster
bootstrap
* Typhoon v1.17.0 introduced bootstrapping using only Terraform
state to store cluster assets, to avoid ever writing sensitive
materials to disk and improve automated use-cases. `asset_dir`
was changed to optional and defaulted to "" (no writes)
* Typhoon v1.18.0 deprecated the `asset_dir` variable, removed
docs, and announced it would be deleted in future.
* Add Terraform output `assets_dir` map
* Remove the `asset_dir` variable

Cluster assets are now stored in Terraform state only. For those
who wish to write those assets to local files, this is possible
doing so explicitly.

```
resource local_file "assets" {
  for_each = module.yavin.assets_dist
  filename = "some-assets/${each.key}"
  content = each.value
}
```

Related:

* https://github.com/poseidon/typhoon/pull/595
* https://github.com/poseidon/typhoon/pull/678
2020-10-17 15:00:15 -07:00
b1e680ac0c Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2020-10-17 13:56:24 -07:00
9fbfbdb854 Update Prometheus from v2.21.0 to v2.22.0
* https://github.com/prometheus/prometheus/releases/tag/v2.22.0
2020-10-17 12:38:25 -07:00
511f5272f4 Update Calico from v3.15.3 to v3.16.3
* https://github.com/projectcalico/calico/releases/tag/v3.16.3
* https://github.com/poseidon/terraform-render-bootstrap/pull/212
2020-10-15 20:08:51 -07:00
46ca5e8813 Update Kubernetes from v1.19.2 to v1.19.3
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1193
2020-10-14 20:47:49 -07:00
394e496cc7 Update Grafana from v7.2.0 to v7.2.1
* https://github.com/grafana/grafana/releases/tag/v7.2.1
2020-10-11 13:21:25 -07:00
a38ec1a856 Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2020-10-11 13:06:53 -07:00
7881f4bd86 Update kube-state-metrics from v1.9.7 to v2.0.0-alpha.1
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha
* https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.1
2020-10-11 12:35:43 -07:00
d5b5b7cb02 Update nginx-ingress from v0.40.0 to v0.40.2
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.40.2
2020-10-06 23:52:15 -07:00
759a48be7c Update mkdocs-material from v5.5.12 to v6.0.1
* Update OS kernel, systemd, and docker verisons
2020-10-02 01:18:38 -07:00
b39a1d70da Update nginx-ingress from v0.35.0 to v0.40.0
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.40.0
2020-10-02 01:00:35 -07:00
901f7939b2 Update Cilium from v1.8.3 to v1.8.4
* https://github.com/cilium/cilium/releases/tag/v1.8.4
2020-10-02 00:24:26 -07:00
d65085ce14 Update Grafana from v7.1.5 to v7.2.0
* https://github.com/grafana/grafana/releases/tag/v7.2.0
2020-09-24 20:58:32 -07:00
343db5b578 Remove references to CoreOS Container Linux
* CoreOS Container Linux was deprecated in v1.18.3 (May 2020)
in favor of Fedora CoreOS and Flatcar Linux. CoreOS Container
Linux references were kept to give folks more time to migrate,
but AMIs have now been deleted. Time is up.

Rel: https://coreos.com/os/eol/
2020-09-24 20:51:02 -07:00
444363be2d Update Kubernetes from v1.19.1 to v1.19.2
* Update flannel from v0.12.0 to v0.13.0-rc2
* Update flannel-cni from v0.4.0 to v0.4.1
* Update CNI plugins from v0.8.6 to v0.8.7
2020-09-16 20:05:54 -07:00
bc7ad25c60 Update Grafana dashboard for Kubelet v1.19
* Fix Kubelet pod and container count metrics dashboard
* https://github.com/kubernetes-monitoring/kubernetes-mixin/pull/499
2020-09-15 23:21:56 -07:00
e838d4dc3d Refresh Prometheus rules/alerts and Grafana dashboards
* Refresh upstream Prometheus rules/alerts and Grafana dashboards
2020-09-13 15:03:27 -07:00
979c092ef6 Reduce apiserver metrics cardinality of non-core APIs
* Reduce `apiserver_request_duration_seconds_count` cardinality
by dropping series for non-core Kubernetes APIs. This is done
to match `apiserver_request_duration_seconds_count` relabeling
* These two relabels must be performed the same way to avoid
affecting new SLO calculations (upcoming)
* See https://github.com/kubernetes-monitoring/kubernetes-mixin/issues/498

Related: https://github.com/poseidon/typhoon/pull/596
2020-09-13 14:47:49 -07:00
db8e94bb4b Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2020-09-12 19:41:15 -07:00
eb093af9ed Drop Kubelet labelmap relabel for node_name
* Originally, Kubelet and CAdvisor metrics used a labelmap
relabel to add Kubernetes SD node labels onto timeseries
* With https://github.com/poseidon/typhoon/pull/596 that
relabel was dropped since node labels aren't usually that
valuable. `__meta_kubernetes_node_name` was retained but
the field name is empty
* Favor just using Prometheus server-side `instance` in
queries that require some node identifier for aggregation
or debugging

Fix https://github.com/poseidon/typhoon/issues/823
2020-09-12 19:40:00 -07:00
36096f844d Promote Cilium from experimental to GA
* Cilium was added as an experimental CNI provider in June
* Since then, I've been choosing it for an increasing number
of clusters and scenarios.
2020-09-12 19:24:55 -07:00
d236628e53 Update Prometheus from v2.20.0 to v2.21.0
* https://github.com/prometheus/prometheus/releases/tag/v2.21.0
2020-09-12 19:20:54 -07:00
577b927a2b Update Fedora CoreOS Config version from v1.0.0 to v1.1.0
* No notable changes in the config spec, just house keeping
* Require any snippets customization to update to v1.1.0. Version
skew between the main config and snippets will show an err message
* https://github.com/coreos/fcct/blob/master/docs/configuration-v1_1.md
2020-09-10 23:38:40 -07:00
000c11edf6 Update IngressClass resources to networking.k8s.io/v1
* Kubernetes v1.19 graduated Ingress and IngressClass from
networking.k8s.io/v1beta1 to networking.k8s.io/v1
2020-09-10 23:25:53 -07:00
29b16c3fc0 Change seccomp annotations to seccompProfile
* seccomp graduated to GA in Kubernetes v1.19. Support for
seccomp alpha annotations will be removed in v1.22
* Replace seccomp annotations with the GA seccompProfile
field in the PodTemplate securityContext
* Switch profile from `docker/default` to `runtime/default`
(no effective change, since docker is the runtime)
* Verify with docker inspect SecurityOpt. Without the profile,
you'd see `seccomp=unconfined`

Related: https://github.com/poseidon/terraform-render-bootstrap/pull/215
2020-09-10 01:15:07 -07:00
0c7a879bc4 Update Kubernetes from v1.19.0 to v1.19.1
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1191
2020-09-09 20:52:29 -07:00
1e654c9e4e Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
* Update mkdocs-material from v5.5.11 to v5.5.12
2020-09-07 21:18:47 -07:00
28ee693e6b Update Cilium from v1.8.2 to v1.8.3
* https://github.com/cilium/cilium/releases/tag/v1.8.3
2020-09-07 21:10:27 -07:00
8c7d95aefd Update mkdocs-material from v5.5.9 to v5.5.11 2020-08-29 13:52:16 -07:00
d45dfdbf91 Update nginx-ingress from v0.34.1 to v0.35.0
* Repo changed to k8s.gcr.io/ingress-nginx/controller
* https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.35.0
2020-08-29 13:38:28 -07:00
d7e0536838 Add code group blocks to improve worker pool docs
* Show Fedora CoreOS and Flatcar Linux examples in
separate tabs, rather than trying to show one
* Add copyright footer for the poseidon org
2020-08-28 00:25:12 -07:00
8dd221a57c Add fleetlock docs and links to addons
* Add links to fleetlock for Fedora CoreOS reboot coordination
* https://github.com/poseidon/fleetlock
2020-08-28 00:02:24 -07:00
f17bb4cf61 Update mkdocs-material from v5.5.6 to v5.5.9 2020-08-27 09:20:18 -07:00
44f1fe620a Update recommended Terraform provider versions
* Sync Terraform provider plugins with those used internally
2020-08-27 09:18:39 -07:00
a504264e24 Update Grafana from v7.1.4 to v7.1.5
* https://github.com/grafana/grafana/releases/tag/v7.1.5
2020-08-27 08:52:07 -07:00
88cf7273dc Update Kubernetes from v1.18.8 to v1.19.0
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md
2020-08-27 08:50:01 -07:00
58def65a09 Update Grafana from v7.1.3 to v7.1.4
* https://github.com/grafana/grafana/releases/tag/v7.1.4
2020-08-22 15:40:09 -07:00
cd7fd29194 Update etcd from v3.4.10 to v3.4.12
* https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.4.md
2020-08-19 21:25:41 -07:00
aafa38476a Fix SELinux race condition on non-bootstrap controllers in multi-controller (#808)
* Fix race condition for bootstrap-secrets SELinux context on non-bootstrap controllers in multi-controller FCOS clusters
* On first boot from disk on non-bootstrap controllers, adding bootstrap-secrets races with kubelet.service starting, which can cause the secrets assets to have the wrong label until kubelet.service restarts (service, reboot, auto-update)
* This can manifest as `kube-apiserver`, `kube-controller-manager`, and `kube-scheduler` pods crashlooping on spare controllers on first cluster creation
2020-08-19 21:18:10 -07:00
9a07f1d30b Update recommended Terraform provider versions
* Sync Terraform provider plugin versions to those used
internally
* Update mkdocs-material from v5.5.1 to v5.5.6
* Fix minor details in docs
2020-08-14 10:05:52 -07:00
c87db3ef37 Update Kubernetes from v1.18.6 to v1.18.8
* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1188
2020-08-13 20:47:43 -07:00
342380cfa4 Update Terraform migration guide SHA
* Mention the first master branch SHA that introduced Terraform
v0.13 forward compatibility
* Link the migration guide on Github until a release is available
and website docs are published
2020-08-13 00:36:47 -07:00
5e70d7e2c8 Migrate from Terraform v0.12.x to v0.13.x
* Recommend Terraform v0.13.x
* Support automatic install of poseidon's provider plugins
* Update tutorial docs for Terraform v0.13.x
* Add migration guide for Terraform v0.13.x (best-effort)
* Require Terraform v0.12.26+ (migration compatibility)
* Require `terraform-provider-ct` v0.6.1
* Require `terraform-provider-matchbox` v0.4.1
* Require `terraform-provider-digitalocean` v1.20+

Related:

* https://www.hashicorp.com/blog/announcing-hashicorp-terraform-0-13/
* https://www.terraform.io/upgrade-guides/0-13.html
* https://registry.terraform.io/providers/poseidon/ct/latest
* https://registry.terraform.io/providers/poseidon/matchbox/latest
2020-08-12 01:54:32 -07:00
aab071309f Update recommended Terraform provider versions
* Sync Terraform provider plugin versions to those used
internally
2020-08-09 12:40:22 -07:00
f6ce12766b Allow terraform-provider-aws v3.0+ plugin
* Typhoon AWS is compatible with terraform-provider-aws v3.x releases
* Continue to allow v2.23+, no v3.x specific features are used
* Set required provider versions in the worker module, since
it can be used independently

Related:

* https://github.com/terraform-providers/terraform-provider-aws/releases/tag/v3.0.0
2020-08-09 12:39:26 -07:00
e1d6ab2f24 Update Grafana from v7.1.1 to v7.1.3
* https://github.com/grafana/grafana/releases/tag/v7.1.3
* https://github.com/grafana/grafana/releases/tag/v7.1.2
2020-08-08 18:59:49 -07:00
8b3d41d6a0 Update mkdocs-material from v5.4.0 to v5.5.1 2020-08-02 15:22:10 -07:00
ccee5d3d89 Update from coreos/flannel-cni to poseidon/flannel-cni
* Update CNI plugins from v0.6.0 to v0.8.6 to fix several CVEs
* Update the base image to alpine:3.12
* Use `flannel-cni` as an init container and remove sleep
* https://github.com/poseidon/terraform-render-bootstrap/pull/205
* https://github.com/poseidon/flannel-cni
* https://quay.io/repository/poseidon/flannel-cni

Background

* Switch from github.com/coreos/flannel-cni v0.3.0 which was last
published by me in 2017 and is no longer accessible to me to maintain
or patch
* Port to the poseidon/flannel-cni rewrite, which releases v0.4.0
to continue the prior release numbering
2020-08-02 15:13:15 -07:00
8aefd4f082 Relex terraform-provider-matchbox version constraint
* Allow use of terraform-provider-matchbox v0.3+ (which
allows v0.3.0 <= version < v1.0) for any pre 1.0 release
* Before, the requirement was v0.3.0 <= version < v0.4.0
2020-08-02 01:09:28 -07:00
78e6409bd0 Fix flannel support on Fedora CoreOS
* Fedora CoreOS now ships systemd-udev's `default.link` while
Flannel relies on being able to pick its own MAC address for
the `flannel.1` link for tunneled traffic to reach cni0 on
the destination side, without being dropped
* This change first appeared in FCOS testing-devel 32.20200624.20.1
and is the behavior going forward in FCOS since it was added
to align FCOS network naming / configs with the rest of Fedora
and address issues related to the default being missing
* Flatcar Linux (and Container Linux) has a specific flannel.link
configuration builtin, so it was not affected
* https://github.com/coreos/fedora-coreos-tracker/issues/574#issuecomment-665487296

Note: Typhoon's recommended and default CNI provider is Calico,
unless `networking` is set to flannel directly.
2020-08-01 21:22:08 -07:00
2aef42d4f6 Update Prometheus from v2.19.2 to v2.20.0
* https://github.com/prometheus/prometheus/releases/tag/v2.20.0
2020-07-25 16:37:28 -07:00
b7d67757de Update Grafana from v7.1.0 to v7.1.1
* https://github.com/grafana/grafana/releases/tag/v7.1.1
2020-07-25 16:33:40 -07:00
26f5d2d753 Fix some links in docs (#788) 2020-07-25 16:32:08 -07:00
cd0a28904e Update Cilium from v1.8.1 to v1.8.2
* https://github.com/cilium/cilium/releases/tag/v1.8.2
2020-07-25 16:06:27 -07:00
618f8b30fd Update CoreDNS from v1.6.7 to v1.7.0
* https://coredns.io/2020/06/15/coredns-1.7.0-release/
* Update Grafana dashboard with revised metrics names
2020-07-25 15:51:31 -07:00
264d23a1b5 Declare etcd data directory permissions
* Set etcd data directory /var/lib/etcd permissions to 700
* On Flatcar Linux, /var/lib/etcd is pre-existing and Ignition
v2 doesn't overwrite the directory. Update the Container Linux
config, but add the manual chmod workaround to bootstrap for
Flatcar Linux users
* https://github.com/etcd-io/etcd/blob/master/CHANGELOG-3.4.md#v3410-2020-07-16
* https://github.com/etcd-io/etcd/pull/11798
2020-07-25 15:48:27 -07:00
f96e91f225 Update etcd from v3.4.9 to v3.4.10
* https://github.com/etcd-io/etcd/releases/tag/v3.4.10
2020-07-18 14:08:22 -07:00
efd4a0319d Update Grafana from v7.0.6 to v7.1.0
* https://github.com/grafana/grafana/releases/tag/v7.1.0
2020-07-18 13:54:56 -07:00
239 changed files with 21443 additions and 8765 deletions

1
.github/FUNDING.yml vendored Normal file
View File

@ -0,0 +1 @@
github: [poseidon]

9
.github/dependabot.yaml vendored Normal file
View File

@ -0,0 +1,9 @@
version: 2
updates:
- package-ecosystem: pip
directory: "/"
schedule:
interval: weekly
pull-request-branch-name:
separator: "-"
open-pull-requests-limit: 3

1
.gitignore vendored Normal file
View File

@ -0,0 +1 @@
site/

View File

@ -4,6 +4,882 @@ Notable changes between versions.
## Latest
## v1.26.1
* Kubernetes [v1.26.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1261)
* Update etcd from v3.5.6 to [v3.5.7](https://github.com/etcd-io/etcd/releases/tag/v3.5.7)
* Update Cilium from v1.12.4 to [v1.12.5](https://github.com/cilium/cilium/releases/tag/v1.12.5)
* Update Calico from v3.24.5 to [v3.25.0](https://github.com/projectcalico/calico/releases/tag/v3.25.0)
* Update CoreDNS from v1.9.3 to [v1.9.4](https://github.com/poseidon/terraform-render-bootstrap/pull/341)
## v1.26.0
* Kubernetes [v1.26.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.26.md#v1260)
* Update etcd from v3.5.5 to [v3.5.6](https://github.com/etcd-io/etcd/releases/tag/v3.5.6)
* Update Cilium from v1.12.3 to [v1.12.4](https://github.com/cilium/cilium/releases/tag/v1.12.4)
* Update flannel from v0.15.1 to [v0.20.2](https://github.com/flannel-io/flannel/releases/tag/v0.20.2)
* Reminder: Modules are no longer published to the [Terraform Module Registry](https://registry.terraform.io/search/modules?q=poseidon) ([#1282](https://github.com/poseidon/typhoon/pull/1282))
* See [#1282](https://github.com/poseidon/typhoon/pull/1282) and [v1.25.4](https://github.com/poseidon/typhoon/releases/tag/v1.25.4) for details
### AWS
* Migrate AWS launch configurations to launch templates ([#1275](https://github.com/poseidon/typhoon/pull/1275))
* Starting Dec 31, 2022 AWS won't add new instance types/families to launch configurations
### Addons
* Update ingress-nginx from v1.3.1 to [v1.5.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.5.1)
* Update Prometheus from v2.40.1 to [v2.40.5](https://github.com/prometheus/prometheus/releases/tag/v2.40.5)
* Update node-exporter from v1.3.1 to [v1.5.0](https://github.com/prometheus/node_exporter/releases/tag/v1.5.0)
* Update kube-state-metrics from v2.6.0 to [v2.7.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.7.0)
* Update Grafana from v9.2.4 to [v9.3.1](https://github.com/grafana/grafana/releases/tag/v9.3.1)
## v1.25.4
* Kubernetes [v1.25.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1254)
* Update Calico from v3.24.1 to [v3.24.5](https://github.com/projectcalico/calico/releases/tag/v3.24.5)
* Allow Kubelet kubeconfig to drain nodes, if desired ([#330](https://github.com/poseidon/terraform-render-bootstrap/pull/330))
* Re-enable Kubelet Graceful Node Shutdown ([#1261](https://github.com/poseidon/typhoon/pull/1261))
* Introduce companion project [poseidon/scuttle](https://github.com/poseidon/scuttle)
* Link to new Mastodon account for release announcements
* [@typhoon@fosstodon.org](https://fosstodon.org/@typhoon)
* [@poseidon@fosstodon.org](https://fosstodon.org/@poseidon)
* Deprecate publishing to the [Terraform Module Registry](https://registry.terraform.io/search/modules?q=poseidon)
* Typhoon docs have always shown using Git-based module sources, not the Terraform Module Registry
* Module usage should be `source = "git::https://github.com/poseidon/typhoon/...` not `source = poseidon/kubernetes/...`
* Terraform's Module Registry requires subtree mirroring typhoon to special terraform-platform-kubernetes repos, only supports release versions (no commit SHAs or forks), only ever contained Flatcar Linux modules (not Fedora CoreOS) for historical reasons
* Note, this does not affect Terraform Providers like `poseidon/matchbox` or `poseidon/ct`, the registry works well for providers
### Fedora CoreOS
* Remove unused `Wants=network.target` from `etcd-member.service` ([#1254](https://github.com/poseidon/typhoon/pull/1254))
### Cloud
* Remove defunct `delete-node.service` from worker node configurations ([#1256](https://github.com/poseidon/typhoon/pull/1256))
### Addons
* Update Prometheus from v2.39.1 to [v2.40.1](https://github.com/prometheus/prometheus/releases/tag/v2.40.1)
* Update Grafana from v9.1.7 to [v9.2.4](https://github.com/grafana/grafana/releases/tag/v9.2.4)
## v1.25.3
* Kubernetes [v1.25.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1253)
* Switch Kubernetes registry from `k8s.gcr.io` to `registry.k8s.io` for addons ([#1246](https://github.com/poseidon/typhoon/pull/1246))
* Update Cilium from v1.12.2 to [v1.12.3](https://github.com/cilium/cilium/releases/tag/v1.12.3) ([#1253](https://github.com/poseidon/typhoon/pull/1253))
### Azure
* Change default Azure `worker_type` from [`Standard_DS1_v2`](https://learn.microsoft.com/en-us/azure/virtual-machines/dv2-dsv2-series#dsv2-series) to [`Standard_D2as_v5`](https://learn.microsoft.com/en-us/azure/virtual-machines/dasv5-dadsv5-series#dasv5-series) ([#1248](https://github.com/poseidon/typhoon/pull/1248))
* Get 2 VCPU, 7 GiB, 12500Mbps (vs 1 VCPU, 3.5GiB, 750 Mbps)
* Small increase in pay-as-you-go price ($53.29 -> $62.78)
* Small increase in spot price ($5.64/mo -> $7.37/mo)
* Change from Intel to AMD EPYC (`D2as_v5` cheaper than `D2s_v5`)
### Flatcar Linux
* Add Flatcar Linux ARM64 support on Azure ([docs](https://typhoon.psdn.io/advanced/arm64/), [#1251](https://github.com/poseidon/typhoon/pull/1251))
* Switch from Azure Hypervisor gen1 to gen2 (**action required**) ([#1248](https://github.com/poseidon/typhoon/pull/1248))
* Run `az vm image terms accept --publish kinvolk --offer flatcar-container-linux-free --plan stable-gen2`
### Docs
* Remove old docs note about not supporting ARM64 with Calico
* Typhoon supports ARM64 with `cilium`, `calico`, and `flannel`
### Addons
* Update Prometheus from v2.38.0 to [v2.39.1](https://github.com/prometheus/prometheus/releases/tag/v2.39.1)
* Update Grafana from v9.1.6 to [v9.1.7](https://github.com/grafana/grafana/releases/tag/v9.1.7)
## v1.25.2
Kubernetes v1.25.2 was skipped since there were minimal changes upstream.
## v1.25.1
* Kubernetes [v1.25.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1251)
* Update etcd from v3.5.4 to [v3.5.5](https://github.com/etcd-io/etcd/releases/tag/v3.5.5)
* Update Cilium from v1.12.1 to [v1.12.2](https://github.com/cilium/cilium/releases/tag/v1.12.2)
* Update Calico from v3.23.3 to [v3.24.1](https://github.com/projectcalico/calico/releases/tag/v3.24.1)
* Revert Kubelet Graceful Node Shutdown on worker nodes ([#1227](https://github.com/poseidon/typhoon/pull/1227))
* Fix issue where non-critical pods are left in Error/Completed state on node shutdown
* Remove feature flag disable workaround for [kubernetes/kubernetes#112081](https://github.com/kubernetes/kubernetes/issues/112081)
* Kubernetes [reverted](https://github.com/kubernetes/kubernetes/pull/112078) `LocalStorageCapacityIsolationFSQuotaMonitoring` back to alpha
* Remove workaround for preventing `search .` propagation in [kubernetes/kubernetes#112135](https://github.com/kubernetes/kubernetes/issues/112135)
* Upstream Kubernetes [fix](https://github.com/kubernetes/kubernetes/pull/112157)
### Addons
* Update kube-state-metrics from v2.5.0 to [v2.6.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.6.0)
* Update ingress-nginx from v1.3.0 to [v1.3.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.3.1)
* Update Grafana from v9.1.0 to [v9.1.6](https://github.com/grafana/grafana/releases/tag/v9.1.6)
## v1.25.0
* Kubernetes [v1.25.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.25.md#v1250)
* Disable LocalStorageCapacityIsolationFSQuotaMonitoring feature gate ([#1220](https://github.com/poseidon/typhoon/pull/1220), fixes [kubernetes#112081](https://github.com/kubernetes/kubernetes/issues/112081))
* Add workaround to revert adding "search ." to containers' `/etc/resolv.conf` ([#1224](https://github.com/poseidon/typhoon/pull/1224), fixes [kubernetes#112135](https://github.com/kubernetes/kubernetes/issues/112135))
* Migrate most Kubelet flags to KubeletConfiguration file ([#1219](https://github.com/poseidon/typhoon/pull/1219))
* Configure Kubelet Graceful Node Shutdown ([#1222](https://github.com/poseidon/typhoon/pull/1222))
* Allow up to 30s for critical pods to gracefully shutdown on node shutdown
* Allow up to 15s for regular pods to gracefully shutdown on node shutdown
* Mark node NotReady promptly on node shutdown
* Lengthen systemd inhibitor lock max delay from 5s to 45s
### Fedora CoreOS
* Change Podman `log-driver` from `journald` to `k8s-file` ([#1221](https://github.com/poseidon/typhoon/pull/1221))
* Fix `etcd-member` and Kubelet systemd service log lines appearing twice in journal logs
## v1.24.4
* Kubernetes [v1.24.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1244)
* Update CoreDNS from v1.8.6 to [v1.9.3](https://github.com/poseidon/terraform-render-bootstrap/pull/318)
* Update Cilium from v1.11.7 to [v1.12.1](https://github.com/cilium/cilium/releases/tag/v1.12.1)
* Update Calico from v3.23.1 to [v3.23.3](https://github.com/projectcalico/calico/releases/tag/v3.23.3)
* Switch Kubernetes registry from `k8s.gcr.io` to `registry.k8s.io` ([#1206](https://github.com/poseidon/typhoon/pull/1206))
* Remove use of deprecated Terraform [template](https://registry.terraform.io/providers/hashicorp/template) provider ([#1194](https://github.com/poseidon/typhoon/pull/1194))
### Fedora CoreOS
* Remove ineffective `/etc/fedora-coreos/iptables-legacy.stamp` ([#1201](https://github.com/poseidon/typhoon/pull/1201))
* Typhoon already uses iptables v1.8.7 (nf_tables) since FCOS 36
* Staying on legacy iptables required a file in `/etc/coreos` instead
### Flatcar Linux
* Migrate Flatcar Linux from Ignition spec v2.3.0 to v3.3.0 ([#1196](https://github.com/poseidon/typhoon/pull/1196)) (**action required**)
* Flatcar Linux 3185.0.0+ [supports](https://flatcar-linux.org/docs/latest/provisioning/ignition/specification/#ignition-v3) Ignition v3.x specs (which are rendered from Butane Configs, like Fedora CoreOS)
* `poseidon/ct` v0.11.0 [supports](https://github.com/poseidon/terraform-provider-ct/pull/131) the `flatcar` Butane Config variant
* Require poseidon/ct v0.11+ and Flatcar Linux 3185.0.0+
* Please modify any Flatcar Linux snippets to use the [Butane Config](https://coreos.github.io/butane/config-flatcar-v1_0/) format (**action required**)
```tf
variant: flatcar
version: 1.0.0
...
```
### AWS
* [Refresh](https://docs.aws.amazon.com/autoscaling/ec2/userguide/asg-instance-refresh.html) instances in autoscaling group when launch configuration changes ([#1208](https://github.com/poseidon/typhoon/pull/1208)) ([docs](https://typhoon.psdn.io/topics/maintenance/#node-configuration-updates), **important**)
* Worker launch configuration changes start an autoscaling group instance refresh to replace instances
* Instance refresh creates surge instances, waits for a warm-up period, then deletes old instances
* Changing `worker_type`, `disk_*`, `worker_price`, `worker_target_groups`, or Butane `worker_snippets` on existing worker nodes will replace instances
* New AMIs or changing `os_stream` will be ignored, to allow Fedora CoreOS or Flatcar Linux to keep themselves updated
* Previously, new launch configurations were made in the same way, but not applied to instances unless manually replaced
* Rename worker autoscaling group `${cluster_name}-worker` ([#1202](https://github.com/poseidon/typhoon/pull/1202))
* Rename launch configuration `${cluster_name}-worker` instead of a random id
### Google
* [Roll](https://cloud.google.com/compute/docs/instance-groups/rolling-out-updates-to-managed-instance-groups) instance template changes to worker managed instance groups ([#1207](https://github.com/poseidon/typhoon/pull/1207)) ([docs](https://typhoon.psdn.io/topics/maintenance/#node-configuration-updates), **important**)
* Worker instance template changes roll out by gradually replacing instances
* Automatic rollouts create surge instances, wait for health checks, then delete old instances (0 unavailable instances)
* Changing `worker_type`, `disk_size`, `worker_preemptible`, or Butane `worker_snippets` on existing worker nodes will replace instances
* New compute images or changing `os_stream` will be ignored, to allow Fedora CoreOS or Flatcar Linux to keep themselves updated
* Previously, new instance templates were made in the same way, but not applied to instances unless manually replaced
* Add health checks to worker managed instance groups (i.e. "autohealing") ([#1207](https://github.com/poseidon/typhoon/pull/1207))
* Use health checks to probe kube-proxy every 30s
* Replace worker nodes that fail the health check 6 times (3min)
* Name `kube-apiserver` and `worker` health checks consistently ([#1207](https://github.com/poseidon/typhoon/pull/1207))
* Use name `${cluster_name}-apiserver-health` and `${cluster_name}-worker-health`
* Rename managed instance group from `${cluster_name}-worker-group` to `${cluster_name}-worker` ([#1207](https://github.com/poseidon/typhoon/pull/1207))
* Fix bug provisioning clusters with multiple controller nodes ([#1195](https://github.com/poseidon/typhoon/pull/1195))
### Addons
* Update Prometheus from v2.37.0 to [v2.38.0](https://github.com/prometheus/prometheus/releases/tag/v2.38.0)
* Update Grafana from v9.0.3 to [v9.1.0](https://github.com/grafana/grafana/releases/tag/v9.1.0)
## v1.24.3
* Kubernetes [v1.24.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1243)
* Update Cilium from v1.11.6 to [v1.11.7](https://github.com/cilium/cilium/releases/tag/v1.11.7)
### Addons
* Update ingress-nginx from v1.2.1 to [v1.3.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.3.0)
* Update Prometheus from v2.36.1 to [v2.37.0](https://github.com/prometheus/prometheus/releases/tag/v2.37.0)
* Update Grafana from v8.5.6 to [v9.0.3](https://github.com/grafana/grafana/releases/tag/v9.0.3)
### Notes
* Poseidon repos will soon change their default branch from `master` to `main`
## v1.24.2
* Kubernetes [v1.24.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1242)
* Update Cilium from v1.11.5 to [v1.11.6](https://github.com/cilium/cilium/releases/tag/v1.11.6)
* Update Calico from v3.22.2 to [v3.23.1](https://github.com/projectcalico/calico/releases/tag/v3.23.1)
### Addons
* Update Prometheus from v2.36.0 to [v2.36.1](https://github.com/prometheus/prometheus/releases/tag/v2.36.1)
* Update Grafana from v8.5.3 to [v8.5.6](https://github.com/grafana/grafana/releases/tag/v8.5.6)
* Update kube-state-metrics from v2.4.2 to [v2.5.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.5.0)
## Known Issues
* Skip AWS Terraform provider v4.17.0 to v4.19.0, which had a regression affecting workers joining ([#1173](https://github.com/poseidon/typhoon/issues/1173))
## v1.24.1
* Kubernetes [v1.24.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1241)
* Update Cilium from v1.11.4 to [v1.11.5](https://github.com/cilium/cilium/releases/tag/v1.11.5)
### Addons
* Update Prometheus from v2.35.0 to [v2.36.0](https://github.com/prometheus/prometheus/releases/tag/v2.36.0)
* Update Grafana from v8.5.1 to [v8.5.3](https://github.com/grafana/grafana/releases/tag/v8.5.3)
* Update nginx-ingress from v1.2.0 to [v1.2.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.2.1)
## v1.24.0
* Kubernetes [v1.24.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.24.md#v1240)
* Update etcd from v3.5.2 to [v3.5.4](https://github.com/etcd-io/etcd/releases/tag/v3.5.4)
* Add Kubelet mounts to enable relabeling workload volumes ([#1152](https://github.com/poseidon/typhoon/pull/1152))
* StorageClass no longer require explicit SELinux mount contexts
### Addons
* Update nginx-ingress from v1.1.3 to [v1.2.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.2.0)
* Update Prometheus from v2.34.0 to [v2.35.0](https://github.com/prometheus/prometheus/releases/tag/v2.35.0)
* Update Grafana from v8.4.5 to [v8.5.1](https://github.com/grafana/grafana/releases/tag/v8.5.1)
## v1.23.6
* Kubernetes [v1.23.6](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1236)
* Update Cilium from v1.11.2 to [v1.11.4](https://github.com/cilium/cilium/releases/tag/v1.11.4)
* Rename Cilium DaemonSet from `cilium-agent` to `cilium` to match Cilium CLI tools ([#303](https://github.com/poseidon/terraform-render-bootstrap/pull/303))
* Update Calico from v3.22.1 to [v3.22.2](https://github.com/projectcalico/calico/releases/tag/v3.22.2)
* Mount /etc/machine-id from host into Kubelet ([#1143](https://github.com/poseidon/typhoon/pull/1143))
* Remove deprecated use of `key_algorithm` in `hashicorp/tls` resources
### Azure
* Allow upgrading Azure Terraform provider to v3.x ([#1144](https://github.com/poseidon/typhoon/pull/1144))
* Rename `worker_address_prefix` output to `worker_address_prefixes`
### Google Cloud
* Fix issue on Flatcar Linux with controller nodes not ignoring os image changes ([#1149](https://github.com/poseidon/typhoon/pull/1149))
* Nodes will auto-update, Terraform should not attempt to delete/recreate them
### Addons
* Update nginx-ingress from v1.1.2 to [v1.1.3](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.1.3)
* Update Prometheus from v2.33.5 to [v2.34.0](https://github.com/prometheus/prometheus/releases/tag/v2.34.0)
* Update Grafana from v8.4.4 to [v8.4.5](https://github.com/grafana/grafana/releases/tag/v8.4.5)
## v1.23.5
* Kubernetes [v1.23.5](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1235)
* Update Cilium from v1.11.1 to [v1.11.2](https://github.com/cilium/cilium/releases/tag/v1.11.2)
* Update Calico from v3.21.2 to [v3.22.1](https://github.com/projectcalico/calico/releases/tag/v3.22.1)
* Fix [calico#5011](https://github.com/projectcalico/calico/issues/5011), broken since v1.23.0
### Addons
* Refresh Prometheus rules and Grafana dashboards ([#1136](https://github.com/poseidon/typhoon/pull/1136))
* Update nginx-ingress from v1.1.1 to [v1.1.2](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.1.2)
* Update Prometheus from v2.33.3 to [v2.33.5](https://github.com/prometheus/prometheus/releases/tag/v2.33.5)
* Update Grafana from v8.4.1 to [v8.4.3](https://github.com/grafana/grafana/releases/tag/v8.4.3)
* Update kube-state-metrics from v2.3.0 to [v2.4.2](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.4.2)
## v1.23.4
* Kubernetes [v1.23.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1234)
* Update etcd from v3.5.1 to [v3.5.2](https://github.com/etcd-io/etcd/releases/tag/v3.5.2)
* Change default CNI `networking` provider from `calico` to `cilium` ([#1114](https://github.com/poseidon/typhoon/pull/1114))
### AWS
* Allow upgrading AWS Terraform Provider to v4.x
### Addons
* Align nginx-ingress `--controller-class` with `IngressClass`
* Watch only `public` IngressClass objects, better [example](https://kubernetes.github.io/ingress-nginx/user-guide/multiple-ingress/)
* Update Prometheus from v2.32.1 to [v2.33.3](https://github.com/prometheus/prometheus/releases/tag/v2.33.3)
* Update Grafana from v8.3.6 to [v8.4.1](https://github.com/grafana/grafana/releases/tag/v8.4.1)
## V1.23.3
* Kubernetes [v1.23.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1233)
### Flatcar Linux
#### Google Cloud
* Switch to using official Kinvolk Flatcar Linux images
* Promote Typhoon on Flatcar Linux / Google Cloud to stable
* Change `os_image` to `flatcar-stable`, `flatcar-beta`, or `flatcar-alpha` (**action required**)
## v1.23.2
* Kubernetes [v1.23.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1232)
* Update Cilium from v1.11.0 to [v1.11.1](https://github.com/cilium/cilium/releases/tag/v1.11.1)
* Remove Kubelet flag `--network-plugin`. Unused since `docker-shim` isn't used ([#1106](https://github.com/poseidon/typhoon/pull/1106))
### Fedora CoreOS
* Switch Kubernetes Container Runtime from `docker` to `containerd` ([#1101](https://github.com/poseidon/typhoon/pull/1101))
* Mask `docker.service` to prevent it from being socket activated ([#1105](https://github.com/poseidon/typhoon/pull/1105))
### Flatcar Linux
#### AWS
* Add experimental Flatcar Linux ARM64 support ([docs](https://typhoon.psdn.io/advanced/arm64/), [#1102](https://github.com/poseidon/typhoon/pull/1102))
* Add `arch` variable to AWS `kubernetes` and `workers` modules
* Allow arm64 full-cluster or mixed/hybrid cluster with arm64 workers
* Requires `flannel` or `cilium` CNI provider
### DigitalOcean
* Upgrade DigitalOcean Terraform provider to [v2.x](https://registry.terraform.io/providers/digitalocean/digitalocean/latest/docs) ([#1109](https://github.com/poseidon/typhoon/pull/1109))
### Addons
* Update nginx-ingress from v1.1.0 to [v1.1.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.1.1)
* Update Grafana from v8.3.3 to [v8.3.4](https://github.com/grafana/grafana/releases/tag/v8.3.4)
## v1.23.1
* Kubernetes [v1.23.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1231)
* Workaround Terraform v1.1 regression in `file` provisioner ([#1093](https://github.com/poseidon/typhoon/pull/1093))
### Flatcar Linux
* Switch Kubernetes Container Runtime from `docker` to `containerd` ([#1087](https://github.com/poseidon/typhoon/pull/1087))
### Addons
* Configure Prometheus to allow a custom scrape query parameter ([#1095](https://github.com/poseidon/typhoon/pull/1095))
* Configure Prometheus to probe Kubernetes Ingress via `blackbox-exporter` ([#1096](https://github.com/poseidon/typhoon/pull/1096))
* Fix Prometheus Service probes to use `blackbox-exporter`, not `blackbox` ([#1096](https://github.com/poseidon/typhoon/pull/1096))
## v1.23.0
* Kubernetes [v1.23.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.23.md#v1230)
* Normalize CA cert mounts in static Pods and kube-proxy ([#1078](https://github.com/poseidon/typhoon/pull/1078))
* Set Kubelet resolver config to `/run/systemd/resolve/resolv.conf` ([#1082](https://github.com/poseidon/typhoon/pull/1082))
* Update Cilium from v1.10.5 to [v1.11.0](https://github.com/cilium/cilium/releases/tag/v1.11.0) ([#1083](https://github.com/poseidon/typhoon/pull/1083))
* With Calico, add missing `caliconodestatuses` CRD ([#289](https://github.com/poseidon/terraform-render-bootstrap/pull/289))
* Change `enable_aggregation` default to true ([#279](https://github.com/poseidon/terraform-render-bootstrap/pull/279))
* Remove deprecated `--port` from `kube-scheduler` ([#1078](https://github.com/poseidon/typhoon/pull/1078))
### AWS
* Change controller node default `disk_iops` to 3000 ([#1073](https://github.com/poseidon/typhoon/pull/1073))
### Azure
* Fix warning about deprecated `backend_address_pool_id` ([#1086](https://github.com/poseidon/typhoon/pull/1086))
### Fedora CoreOS
* Fix Fedora ARM64 workers to official Fedora CoreOS AMIs ([#1072](https://github.com/poseidon/typhoon/pull/1072))
* Should have been changed alongside controller AMIs in ([#1038](https://github.com/poseidon/typhoon/pull/1038))
* Old Poseidon built ARM64 AMIs have been deleted
### Addons
* Update nginx-ingress from v1.0.5 to [v1.1.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.1.0)
* Update Prometheus from v2.31.1 to [v2.32.0](https://github.com/prometheus/prometheus/releases/tag/v2.32.0)
* Update kube-state-metrics from v2.2.4 to [v2.3.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.3.0)
* Update node-exporter from v1.3.0 to [v1.3.1](https://github.com/prometheus/node_exporter/releases/tag/v1.3.1)
* Update Grafana from v8.2.4 to [v8.3.3](https://github.com/grafana/grafana/releases/tag/v8.3.3)
### Known Issues
* Calico does not yet support Kubernetes v1.23.0, use `flannel` or `cilium` ([calico#5011](https://github.com/projectcalico/calico/issues/5011))
## v1.22.4
* Kubernetes [v1.22.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1224)
* Update CoreDNS from v1.8.4 to [v1.8.6](https://github.com/poseidon/terraform-render-bootstrap/pull/284)
* Update Calico from v3.20.2 to [v3.21.0](https://github.com/projectcalico/calico/releases/tag/v3.21.0)
* Update flannel from v0.14.0 to [v0.15.1](https://github.com/flannel-io/flannel/releases/tag/v0.15.1)
### Google
* Allow use of Terraform provider `google` [v4.0+](https://github.com/hashicorp/terraform-provider-google/releases/tag/v4.0.0)
### Flatcar Linux
* Change Kubelet mounts for cgroups v2 ([#1064](https://github.com/poseidon/typhoon/pull/1064))
* Update cgroup driver from cgroupfs to systemd (Flatcar Linux changed default) ([#1064](https://github.com/poseidon/typhoon/pull/1064))
### Addons
* Update Prometheus from v2.30.3 to [v2.31.1](https://github.com/prometheus/prometheus/releases/tag/v2.31.1)
* Update node-exporter from v1.2.2 to [v1.3.0](https://github.com/prometheus/node_exporter/releases/tag/v1.3.0)
* Update kube-state-metrics from v2.2.3 to [v2.2.4](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.2.4)
* Update Grafana from v8.2.1 to [v8.2.4](https://github.com/grafana/grafana/releases/tag/v8.2.4)
* Update nginx-ingress from v1.0.4 to [v1.0.5](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.0.5)
## v1.23.3
* Kubernetes [v1.22.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1223)
* Update etcd from v3.5.0 to [v3.5.1](https://github.com/etcd-io/etcd/releases/tag/v3.5.1)
* Update Cilium from v1.10.4 to [v1.10.5](https://github.com/cilium/cilium/releases/tag/v1.10.5)
* Update Calico from v3.20.1 to [v3.20.2](https://github.com/projectcalico/calico/releases/tag/v3.20.2)
* Use Calico's iptables legacy vs nft auto-detection
* Update flannel from v0.13.0 to v0.14.0
### Bare-Metal
* Require Terraform provider `poseidon/matchbox` v0.5+ ([#1048](https://github.com/poseidon/typhoon/pull/1048))
### Addons
* Update nginx-ingress from v1.0.0 to [v1.0.4](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.0.4)
* Update Prometheus from v2.29.2 to [v2.30.3](https://github.com/prometheus/prometheus/releases/tag/v2.30.3)
* Update kube-state-metrics from v2.2.0 to [v2.2.3](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.2.3)
* Update Grafana from v8.1.2 to [v8.2.1](https://github.com/grafana/grafana/releases/tag/v8.2.1)
## v1.22.2
* Kubernetes [v1.22.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1222)
* Update Cilium from v1.10.3 to [v1.10.4](https://github.com/cilium/cilium/releases/tag/v1.10.4)
* Update Calico from v3.20.0 to [v3.20.1](https://github.com/projectcalico/calico/releases/tag/v3.20.1)
* Fix access to ClusterIP services with Cilium ([#276](https://github.com/poseidon/terraform-render-bootstrap/pull/276))
### Fedora CoreOS
* Use Fedora CoreOS ARM64 AMIs ([#1038](https://github.com/poseidon/typhoon/pull/1038))
### Addons
* Update Prometheus from v2.29.1 to [v2.29.2](https://github.com/prometheus/prometheus/releases/tag/v2.29.2)
* Update kube-state-metrics from v2.1.1 to [v2.2.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.2.0)
## v1.22.1
* Kubernetes [v1.22.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1221)
* Update Calico from v3.19.1 to [v3.20.0](https://github.com/projectcalico/calico/releases/tag/v3.20.0)
### Addons
* Update nginx-ingress from v1.0.0-beta.1 to [v1.0.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.0.0)
* Update Prometheus from v2.28.1 to [v2.29.1](https://github.com/prometheus/prometheus/releases/tag/v2.29.1)
* Update Grafana from v8.1.1 to [v8.1.2](https://github.com/grafana/grafana/releases/tag/v8.1.2)
## v1.22.0
* Kubernetes [v1.22.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.22.md#v1220)
* Update etcd from v3.4.16 to [v3.5.0](https://github.com/etcd-io/etcd/releases/tag/v3.5.0)
* Switch `kube-controller-manager` and `kube-scheduler` to use secure port only
* Update Prometheus config to discover endpoints and use a bearer token to scrape
### Fedora CoreOS
* Add Cilium cgroups v2 support on Fedora CoreOS
* Update Butane Config version from v1.2.0 to v1.4.0
* Rename Fedora CoreOS Config to Butane Config
* Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customizations to update to v1.4.0
### Addons
* Update nginx-ingress from v0.47.0 to [v1.0.0-beta.1](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v1.0.0-beta.1)
* Update node-exporter from v1.2.0 to [v1.2.2](https://github.com/prometheus/node_exporter/releases/tag/v1.2.2)
* Update kube-state-metrics from v2.1.0 to [v2.1.1](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.1.1)
* Update Grafana from v8.0.6 to [v8.1.1](https://github.com/grafana/grafana/releases/tag/v8.1.1)
## v1.21.3
* Kubernetes [v1.21.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1213)
* Update Cilium from v1.10.1 to [v1.10.3](https://github.com/cilium/cilium/releases/tag/v1.10.3)
* Require [poseidon/ct](https://github.com/poseidon/terraform-provider-ct) Terraform provider v0.9+ ([notes](https://typhoon.psdn.io/topics/maintenance/#upgrade-terraform-provider-ct))
### AWS
* Change default disk type from `gp2` to `gp3` ([#1012](https://github.com/poseidon/typhoon/pull/1012))
### Addons
* Update Prometheus from v2.28.0 to [v2.28.1](https://github.com/prometheus/prometheus/releases/tag/v2.28.1)
* Update node-exporter from v1.1.2 to [v1.2.0](https://github.com/prometheus/node_exporter/releases/tag/v1.2.0)
* Update Grafana from v8.0.3 to [v8.0.6](https://github.com/grafana/grafana/releases/tag/v8.0.6)
### Known Issues
* Cilium with recent Fedora CoreOS will have networking issues ([fedora-coreos#881](https://github.com/coreos/fedora-coreos-tracker/issues/881)) (fixed in v1.21.4)
## v1.21.2
* Kubernetes [v1.21.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1212)
* Add Terraform v1.0.x support ([#974](https://github.com/poseidon/typhoon/pull/974))
* Continue to support Terraform v0.13.x, v0.14.4+, and v0.15.x
* Update CoreDNS from v1.8.0 to [v1.8.4]([#1006](https://github.com/poseidon/typhoon/pull/1006))
* Update Cilium from v1.9.6 to [v1.10.1](https://github.com/cilium/cilium/releases/tag/v1.10.1)
* Update Calico from v3.19.0 to [v3.19.1](https://github.com/projectcalico/calico/releases/tag/v3.19.1)
### Addons
* Update kube-state-metrics from v2.0.0 to [v2.1.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.1.0)
* Update Prometheus from v2.27.0 to [v2.28.0](https://github.com/prometheus/prometheus/releases/tag/v2.28.0)
* Update Grafana from v7.5.6 to [v8.0.3](https://github.com/grafana/grafana/releases/tag/v8.0.3)
* Update nginx-ingress from v0.46.0 to [v0.47.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.47.0)
### Fedora CoreOS
#### AWS
* Extend experimental Fedora CoreOS arm64 support with Cilium
* CNI provider may now be `flannel` or `cilium` (new)
#### Bare-Metal
* Workaround systemd path unit issue [fedora-coreos-tracker/#861](https://github.com/coreos/fedora-coreos-tracker/issues/861)
#### DigitalOcean
* Workaround systemd path unit issue [fedora-coreos-tracker/#861](https://github.com/coreos/fedora-coreos-tracker/issues/861)
### Known Issues
* Cilium with recent Fedora CoreOS will have networking issues ([fedora-coreos#881](https://github.com/coreos/fedora-coreos-tracker/issues/881)) (fixed in v1.21.4)
## v1.21.1
* Kubernetes [v1.21.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1211)
* Add Terraform v0.15.x support ([#974](https://github.com/poseidon/typhoon/pull/974))
* Continue to support Terraform v0.13.x and v0.14.4+
* Update etcd from v3.4.15 to [v3.4.16](https://github.com/etcd-io/etcd/releases/tag/v3.4.16)
* Update Cilium from v1.9.5 to [v1.9.6](https://github.com/cilium/cilium/releases/tag/v1.9.6)
* Update Calico from v3.18.1 to [v3.19.0](https://github.com/projectcalico/calico/releases/tag/v3.19.0)
### AWS
* Reduce the default `disk_size` from 40GB to 30GB ([#983](https://github.com/poseidon/typhoon/pull/983))
### Azure
* Reduce the default `disk_size` from 40GB to 30GB ([#983](https://github.com/poseidon/typhoon/pull/983))
### Google Cloud
* Reduce the default `disk_size` from 40GB to 30GB ([#983](https://github.com/poseidon/typhoon/pull/983))
### Fedora CoreOS
* Update Kubelet mounts for cgroups v2 ([#978](https://github.com/poseidon/typhoon/pull/978))
### Addons
* Update kube-state-metrics from v2.0.0-rc.1 to [v2.0.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0)
* Update Prometheus from v2.25.2 to [v2.27.0](https://github.com/prometheus/prometheus/releases/tag/v2.27.0)
* Update Grafana from v7.5.3 to [v7.5.6](https://github.com/grafana/grafana/releases/tag/v7.5.6)
* Update nginx-ingress from v0.45.0 to [v0.46.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.46.0)
## v1.21.0
* Kubernetes [v1.21.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1210)
* Enable `tokencleaner` controller ([#969](https://github.com/poseidon/typhoon/pull/969))
* Enable `kube-scheduler` and `kube-controller-manager` separate authn/z kubeconfig
* Change CNI config location from /etc/kubernetes/cni/net.d to /etc/cni/net.d ([#965](https://github.com/poseidon/typhoon/pull/965))
* Change `kube-controller-manager` to mount `/var/lib/kubelet/volumeplugins` directly
* Remove unused `cloud-provider` flags
* Update Fedora CoreOS Config version from v1.1.0 to v1.2.0 ([#970](https://github.com/poseidon/typhoon/pull/970))
* Require [poseidon/ct](https://github.com/poseidon/terraform-provider-ct) Terraform provider v0.8+ ([notes](https://typhoon.psdn.io/topics/maintenance/#upgrade-terraform-provider-ct))
* Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customizations to update to v1.2.0
### AWS
* Allow setting custom initial node taints on worker pools ([#968](https://github.com/poseidon/typhoon/pull/968))
* Add `node_taints` variable to internal `workers` pool module to set initial node taints
* Add `daemonset_tolerations` so `kube-system` DaemonSets can tolerate custom taints
### Azure
* Allow setting custom initial node taints on worker pools ([#968](https://github.com/poseidon/typhoon/pull/968))
* Add `node_taints` variable to internal `workers` pool module to set initial node taints
* Add `daemonset_tolerations` so `kube-system` DaemonSets can tolerate custom taints
* Remove deprecated `azurerm_lb_backend_address_pool` field `resource_group_name` ([#972](https://github.com/poseidon/typhoon/pull/972))
### Google Cloud
* Allow setting custom initial node taints on worker pools ([#968](https://github.com/poseidon/typhoon/pull/968))
* Add `node_taints` variable to internal `workers` pool module to set initial node taints
* Add `daemonset_tolerations` so `kube-system` DaemonSets can tolerate custom taints
### Addons
* Update nginx-ingress from v0.44.0 to [v0.45.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.45.0)
* Update kube-state-metrics from v2.0.0-rc.0 to [v2.0.0-rc.1](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-rc.1)
* Update Grafana from v7.4.5 to [v7.5.3](https://github.com/grafana/grafana/releases/tag/v7.5.3)
## v1.20.5
* Kubernetes [v1.20.5](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1205)
* Update etcd from v3.4.14 to [v3.4.15](https://github.com/etcd-io/etcd/releases/tag/v3.4.15)
* Update Cilium from v1.9.4 to [v1.9.5](https://github.com/cilium/cilium/releases/tag/v1.9.5)
* Update Calico from v3.17.3 to [v3.18.1](https://github.com/projectcalico/calico/releases/tag/v3.18.1)
* Update CoreDNS from v1.7.0 to [v1.8.0](https://coredns.io/2020/10/22/coredns-1.8.0-release/)
* Mark bootstrap token as sensitive in Terraform plans ([#949](https://github.com/poseidon/typhoon/pull/949))
### Fedora CoreOS
* Set Kubelet `provider-id` ([#951](https://github.com/poseidon/typhoon/pull/951))
### Flatcar Linux
#### AWS
* Set Kubelet `provider-id` ([#951](https://github.com/poseidon/typhoon/pull/951))
* Remove `os_image` option `flatcar-edge` ([#943](https://github.com/poseidon/typhoon/pull/943))
#### Azure
* Remove `os_image` option `flatcar-edge` ([#943](https://github.com/poseidon/typhoon/pull/943))
#### Bare-Metal
* Remove `os_channel` option `flatcar-edge` ([#943](https://github.com/poseidon/typhoon/pull/943))
### Addons
* Update Prometheus from v2.25.0 to [v2.25.2](https://github.com/prometheus/prometheus/releases/tag/v2.25.2)
* Update kube-state-metrics from v2.0.0-alpha.3 to [v2.0.0-rc.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-rc.0)
* Switch image from `quay.io` to `k8s.gcr.io` ([#946](https://github.com/poseidon/typhoon/pull/946))
* Update node-exporter from v1.1.1 to [v1.1.2](https://github.com/prometheus/node_exporter/releases/tag/v1.1.2)
* Update Grafana from v7.4.2 to [v7.4.5](https://github.com/grafana/grafana/releases/tag/v7.4.5)
## v1.20.4
* Kubernetes [v1.20.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1204)
* Update Cilium from v1.9.1 to [v1.9.4](https://github.com/cilium/cilium/releases/tag/v1.9.4)
* Update Calico from v3.17.1 to [v3.17.3](https://github.com/projectcalico/calico/releases/tag/v3.17.3)
* Update flannel-cni from v0.4.1 to [v0.4.2](https://github.com/poseidon/flannel-cni/releases/tag/v0.4.2)
### Addons
* Update nginx-ingress from v0.43.0 to [v0.44.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.44.0)
* Update Prometheus from v2.24.0 to [v2.25.0](https://github.com/prometheus/prometheus/releases/tag/v2.25.0)
* Update node-exporter from v1.0.1 to [v1.1.1](https://github.com/prometheus/node_exporter/releases/tag/v1.1.1)
* Update Grafana from v7.3.7 to [v7.4.2](https://github.com/grafana/grafana/releases/tag/v7.4.2)
## v1.20.2
* Kubernetes [v1.20.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1202)
* Support Terraform v0.13.x and v0.14.4+ ([#924](https://github.com/poseidon/typhoon/pull/923))
### Addons
* Update nginx-ingress from v0.41.2 to [v0.43.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.43.0)
* Update Prometheus from v2.23.0 to [v2.24.0](https://github.com/prometheus/prometheus/releases/tag/v2.24.0)
* Update Grafana from v7.3.6 to [v7.3.7](https://github.com/grafana/grafana/releases/tag/v7.3.7)
## v1.20.1
* Kubernetes [v1.20.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1201)
### Fedora CoreOS
* Fedora CoreOS 33 has stronger crypto defaults ([**notice**](https://docs.fedoraproject.org/en-US/fedora-coreos/faq/#_why_does_ssh_stop_working_after_upgrading_to_fedora_33), [#915](https://github.com/poseidon/typhoon/issues/915))
* Use a non-RSA SSH key or add the workaround provided in upstream [Fedora docs](https://docs.fedoraproject.org/en-US/fedora-coreos/faq/#_why_does_ssh_stop_working_after_upgrading_to_fedora_33) as a [snippet](https://typhoon.psdn.io/advanced/customization/#fedora-coreos) (**action required**)
### Addons
* Update Grafana from v7.3.5 to [v7.3.6](https://github.com/grafana/grafana/releases/tag/v7.3.6)
## v1.20.0
* Kubernetes [v1.20.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1200)
* Add input variable validations ([#880](https://github.com/poseidon/typhoon/pull/880))
* Require Terraform v0.13+ ([migration guide](https://typhoon.psdn.io/topics/maintenance/#terraform-versions))
* Set output sensitive to suppress console display for some cases ([#885](https://github.com/poseidon/typhoon/pull/885))
* Add service account token [volume projection](https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/#service-account-token-volume-projection) ([#897](https://github.com/poseidon/typhoon/pull/897))
* Scope kube-scheduler and kube-controller-manager permissions ([#898](https://github.com/poseidon/typhoon/pull/898))
* Update etcd from v3.4.12 to [v3.4.14](https://github.com/etcd-io/etcd/releases/tag/v3.4.14)
* Update Calico from v3.16.5 to v3.17.1 ([#890](https://github.com/poseidon/typhoon/pull/890))
* Enable Calico MTU auto-detection
* Remove [workaround](https://github.com/poseidon/typhoon/pull/724) to Calico cni-plugin [issue](https://github.com/projectcalico/cni-plugin/issues/874)
* Update Cilium from v1.9.0 to [v1.9.1](https://github.com/cilium/cilium/releases/tag/v1.9.1)
* Relax `terraform-provider-ct` version constraint to v0.6+ ([#893](https://github.com/poseidon/typhoon/pull/893))
* Allow upgrading `terraform-provider-ct` to v0.7.x ([warn](https://typhoon.psdn.io/topics/maintenance/#upgrade-terraform-provider-ct))
### AWS
* Enable Network Load Balancer (NLB) dualstack ([#883](https://github.com/poseidon/typhoon/pull/883))
* NLB subnets assigned both IPv4 and IPv6 addresses
* NLB DNS name has both A and AAAA records
* NLB to target node traffic is IPv4 (no change)
### Bare-Metal
* Remove iSCSI `/etc/iscsi` and `iscsadm` mounts from Kubelet ([#912](https://github.com/poseidon/typhoon/pull/912))
### Fedora CoreOS
#### AWS
* Fix AMI query for which could fail in some regions ([#887](https://github.com/poseidon/typhoon/pull/887))
#### Bare-Metal
* Promote Fedora CoreOS to stable
* Use initramfs and rootfs images as initrd's ([#889](https://github.com/poseidon/typhoon/pull/889))
* Requires Fedora CoreOS version with rootfs images (e.g. 32.20200923.3.0+)
### Addons
* Update Prometheus from v2.22.2 to [v2.23.0](https://github.com/prometheus/prometheus/releases/tag/v2.23.0)
* Update kube-state-metrics from v2.0.0-alpha.2 to [v2.0.0-alpha.3](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.3)
* Update Grafana from v7.3.2 to [v7.3.5](https://github.com/grafana/grafana/releases/tag/v7.3.5)
## v1.19.4
* Kubernetes [v1.19.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1194)
* Update Cilium from v1.8.4 to [v1.9.0](https://github.com/cilium/cilium/releases/tag/v1.9.0)
* Update Calico from v3.16.3 to [v3.16.5](https://github.com/projectcalico/calico/releases/tag/v3.16.5)
* Remove `asset_dir` variable (defaulted off in [v1.17.0](https://github.com/poseidon/typhoon/pull/595), deprecated in [v1.18.0](https://github.com/poseidon/typhoon/pull/678))
### Fedora CoreOS
* Improve `etcd-member.service` systemd unit ([#868](https://github.com/poseidon/typhoon/pull/868))
* Allow a snippet with a systemd dropin to set an alternate image (e.g. mirror)
* Fix local node delete oneshot on node shutdown ([#856](https://github.com/poseidon/typhoon/pull/855))
#### AWS
* Add experimental Fedora CoreOS arm64 support ([docs](https://typhoon.psdn.io/advanced/arm64/), [#875](https://github.com/poseidon/typhoon/pull/875))
* Allow arm64 full-cluster or mixed/hybrid cluster with worker pools
* Add `arch` variable to cluster module
* Add `daemonset_tolerations` variable to cluster module
* Add `node_taints` variable to workers module
* Requires flannel CNI provider and use of experimental AMI (see docs)
### Flatcar Linux
* Rename `container-linux` modules to `flatcar-linux` ([#858](https://github.com/poseidon/typhoon/issues/858)) (**action required**)
* Change on-host system containers from rkt to docker
* Change `etcd-member.service` container runnner from rkt to docker ([#867](https://github.com/poseidon/typhoon/pull/867))
* Change `kubelet.service` container runner from rkt-fly to docker ([#855](https://github.com/poseidon/typhoon/pull/855))
* Change `bootstrap.service` container runner from rkt to docker ([#873](https://github.com/poseidon/typhoon/pull/873))
* Change `delete-node.service` to use docker and an inline ExecStart ([#855](https://github.com/poseidon/typhoon/pull/855))
* Fix local node delete oneshot on node shutdown ([#855](https://github.com/poseidon/typhoon/pull/855))
* Remove CoreOS Container Linux Matchbox profiles ([#859](https://github.com/poseidon/typhoon/pull/858))
### Addons
* Update nginx-ingress from v0.40.2 to [v0.41.2](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.41.2)
* Update Prometheus from v2.22.0 to [v2.22.1](https://github.com/prometheus/prometheus/releases/tag/v2.22.1)
* Update kube-state-metrics from v2.0.0-alpha.1 to [v2.0.0-alpha.2](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.2)
* Update Grafana from v7.2.1 to [v7.3.2](https://github.com/grafana/grafana/releases/tag/v7.3.2)
## v1.19.3
* Kubernetes [v1.19.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1193)
* Update Cilium from v1.8.3 to [v1.8.4](https://github.com/cilium/cilium/releases/tag/v1.8.4)
* Update Calico from v1.15.3 to [v1.16.3](https://github.com/projectcalico/calico/releases/tag/v3.16.3) ([#851](https://github.com/poseidon/typhoon/pull/851))
* Update flannel from v0.13.0-rc2 to v0.13.0 ([#219](https://github.com/poseidon/terraform-render-bootstrap/pull/219))
### Flatcar Linux
* Remove references to CoreOS Container Linux ([#839](https://github.com/poseidon/typhoon/pull/839))
* Fix error querying for coreos AMI on AWS ([#838](https://github.com/poseidon/typhoon/issues/838))
### Addons
* Update nginx-ingress from v0.35.0 to [v0.40.2](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.40.2)
* Update Grafana from v7.1.5 to [v7.2.1](https://github.com/grafana/grafana/releases/tag/v7.2.1)
* Update Prometheus from v2.21.0 to [v2.22.0](https://github.com/prometheus/prometheus/releases/tag/v2.22.0)
* Update kube-state-metrics from v1.9.7 to [v2.0.0-alpha.1](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.1)
## v1.19.2
* Kubernetes [v1.19.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1192)
* Update flannel from v0.12.0 to v0.13.0-rc2 ([#216](https://github.com/poseidon/terraform-render-bootstrap/pull/216))
* Update flannel-cni from v0.4.0 to v0.4.1
* Update CNI plugins from v0.8.6 to v0.8.7
### Addons
* Refresh Prometheus rules/alerts and Grafana dashboards ([#831](https://github.com/poseidon/typhoon/pull/831))
* Reduce apiserver metrics cardinality for non-core APIs ([#830](https://github.com/poseidon/typhoon/pull/830))
## v1.19.1
* Kubernetes [v1.19.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1191)
* Change control plane seccomp annotations to GA `seccompProfile` ([#822](https://github.com/poseidon/typhoon/pull/822))
* Update Cilium from v1.8.2 to [v1.8.3](https://github.com/cilium/cilium/releases/tag/v1.8.3)
* Promote Cilium from experimental to general availability ([#827](https://github.com/poseidon/typhoon/pull/827))
* Update Calico from v1.15.2 to [v1.15.3](https://github.com/projectcalico/calico/releases/tag/v3.15.3)
### Fedora CoreOS
* Update Fedora CoreOS Config version from v1.0.0 to v1.1.0
* Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customizations to update to v1.1.0
### Addons
* Update IngressClass resources to `networking.k8s.io/v1` ([#824](https://github.com/poseidon/typhoon/pull/824))
* Update Prometheus from v2.20.0 to [v2.21.0](https://github.com/prometheus/prometheus/releases/tag/v2.21.0)
* Remove Kubernetes node name labelmap `relabel_config` from etcd, Kubelet, and CAdvisor scrape config ([#828](https://github.com/poseidon/typhoon/pull/828))
## v1.19.0
* Kubernetes [v1.19.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1190)
* Update etcd from v3.4.10 to [v3.4.12](https://github.com/etcd-io/etcd/releases/tag/v3.4.12)
* Update Calico from v3.15.1 to [v3.15.2](https://docs.projectcalico.org/v3.15/release-notes/)
### Fedora CoreOS
* Fix race condition during bootstrap of multi-controller clusters ([#808](https://github.com/poseidon/typhoon/pull/808))
* Fix SELinux label of bootstrap-secrets on non-bootstrap controllers
### Addons
* Introduce [fleetlock](https://github.com/poseidon/fleetlock) for Fedora CoreOS reboot coordination ([#814](https://github.com/poseidon/typhoon/pull/814))
* Update nginx-ingress from v0.34.1 to [v0.35.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.35.0)
* Repository changed to `k8s.gcr.io/ingress-nginx/controller`
* Update Grafana from v7.1.3 to [v7.1.5](https://github.com/grafana/grafana/releases/tag/v7.1.5)
## v1.18.8
* Kubernetes [v1.18.8](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1188)
* Migrate from Terraform v0.12.x to v0.13.x ([#804](https://github.com/poseidon/typhoon/pull/804)) (**action required**)
* Recommend Terraform v0.13.x ([migration guide](https://typhoon.psdn.io/topics/maintenance/#terraform-versions))
* Support automatic install of poseidon's provider plugins ([poseidon/ct](https://registry.terraform.io/providers/poseidon/ct/latest), [poseidon/matchbox](https://registry.terraform.io/providers/poseidon/matchbox/latest))
* Require Terraform v0.12.26+ (migration compatibility)
* Require `terraform-provider-ct` v0.6.1
* Require `terraform-provider-matchbox` v0.4.1
* Update etcd from v3.4.9 to [v3.4.10](https://github.com/etcd-io/etcd/releases/tag/v3.4.10)
* Update CoreDNS from v1.6.7 to [v1.7.0](https://coredns.io/2020/06/15/coredns-1.7.0-release/)
* Update Cilium from v1.8.1 to [v1.8.2](https://github.com/cilium/cilium/releases/tag/v1.8.2)
* Update [coreos/flannel-cni](https://github.com/coreos/flannel-cni) to [poseidon/flannel-cni](https://github.com/poseidon/flannel-cni) ([#798](https://github.com/poseidon/typhoon/pull/798))
* Update CNI plugins and fix CVEs with Flannel CNI (non-default)
* Transition to a poseidon maintained container image
### AWS
* Allow `terraform-provider-aws` v3.0+ ([#803](https://github.com/poseidon/typhoon/pull/803))
* Recommend updating `terraform-provider-aws` to v3.0+
* Continue to allow v2.23+, no v3.x specific features are used
### DigitalOcean
* Require `terraform-provider-digitalocean` v1.21+ for Terraform v0.13.x (unenforced)
* Require `terraform-provider-digitalocean` v1.20+ for Terraform v0.12.x
### Fedora CoreOS
* Fix support for Flannel with Fedora CoreOS ([#795](https://github.com/poseidon/typhoon/pull/795))
* Configure `flannel.1` link to select its own MAC address to solve flannel
pod-to-pod traffic drops starting with default link changes in Fedora CoreOS
32.20200629.3.0 ([details](https://github.com/coreos/fedora-coreos-tracker/issues/574#issuecomment-665487296))
#### Addons
* Update Prometheus from v2.19.2 to [v2.20.0](https://github.com/prometheus/prometheus/releases/tag/v2.20.0)
* Update Grafana from v7.0.6 to [v7.1.3](https://github.com/grafana/grafana/releases/tag/v7.1.3)
## v1.18.6
* Kubernetes [v1.18.6](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1186)

View File

@ -1,4 +1,6 @@
# Typhoon <img align="right" src="https://storage.googleapis.com/poseidon/typhoon-logo.png">
# Typhoon [![Release](https://img.shields.io/github/v/release/poseidon/typhoon)](https://github.com/poseidon/typhoon/releases) [![Stars](https://img.shields.io/github/stars/poseidon/typhoon)](https://github.com/poseidon/typhoon/stargazers) [![Sponsors](https://img.shields.io/github/sponsors/poseidon?logo=github)](https://github.com/sponsors/poseidon) [![Mastodon](https://img.shields.io/badge/follow-news-6364ff?logo=mastodon)](https://fosstodon.org/@typhoon)
<img align="right" src="https://storage.googleapis.com/poseidon/typhoon-logo.png">
Typhoon is a minimal and free Kubernetes distribution.
@ -11,10 +13,10 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
* Kubernetes v1.18.6 (upstream)
* Kubernetes v1.26.1 (upstream)
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/cl/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/flatcar-linux/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
* Ready for Ingress, Prometheus, Grafana, CSI, or other [addons](https://typhoon.psdn.io/addons/overview/)
## Modules
@ -27,19 +29,28 @@ Typhoon is available for [Fedora CoreOS](https://getfedora.org/coreos/).
|---------------|------------------|------------------|--------|
| AWS | Fedora CoreOS | [aws/fedora-coreos/kubernetes](aws/fedora-coreos/kubernetes) | stable |
| Azure | Fedora CoreOS | [azure/fedora-coreos/kubernetes](azure/fedora-coreos/kubernetes) | alpha |
| Bare-Metal | Fedora CoreOS | [bare-metal/fedora-coreos/kubernetes](bare-metal/fedora-coreos/kubernetes) | beta |
| Bare-Metal | Fedora CoreOS | [bare-metal/fedora-coreos/kubernetes](bare-metal/fedora-coreos/kubernetes) | stable |
| DigitalOcean | Fedora CoreOS | [digital-ocean/fedora-coreos/kubernetes](digital-ocean/fedora-coreos/kubernetes) | beta |
| Google Cloud | Fedora CoreOS | [google-cloud/fedora-coreos/kubernetes](google-cloud/fedora-coreos/kubernetes) | stable |
| Platform | Operating System | Terraform Module | Status |
|---------------|------------------|------------------|--------|
| AWS | Fedora CoreOS (ARM64) | [aws/fedora-coreos/kubernetes](aws/fedora-coreos/kubernetes) | alpha |
Typhoon is available for [Flatcar Linux](https://www.flatcar-linux.org/releases/).
| Platform | Operating System | Terraform Module | Status |
|---------------|------------------|------------------|--------|
| AWS | Flatcar Linux | [aws/container-linux/kubernetes](aws/container-linux/kubernetes) | stable |
| Azure | Flatcar Linux | [azure/container-linux/kubernetes](azure/container-linux/kubernetes) | alpha |
| Bare-Metal | Flatcar Linux | [bare-metal/container-linux/kubernetes](bare-metal/container-linux/kubernetes) | stable |
| DigitalOcean | Flatcar Linux | [digital-ocean/container-linux/kubernetes](digital-ocean/container-linux/kubernetes) | beta |
| Google Cloud | Flatcar Linux | [google-cloud/container-linux/kubernetes](google-cloud/container-linux/kubernetes) | beta |
| AWS | Flatcar Linux | [aws/flatcar-linux/kubernetes](aws/flatcar-linux/kubernetes) | stable |
| Azure | Flatcar Linux | [azure/flatcar-linux/kubernetes](azure/flatcar-linux/kubernetes) | alpha |
| Bare-Metal | Flatcar Linux | [bare-metal/flatcar-linux/kubernetes](bare-metal/flatcar-linux/kubernetes) | stable |
| DigitalOcean | Flatcar Linux | [digital-ocean/flatcar-linux/kubernetes](digital-ocean/flatcar-linux/kubernetes) | beta |
| Google Cloud | Flatcar Linux | [google-cloud/flatcar-linux/kubernetes](google-cloud/flatcar-linux/kubernetes) | stable |
| Platform | Operating System | Terraform Module | Status |
|---------------|------------------|------------------|--------|
| AWS | Flatcar Linux (ARM64) | [aws/flatcar-linux/kubernetes](aws/flatcar-linux/kubernetes) | alpha |
| Azure | Flatcar Linux (ARM64) | [azure/flatcar-linux/kubernetes](azure/flatcar-linux/kubernetes) | alpha |
## Documentation
@ -54,7 +65,7 @@ Define a Kubernetes cluster by using the Terraform module for your chosen platfo
```tf
module "yavin" {
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.18.6"
source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.26.1"
# Google Cloud
cluster_name = "yavin"
@ -63,7 +74,7 @@ module "yavin" {
dns_zone_name = "example-zone"
# configuration
ssh_authorized_key = "ssh-rsa AAAAB3Nz..."
ssh_authorized_key = "ssh-ed25519 AAAAB3Nz..."
# optional
worker_count = 2
@ -93,9 +104,9 @@ In 4-8 minutes (varies by platform), the cluster will be ready. This Google Clou
$ export KUBECONFIG=/home/user/.kube/configs/yavin-config
$ kubectl get nodes
NAME ROLES STATUS AGE VERSION
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.18.6
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.18.6
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.18.6
yavin-controller-0.c.example-com.internal <none> Ready 6m v1.26.1
yavin-worker-jrbf.c.example-com.internal <none> Ready 5m v1.26.1
yavin-worker-mzdm.c.example-com.internal <none> Ready 5m v1.26.1
```
List the pods.
@ -126,7 +137,7 @@ Typhoon is strict about minimalism, maturity, and scope. These are not in scope:
## Help
Ask questions on the IRC #typhoon channel on [freenode.net](http://freenode.net/).
Schedule a meeting via [Github Sponsors](https://github.com/sponsors/poseidon?frequency=one-time) to discuss your use case.
## Motivation
@ -136,12 +147,24 @@ Typhoon addresses real world needs, which you may share. It is honest about limi
## Social Contract
Typhoon is not a product, trial, or free-tier. It is not run by a company, does not offer support or services, and does not accept or make any money. It is not associated with any operating system or platform vendor.
Typhoon is not a product, trial, or free-tier. Typhoon does not offer support, services, or charge money. And Typhoon is independent of operating system or platform vendors.
Typhoon clusters will contain only [free](https://www.debian.org/intro/free) components. Cluster components will not collect data on users without their permission.
## Donations
## Sponsors
Typhoon does not accept money donations. Instead, we encourage you to donate to one of [these organizations](https://github.com/poseidon/typhoon/wiki/Donations) to show your appreciation.
Poseidon's Github [Sponsors](https://github.com/sponsors/poseidon) support the infrastructure and operational costs of providing Typhoon.
* [DigitalOcean](https://www.digitalocean.com/) kindly provides credits to support Typhoon test clusters.
<a href="https://www.digitalocean.com/">
<img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_blue.svg" width="201px">
</a>
<br>
<br>
<a href="https://deploy.equinix.com/">
<img src="https://storage.googleapis.com/poseidon/equinix.png" width="201px">
</a>
<br>
<br>
If you'd like your company here, please contact dghubble at psdn.io.

View File

@ -37,6 +37,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -49,6 +50,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -72,7 +74,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(coredns_dns_request_count_total{instance=~\"$instance\"}[5m])) by (proto)",
"expr": "sum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m])) by (proto)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{proto}}",
@ -128,6 +130,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -140,6 +143,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -163,7 +167,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(coredns_dns_request_type_count_total{instance=~\"$instance\"}[5m])) by (type)",
"expr": "sum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m])) by (type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{type}}",
@ -219,6 +223,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -231,6 +236,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -254,7 +260,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(coredns_dns_request_count_total{instance=~\"$instance\"}[5m])) by (zone)",
"expr": "sum(rate(coredns_dns_requests_total{instance=~\"$instance\"}[5m])) by (zone)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{zone}}",
@ -323,6 +329,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -335,6 +342,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": false
},
@ -428,6 +436,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -440,6 +449,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": false
},
@ -463,7 +473,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(coredns_dns_response_rcode_count_total{instance=~\"$instance\"}[5m])) by (rcode)",
"expr": "sum(rate(coredns_dns_responses_total{instance=~\"$instance\"}[5m])) by (rcode)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{rcode}}",
@ -532,6 +542,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -544,6 +555,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": false
},
@ -637,6 +649,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -649,6 +662,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": false
},
@ -755,6 +769,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -767,6 +782,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": false
},
@ -790,7 +806,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(coredns_cache_size{instance=~\"$instance\"}) by (type)",
"expr": "sum(coredns_cache_entries{instance=~\"$instance\"}) by (type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{type}}",
@ -846,6 +862,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -858,6 +875,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": false
},

View File

@ -11,7 +11,6 @@ data:
"editable": true,
"gnetId": null,
"hideControls": false,
"id": 6,
"links": [
],
@ -141,7 +140,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[5m]))",
"expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "RPC Rate",
@ -150,7 +149,7 @@ data:
"step": 2
},
{
"expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code!=\"OK\"}[5m]))",
"expr": "sum(rate(grpc_server_handled_total{job=\"$cluster\",grpc_type=\"unary\",grpc_code=~\"Unknown|FailedPrecondition|ResourceExhausted|Internal|Unavailable|DataLoss|DeadlineExceeded\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "RPC Failed Rate",
@ -343,7 +342,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "etcd_debugging_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
"expr": "etcd_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
"hide": false,
"interval": "",
"intervalFactor": 2,
@ -431,7 +430,7 @@ data:
"steppedLine": true,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[$__rate_interval])) by (instance, le))",
"hide": false,
"intervalFactor": 2,
"legendFormat": "{{instance}} WAL fsync",
@ -440,7 +439,7 @@ data:
"step": 4
},
{
"expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[$__rate_interval])) by (instance, le))",
"intervalFactor": 2,
"legendFormat": "{{instance}} DB fsync",
"metric": "etcd_disk_backend_commit_duration_seconds_bucket",
@ -618,7 +617,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[5m])",
"expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[$__rate_interval])",
"intervalFactor": 2,
"legendFormat": "{{instance}} Client Traffic In",
"metric": "etcd_network_client_grpc_received_bytes_total",
@ -704,7 +703,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[5m])",
"expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[$__rate_interval])",
"intervalFactor": 2,
"legendFormat": "{{instance}} Client Traffic Out",
"metric": "etcd_network_client_grpc_sent_bytes_total",
@ -790,7 +789,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[5m])) by (instance)",
"expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[$__rate_interval])) by (instance)",
"intervalFactor": 2,
"legendFormat": "{{instance}} Peer Traffic In",
"metric": "etcd_network_peer_received_bytes_total",
@ -879,7 +878,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$cluster\"}[5m])) by (instance)",
"expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$cluster\"}[$__rate_interval])) by (instance)",
"hide": false,
"interval": "",
"intervalFactor": 2,
@ -973,7 +972,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[5m]))",
"expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[$__rate_interval]))",
"intervalFactor": 2,
"legendFormat": "Proposal Failure Rate",
"metric": "etcd_server_proposals_failed_total",
@ -989,7 +988,7 @@ data:
"step": 2
},
{
"expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[5m]))",
"expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[$__rate_interval]))",
"intervalFactor": 2,
"legendFormat": "Proposal Commit Rate",
"metric": "etcd_server_proposals_committed_total",
@ -997,7 +996,7 @@ data:
"step": 2
},
{
"expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[5m]))",
"expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[$__rate_interval]))",
"intervalFactor": 2,
"legendFormat": "Proposal Apply Rate",
"refId": "D",
@ -1132,6 +1131,131 @@ data:
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"decimals": 0,
"editable": true,
"error": false,
"fieldConfig": {
"defaults": {
"custom": {
}
},
"overrides": [
]
},
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 28
},
"hiddenSeries": false,
"id": 42,
"isNew": true,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "7.4.3",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum by (instance, le) (rate(etcd_network_peer_round_trip_time_seconds_bucket{job=\"$cluster\"}[$__rate_interval])))",
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{instance}} Peer round trip time",
"metric": "etcd_network_peer_round_trip_time_seconds_bucket",
"refId": "A",
"step": 2
}
],
"thresholds": [
],
"timeFrom": null,
"timeRegions": [
],
"timeShift": null,
"title": "Peer round trip time",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"$$hashKey": "object:925",
"decimals": null,
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"$$hashKey": "object:926",
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"title": "New row"
@ -1141,7 +1265,7 @@ data:
"sharedCrosshair": false,
"style": "dark",
"tags": [
"etcd-mixin"
],
"templating": {
"list": [
@ -1151,7 +1275,7 @@ data:
"value": "Prometheus"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -1177,7 +1301,7 @@ data:
],
"query": "label_values(etcd_server_has_leader, job)",
"refresh": 1,
"refresh": 2,
"regex": "",
"sort": 2,
"tagValuesQuery": "",

View File

@ -0,0 +1,7644 @@
apiVersion: v1
data:
cluster-total.json: |-
{
"__inputs": [
],
"__requires": [
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": null,
"links": [
],
"panels": [
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Current Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 1
},
"id": 3,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Received",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 1
},
"id": 4,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Transmitted",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"columns": [
{
"text": "Time",
"value": "Time"
},
{
"text": "Value #A",
"value": "Value #A"
},
{
"text": "Value #B",
"value": "Value #B"
},
{
"text": "Value #C",
"value": "Value #C"
},
{
"text": "Value #D",
"value": "Value #D"
},
{
"text": "Value #E",
"value": "Value #E"
},
{
"text": "Value #F",
"value": "Value #F"
},
{
"text": "Value #G",
"value": "Value #G"
},
{
"text": "Value #H",
"value": "Value #H"
},
{
"text": "namespace",
"value": "namespace"
}
],
"datasource": "$datasource",
"fill": 1,
"fontSize": "90%",
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 10
},
"id": 5,
"lines": true,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null as zero",
"renderer": "flot",
"scroll": true,
"showHeader": true,
"sort": {
"col": 0,
"desc": false
},
"spaceLength": 10,
"span": 24,
"styles": [
{
"alias": "Time",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Time",
"thresholds": [
],
"type": "hidden",
"unit": "short"
},
{
"alias": "Current Bandwidth Received",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Current Bandwidth Transmitted",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Average Bandwidth Received",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Average Bandwidth Transmitted",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Rate of Received Packets",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Transmitted Packets",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Received Packets Dropped",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Transmitted Packets Dropped",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #H",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Namespace",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTooltip": "Drill down",
"linkUrl": "d/8b7a8b326d7a6f1f04244066368c67af/kubernetes-networking-namespace-pods?orgId=1&refresh=30s&var-namespace=$__cell",
"pattern": "namespace",
"thresholds": [
],
"type": "number",
"unit": "short"
}
],
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "A",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 10
},
{
"expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "C",
"step": 10
},
{
"expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "D",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "G",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "H",
"step": 10
}
],
"timeFrom": null,
"timeShift": null,
"title": "Current Status",
"type": "table"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 10
},
"id": 6,
"panels": [
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 11
},
"id": 7,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Average Rate of Bytes Received",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 11
},
"id": 8,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Average Rate of Bytes Transmitted",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Average Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 11
},
"id": 9,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bandwidth History",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 12
},
"id": 10,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Receive Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 21
},
"id": 11,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Transmit Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 30
},
"id": 12,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 31
},
"id": 13,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 40
},
"id": 14,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Packets",
"titleSize": "h6",
"type": "row"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 31
},
"id": 15,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 50
},
"id": 16,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 59
},
"id": 17,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\".+\"}[$interval:$resolution])) by (namespace))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{namespace}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 59
},
"id": 18,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
{
"targetBlank": true,
"title": "What is TCP Retransmit?",
"url": "https://accedian.com/enterprises/blog/network-packet-loss-retransmissions-and-duplicate-acknowledgements/"
}
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_OutSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of TCP Retransmits out of all sent segments",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 59
},
"id": 19,
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": true,
"min": true,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 2,
"links": [
{
"targetBlank": true,
"title": "Why monitor SYN retransmits?",
"url": "https://github.com/prometheus/node_exporter/issues/1023#issuecomment-408128365"
}
],
"minSpan": 24,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(rate(node_netstat_TcpExt_TCPSynRetrans{cluster=\"$cluster\"}[$interval:$resolution]) / rate(node_netstat_Tcp_RetransSegs{cluster=\"$cluster\"}[$interval:$resolution])) by (instance))",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{instance}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of TCP SYN Retransmits out of all retransmits",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Errors",
"titleSize": "h6",
"type": "row"
}
],
"refresh": "10s",
"rows": [
],
"schemaVersion": 18,
"style": "dark",
"tags": [
"kubernetes-mixin"
],
"templating": {
"list": [
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "resolution",
"options": [
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": true,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
}
],
"query": "30s,5m,1h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "interval",
"options": [
{
"selected": true,
"text": "4h",
"value": "4h"
}
],
"query": "4h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"label": "Data Source",
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kubernetes-cadvisor\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "UTC",
"title": "Kubernetes / Networking / Cluster",
"uid": "ff635a025bcfea7bc3dd4f508990a3e9",
"version": 0
}
namespace-by-pod.json: |-
{
"__inputs": [
],
"__requires": [
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": null,
"links": [
],
"panels": [
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Current Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"decimals": 0,
"format": "time_series",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 1
},
"height": 9,
"id": 3,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"minSpan": 12,
"nullPointMode": "connected",
"nullText": null,
"options": {
"fieldOptions": {
"calcs": [
"last"
],
"defaults": {
"max": 10000000000,
"min": 0,
"title": "$namespace",
"unit": "Bps"
},
"mappings": [
],
"override": {
},
"thresholds": [
{
"color": "dark-green",
"index": 0,
"value": null
},
{
"color": "dark-yellow",
"index": 1,
"value": 5000000000
},
{
"color": "dark-red",
"index": 2,
"value": 7000000000
}
],
"values": false
}
},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 12,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))",
"format": "time_series",
"instant": null,
"intervalFactor": 1,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Received",
"type": "gauge",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"decimals": 0,
"format": "time_series",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 1
},
"height": 9,
"id": 4,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"minSpan": 12,
"nullPointMode": "connected",
"nullText": null,
"options": {
"fieldOptions": {
"calcs": [
"last"
],
"defaults": {
"max": 10000000000,
"min": 0,
"title": "$namespace",
"unit": "Bps"
},
"mappings": [
],
"override": {
},
"thresholds": [
{
"color": "dark-green",
"index": 0,
"value": null
},
{
"color": "dark-yellow",
"index": 1,
"value": 5000000000
},
{
"color": "dark-red",
"index": 2,
"value": 7000000000
}
],
"values": false
}
},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 12,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution]))",
"format": "time_series",
"instant": null,
"intervalFactor": 1,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Transmitted",
"type": "gauge",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"columns": [
{
"text": "Time",
"value": "Time"
},
{
"text": "Value #A",
"value": "Value #A"
},
{
"text": "Value #B",
"value": "Value #B"
},
{
"text": "Value #C",
"value": "Value #C"
},
{
"text": "Value #D",
"value": "Value #D"
},
{
"text": "Value #E",
"value": "Value #E"
},
{
"text": "Value #F",
"value": "Value #F"
},
{
"text": "pod",
"value": "pod"
}
],
"datasource": "$datasource",
"fill": 1,
"fontSize": "100%",
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 10
},
"id": 5,
"lines": true,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null as zero",
"renderer": "flot",
"scroll": true,
"showHeader": true,
"sort": {
"col": 0,
"desc": false
},
"spaceLength": 10,
"span": 24,
"styles": [
{
"alias": "Time",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Time",
"thresholds": [
],
"type": "hidden",
"unit": "short"
},
{
"alias": "Bandwidth Received",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Bandwidth Transmitted",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Rate of Received Packets",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Transmitted Packets",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Received Packets Dropped",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Transmitted Packets Dropped",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Pod",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTooltip": "Drill down",
"linkUrl": "d/7a18067ce943a40ae25454675c19ff5c/kubernetes-networking-pod?orgId=1&refresh=30s&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
],
"type": "number",
"unit": "short"
}
],
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "A",
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 10
},
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "C",
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "D",
"step": 10
},
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
}
],
"timeFrom": null,
"timeShift": null,
"title": "Current Status",
"type": "table"
},
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 19
},
"id": 6,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 20
},
"id": 7,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Receive Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 20
},
"id": 8,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Transmit Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 29
},
"id": 9,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 30
},
"id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 12,
"y": 30
},
"id": 11,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Packets",
"titleSize": "h6",
"type": "row"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 30
},
"id": 12,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 40
},
"id": 13,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 12,
"y": 40
},
"id": 14,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Errors",
"titleSize": "h6",
"type": "row"
}
],
"refresh": "10s",
"rows": [
],
"schemaVersion": 18,
"style": "dark",
"tags": [
"kubernetes-mixin"
],
"templating": {
"list": [
{
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"label": "Data Source",
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kubernetes-cadvisor\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": ".+",
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "kube-system",
"value": "kube-system"
},
"datasource": "$datasource",
"definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
"hide": 0,
"includeAll": true,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "resolution",
"options": [
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": true,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
}
],
"query": "30s,5m,1h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "interval",
"options": [
{
"selected": true,
"text": "4h",
"value": "4h"
}
],
"query": "4h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "UTC",
"title": "Kubernetes / Networking / Namespace (Pods)",
"uid": "8b7a8b326d7a6f1f04244066368c67af",
"version": 0
}
namespace-by-workload.json: |-
{
"__inputs": [
],
"__requires": [
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": null,
"links": [
],
"panels": [
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Current Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 1
},
"id": 3,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ workload }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Received",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 1
},
"id": 4,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ workload }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Transmitted",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"columns": [
{
"text": "Time",
"value": "Time"
},
{
"text": "Value #A",
"value": "Value #A"
},
{
"text": "Value #B",
"value": "Value #B"
},
{
"text": "Value #C",
"value": "Value #C"
},
{
"text": "Value #D",
"value": "Value #D"
},
{
"text": "Value #E",
"value": "Value #E"
},
{
"text": "Value #F",
"value": "Value #F"
},
{
"text": "Value #G",
"value": "Value #G"
},
{
"text": "Value #H",
"value": "Value #H"
},
{
"text": "workload",
"value": "workload"
}
],
"datasource": "$datasource",
"fill": 1,
"fontSize": "90%",
"gridPos": {
"h": 9,
"w": 24,
"x": 0,
"y": 10
},
"id": 5,
"lines": true,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null as zero",
"renderer": "flot",
"scroll": true,
"showHeader": true,
"sort": {
"col": 0,
"desc": false
},
"spaceLength": 10,
"span": 24,
"styles": [
{
"alias": "Time",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Time",
"thresholds": [
],
"type": "hidden",
"unit": "short"
},
{
"alias": "Current Bandwidth Received",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Current Bandwidth Transmitted",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Average Bandwidth Received",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Average Bandwidth Transmitted",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Rate of Received Packets",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Transmitted Packets",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Received Packets Dropped",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Rate of Transmitted Packets Dropped",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #H",
"thresholds": [
],
"type": "number",
"unit": "pps"
},
{
"alias": "Workload",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTooltip": "Drill down",
"linkUrl": "d/728bf77cc1166d2f3133bf25846876cc/kubernetes-networking-workload?orgId=1&refresh=30s&var-namespace=$namespace&var-type=$type&var-workload=$__cell",
"pattern": "workload",
"thresholds": [
],
"type": "number",
"unit": "short"
}
],
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "A",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 10
},
{
"expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "C",
"step": 10
},
{
"expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "D",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "G",
"step": 10
},
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "H",
"step": 10
}
],
"timeFrom": null,
"timeShift": null,
"title": "Current Status",
"type": "table"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 19
},
"id": 6,
"panels": [
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 20
},
"id": 7,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ workload }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Average Rate of Bytes Received",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 20
},
"id": 8,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ workload }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Average Rate of Bytes Transmitted",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Average Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 29
},
"id": 9,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bandwidth HIstory",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 38
},
"id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{workload}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Receive Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 38
},
"id": 11,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{workload}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Transmit Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 39
},
"id": 12,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 40
},
"id": 13,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{workload}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 40
},
"id": 14,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{workload}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Packets",
"titleSize": "h6",
"type": "row"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 40
},
"id": 15,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 41
},
"id": 16,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{workload}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 41
},
"id": 17,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{workload}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Errors",
"titleSize": "h6",
"type": "row"
}
],
"refresh": "10s",
"rows": [
],
"schemaVersion": 18,
"style": "dark",
"tags": [
"kubernetes-mixin"
],
"templating": {
"list": [
{
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"label": "Data Source",
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kubernetes-cadvisor\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "kube-system",
"value": "kube-system"
},
"datasource": "$datasource",
"definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "deployment",
"value": "deployment"
},
"datasource": "$datasource",
"definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "type",
"options": [
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "resolution",
"options": [
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": true,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
}
],
"query": "30s,5m,1h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "interval",
"options": [
{
"selected": true,
"text": "4h",
"value": "4h"
}
],
"query": "4h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "UTC",
"title": "Kubernetes / Networking / Namespace (Workload)",
"uid": "bbb2a765a623ae38130206c7d94a160f",
"version": 0
}
pod-total.json: |-
{
"__inputs": [
],
"__requires": [
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": null,
"links": [
],
"panels": [
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Current Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"decimals": 0,
"format": "time_series",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 1
},
"height": 9,
"id": 3,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"minSpan": 12,
"nullPointMode": "connected",
"nullText": null,
"options": {
"fieldOptions": {
"calcs": [
"last"
],
"defaults": {
"max": 10000000000,
"min": 0,
"title": "$namespace: $pod",
"unit": "Bps"
},
"mappings": [
],
"override": {
},
"thresholds": [
{
"color": "dark-green",
"index": 0,
"value": null
},
{
"color": "dark-yellow",
"index": 1,
"value": 5000000000
},
{
"color": "dark-red",
"index": 2,
"value": 7000000000
}
],
"values": false
}
},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 12,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))",
"format": "time_series",
"instant": null,
"intervalFactor": 1,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Received",
"type": "gauge",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"decimals": 0,
"format": "time_series",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 1
},
"height": 9,
"id": 4,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"minSpan": 12,
"nullPointMode": "connected",
"nullText": null,
"options": {
"fieldOptions": {
"calcs": [
"last"
],
"defaults": {
"max": 10000000000,
"min": 0,
"title": "$namespace: $pod",
"unit": "Bps"
},
"mappings": [
],
"override": {
},
"thresholds": [
{
"color": "dark-green",
"index": 0,
"value": null
},
{
"color": "dark-yellow",
"index": 1,
"value": 5000000000
},
{
"color": "dark-red",
"index": 2,
"value": 7000000000
}
],
"values": false
}
},
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 12,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution]))",
"format": "time_series",
"instant": null,
"intervalFactor": 1,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Transmitted",
"type": "gauge",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "current"
},
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 10
},
"id": 5,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 11
},
"id": 6,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Receive Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 11
},
"id": 7,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Transmit Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 20
},
"id": 8,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 21
},
"id": 9,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 12,
"y": 21
},
"id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Packets",
"titleSize": "h6",
"type": "row"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 21
},
"id": 11,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 0,
"y": 32
},
"id": 12,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 10,
"w": 12,
"x": 12,
"y": 32
},
"id": 13,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\",namespace=~\"$namespace\", pod=~\"$pod\"}[$interval:$resolution])) by (pod)",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Errors",
"titleSize": "h6",
"type": "row"
}
],
"refresh": "10s",
"rows": [
],
"schemaVersion": 18,
"style": "dark",
"tags": [
"kubernetes-mixin"
],
"templating": {
"list": [
{
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"label": "Data Source",
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kubernetes-cadvisor\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": ".+",
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "kube-system",
"value": "kube-system"
},
"datasource": "$datasource",
"definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
"hide": 0,
"includeAll": true,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": ".+",
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"definition": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "pod",
"options": [
],
"query": "label_values(container_network_receive_packets_total{cluster=\"$cluster\",namespace=~\"$namespace\"}, pod)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "resolution",
"options": [
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": true,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
}
],
"query": "30s,5m,1h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "interval",
"options": [
{
"selected": true,
"text": "4h",
"value": "4h"
}
],
"query": "4h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "UTC",
"title": "Kubernetes / Networking / Pod",
"uid": "7a18067ce943a40ae25454675c19ff5c",
"version": 0
}
workload-total.json: |-
{
"__inputs": [
],
"__requires": [
],
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"gnetId": null,
"graphTooltip": 0,
"hideControls": false,
"id": null,
"links": [
],
"panels": [
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Current Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 1
},
"id": 3,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ pod }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Received",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 1
},
"id": 4,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ pod }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Rate of Bytes Transmitted",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 10
},
"id": 5,
"panels": [
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 11
},
"id": 6,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(avg(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ pod }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Average Rate of Bytes Received",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 11
},
"id": 7,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"sort": "current",
"sortDesc": true,
"total": false,
"values": true
},
"lines": false,
"linewidth": 1,
"links": [
],
"minSpan": 24,
"nullPointMode": "null",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 24,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(avg(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{ pod }}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Average Rate of Bytes Transmitted",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "series",
"name": null,
"show": false,
"values": [
"current"
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Average Bandwidth",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 11
},
"id": 8,
"panels": [
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Bandwidth HIstory",
"titleSize": "h6",
"type": "row"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 12
},
"id": 9,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Receive Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 12
},
"id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Transmit Bandwidth",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 21
},
"id": 11,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 22
},
"id": 12,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 22
},
"id": 13,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Packets",
"titleSize": "h6",
"type": "row"
},
{
"collapse": true,
"collapsed": true,
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 22
},
"id": 14,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 0,
"y": 23
},
"id": 15,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 2,
"fillGradient": 0,
"gridPos": {
"h": 9,
"w": 12,
"x": 12,
"y": 23
},
"id": 16,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [
],
"minSpan": 12,
"nullPointMode": "connected",
"paceLength": 10,
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sort_desc(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\",namespace=~\"$namespace\"}[$interval:$resolution])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "{{pod}}",
"refId": "A",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": true,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Errors",
"titleSize": "h6",
"type": "row"
}
],
"refresh": "10s",
"rows": [
],
"schemaVersion": 18,
"style": "dark",
"tags": [
"kubernetes-mixin"
],
"templating": {
"list": [
{
"current": {
"text": "default",
"value": "default"
},
"hide": 0,
"label": "Data Source",
"name": "datasource",
"options": [
],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(kube_pod_info{job=\"kube-state-metrics\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": ".+",
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "kube-system",
"value": "kube-system"
},
"datasource": "$datasource",
"definition": "label_values(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\"}, namespace)",
"hide": 0,
"includeAll": true,
"label": null,
"multi": false,
"name": "namespace",
"options": [
],
"query": "label_values(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "workload",
"options": [
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\"}, workload)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "deployment",
"value": "deployment"
},
"datasource": "$datasource",
"definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "type",
"options": [
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\",namespace=~\"$namespace\", workload=~\"$workload\"}, workload_type)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "resolution",
"options": [
{
"selected": false,
"text": "30s",
"value": "30s"
},
{
"selected": true,
"text": "5m",
"value": "5m"
},
{
"selected": false,
"text": "1h",
"value": "1h"
}
],
"query": "30s,5m,1h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "5m",
"value": "5m"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"multi": false,
"name": "interval",
"options": [
{
"selected": true,
"text": "4h",
"value": "4h"
}
],
"query": "4h",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "interval",
"useTags": false
}
]
},
"time": {
"from": "now-1h",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"5s",
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "UTC",
"title": "Kubernetes / Networking / Workload",
"uid": "728bf77cc1166d2f3133bf25846876cc",
"version": 0
}
kind: ConfigMap
metadata:
name: grafana-dashboards-k8s-network
namespace: monitoring

View File

@ -20,2349 +20,2106 @@ data:
"id": null,
"links": [
],
"panels": [
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"links": [
],
"mappings": [
],
"thresholds": {
"mode": "absolute",
"steps": [
]
},
"unit": "none"
}
},
"gridPos": {
"h": 7,
"w": 4,
"x": 0,
"y": 0
},
"id": 2,
"links": [
],
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "7",
"targets": [
{
"expr": "sum(kubelet_node_name{cluster=\"$cluster\", job=\"kubelet\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
"refId": "A"
}
],
"title": "Running Kubelets",
"transparent": false,
"type": "stat"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"links": [
],
"mappings": [
],
"thresholds": {
"mode": "absolute",
"steps": [
]
},
"unit": "none"
}
},
"gridPos": {
"h": 7,
"w": 4,
"x": 4,
"y": 0
},
"id": 3,
"links": [
],
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "7",
"targets": [
{
"expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Running Pods",
"transparent": false,
"type": "stat"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"links": [
],
"mappings": [
],
"thresholds": {
"mode": "absolute",
"steps": [
]
},
"unit": "none"
}
},
"gridPos": {
"h": 7,
"w": 4,
"x": 8,
"y": 0
},
"id": 4,
"links": [
],
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "7",
"targets": [
{
"expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Running Containers",
"transparent": false,
"type": "stat"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"links": [
],
"mappings": [
],
"thresholds": {
"mode": "absolute",
"steps": [
]
},
"unit": "none"
}
},
"gridPos": {
"h": 7,
"w": 4,
"x": 12,
"y": 0
},
"id": 5,
"links": [
],
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "7",
"targets": [
{
"expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\", state=\"actual_state_of_world\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Actual Volume Count",
"transparent": false,
"type": "stat"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"links": [
],
"mappings": [
],
"thresholds": {
"mode": "absolute",
"steps": [
]
},
"unit": "none"
}
},
"gridPos": {
"h": 7,
"w": 4,
"x": 16,
"y": 0
},
"id": 6,
"links": [
],
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "7",
"targets": [
{
"expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\",state=\"desired_state_of_world\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Desired Volume Count",
"transparent": false,
"type": "stat"
},
{
"datasource": "$datasource",
"fieldConfig": {
"defaults": {
"links": [
],
"mappings": [
],
"thresholds": {
"mode": "absolute",
"steps": [
]
},
"unit": "none"
}
},
"gridPos": {
"h": 7,
"w": 4,
"x": 20,
"y": 0
},
"id": 7,
"links": [
],
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "7",
"targets": [
{
"expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"title": "Config Error Count",
"transparent": false,
"type": "stat"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 7
},
"id": 8,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (operation_type, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Operation Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 7
},
"id": 9,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Operation Error Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 14
},
"id": 10,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Operation duration 99th quantile",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 21
},
"id": 11,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} pod",
"refId": "A"
},
{
"expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} worker",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Pod Start Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 21
},
"id": 12,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} pod",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} worker",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Pod Start Duration",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 28
},
"id": 13,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Storage Operation Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 28
},
"id": 14,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Storage Operation Error Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 35
},
"id": 15,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_name, volume_plugin, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Storage Operation Duration 99th quantile",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 42
},
"id": 16,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Cgroup manager operation rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 42
},
"id": 17,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, operation_type, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Cgroup manager 99th quantile",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "Pod lifecycle event generator",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 49
},
"id": 18,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "PLEG relist rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 49
},
"id": 19,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "PLEG relist interval",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 56
},
"id": 20,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "PLEG relist duration",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 63
},
"id": 21,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
"refId": "D"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "RPC Rate",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 24,
"x": 0,
"y": 70
},
"id": 22,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[$__rate_interval])) by (instance, verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{verb}} {{url}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Request duration 99th quantile",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 77
},
"id": 23,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Memory",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 77
},
"id": 24,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[$__rate_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "CPU usage",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 77
},
"id": 25,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Goroutines",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"refresh": "10s",
"rows": [
{
"collapse": false,
"collapsed": false,
"panels": [
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 2,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(up{cluster=\"$cluster\", job=\"kubelet\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"title": "Up",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "min"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 3,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": "",
"title": "Running Pods",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "min"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 4,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": "",
"title": "Running Container",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "min"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 5,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\", state=\"actual_state_of_world\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": "",
"title": "Actual Volume Count",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "min"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 6,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(volume_manager_total_volumes{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\",state=\"desired_state_of_world\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": "",
"title": "Desired Volume Count",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "min"
},
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 7,
"interval": null,
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 2,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "sum(rate(kubelet_node_config_error{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": "",
"title": "Config Error Count",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "min"
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 8,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_runtime_operations_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (operation_type, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Operation Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 9,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_runtime_operations_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Operation Error Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 10,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_runtime_operations_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Operation duration 99th quantile",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 11,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} pod",
"refId": "A"
},
{
"expr": "sum(rate(kubelet_pod_worker_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} worker",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Pod Start Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 12,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_start_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} pod",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} worker",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Pod Start Duration",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 13,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(storage_operation_duration_seconds_count{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Storage Operation Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 14,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(storage_operation_errors_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Storage Operation Error Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 15,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"hideEmpty": true,
"hideZero": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(storage_operation_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_name, volume_plugin, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_name}} {{volume_plugin}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Storage Operation Duration 99th quantile",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 16,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_cgroup_manager_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Cgroup manager operation rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 17,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_cgroup_manager_duration_seconds_bucket{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, operation_type, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{operation_type}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Cgroup manager 99th quantile",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "Pod lifecycle event generator",
"fill": 1,
"gridPos": {
},
"id": 18,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubelet_pleg_relist_duration_seconds_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "PLEG relist rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 19,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_interval_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "PLEG relist interval",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 20,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "PLEG relist duration",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 21,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
"refId": "D"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "RPC Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 22,
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": true
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{verb}} {{url}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Request duration 99th quantile",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 23,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Memory",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 24,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "CPU usage",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 25,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "go_goroutines{cluster=\"$cluster\",job=\"kubelet\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Goroutines",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
}
],
"schemaVersion": 14,
"style": "dark",
@ -2377,7 +2134,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -2401,7 +2158,7 @@ data:
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"query": "label_values(up{job=\"kubelet\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -2421,13 +2178,13 @@ data:
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
"label": null,
"label": "instance",
"multi": false,
"name": "instance",
"options": [
],
"query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
"query": "label_values(up{job=\"kubelet\",cluster=\"$cluster\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -2470,7 +2227,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Kubelet",
"uid": "3138fa155d5915769fbded898ac09fd9",
"version": 0
@ -2524,7 +2281,11 @@ data:
},
"id": 2,
"interval": null,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
@ -2563,7 +2324,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(up{job=\"kube-proxy\"})",
"expr": "sum(up{cluster=\"$cluster\", job=\"kube-proxy\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -2595,18 +2356,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -2630,7 +2394,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
"expr": "sum(rate(kubeproxy_sync_proxy_rules_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "rate",
@ -2686,10 +2450,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -2698,6 +2464,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -2721,7 +2488,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
"expr": "histogram_quantile(0.99,rate(kubeproxy_sync_proxy_rules_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2790,18 +2557,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -2825,7 +2595,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{job=\"kube-proxy\", instance=~\"$instance\"}[5m]))",
"expr": "sum(rate(kubeproxy_network_programming_duration_seconds_count{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "rate",
@ -2881,10 +2651,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -2893,6 +2665,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -2916,7 +2689,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(kubeproxy_network_programming_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\"}[$__rate_interval])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2985,18 +2758,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3020,28 +2796,28 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
@ -3097,18 +2873,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3132,7 +2911,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@ -3201,10 +2980,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -3213,6 +2994,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -3236,7 +3018,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@ -3305,18 +3087,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3340,7 +3125,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{job=\"kube-proxy\",instance=~\"$instance\"}",
"expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -3396,18 +3181,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3431,7 +3219,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{job=\"kube-proxy\",instance=~\"$instance\"}[5m])",
"expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}[$__rate_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -3487,18 +3275,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3522,7 +3313,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "go_goroutines{job=\"kube-proxy\",instance=~\"$instance\"}",
"expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-proxy\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -3592,7 +3383,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -3606,6 +3397,32 @@ data:
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kube-proxy\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 0,
@ -3616,7 +3433,7 @@ data:
"options": [
],
"query": "label_values(kubeproxy_network_programming_duration_seconds_bucket{job=\"kube-proxy\"}, instance)",
"query": "label_values(up{job=\"kube-proxy\", cluster=\"$cluster\", job=\"kube-proxy\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -3659,7 +3476,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Proxy",
"uid": "632e265de029684c40b21cb76bca4f94",
"version": 0

View File

@ -31,11 +31,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 1,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -59,7 +62,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster=\"$cluster\"}[$__interval]))",
"expr": "cluster:node_cpu:ratio_rate5m{cluster=\"$cluster\"}",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -72,7 +75,7 @@ data:
"title": "CPU Utilisation",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -115,11 +118,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -143,7 +149,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_cpu_cores{cluster=\"$cluster\"})",
"expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -156,7 +162,7 @@ data:
"title": "CPU Requests Commitment",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -199,11 +205,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -227,7 +236,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_cpu_cores{cluster=\"$cluster\"})",
"expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"cpu\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -240,7 +249,7 @@ data:
"title": "CPU Limits Commitment",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -283,11 +292,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -311,7 +323,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})",
"expr": "1 - sum(:node_memory_MemAvailable_bytes:sum{cluster=\"$cluster\"}) / sum(node_memory_MemTotal_bytes{job=\"node-exporter\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -324,7 +336,7 @@ data:
"title": "Memory Utilisation",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -367,11 +379,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -395,7 +410,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})",
"expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -408,7 +423,7 @@ data:
"title": "Memory Requests Commitment",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -451,11 +466,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -479,7 +497,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable_memory_bytes{cluster=\"$cluster\"})",
"expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) / sum(kube_node_status_allocatable{job=\"kube-state-metrics\",resource=\"memory\",cluster=\"$cluster\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -492,7 +510,7 @@ data:
"title": "Memory Limits Commitment",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -546,11 +564,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -574,7 +595,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -590,7 +611,7 @@ data:
"title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -644,11 +665,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -686,8 +710,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"pattern": "Value #A",
"thresholds": [
@ -704,8 +729,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to workloads",
"linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"linkUrl": "/d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"pattern": "Value #B",
"thresholds": [
@ -722,6 +748,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -740,6 +767,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -758,6 +786,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -776,6 +805,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -794,6 +824,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
@ -812,8 +843,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"pattern": "namespace",
"thresholds": [
@ -839,7 +871,7 @@ data:
],
"targets": [
{
"expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -848,7 +880,7 @@ data:
"step": 10
},
{
"expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
"expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -857,7 +889,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -866,7 +898,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -875,7 +907,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -884,7 +916,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -893,7 +925,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\"}) by (namespace) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\"}) by (namespace) / sum(namespace_cpu:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -910,7 +942,7 @@ data:
"title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -965,11 +997,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -993,7 +1028,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace)",
"expr": "sum(container_memory_rss{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -1009,7 +1044,7 @@ data:
"title": "Memory Usage (w/o cache)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1063,11 +1098,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1105,8 +1143,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"pattern": "Value #A",
"thresholds": [
@ -1123,8 +1162,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to workloads",
"linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"linkUrl": "/d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
"pattern": "Value #B",
"thresholds": [
@ -1141,6 +1181,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -1159,6 +1200,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -1177,6 +1219,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -1195,6 +1238,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -1213,6 +1257,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
@ -1231,8 +1276,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"pattern": "namespace",
"thresholds": [
@ -1258,7 +1304,7 @@ data:
],
"targets": [
{
"expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(kube_pod_owner{job=\"kube-state-metrics\", cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1267,7 +1313,7 @@ data:
"step": 10
},
{
"expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
"expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1276,7 +1322,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace)",
"expr": "sum(container_memory_rss{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1285,7 +1331,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1294,7 +1340,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(container_memory_rss{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_requests:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1303,7 +1349,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1312,7 +1358,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\"}) by (namespace)",
"expr": "sum(container_memory_rss{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", container!=\"\"}) by (namespace) / sum(namespace_memory:kube_pod_container_resource_limits:sum{cluster=\"$cluster\"}) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1329,7 +1375,7 @@ data:
"title": "Requests by Namespace",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -1384,11 +1430,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1426,6 +1475,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -1444,6 +1494,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -1462,6 +1513,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -1480,6 +1532,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -1498,6 +1551,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -1516,6 +1570,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -1534,8 +1589,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"pattern": "namespace",
"thresholds": [
@ -1561,7 +1617,7 @@ data:
],
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1570,7 +1626,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1579,7 +1635,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1588,7 +1644,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1597,7 +1653,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1606,7 +1662,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -1623,7 +1679,7 @@ data:
"title": "Current Network Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -1661,7 +1717,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Current Network Usage",
"titleSize": "h6"
},
{
@ -1678,11 +1734,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1701,12 +1760,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -1722,7 +1781,7 @@ data:
"title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1753,19 +1812,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -1776,11 +1823,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 13,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1799,12 +1849,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -1820,7 +1870,7 @@ data:
"title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1857,7 +1907,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Bandwidth",
"titleSize": "h6"
},
{
@ -1874,11 +1924,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 14,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1897,12 +1950,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "avg(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -1918,7 +1971,7 @@ data:
"title": "Average Container Bandwidth by Namespace: Received",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1949,19 +2002,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -1972,11 +2013,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 15,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1995,12 +2039,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "avg(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -2016,7 +2060,7 @@ data:
"title": "Average Container Bandwidth by Namespace: Transmitted",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2053,7 +2097,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Average Container Bandwidth by Namespace",
"titleSize": "h6"
},
{
@ -2070,11 +2114,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 16,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2093,12 +2140,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -2114,7 +2161,7 @@ data:
"title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2129,7 +2176,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2145,19 +2192,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -2168,11 +2203,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 17,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2191,12 +2229,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -2212,7 +2250,7 @@ data:
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2227,7 +2265,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2249,7 +2287,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets",
"titleSize": "h6"
},
{
@ -2266,11 +2304,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 18,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2289,12 +2330,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -2310,7 +2351,7 @@ data:
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2325,7 +2366,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -2341,19 +2382,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -2364,11 +2393,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 19,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2387,12 +2419,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
"expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
@ -2408,7 +2440,198 @@ data:
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Rate of Packets Dropped",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"decimals": -1,
"fill": 10,
"id": 20,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "ceil(sum by(namespace) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", container!=\"\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval])))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "IOPS(Reads+Writes)",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 21,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", container!=\"\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{namespace}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ThroughPut(Read+Write)",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2445,7 +2668,315 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Storage IO",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 22,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"sort": {
"col": 4,
"desc": true
},
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"styles": [
{
"alias": "Time",
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"pattern": "Time",
"type": "hidden"
},
{
"alias": "IOPS(Reads)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "IOPS(Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "IOPS(Reads + Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "Throughput(Read)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Throughput(Write)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Throughput(Read + Write)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Namespace",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "/d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
"pattern": "namespace",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"pattern": "/.*/",
"thresholds": [
],
"type": "string",
"unit": "short"
}
],
"targets": [
{
"expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "A",
"step": 10
},
{
"expr": "sum by(namespace) (rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 10
},
{
"expr": "sum by(namespace) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "C",
"step": 10
},
{
"expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "D",
"step": 10
},
{
"expr": "sum by(namespace) (rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
},
{
"expr": "sum by(namespace) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace!=\"\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Storage IO",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
"type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Storage IO - Distribution",
"titleSize": "h6"
}
],
@ -2462,7 +2993,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -2472,33 +3003,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(node_cpu_seconds_total, cluster)",
"refresh": 1,
"regex": "",
"sort": 2,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
@ -2514,7 +3018,7 @@ data:
"options": [
],
"query": "label_values(node_cpu_seconds_total, cluster)",
"query": "label_values(up{job=\"kubernetes-cadvisor\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -2557,7 +3061,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Compute Resources / Cluster",
"uid": "efa86fd1d0c121a26444b636a3f509a8",
"version": 0
@ -2593,11 +3097,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 1,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2621,7 +3128,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -2634,7 +3141,7 @@ data:
"title": "CPU Utilisation (from requests)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -2677,11 +3184,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2705,7 +3215,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -2718,7 +3228,7 @@ data:
"title": "CPU Utilisation (from limits)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -2761,11 +3271,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2789,7 +3302,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"})",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -2799,10 +3312,10 @@ data:
"thresholds": "70,80",
"timeFrom": null,
"timeShift": null,
"title": "Memory Utilization (from requests)",
"title": "Memory Utilisation (from requests)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -2845,11 +3358,14 @@ data:
"fill": 1,
"format": "percentunit",
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2873,7 +3389,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"})",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"})",
"format": "time_series",
"instant": true,
"intervalFactor": 2,
@ -2886,7 +3402,7 @@ data:
"title": "Memory Utilisation (from limits)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "singlestat",
@ -2940,11 +3456,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2965,8 +3484,9 @@ data:
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
},
@ -2975,8 +3495,9 @@ data:
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
}
@ -2987,7 +3508,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3019,7 +3540,7 @@ data:
"title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3073,11 +3594,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3115,6 +3639,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -3133,6 +3658,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -3151,6 +3677,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -3169,6 +3696,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -3187,6 +3715,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -3205,8 +3734,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@ -3232,7 +3762,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3241,7 +3771,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3250,7 +3780,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3259,7 +3789,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3268,7 +3798,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3285,7 +3815,7 @@ data:
"title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -3340,11 +3870,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3365,8 +3898,9 @@ data:
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
},
@ -3375,8 +3909,9 @@ data:
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
}
@ -3387,7 +3922,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}) by (pod)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3419,7 +3954,7 @@ data:
"title": "Memory Usage (w/o cache)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3473,11 +4008,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3515,6 +4053,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -3533,6 +4072,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -3551,6 +4091,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -3569,6 +4110,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -3587,6 +4129,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -3605,6 +4148,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -3623,6 +4167,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
@ -3641,6 +4186,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #H",
@ -3659,8 +4205,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@ -3686,7 +4233,7 @@ data:
],
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3695,7 +4242,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3704,7 +4251,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3713,7 +4260,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3722,7 +4269,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3731,7 +4278,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"expr": "sum(container_memory_rss{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3740,7 +4287,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"expr": "sum(container_memory_cache{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3749,7 +4296,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"expr": "sum(container_memory_swap{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -3766,7 +4313,7 @@ data:
"title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -3821,11 +4368,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3863,6 +4413,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -3881,6 +4432,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -3899,6 +4451,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -3917,6 +4470,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -3935,6 +4489,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -3953,6 +4508,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -3971,8 +4527,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@ -3998,7 +4555,7 @@ data:
],
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4007,7 +4564,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4016,7 +4573,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4025,7 +4582,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4034,7 +4591,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4043,7 +4600,7 @@ data:
"step": 10
},
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4060,7 +4617,7 @@ data:
"title": "Current Network Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -4098,7 +4655,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Current Network Usage",
"titleSize": "h6"
},
{
@ -4115,11 +4672,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4138,12 +4698,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4159,7 +4719,7 @@ data:
"title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4190,19 +4750,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -4213,11 +4761,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4236,12 +4787,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4257,7 +4808,7 @@ data:
"title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4294,7 +4845,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Bandwidth",
"titleSize": "h6"
},
{
@ -4311,11 +4862,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4334,12 +4888,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4355,7 +4909,7 @@ data:
"title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4370,7 +4924,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -4386,19 +4940,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -4409,11 +4951,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 13,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4432,12 +4977,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4453,7 +4998,7 @@ data:
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4468,7 +5013,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -4490,7 +5035,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets",
"titleSize": "h6"
},
{
@ -4507,11 +5052,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 14,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4530,12 +5078,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4551,7 +5099,7 @@ data:
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4566,7 +5114,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -4582,19 +5130,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -4605,11 +5141,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 15,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4628,12 +5167,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4649,7 +5188,198 @@ data:
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Rate of Packets Dropped",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"decimals": -1,
"fill": 10,
"id": 16,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "ceil(sum by(pod) (rate(container_fs_reads_total{container!=\"\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{container!=\"\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "IOPS(Reads+Writes)",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 17,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by(pod) (rate(container_fs_reads_bytes_total{container!=\"\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{container!=\"\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ThroughPut(Read+Write)",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4686,7 +5416,315 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Storage IO",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 18,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"sort": {
"col": 4,
"desc": true
},
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"styles": [
{
"alias": "Time",
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"pattern": "Time",
"type": "hidden"
},
{
"alias": "IOPS(Reads)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "IOPS(Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "IOPS(Reads + Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "Throughput(Read)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Throughput(Write)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Throughput(Read + Write)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Pod",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"pattern": "/.*/",
"thresholds": [
],
"type": "string",
"unit": "short"
}
],
"targets": [
{
"expr": "sum by(pod) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "A",
"step": 10
},
{
"expr": "sum by(pod) (rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 10
},
{
"expr": "sum by(pod) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "C",
"step": 10
},
{
"expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "D",
"step": 10
},
{
"expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
},
{
"expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Storage IO",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
"type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Storage IO - Distribution",
"titleSize": "h6"
}
],
@ -4703,7 +5741,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -4728,8 +5766,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -4755,8 +5793,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -4798,7 +5836,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Compute Resources / Namespace (Pods)",
"uid": "85a562078cdf77779eaa1add43ccec1e",
"version": 0
@ -4833,11 +5871,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 1,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4853,7 +5894,17 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "max capacity",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": true,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@ -4861,7 +5912,15 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"cpu\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "max capacity",
"legendLink": null,
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -4877,7 +5936,7 @@ data:
"title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4931,11 +5990,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4973,6 +6035,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -4991,6 +6054,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -5009,6 +6073,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -5027,6 +6092,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -5045,6 +6111,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -5063,6 +6130,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "pod",
@ -5090,7 +6158,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5099,7 +6167,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5108,7 +6176,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5117,7 +6185,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5126,7 +6194,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5143,7 +6211,7 @@ data:
"title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -5198,11 +6266,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5218,7 +6289,17 @@ data:
"points": false,
"renderer": "flot",
"seriesOverrides": [
{
"alias": "max capacity",
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": true,
"linewidth": 2,
"stack": false
}
],
"spaceLength": 10,
"span": 12,
@ -5226,7 +6307,15 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\", container!=\"\"}) by (pod)",
"expr": "sum(kube_node_status_capacity{cluster=\"$cluster\", node=~\"$node\", resource=\"memory\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "max capacity",
"legendLink": null,
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -5242,7 +6331,7 @@ data:
"title": "Memory Usage (w/o cache)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5296,11 +6385,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5338,6 +6430,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -5356,6 +6449,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -5374,6 +6468,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -5392,6 +6487,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -5410,6 +6506,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -5428,6 +6525,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -5446,6 +6544,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
@ -5464,6 +6563,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #H",
@ -5482,6 +6582,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "pod",
@ -5509,7 +6610,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5518,7 +6619,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5527,7 +6628,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5536,7 +6637,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5545,7 +6646,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=\"$node\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5554,7 +6655,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5563,7 +6664,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5572,7 +6673,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
"expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -5589,7 +6690,7 @@ data:
"title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -5644,7 +6745,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -5669,8 +6770,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -5691,13 +6792,13 @@ data:
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"multi": true,
"name": "node",
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
"refresh": 1,
"query": "label_values(kube_node_info{cluster=\"$cluster\"}, node)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -5739,7 +6840,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Compute Resources / Node (Pods)",
"uid": "200ac8fdbfbb74b39aff88118e4d1c2c",
"version": 0

View File

@ -30,11 +30,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 1,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -75,7 +78,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{namespace=\"$namespace\", pod=\"$pod\", cluster=\"$cluster\"}) by (container)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}}",
@ -83,7 +86,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "requests",
@ -91,7 +94,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"cpu\"}\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "limits",
@ -107,7 +110,7 @@ data:
"title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -161,11 +164,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"max": true,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -189,7 +195,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", cluster=\"$cluster\"}[5m])) by (container)",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{job=\"kubernetes-cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container) /sum(increase(container_cpu_cfs_periods_total{job=\"kubernetes-cadvisor\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", cluster=\"$cluster\"}[$__rate_interval])) by (container)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}}",
@ -203,7 +209,7 @@ data:
"fill": true,
"line": true,
"op": "gt",
"value": 1,
"value": 0.80000000000000004,
"yaxis": "left"
}
],
@ -212,7 +218,7 @@ data:
"title": "CPU Throttling",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -266,11 +272,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -308,6 +317,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -326,6 +336,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -344,6 +355,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -362,6 +374,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -380,6 +393,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -398,6 +412,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "container",
@ -425,7 +440,7 @@ data:
],
"targets": [
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -434,7 +449,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -443,7 +458,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -452,7 +467,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -461,7 +476,7 @@ data:
"step": 10
},
{
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -478,7 +493,7 @@ data:
"title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -533,11 +548,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -559,7 +577,7 @@ data:
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
},
@ -569,7 +587,7 @@ data:
"dashes": true,
"fill": 0,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
}
@ -580,7 +598,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}}",
@ -588,7 +606,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "requests",
@ -596,7 +614,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
"expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", resource=\"memory\"}\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "limits",
@ -609,10 +627,10 @@ data:
],
"timeFrom": null,
"timeShift": null,
"title": "Memory Usage",
"title": "Memory Usage (WSS)",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -666,11 +684,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -700,7 +721,7 @@ data:
"type": "hidden"
},
{
"alias": "Memory Usage",
"alias": "Memory Usage (WSS)",
"colorMode": null,
"colors": [
@ -708,6 +729,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -726,6 +748,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -744,6 +767,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -762,6 +786,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -780,6 +805,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -798,6 +824,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -816,6 +843,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #G",
@ -834,6 +862,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #H",
@ -852,6 +881,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "container",
@ -879,7 +909,7 @@ data:
],
"targets": [
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -888,7 +918,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -897,7 +927,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_requests{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -906,7 +936,7 @@ data:
"step": 10
},
{
"expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container)",
"expr": "sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -915,7 +945,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"expr": "sum(container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(cluster:namespace:pod_memory:active:kube_pod_container_resource_limits{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -924,7 +954,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
"expr": "sum(container_memory_rss{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -933,7 +963,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
"expr": "sum(container_memory_cache{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -942,7 +972,7 @@ data:
"step": 10
},
{
"expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
"expr": "sum(container_memory_swap{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container != \"\", container != \"POD\"}) by (container)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -959,7 +989,7 @@ data:
"title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -1014,11 +1044,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1037,12 +1070,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1058,7 +1091,7 @@ data:
"title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1089,19 +1122,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -1112,11 +1133,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1135,12 +1159,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1156,7 +1180,7 @@ data:
"title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1193,7 +1217,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Bandwidth",
"titleSize": "h6"
},
{
@ -1210,11 +1234,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1233,12 +1260,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1254,7 +1281,7 @@ data:
"title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1269,7 +1296,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1285,19 +1312,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -1308,11 +1323,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1331,12 +1349,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1352,7 +1370,7 @@ data:
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1367,7 +1385,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1389,7 +1407,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets",
"titleSize": "h6"
},
{
@ -1406,11 +1424,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1429,12 +1450,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1450,7 +1471,7 @@ data:
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1465,7 +1486,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -1481,19 +1502,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -1504,11 +1513,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1527,12 +1539,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
"expr": "sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1548,7 +1560,214 @@ data:
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Rate of Packets Dropped",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"decimals": -1,
"fill": 10,
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "ceil(sum by(pod) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Reads",
"legendLink": null,
"step": 10
},
{
"expr": "ceil(sum by(pod) (rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\",namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval])))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Writes",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "IOPS",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 13,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by(pod) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Reads",
"legendLink": null,
"step": 10
},
{
"expr": "sum by(pod) (rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "Writes",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ThroughPut",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1585,7 +1804,506 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Storage IO - Distribution(Pod - Read & Writes)",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"decimals": -1,
"fill": 10,
"id": 14,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "ceil(sum by(container) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval])))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "IOPS(Reads+Writes)",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 10,
"id": 15,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 0,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"spaceLength": 10,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{container}}",
"legendLink": null,
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ThroughPut(Read+Write)",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Storage IO - Distribution(Containers)",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"id": 16,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null as zero",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [
],
"sort": {
"col": 4,
"desc": true
},
"spaceLength": 10,
"span": 12,
"stack": false,
"steppedLine": false,
"styles": [
{
"alias": "Time",
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"pattern": "Time",
"type": "hidden"
},
{
"alias": "IOPS(Reads)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "IOPS(Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "IOPS(Reads + Writes)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": -1,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "Throughput(Read)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Throughput(Write)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Throughput(Read + Write)",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
"thresholds": [
],
"type": "number",
"unit": "Bps"
},
{
"alias": "Container",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "container",
"thresholds": [
],
"type": "number",
"unit": "short"
},
{
"alias": "",
"colorMode": null,
"colors": [
],
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"pattern": "/.*/",
"thresholds": [
],
"type": "string",
"unit": "short"
}
],
"targets": [
{
"expr": "sum by(container) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "A",
"step": 10
},
{
"expr": "sum by(container) (rate(container_fs_writes_total{job=\"kubernetes-cadvisor\",device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "B",
"step": 10
},
{
"expr": "sum by(container) (rate(container_fs_reads_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "C",
"step": 10
},
{
"expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "D",
"step": 10
},
{
"expr": "sum by(container) (rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "E",
"step": 10
},
{
"expr": "sum by(container) (rate(container_fs_reads_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]) + rate(container_fs_writes_bytes_total{job=\"kubernetes-cadvisor\", device=~\"mmcblk.p.+|nvme.+|rbd.+|sd.+|vd.+|xvd.+|dm-.+|dasd.+\", container!=\"\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[$__rate_interval]))",
"format": "table",
"instant": true,
"intervalFactor": 2,
"legendFormat": "",
"refId": "F",
"step": 10
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Current Storage IO",
"tooltip": {
"shared": false,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
"type": "table",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Storage IO - Distribution",
"titleSize": "h6"
}
],
@ -1602,7 +2320,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -1627,8 +2345,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -1654,8 +2372,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -1681,7 +2399,7 @@ data:
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
"query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -1724,7 +2442,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Compute Resources / Pod",
"uid": "6581e46e4e5c7ba40a07646395ef7b23",
"version": 0
@ -1759,11 +2477,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 1,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1787,7 +2508,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -1803,7 +2524,7 @@ data:
"title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -1857,11 +2578,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -1899,6 +2623,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -1917,6 +2642,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -1935,6 +2661,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -1953,6 +2680,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -1971,6 +2699,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -1989,8 +2718,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@ -2016,7 +2746,7 @@ data:
],
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2025,7 +2755,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2034,7 +2764,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2043,7 +2773,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2052,7 +2782,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2069,7 +2799,7 @@ data:
"title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -2124,11 +2854,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2152,7 +2885,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -2168,7 +2901,7 @@ data:
"title": "Memory Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2222,11 +2955,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2264,6 +3000,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -2282,6 +3019,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -2300,6 +3038,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -2318,6 +3057,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -2336,6 +3076,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -2354,8 +3095,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@ -2381,7 +3123,7 @@ data:
],
"targets": [
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2390,7 +3132,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2399,7 +3141,7 @@ data:
"step": 10
},
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2408,7 +3150,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2417,7 +3159,7 @@ data:
"step": 10
},
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2434,7 +3176,7 @@ data:
"title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -2489,11 +3231,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2531,6 +3276,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -2549,6 +3295,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -2567,6 +3314,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -2585,6 +3333,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -2603,6 +3352,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -2621,6 +3371,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -2639,8 +3390,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"linkUrl": "/d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
"pattern": "pod",
"thresholds": [
@ -2666,7 +3418,7 @@ data:
],
"targets": [
{
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2675,7 +3427,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2684,7 +3436,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2693,7 +3445,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2702,7 +3454,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2711,7 +3463,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -2728,7 +3480,7 @@ data:
"title": "Current Network Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -2766,7 +3518,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Current Network Usage",
"titleSize": "h6"
},
{
@ -2783,11 +3535,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2806,12 +3561,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -2827,7 +3582,7 @@ data:
"title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2858,19 +3613,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -2881,11 +3624,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -2904,12 +3650,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -2925,7 +3671,7 @@ data:
"title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2962,7 +3708,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Bandwidth",
"titleSize": "h6"
},
{
@ -2979,11 +3725,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3002,12 +3751,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3023,7 +3772,7 @@ data:
"title": "Average Container Bandwidth by Pod: Received",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3054,19 +3803,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -3077,11 +3814,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3100,12 +3840,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3121,7 +3861,7 @@ data:
"title": "Average Container Bandwidth by Pod: Transmitted",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3158,7 +3898,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Average Container Bandwidth by Pod",
"titleSize": "h6"
},
{
@ -3175,11 +3915,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3198,12 +3941,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3219,7 +3962,7 @@ data:
"title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3234,7 +3977,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -3250,19 +3993,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -3273,11 +4004,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3296,12 +4030,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3317,7 +4051,7 @@ data:
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3332,7 +4066,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -3354,7 +4088,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets",
"titleSize": "h6"
},
{
@ -3371,11 +4105,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3394,12 +4131,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3415,7 +4152,7 @@ data:
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3430,7 +4167,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -3446,19 +4183,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -3469,11 +4194,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 13,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3492,12 +4220,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{pod}}",
@ -3513,7 +4241,7 @@ data:
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3528,7 +4256,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -3550,7 +4278,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets Dropped",
"titleSize": "h6"
}
],
@ -3567,7 +4295,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -3592,8 +4320,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -3619,35 +4347,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "workload",
"options": [
],
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
"refresh": 1,
"query": "label_values(kube_namespace_status_phase{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -3673,8 +4374,35 @@ data:
"options": [
],
"query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
"refresh": 1,
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload_type)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": "",
"value": ""
},
"datasource": "$datasource",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "workload",
"options": [
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}, workload)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -3716,7 +4444,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Compute Resources / Workload",
"uid": "a164a7f0339f99e89cea5cb47e9be617",
"version": 0
@ -3751,11 +4479,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 1,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3776,8 +4507,9 @@ data:
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
},
@ -3786,8 +4518,9 @@ data:
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
}
@ -3798,7 +4531,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}} - {{workload_type}}",
@ -3830,7 +4563,7 @@ data:
"title": "CPU Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -3884,11 +4617,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -3926,6 +4662,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -3944,6 +4681,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -3962,6 +4700,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -3980,6 +4719,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -3998,6 +4738,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -4016,6 +4757,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -4034,8 +4776,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
"linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
"pattern": "workload",
"thresholds": [
@ -4052,6 +4795,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "workload_type",
@ -4079,7 +4823,7 @@ data:
],
"targets": [
{
"expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
"expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4088,7 +4832,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4097,7 +4841,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4106,7 +4850,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4115,7 +4859,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4124,7 +4868,7 @@ data:
"step": 10
},
{
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4141,7 +4885,7 @@ data:
"title": "CPU Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -4196,11 +4940,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4221,8 +4968,9 @@ data:
"color": "#F2495C",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
},
@ -4231,8 +4979,9 @@ data:
"color": "#FF9830",
"dashes": true,
"fill": 0,
"hiddenSeries": true,
"hideTooltip": true,
"legend": false,
"legend": true,
"linewidth": 2,
"stack": false
}
@ -4243,7 +4992,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}} - {{workload_type}}",
@ -4275,7 +5024,7 @@ data:
"title": "Memory Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -4329,11 +5078,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4371,6 +5123,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 0,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -4389,6 +5142,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -4407,6 +5161,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -4425,6 +5180,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -4443,6 +5199,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -4461,6 +5218,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -4479,8 +5237,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
"linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
"pattern": "workload",
"thresholds": [
@ -4497,6 +5256,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "workload_type",
@ -4524,7 +5284,7 @@ data:
],
"targets": [
{
"expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
"expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4533,7 +5293,7 @@ data:
"step": 10
},
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4542,7 +5302,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4551,7 +5311,7 @@ data:
"step": 10
},
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4560,7 +5320,7 @@ data:
"step": 10
},
{
"expr": "sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4569,7 +5329,7 @@ data:
"step": 10
},
{
"expr": "sum(\n container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"expr": "sum(\n container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n * on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\"}\n* on(namespace,pod)\n group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4586,7 +5346,7 @@ data:
"title": "Memory Quota",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -4641,11 +5401,14 @@ data:
"datasource": "$datasource",
"fill": 1,
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4683,6 +5446,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -4701,6 +5465,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -4719,6 +5484,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #C",
@ -4737,6 +5503,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #D",
@ -4755,6 +5522,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #E",
@ -4773,6 +5541,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #F",
@ -4791,8 +5560,9 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": true,
"linkTargetBlank": false,
"linkTooltip": "Drill down to pods",
"linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type",
"linkUrl": "/d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type",
"pattern": "workload",
"thresholds": [
@ -4809,6 +5579,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "workload_type",
@ -4836,7 +5607,7 @@ data:
],
"targets": [
{
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4845,7 +5616,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4854,7 +5625,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4863,7 +5634,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4872,7 +5643,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4881,7 +5652,7 @@ data:
"step": 10
},
{
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
"format": "table",
"instant": true,
"intervalFactor": 2,
@ -4898,7 +5669,7 @@ data:
"title": "Current Network Usage",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -4936,7 +5707,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Current Network Usage",
"titleSize": "h6"
},
{
@ -4953,11 +5724,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -4976,12 +5750,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -4997,7 +5771,7 @@ data:
"title": "Receive Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5028,19 +5802,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -5051,11 +5813,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5074,12 +5839,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5095,7 +5860,7 @@ data:
"title": "Transmit Bandwidth",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5132,7 +5897,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Bandwidth",
"titleSize": "h6"
},
{
@ -5149,11 +5914,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5172,12 +5940,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(avg(irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5193,7 +5961,7 @@ data:
"title": "Average Container Bandwidth by Workload: Received",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5224,19 +5992,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -5247,11 +6003,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5270,12 +6029,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(avg(irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5291,7 +6050,7 @@ data:
"title": "Average Container Bandwidth by Workload: Transmitted",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5328,7 +6087,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Average Container Bandwidth by Workload",
"titleSize": "h6"
},
{
@ -5345,11 +6104,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5368,12 +6130,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_receive_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5389,7 +6151,7 @@ data:
"title": "Rate of Received Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5404,7 +6166,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -5420,19 +6182,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -5443,11 +6193,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5466,12 +6219,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_transmit_packets_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5487,7 +6240,7 @@ data:
"title": "Rate of Transmitted Packets",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5502,7 +6255,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -5524,7 +6277,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets",
"titleSize": "h6"
},
{
@ -5541,11 +6294,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5564,12 +6320,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_receive_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5585,7 +6341,7 @@ data:
"title": "Rate of Received Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5600,7 +6356,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -5616,19 +6372,7 @@ data:
"show": false
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"titleSize": "h6"
},
{
"collapse": false,
"height": "250px",
"panels": [
},
{
"aliasColors": {
@ -5639,11 +6383,14 @@ data:
"datasource": "$datasource",
"fill": 10,
"id": 13,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"total": false,
"values": false
@ -5662,12 +6409,12 @@ data:
],
"spaceLength": 10,
"span": 12,
"span": 6,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])\n* on (namespace,pod) \ngroup_left(workload,workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"expr": "(sum(irate(container_network_transmit_packets_dropped_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{workload}}",
@ -5683,7 +6430,7 @@ data:
"title": "Rate of Transmitted Packets Dropped",
"tooltip": {
"shared": false,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -5698,7 +6445,7 @@ data:
},
"yaxes": [
{
"format": "Bps",
"format": "pps",
"label": null,
"logBase": 1,
"max": null,
@ -5720,7 +6467,7 @@ data:
"repeatIteration": null,
"repeatRowId": null,
"showTitle": true,
"title": "Network",
"title": "Rate of Packets Dropped",
"titleSize": "h6"
}
],
@ -5737,7 +6484,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -5747,38 +6494,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "deployment",
"value": "deployment"
},
"datasource": "$datasource",
"definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "type",
"options": [
],
"query": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
@ -5794,8 +6509,8 @@ data:
"options": [
],
"query": "label_values(kube_pod_info, cluster)",
"refresh": 1,
"query": "label_values(up{job=\"kube-state-metrics\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -5821,13 +6536,45 @@ data:
"options": [
],
"query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
"refresh": 1,
"query": "label_values(kube_pod_info{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"auto": false,
"auto_count": 30,
"auto_min": "10s",
"current": {
"text": "deployment",
"value": "deployment"
},
"datasource": "$datasource",
"definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
"hide": 0,
"includeAll": false,
"label": null,
"multi": false,
"name": "type",
"options": [
],
"query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=~\".+\"}, workload_type)",
"refresh": 2,
"regex": "",
"skipUrlSync": false,
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
@ -5864,7 +6611,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Compute Resources / Namespace (Workloads)",
"uid": "a87fb0d919ec0ea5f6543124e16c42a5",
"version": 0

View File

@ -20,6 +20,24 @@ data:
"id": null,
"links": [
],
"panels": [
{
"content": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.",
"datasource": null,
"description": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.",
"gridPos": {
"h": 2,
"w": 24,
"x": 0,
"y": 0
},
"id": 2,
"mode": "markdown",
"span": 12,
"title": "Notice",
"type": "text"
}
],
"refresh": "10s",
"rows": [
@ -37,7 +55,9 @@ data:
"#d44a3a"
],
"datasource": "$datasource",
"format": "none",
"decimals": 3,
"description": "How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?",
"format": "percentunit",
"gauge": {
"maxValue": 100,
"minValue": 0,
@ -48,8 +68,12 @@ data:
"gridPos": {
},
"id": 2,
"interval": null,
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
@ -78,7 +102,7 @@ data:
"to": "null"
}
],
"span": 2,
"span": 4,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
@ -88,7 +112,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(up{job=\"apiserver\", cluster=\"$cluster\"})",
"expr": "apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -96,7 +120,7 @@ data:
}
],
"thresholds": "",
"title": "Up",
"title": "Availability (30d) > 99.000%",
"tooltip": {
"shared": false
},
@ -109,7 +133,7 @@ data:
"value": "null"
}
],
"valueName": "min"
"valueName": "avg"
},
{
"aliasColors": {
@ -119,19 +143,24 @@ data:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"decimals": 3,
"description": "How much error budget is left looking at our 0.990% availability guarantees?",
"fill": 10,
"fillGradient": 0,
"gridPos": {
},
"id": 3,
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -150,37 +179,16 @@ data:
],
"spaceLength": 10,
"span": 5,
"span": 8,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"2..\", cluster=\"$cluster\"}[5m]))",
"expr": "100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"legendFormat": "errorbudget",
"refId": "A"
},
{
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"3..\", cluster=\"$cluster\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"4..\", cluster=\"$cluster\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"5..\", cluster=\"$cluster\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
"refId": "D"
}
],
"thresholds": [
@ -188,7 +196,7 @@ data:
],
"timeFrom": null,
"timeShift": null,
"title": "RPC Rate",
"title": "ErrorBudget (30d) > 99.000%",
"tooltip": {
"shared": false,
"sort": 0,
@ -206,7 +214,8 @@ data:
},
"yaxes": [
{
"format": "ops",
"decimals": 3,
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
@ -214,7 +223,221 @@ data:
"show": true
},
{
"format": "ops",
"decimals": 3,
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"decimals": 3,
"description": "How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?",
"format": "percentunit",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 3,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"title": "Read Availability (30d)",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "How many read requests (LIST,GET) per second do the apiservers get by code?",
"fill": 10,
"fillGradient": 0,
"gridPos": {
},
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
{
"alias": "/2../i",
"color": "#56A64B"
},
{
"alias": "/3../i",
"color": "#F2CC0C"
},
{
"alias": "/4../i",
"color": "#3274D9"
},
{
"alias": "/5../i",
"color": "#E02F44"
}
],
"spaceLength": 10,
"span": 3,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ code }}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Read SLI - Requests",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "reqps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "reqps",
"label": null,
"logBase": 1,
"max": null,
@ -231,21 +454,25 @@ data:
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 4,
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": true,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
"values": false
},
"lines": true,
"linewidth": 1,
@ -262,15 +489,15 @@ data:
],
"spaceLength": 10,
"span": 5,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", verb!=\"WATCH\", cluster=\"$cluster\"}[5m])) by (verb, le))",
"expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}}",
"legendFormat": "{{ resource }}",
"refId": "A"
}
],
@ -279,7 +506,505 @@ data:
],
"timeFrom": null,
"timeShift": null,
"title": "Request duration 99th quantile",
"title": "Read SLI - Errors",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "How many seconds is the 99th percentile for reading (LIST|GET) a given resource?",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ resource }}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Read SLI - Duration",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"cacheTimeout": null,
"colorBackground": false,
"colorValue": false,
"colors": [
"#299c46",
"rgba(237, 129, 40, 0.89)",
"#d44a3a"
],
"datasource": "$datasource",
"decimals": 3,
"description": "How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?",
"format": "percentunit",
"gauge": {
"maxValue": 100,
"minValue": 0,
"show": false,
"thresholdLabels": false,
"thresholdMarkers": true
},
"gridPos": {
},
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
"mappingType": 1,
"mappingTypes": [
{
"name": "value to text",
"value": 1
},
{
"name": "range to text",
"value": 2
}
],
"maxDataPoints": 100,
"nullPointMode": "connected",
"nullText": null,
"postfix": "",
"postfixFontSize": "50%",
"prefix": "",
"prefixFontSize": "50%",
"rangeMaps": [
{
"from": "null",
"text": "N/A",
"to": "null"
}
],
"span": 3,
"sparkline": {
"fillColor": "rgba(31, 118, 189, 0.18)",
"full": false,
"lineColor": "rgb(31, 120, 193)",
"show": false
},
"tableColumn": "",
"targets": [
{
"expr": "apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
"refId": "A"
}
],
"thresholds": "",
"title": "Write Availability (30d)",
"tooltip": {
"shared": false
},
"type": "singlestat",
"valueFontSize": "80%",
"valueMaps": [
{
"op": "=",
"text": "N/A",
"value": "null"
}
],
"valueName": "avg"
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?",
"fill": 10,
"fillGradient": 0,
"gridPos": {
},
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
{
"alias": "/2../i",
"color": "#56A64B"
},
{
"alias": "/3../i",
"color": "#F2CC0C"
},
{
"alias": "/4../i",
"color": "#3274D9"
},
{
"alias": "/5../i",
"color": "#E02F44"
}
],
"spaceLength": 10,
"span": 3,
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ code }}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Write SLI - Requests",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "reqps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "reqps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ resource }}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Write SLI - Errors",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "percentunit",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"description": "How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 12,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 3,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{ resource }}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "Write SLI - Duration",
"tooltip": {
"shared": false,
"sort": 0,
@ -336,18 +1061,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 5,
"id": 13,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": false,
"sideWidth": null,
"total": false,
"values": false
},
@ -371,7 +1099,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)",
"expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{name}}",
@ -427,18 +1155,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 6,
"id": 14,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": false,
"sideWidth": null,
"total": false,
"values": false
},
@ -462,7 +1193,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)",
"expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{name}}",
@ -518,10 +1249,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 7,
"id": 15,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -530,6 +1263,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -553,7 +1287,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name, le))",
"expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])) by (instance, name, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{name}}",
@ -622,318 +1356,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 8,
"id": 16,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "etcd_helper_cache_entry_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
"refId": "A"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ETCD Cache Entry Total",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 9,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(etcd_helper_cache_hit_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} hit",
"refId": "A"
},
{
"expr": "sum(rate(etcd_helper_cache_miss_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} miss",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ETCD Cache Hit/Miss Rate",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "ops",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
},
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 10,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [
],
"nullPointMode": "null",
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"repeat": null,
"seriesOverrides": [
],
"spaceLength": 10,
"span": 4,
"stack": false,
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_get_duration_seconds_bucket{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} get",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_add_duration_seconds_bucket{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} miss",
"refId": "B"
}
],
"thresholds": [
],
"timeFrom": null,
"timeShift": null,
"title": "ETCD Cache Duration 99th Quantile",
"tooltip": {
"shared": false,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": [
]
},
"yaxes": [
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
},
{
"format": "s",
"label": null,
"logBase": 1,
"max": null,
"min": 0,
"show": true
}
]
}
],
"repeat": null,
"repeatIteration": null,
"repeatRowId": null,
"showTitle": false,
"title": "Dashboard Row",
"titleSize": "h6",
"type": "row"
},
{
"collapse": false,
"collapsed": false,
"panels": [
{
"aliasColors": {
},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"gridPos": {
},
"id": 11,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1013,18 +1450,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 12,
"id": 17,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1048,7 +1488,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])",
"expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[$__rate_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -1104,18 +1544,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 13,
"id": 18,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1209,7 +1652,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -1222,20 +1665,19 @@ data:
{
"allValue": null,
"current": {
"text": "prod",
"value": "prod"
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": null,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(apiserver_request_total, cluster)",
"refresh": 1,
"query": "label_values(up{job=\"apiserver\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
@ -1260,7 +1702,7 @@ data:
"options": [
],
"query": "label_values(apiserver_request_total{job=\"apiserver\", cluster=\"$cluster\"}, instance)",
"query": "label_values(up{job=\"apiserver\", cluster=\"$cluster\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -1303,7 +1745,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / API server",
"uid": "09ec8aa1e996d6ffcd6817bbaff4db1b",
"version": 0
@ -1357,7 +1799,11 @@ data:
},
"id": 2,
"interval": null,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
@ -1396,7 +1842,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(up{job=\"kube-controller-manager\"})",
"expr": "sum(up{cluster=\"$cluster\", job=\"kube-controller-manager\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -1428,10 +1874,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -1440,6 +1888,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -1463,10 +1912,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(workqueue_adds_total{job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name)",
"expr": "sum(rate(workqueue_adds_total{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{name}}",
"legendFormat": "{{cluster}} {{instance}} {{name}}",
"refId": "A"
}
],
@ -1532,10 +1981,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -1544,6 +1995,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -1567,10 +2019,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(workqueue_depth{job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name)",
"expr": "sum(rate(workqueue_depth{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{name}}",
"legendFormat": "{{cluster}} {{instance}} {{name}}",
"refId": "A"
}
],
@ -1636,10 +2088,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -1648,6 +2102,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -1671,10 +2126,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\"}[5m])) by (instance, name, le))",
"expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, name, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} {{name}}",
"legendFormat": "{{cluster}} {{instance}} {{name}}",
"refId": "A"
}
],
@ -1740,18 +2195,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1775,28 +2233,28 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{job=\"kube-controller-manager\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
@ -1852,18 +2310,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1887,7 +2348,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@ -1956,10 +2417,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -1968,6 +2431,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -1991,7 +2455,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@ -2060,18 +2524,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -2095,7 +2562,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{job=\"kube-controller-manager\",instance=~\"$instance\"}",
"expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2151,18 +2618,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -2186,7 +2656,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{job=\"kube-controller-manager\",instance=~\"$instance\"}[5m])",
"expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}[$__rate_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2242,18 +2712,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 11,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -2277,7 +2750,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "go_goroutines{job=\"kube-controller-manager\",instance=~\"$instance\"}",
"expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-controller-manager\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -2347,7 +2820,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -2361,6 +2834,32 @@ data:
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kube-controller-manager\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 0,
@ -2371,7 +2870,7 @@ data:
"options": [
],
"query": "label_values(process_cpu_seconds_total{job=\"kube-controller-manager\"}, instance)",
"query": "label_values(up{cluster=\"$cluster\", job=\"kube-controller-manager\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -2414,7 +2913,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Controller Manager",
"uid": "72e0e05bef5099e5f049b05fdc429ed4",
"version": 0
@ -2455,18 +2954,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 2,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -2490,14 +2992,14 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "(\n sum without(instance, node) (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n",
"expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Used Space",
"refId": "A"
},
{
"expr": "sum without(instance, node) (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n",
"expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Free Space",
@ -2566,7 +3068,11 @@ data:
},
"id": 3,
"interval": null,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
@ -2605,7 +3111,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "(\n kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n -\n kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n)\n/\nkubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n",
"expr": "max without(instance,node) (\n(\n topk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n topk(1, kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n/\ntopk(1, kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -2650,18 +3156,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": true,
"current": true,
"max": true,
"min": true,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -2685,14 +3194,14 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n",
"expr": "sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": "Used inodes",
"refId": "A"
},
{
"expr": "(\n sum without(instance, node) (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n -\n sum without(instance, node) (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n)\n",
"expr": "(\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n -\n sum without(instance, node) (topk(1, (kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})))\n)\n",
"format": "time_series",
"intervalFactor": 1,
"legendFormat": " Free inodes",
@ -2761,7 +3270,11 @@ data:
},
"id": 5,
"interval": null,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
@ -2800,7 +3313,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n/\nkubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n",
"expr": "max without(instance,node) (\ntopk(1, kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n/\ntopk(1, kubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"})\n* 100)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -2846,7 +3359,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -2870,7 +3383,7 @@ data:
"options": [
],
"query": "label_values(kubelet_volume_stats_capacity_bytes, cluster)",
"query": "label_values(kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -2965,7 +3478,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Persistent Volumes",
"uid": "919b92a8e8041bd567af9edab12c840c",
"version": 0
@ -3019,7 +3532,11 @@ data:
},
"id": 2,
"interval": null,
"interval": "1m",
"legend": {
"alignAsTable": true,
"rightSide": true
},
"links": [
],
@ -3058,7 +3575,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(up{job=\"kube-scheduler\"})",
"expr": "sum(up{cluster=\"$cluster\", job=\"kube-scheduler\"})",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -3090,10 +3607,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 3,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -3102,6 +3621,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -3125,31 +3645,31 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_e2e_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} e2e",
"legendFormat": "{{cluster}} {{instance}} e2e",
"refId": "A"
},
{
"expr": "sum(rate(scheduler_binding_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_binding_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} binding",
"legendFormat": "{{cluster}} {{instance}} binding",
"refId": "B"
},
{
"expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_scheduling_algorithm_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} scheduling algorithm",
"legendFormat": "{{cluster}} {{instance}} scheduling algorithm",
"refId": "C"
},
{
"expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])) by (instance)",
"expr": "sum(rate(scheduler_volume_scheduling_duration_seconds_count{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance)",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} volume",
"legendFormat": "{{cluster}} {{instance}} volume",
"refId": "D"
}
],
@ -3202,10 +3722,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 4,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -3214,6 +3736,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -3237,31 +3760,31 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} e2e",
"legendFormat": "{{cluster}} {{instance}} e2e",
"refId": "A"
},
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} binding",
"legendFormat": "{{cluster}} {{instance}} binding",
"refId": "B"
},
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} scheduling algorithm",
"legendFormat": "{{cluster}} {{instance}} scheduling algorithm",
"refId": "C"
},
{
"expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{job=\"kube-scheduler\",instance=~\"$instance\"}[5m])) by (instance, le))",
"expr": "histogram_quantile(0.99, sum(rate(scheduler_volume_scheduling_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}[$__rate_interval])) by (cluster, instance, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}} volume",
"legendFormat": "{{cluster}} {{instance}} volume",
"refId": "D"
}
],
@ -3327,18 +3850,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 5,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3362,28 +3888,28 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"2..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "2xx",
"refId": "A"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"3..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "3xx",
"refId": "B"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"4..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "4xx",
"refId": "C"
},
{
"expr": "sum(rate(rest_client_requests_total{job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
"expr": "sum(rate(rest_client_requests_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\",code=~\"5..\"}[$__rate_interval]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "5xx",
@ -3439,18 +3965,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 6,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3474,7 +4003,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[$__rate_interval])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@ -3543,10 +4072,12 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 7,
"interval": "1m",
"legend": {
"alignAsTable": true,
"avg": false,
@ -3555,6 +4086,7 @@ data:
"min": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": true
},
@ -3578,7 +4110,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
"expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[$__rate_interval])) by (verb, url, le))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{verb}} {{url}}",
@ -3647,18 +4179,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 8,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3682,7 +4217,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "process_resident_memory_bytes{job=\"kube-scheduler\", instance=~\"$instance\"}",
"expr": "process_resident_memory_bytes{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -3738,18 +4273,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 9,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3773,7 +4311,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(process_cpu_seconds_total{job=\"kube-scheduler\", instance=~\"$instance\"}[5m])",
"expr": "rate(process_cpu_seconds_total{cluster=\"$cluster\", job=\"kube-scheduler\", instance=~\"$instance\"}[$__rate_interval])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -3829,18 +4367,21 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
"id": 10,
"interval": "1m",
"legend": {
"alignAsTable": false,
"alignAsTable": true,
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"rightSide": true,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -3864,7 +4405,7 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "go_goroutines{job=\"kube-scheduler\",instance=~\"$instance\"}",
"expr": "go_goroutines{cluster=\"$cluster\", job=\"kube-scheduler\",instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{instance}}",
@ -3934,7 +4475,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -3948,6 +4489,32 @@ data:
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [
],
"query": "label_values(up{job=\"kube-scheduler\"}, cluster)",
"refresh": 2,
"regex": "",
"sort": 1,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
},
"datasource": "$datasource",
"hide": 0,
@ -3958,7 +4525,7 @@ data:
"options": [
],
"query": "label_values(process_cpu_seconds_total{job=\"kube-scheduler\"}, instance)",
"query": "label_values(up{job=\"kube-scheduler\", cluster=\"$cluster\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 1,
@ -4001,7 +4568,7 @@ data:
"30d"
]
},
"timezone": "",
"timezone": "UTC",
"title": "Kubernetes / Scheduler",
"uid": "2e6b6a3b4bddf1427b3a55aa1311c656",
"version": 0

View File

@ -172,7 +172,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "sum(avg_over_time(nginx_ingress_controller_nginx_process_connections{cluster=~\"$cluster\", controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\"}[2m]))",
"expr": "sum(avg_over_time(nginx_ingress_controller_nginx_process_connections{cluster=~\"$cluster\", controller_pod=~\"$controller\",controller_class=~\"$controller_class\",controller_namespace=~\"$namespace\",state=\"active\"}[2m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -296,6 +296,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -308,6 +309,7 @@ data:
"min": false,
"rightSide": "true",
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -387,6 +389,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -399,6 +402,7 @@ data:
"min": false,
"rightSide": "true",
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -491,6 +495,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -503,6 +508,7 @@ data:
"min": false,
"rightSide": "true",
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -609,6 +615,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -621,6 +628,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -707,6 +715,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -719,6 +728,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},
@ -798,6 +808,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -810,6 +821,7 @@ data:
"min": false,
"rightSide": false,
"show": "true",
"sideWidth": null,
"total": false,
"values": "true"
},

View File

@ -15,13 +15,13 @@ data:
},
"editable": false,
"gnetId": null,
"graphTooltip": 0,
"graphTooltip": 1,
"hideControls": false,
"id": null,
"links": [
],
"refresh": "",
"refresh": "30s",
"rows": [
{
"collapse": false,
@ -36,6 +36,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -48,6 +49,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -71,9 +73,8 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "(\n (1 - rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"}[$__interval]))\n/ ignoring(cpu) group_left\n count without (cpu)( node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n",
"expr": "(\n (1 - sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\", instance=\"$instance\"}[$__rate_interval])))\n/ ignoring(cpu) group_left\n count without (cpu, mode) (node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\", instance=\"$instance\"})\n)\n",
"format": "time_series",
"interval": "1m",
"intervalFactor": 5,
"legendFormat": "{{cpu}}",
"refId": "A"
@ -128,6 +129,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 0,
"fillGradient": 0,
"gridPos": {
},
@ -140,6 +142,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -253,6 +256,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -265,6 +269,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -417,7 +422,7 @@ data:
"tableColumn": "",
"targets": [
{
"expr": "100 -\n(\n node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n* 100\n)\n",
"expr": "100 -\n(\n avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"})\n/\n avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "",
@ -459,6 +464,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 0,
"fillGradient": 0,
"gridPos": {
},
@ -471,6 +477,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -501,25 +508,22 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__interval])",
"expr": "rate(node_disk_read_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__rate_interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}} read",
"refId": "A"
},
{
"expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__interval])",
"expr": "rate(node_disk_written_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__rate_interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}} written",
"refId": "B"
},
{
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__interval])",
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", instance=\"$instance\", device!~\"dm.*\"}[$__rate_interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}} io time",
"refId": "C"
@ -574,6 +578,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -586,6 +591,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -692,6 +698,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 0,
"fillGradient": 0,
"gridPos": {
},
@ -704,6 +711,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -727,9 +735,8 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
"expr": "rate(node_network_receive_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}}",
"refId": "A"
@ -784,6 +791,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 0,
"fillGradient": 0,
"gridPos": {
},
@ -796,6 +804,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -819,9 +828,8 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__interval])",
"expr": "rate(node_network_transmit_bytes_total{job=\"node-exporter\", instance=\"$instance\", device!=\"lo\"}[$__rate_interval])",
"format": "time_series",
"interval": "1m",
"intervalFactor": 2,
"legendFormat": "{{device}}",
"refId": "A"
@ -880,17 +888,17 @@ data:
"schemaVersion": 14,
"style": "dark",
"tags": [
"node-exporter-mixin"
],
"templating": {
"list": [
{
"current": {
"text": "Prometheus",
"value": "Prometheus"
"text": "default",
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -958,7 +966,7 @@ data:
]
},
"timezone": "",
"title": "Nodes",
"title": "Node Exporter / Nodes",
"uid": "fa49a4706d07a042595b664c87fb33ea",
"version": 0
}

View File

@ -21,7 +21,7 @@ data:
"links": [
],
"refresh": "",
"refresh": "60s",
"rows": [
{
"collapse": false,
@ -36,6 +36,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -48,6 +49,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -71,10 +73,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}\n)\n",
"expr": "(\n prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} \n- \n ignoring(remote_name, url) group_right(instance) (prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} != 0)\n)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -127,6 +129,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -139,6 +142,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -162,10 +166,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n)\n",
"expr": "clamp_min(\n rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n, 0)\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -231,6 +235,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -243,6 +248,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -266,10 +272,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) \n- \n rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n",
"expr": "rate(\n prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n- \n ignoring(remote_name, url) group_right(instance) (rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n- \n (rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -335,6 +341,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -347,6 +354,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -374,7 +382,7 @@ data:
"expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -427,6 +435,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -439,6 +448,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -465,7 +475,7 @@ data:
"expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -518,6 +528,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -530,6 +541,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -556,7 +568,7 @@ data:
"expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -609,6 +621,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -621,6 +634,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -647,7 +661,7 @@ data:
"expr": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -713,6 +727,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -725,6 +740,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -751,7 +767,7 @@ data:
"expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -804,6 +820,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -816,6 +833,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -839,10 +857,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}",
"expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"} or prometheus_remote_storage_samples_pending{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -908,6 +926,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -920,6 +939,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -999,6 +1019,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -1011,6 +1032,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1037,7 +1059,7 @@ data:
"expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{consumer}}",
"refId": "A"
}
],
@ -1103,6 +1125,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -1115,6 +1138,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1138,10 +1162,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -1194,6 +1218,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -1206,6 +1231,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1229,10 +1255,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -1285,6 +1311,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -1297,6 +1324,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1320,10 +1348,10 @@ data:
"steppedLine": false,
"targets": [
{
"expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_retried_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -1376,6 +1404,7 @@ data:
"dashes": false,
"datasource": "$datasource",
"fill": 1,
"fillGradient": 0,
"gridPos": {
},
@ -1388,6 +1417,7 @@ data:
"min": false,
"rightSide": false,
"show": true,
"sideWidth": null,
"total": false,
"values": false
},
@ -1414,7 +1444,7 @@ data:
"expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
"legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
"refId": "A"
}
],
@ -1471,7 +1501,7 @@ data:
"schemaVersion": 14,
"style": "dark",
"tags": [
"prometheus-mixin"
],
"templating": {
"list": [
@ -1487,41 +1517,6 @@ data:
"regex": "",
"type": "datasource"
},
{
"allValue": null,
"current": {
"text": {
"selected": true,
"text": "All",
"value": "$__all"
},
"value": {
"selected": true,
"text": "All",
"value": "$__all"
}
},
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
"label": null,
"multi": false,
"name": "instance",
"options": [
],
"query": "label_values(prometheus_build_info, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
@ -1557,6 +1552,41 @@ data:
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
"text": {
"selected": true,
"text": "All",
"value": "$__all"
},
"value": {
"selected": true,
"text": "All",
"value": "$__all"
}
},
"datasource": "$datasource",
"hide": 0,
"includeAll": true,
"label": null,
"multi": false,
"name": "instance",
"options": [
],
"query": "label_values(prometheus_build_info{cluster=~\"$cluster\"}, instance)",
"refresh": 2,
"regex": "",
"sort": 0,
"tagValuesQuery": "",
"tags": [
],
"tagsQuery": "",
"type": "query",
"useTags": false
},
{
"allValue": null,
"current": {
@ -1567,11 +1597,11 @@ data:
"includeAll": true,
"label": null,
"multi": false,
"name": "queue",
"name": "url",
"options": [
],
"query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, queue)",
"query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)",
"refresh": 2,
"regex": "",
"sort": 0,
@ -1615,7 +1645,7 @@ data:
]
},
"timezone": "browser",
"title": "Prometheus Remote Write",
"title": "Prometheus / Remote Write",
"version": 0
}
prometheus.json: |-
@ -1632,7 +1662,7 @@ data:
"links": [
],
"refresh": "10s",
"refresh": "60s",
"rows": [
{
"collapse": false,
@ -1690,6 +1720,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #A",
@ -1708,6 +1739,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "Value #B",
@ -1726,6 +1758,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "instance",
@ -1744,6 +1777,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "job",
@ -1762,6 +1796,7 @@ data:
"dateFormat": "YYYY-MM-DD HH:mm:ss",
"decimals": 2,
"link": false,
"linkTargetBlank": false,
"linkTooltip": "Drill down",
"linkUrl": "",
"pattern": "version",
@ -1815,7 +1850,7 @@ data:
"title": "Prometheus Stats",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"transform": "table",
@ -1914,7 +1949,7 @@ data:
"title": "Target Sync",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2000,7 +2035,7 @@ data:
"title": "Targets",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2098,7 +2133,7 @@ data:
"title": "Average Scrape Interval Duration",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2167,6 +2202,14 @@ data:
"stack": true,
"steppedLine": false,
"targets": [
{
"expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_body_size_limit_total[1m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "exceeded body size limit: {{job}}",
"legendLink": null,
"step": 10
},
{
"expr": "sum by (job) (rate(prometheus_target_scrapes_exceeded_sample_limit_total[1m]))",
"format": "time_series",
@ -2208,7 +2251,7 @@ data:
"title": "Scrape failures",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2294,7 +2337,7 @@ data:
"title": "Appended Samples",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2392,7 +2435,7 @@ data:
"title": "Head Series",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2478,7 +2521,7 @@ data:
"title": "Head Chunks",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2576,7 +2619,7 @@ data:
"title": "Query Rate",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2662,7 +2705,7 @@ data:
"title": "Stage Duration",
"tooltip": {
"shared": true,
"sort": 0,
"sort": 2,
"value_type": "individual"
},
"type": "graph",
@ -2706,7 +2749,7 @@ data:
"schemaVersion": 14,
"style": "dark",
"tags": [
"prometheus-mixin"
],
"templating": {
"list": [
@ -2716,7 +2759,7 @@ data:
"value": "default"
},
"hide": 0,
"label": null,
"label": "Data Source",
"name": "datasource",
"options": [
@ -2727,7 +2770,7 @@ data:
"type": "datasource"
},
{
"allValue": null,
"allValue": ".+",
"current": {
"selected": true,
"text": "All",
@ -2742,7 +2785,7 @@ data:
"options": [
],
"query": "label_values(prometheus_build_info, job)",
"query": "label_values(prometheus_build_info{job=\"prometheus\"}, job)",
"refresh": 1,
"regex": "",
"sort": 2,
@ -2755,7 +2798,7 @@ data:
"useTags": false
},
{
"allValue": null,
"allValue": ".+",
"current": {
"selected": true,
"text": "All",
@ -2770,7 +2813,7 @@ data:
"options": [
],
"query": "label_values(prometheus_build_info, instance)",
"query": "label_values(prometheus_build_info{job=~\"$job\"}, instance)",
"refresh": 1,
"regex": "",
"sort": 2,
@ -2814,7 +2857,7 @@ data:
]
},
"timezone": "utc",
"title": "Prometheus",
"title": "Prometheus / Overview",
"uid": "",
"version": 0
}

View File

@ -18,12 +18,13 @@ spec:
labels:
name: grafana
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: grafana
image: docker.io/grafana/grafana:7.0.6
image: docker.io/grafana/grafana:9.3.1
env:
- name: GF_PATHS_CONFIG
value: "/etc/grafana/custom.ini"
@ -31,15 +32,22 @@ spec:
- name: http
containerPort: 8080
livenessProbe:
httpGet:
path: /metrics
tcpSocket:
port: 8080
initialDelaySeconds: 10
initialDelaySeconds: 30
periodSeconds: 10
timeoutSeconds: 1
failureThreshold: 5
successThreshold: 1
readinessProbe:
httpGet:
path: /api/health
scheme: HTTP
path: /robots.txt
port: 8080
initialDelaySeconds: 10
periodSeconds: 30
successThreshold: 1
timeoutSeconds: 5
resources:
requests:
cpu: 100m
@ -68,6 +76,8 @@ spec:
mountPath: /etc/grafana/dashboards/k8s-resources-1
- name: dashboards-k8s-resources-2
mountPath: /etc/grafana/dashboards/k8s-resources-2
- name: dashboards-k8s-network
mountPath: /etc/grafana/dashboards/k8s-network
- name: dashboards-coredns
mountPath: /etc/grafana/dashboards/coredns
- name: dashboards-nginx-ingress
@ -100,6 +110,9 @@ spec:
- name: dashboards-k8s-resources-1
configMap:
name: grafana-dashboards-k8s-resources-1
- name: dashboards-k8s-network
configMap:
name: grafana-dashboards-k8s-network
- name: dashboards-k8s-resources-2
configMap:
name: grafana-dashboards-k8s-resources-2

View File

@ -1,6 +1,6 @@
apiVersion: networking.k8s.io/v1beta1
apiVersion: networking.k8s.io/v1
kind: IngressClass
metadata:
name: public
spec:
controller: k8s.io/ingress-nginx
controller: k8s.io/public

View File

@ -17,14 +17,16 @@ spec:
labels:
name: nginx-ingress-controller
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: nginx-ingress-controller
image: us.gcr.io/k8s-artifacts-prod/ingress-nginx/controller:v0.34.1
image: registry.k8s.io/ingress-nginx/controller:v1.5.1
args:
- /nginx-ingress-controller
- --controller-class=k8s.io/public
- --ingress-class=public
# use downward API
env:
@ -47,7 +49,6 @@ spec:
containerPort: 10254
hostPort: 10254
livenessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
@ -55,15 +56,16 @@ spec:
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
readinessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
scheme: HTTP
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
lifecycle:
preStop:

View File

@ -10,6 +10,7 @@ rules:
- configmaps
- pods
- secrets
- endpoints
verbs:
- get
- apiGroups:
@ -37,3 +38,11 @@ rules:
- endpoints
verbs:
- get
- apiGroups:
- "coordination.k8s.io"
resources:
- leases
verbs:
- create
- get
- update

View File

@ -1,6 +1,6 @@
apiVersion: networking.k8s.io/v1beta1
apiVersion: networking.k8s.io/v1
kind: IngressClass
metadata:
name: public
spec:
controller: k8s.io/ingress-nginx
controller: k8s.io/public

View File

@ -17,14 +17,16 @@ spec:
labels:
name: nginx-ingress-controller
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: nginx-ingress-controller
image: us.gcr.io/k8s-artifacts-prod/ingress-nginx/controller:v0.34.1
image: registry.k8s.io/ingress-nginx/controller:v1.5.1
args:
- /nginx-ingress-controller
- --controller-class=k8s.io/public
- --ingress-class=public
# use downward API
env:
@ -47,7 +49,6 @@ spec:
containerPort: 10254
hostPort: 10254
livenessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
@ -55,15 +56,16 @@ spec:
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
readinessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
scheme: HTTP
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
lifecycle:
preStop:

View File

@ -10,6 +10,7 @@ rules:
- configmaps
- pods
- secrets
- endpoints
verbs:
- get
- apiGroups:
@ -32,8 +33,11 @@ rules:
verbs:
- create
- apiGroups:
- ""
- "coordination.k8s.io"
resources:
- endpoints
- leases
verbs:
- create
- get
- update

View File

@ -1,6 +1,6 @@
apiVersion: networking.k8s.io/v1beta1
apiVersion: networking.k8s.io/v1
kind: IngressClass
metadata:
name: public
spec:
controller: k8s.io/ingress-nginx
controller: k8s.io/public

View File

@ -1,7 +1,7 @@
apiVersion: apps/v1
kind: Deployment
metadata:
name: ingress-controller-public
name: nginx-ingress-controller
namespace: ingress
spec:
replicas: 2
@ -10,21 +10,23 @@ spec:
maxUnavailable: 1
selector:
matchLabels:
name: ingress-controller-public
name: nginx-ingress-controller
phase: prod
template:
metadata:
labels:
name: ingress-controller-public
name: nginx-ingress-controller
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: nginx-ingress-controller
image: us.gcr.io/k8s-artifacts-prod/ingress-nginx/controller:v0.34.1
image: registry.k8s.io/ingress-nginx/controller:v1.5.1
args:
- /nginx-ingress-controller
- --controller-class=k8s.io/public
- --ingress-class=public
# use downward API
env:
@ -76,4 +78,3 @@ spec:
runAsUser: 101 # www-data
restartPolicy: Always
terminationGracePeriodSeconds: 300

View File

@ -10,6 +10,7 @@ rules:
- configmaps
- pods
- secrets
- endpoints
verbs:
- get
- apiGroups:
@ -32,8 +33,10 @@ rules:
verbs:
- create
- apiGroups:
- ""
- "coordination.k8s.io"
resources:
- endpoints
- leases
verbs:
- create
- get
- update

View File

@ -1,6 +1,6 @@
apiVersion: networking.k8s.io/v1beta1
apiVersion: networking.k8s.io/v1
kind: IngressClass
metadata:
name: public
spec:
controller: k8s.io/ingress-nginx
controller: k8s.io/public

View File

@ -17,14 +17,16 @@ spec:
labels:
name: nginx-ingress-controller
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: nginx-ingress-controller
image: us.gcr.io/k8s-artifacts-prod/ingress-nginx/controller:v0.34.1
image: registry.k8s.io/ingress-nginx/controller:v1.5.1
args:
- /nginx-ingress-controller
- --controller-class=k8s.io/public
- --ingress-class=public
# use downward API
env:
@ -47,7 +49,6 @@ spec:
containerPort: 10254
hostPort: 10254
livenessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
@ -55,15 +56,16 @@ spec:
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
readinessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
scheme: HTTP
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
lifecycle:
preStop:

View File

@ -10,6 +10,7 @@ rules:
- configmaps
- pods
- secrets
- endpoints
verbs:
- get
- apiGroups:
@ -32,8 +33,10 @@ rules:
verbs:
- create
- apiGroups:
- ""
- "coordination.k8s.io"
resources:
- endpoints
- leases
verbs:
- create
- get
- update

View File

@ -1,6 +1,6 @@
apiVersion: networking.k8s.io/v1beta1
apiVersion: networking.k8s.io/v1
kind: IngressClass
metadata:
name: public
spec:
controller: k8s.io/ingress-nginx
controller: k8s.io/public

View File

@ -17,14 +17,16 @@ spec:
labels:
name: nginx-ingress-controller
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
containers:
- name: nginx-ingress-controller
image: us.gcr.io/k8s-artifacts-prod/ingress-nginx/controller:v0.34.1
image: registry.k8s.io/ingress-nginx/controller:v1.5.1
args:
- /nginx-ingress-controller
- --controller-class=k8s.io/public
- --ingress-class=public
# use downward API
env:
@ -47,7 +49,6 @@ spec:
containerPort: 10254
hostPort: 10254
livenessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
@ -55,15 +56,16 @@ spec:
initialDelaySeconds: 10
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
readinessProbe:
failureThreshold: 3
httpGet:
path: /healthz
port: 10254
scheme: HTTP
periodSeconds: 10
successThreshold: 1
failureThreshold: 3
timeoutSeconds: 5
lifecycle:
preStop:

View File

@ -10,6 +10,7 @@ rules:
- configmaps
- pods
- secrets
- endpoints
verbs:
- get
- apiGroups:
@ -32,8 +33,10 @@ rules:
verbs:
- create
- apiGroups:
- ""
- "coordination.k8s.io"
resources:
- endpoints
- leases
verbs:
- create
- get
- update

View File

@ -34,7 +34,7 @@ data:
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
@ -68,13 +68,58 @@ data:
- source_labels: [__name__, group]
regex: apiserver_request_duration_seconds_bucket;.+
action: drop
- source_labels: [__name__, group]
regex: apiserver_request_duration_seconds_count;.+
action: drop
# Scrape config for kube-controller-manager endpoints.
#
# kube-controller-manager service endpoints can be discovered by using the
# `endpoints` role and relabelling to only keep only endpoints associated with
# kube-system/kube-controller-manager and the `https` port.
- job_name: 'kube-controller-manager'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: kube-system;kube-controller-manager;metrics
- replacement: kube-controller-manager
action: replace
target_label: job
# Scrape config for kube-scheduler endpoints.
#
# kube-scheduler service endpoints can be discovered by using the `endpoints`
# role and relabelling to only keep only endpoints associated with
# kube-system/kube-scheduler and the `https` port.
- job_name: 'kube-scheduler'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: kube-system;kube-scheduler;metrics
- replacement: kube-scheduler
action: replace
target_label: job
# Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
# metrics from a node by scraping kubelet (127.0.0.1:10250/metrics).
- job_name: 'kubelet'
kubernetes_sd_configs:
- role: node
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
@ -82,10 +127,6 @@ data:
insecure_skip_verify: true
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_name
# Scrape config for Kubelet cAdvisor. Explore metrics from a node by
# scraping kubelet (127.0.0.1:10250/metrics/cadvisor).
- job_name: 'kubernetes-cadvisor'
@ -100,9 +141,6 @@ data:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- action: labelmap
regex: __meta_kubernetes_node_name
metric_relabel_configs:
- source_labels: [__name__, image]
action: drop
@ -121,13 +159,11 @@ data:
- source_labels: [__meta_kubernetes_node_label_node_kubernetes_io_controller]
action: keep
regex: 'true'
- action: labelmap
regex: __meta_kubernetes_node_name
- source_labels: [__meta_kubernetes_node_address_InternalIP]
action: replace
target_label: __address__
replacement: '${1}:2381'
# Scrape config for service endpoints.
#
# The relabeling allows the actual service scrape endpoint to be configured
@ -139,6 +175,7 @@ data:
# * `prometheus.io/path`: If the metrics path is not `/metrics` override this.
# * `prometheus.io/port`: If the metrics are exposed on a different port to the
# service then set this appropriately.
# * `prometheus.io/param`: Custom metrics query parameter, like "format=prometheus".
- job_name: 'kubernetes-service-endpoints'
kubernetes_sd_configs:
- role: endpoints
@ -161,6 +198,11 @@ data:
target_label: __address__
regex: ([^:]+)(?::\d+)?;(\d+)
replacement: $1:$2
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_param]
action: replace
target_label: __param_$1
regex: ([^=]+)=(.*)
replacement: $2
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
@ -172,44 +214,12 @@ data:
- source_labels: [__meta_kubernetes_service_name]
action: replace
target_label: job
metric_relabel_configs:
- source_labels: [__name__]
action: drop
regex: etcd_(debugging|disk|request|server).*
# Example scrape config for probing services via the Blackbox Exporter.
#
# The relabeling allows the actual service scrape endpoint to be configured
# via the following annotations:
#
# * `prometheus.io/probe`: Only probe services that have a value of `true`
- job_name: 'kubernetes-services'
metrics_path: /probe
params:
module: [http_2xx]
kubernetes_sd_configs:
- role: service
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__address__]
target_label: __param_target
- target_label: __address__
replacement: blackbox
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: job
# Example scrape config for pods
#
# The relabeling allows the actual pod scrape endpoint to be configured via the
@ -246,6 +256,67 @@ data:
action: replace
target_label: kubernetes_pod_name
# Example scrape config for probing Services via the Blackbox Exporter.
#
# Relabeling allows service scraping to be configured via annotations:
# * `prometheus.io/probe`: Only probe services that have a value of `true`
- job_name: 'kubernetes-services'
metrics_path: /probe
params:
module: [http_2xx]
kubernetes_sd_configs:
- role: service
relabel_configs:
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__address__]
target_label: __param_target
- target_label: __address__
replacement: blackbox-exporter:8080
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_service_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: job
# Example scrape config for probing Ingresses via a Blackbox Exporter.
#
# Relabeling allows service scraping to be configured via annotations:
# * `prometheus.io/probe`: Only probe ingresses that have a value of `true`
- job_name: 'kubernetes-ingresses'
metrics_path: /probe
params:
module: [http_2xx]
kubernetes_sd_configs:
- role: ingress
relabel_configs:
- source_labels: [__meta_kubernetes_ingress_annotation_prometheus_io_probe]
action: keep
regex: true
- source_labels: [__meta_kubernetes_ingress_scheme, __address__, __meta_kubernetes_ingress_path]
regex: (.+);(.+);(.+)
replacement: ${1}://${2}${3}
target_label: __param_target
- target_label: __address__
replacement: blackbox-exporter:8080
- source_labels: [__param_target]
target_label: instance
- action: labelmap
regex: __meta_kubernetes_ingress_label_(.+)
- source_labels: [__meta_kubernetes_namespace]
target_label: namespace
- source_labels: [__meta_kubernetes_service_name]
target_label: job
# Rule files
rule_files:
- "/etc/prometheus/rules/*.rules"

View File

@ -14,13 +14,14 @@ spec:
labels:
name: prometheus
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
serviceAccountName: prometheus
containers:
- name: prometheus
image: quay.io/prometheus/prometheus:v2.19.2
image: quay.io/prometheus/prometheus:v2.40.5
args:
- --web.listen-address=0.0.0.0:9090
- --config.file=/etc/prometheus/prometheus.yaml

View File

@ -1,11 +1,9 @@
# Allow Prometheus to scrape service endpoints
# Allow Prometheus to discover service endpoints
apiVersion: v1
kind: Service
metadata:
name: kube-controller-manager
namespace: kube-system
annotations:
prometheus.io/scrape: 'true'
spec:
type: ClusterIP
clusterIP: None
@ -14,5 +12,5 @@ spec:
ports:
- name: metrics
protocol: TCP
port: 10252
targetPort: 10252
port: 10257
targetPort: 10257

View File

@ -1,11 +1,9 @@
# Allow Prometheus to scrape service endpoints
# Allow Prometheus to discover service endpoints
apiVersion: v1
kind: Service
metadata:
name: kube-scheduler
namespace: kube-system
annotations:
prometheus.io/scrape: 'true'
spec:
type: ClusterIP
clusterIP: None
@ -14,5 +12,5 @@ spec:
ports:
- name: metrics
protocol: TCP
port: 10251
targetPort: 10251
port: 10259
targetPort: 10259

View File

@ -78,13 +78,6 @@ rules:
verbs:
- list
- watch
- apiGroups:
- autoscaling.k8s.io
resources:
- verticalpodautoscalers
verbs:
- list
- watch
- apiGroups:
- admissionregistration.k8s.io
resources:
@ -97,6 +90,14 @@ rules:
- networking.k8s.io
resources:
- networkpolicies
- ingresses
verbs:
- list
- watch
- apiGroups:
- coordination.k8s.io
resources:
- leases
verbs:
- list
- watch

View File

@ -18,16 +18,19 @@ spec:
labels:
name: kube-state-metrics
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
securityContext:
seccompProfile:
type: RuntimeDefault
serviceAccountName: kube-state-metrics
containers:
- name: kube-state-metrics
image: quay.io/coreos/kube-state-metrics:v1.9.7
image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.7.0
ports:
- name: metrics
containerPort: 8080
- name: telemetry
containerPort: 8081
livenessProbe:
httpGet:
path: /healthz
@ -40,3 +43,5 @@ spec:
port: 8081
initialDelaySeconds: 5
timeoutSeconds: 5
securityContext:
runAsUser: 65534

View File

@ -17,24 +17,24 @@ spec:
labels:
name: node-exporter
phase: prod
annotations:
seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
spec:
serviceAccountName: node-exporter
securityContext:
runAsNonRoot: true
runAsUser: 65534
runAsGroup: 65534
fsGroup: 65534
seccompProfile:
type: RuntimeDefault
hostNetwork: true
hostPID: true
containers:
- name: node-exporter
image: quay.io/prometheus/node-exporter:v1.0.1
image: quay.io/prometheus/node-exporter:v1.5.0
args:
- --path.procfs=/host/proc
- --path.sysfs=/host/sys
- --path.rootfs=/host/root
- --collector.filesystem.ignored-mount-points=^/(dev|proc|sys|var/lib/docker/.+)($|/)
- --collector.filesystem.ignored-fs-types=^(autofs|binfmt_misc|cgroup|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|mqueue|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|sysfs|tracefs)$
ports:
- name: metrics
containerPort: 9100
@ -46,6 +46,9 @@ spec:
limits:
cpu: 200m
memory: 100Mi
securityContext:
seLinuxOptions:
type: spc_t
volumeMounts:
- name: proc
mountPath: /host/proc
@ -55,9 +58,12 @@ spec:
readOnly: true
- name: root
mountPath: /host/root
mountPropagation: HostToContainer
readOnly: true
tolerations:
- key: node-role.kubernetes.io/master
- key: node-role.kubernetes.io/controller
operator: Exists
- key: node-role.kubernetes.io/control-plane
operator: Exists
- key: node.kubernetes.io/not-ready
operator: Exists

View File

@ -10,6 +10,17 @@ rules:
- services
- endpoints
- pods
verbs: ["get", "list", "watch"]
verbs:
- get
- list
- watch
- nonResourceURLs: ["/metrics"]
verbs: ["get"]
- apiGroups:
- networking.k8s.io
resources:
- ingresses
verbs:
- get
- list
- watch

View File

@ -9,10 +9,11 @@ data:
{
"alert": "etcdMembersDown",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": members are down ({{ $value }})."
"description": "etcd cluster \"{{ $labels.job }}\": members are down ({{ $value }}).",
"summary": "etcd cluster members are down."
},
"expr": "max by (job) (\n sum by (job) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count by (job,endpoint) (\n sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[3m])) > 0.01\n )\n)\n> 0\n",
"for": "3m",
"expr": "max without (endpoint) (\n sum without (instance) (up{job=~\".*etcd.*\"} == bool 0)\nor\n count without (To) (\n sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[120s])) > 0.01\n )\n)\n> 0\n",
"for": "10m",
"labels": {
"severity": "critical"
}
@ -20,9 +21,10 @@ data:
{
"alert": "etcdInsufficientMembers",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": insufficient members ({{ $value }})."
"description": "etcd cluster \"{{ $labels.job }}\": insufficient members ({{ $value }}).",
"summary": "etcd cluster has insufficient number of members."
},
"expr": "sum(up{job=~\".*etcd.*\"} == bool 1) by (job) < ((count(up{job=~\".*etcd.*\"}) by (job) + 1) / 2)\n",
"expr": "sum(up{job=~\".*etcd.*\"} == bool 1) without (instance) < ((count(up{job=~\".*etcd.*\"}) without (instance) + 1) / 2)\n",
"for": "3m",
"labels": {
"severity": "critical"
@ -31,7 +33,8 @@ data:
{
"alert": "etcdNoLeader",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": member {{ $labels.instance }} has no leader."
"description": "etcd cluster \"{{ $labels.job }}\": member {{ $labels.instance }} has no leader.",
"summary": "etcd cluster has no leader."
},
"expr": "etcd_server_has_leader{job=~\".*etcd.*\"} == 0\n",
"for": "1m",
@ -42,9 +45,10 @@ data:
{
"alert": "etcdHighNumberOfLeaderChanges",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated."
"description": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.",
"summary": "etcd cluster has high number of leader changes."
},
"expr": "increase((max by (job) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 3\n",
"expr": "increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 4\n",
"for": "5m",
"labels": {
"severity": "warning"
@ -53,9 +57,10 @@ data:
{
"alert": "etcdGRPCRequestsSlow",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}."
"description": "etcd cluster \"{{ $labels.job }}\": 99th percentile of gRPC requests is {{ $value }}s on etcd instance {{ $labels.instance }} for {{ $labels.grpc_method }} method.",
"summary": "etcd grpc requests are slow"
},
"expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_type=\"unary\"}[5m])) by (job, instance, grpc_service, grpc_method, le))\n> 0.15\n",
"expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_method!=\"Defragment\", grpc_type=\"unary\"}[5m])) without(grpc_type))\n> 0.15\n",
"for": "10m",
"labels": {
"severity": "critical"
@ -64,7 +69,8 @@ data:
{
"alert": "etcdMemberCommunicationSlow",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}."
"description": "etcd cluster \"{{ $labels.job }}\": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.",
"summary": "etcd cluster member communication is slow."
},
"expr": "histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.15\n",
"for": "10m",
@ -75,7 +81,8 @@ data:
{
"alert": "etcdHighNumberOfFailedProposals",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}."
"description": "etcd cluster \"{{ $labels.job }}\": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.",
"summary": "etcd cluster has high number of proposal failures."
},
"expr": "rate(etcd_server_proposals_failed_total{job=~\".*etcd.*\"}[15m]) > 5\n",
"for": "15m",
@ -86,7 +93,8 @@ data:
{
"alert": "etcdHighFsyncDurations",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": 99th percentile fync durations are {{ $value }}s on etcd instance {{ $labels.instance }}."
"description": "etcd cluster \"{{ $labels.job }}\": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.",
"summary": "etcd cluster 99th percentile fsync durations are too high."
},
"expr": "histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.5\n",
"for": "10m",
@ -94,10 +102,23 @@ data:
"severity": "warning"
}
},
{
"alert": "etcdHighFsyncDurations",
"annotations": {
"description": "etcd cluster \"{{ $labels.job }}\": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.",
"summary": "etcd cluster 99th percentile fsync durations are too high."
},
"expr": "histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 1\n",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdHighCommitDurations",
"annotations": {
"message": "etcd cluster \"{{ $labels.job }}\": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}."
"description": "etcd cluster \"{{ $labels.job }}\": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.",
"summary": "etcd cluster 99th percentile commit durations are too high."
},
"expr": "histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.25\n",
"for": "10m",
@ -106,33 +127,24 @@ data:
}
},
{
"alert": "etcdHighNumberOfFailedHTTPRequests",
"alert": "etcdBackendQuotaLowSpace",
"annotations": {
"message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}"
"description": "etcd cluster \"{{ $labels.job }}\": database size exceeds the defined quota on etcd instance {{ $labels.instance }}, please defrag or increase the quota as the writes to etcd will be disabled when it is full.",
"summary": "etcd cluster database is running full."
},
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.01\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "etcdHighNumberOfFailedHTTPRequests",
"annotations": {
"message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}."
},
"expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.05\n",
"expr": "(etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100 > 95\n",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "etcdHTTPRequestsSlow",
"alert": "etcdExcessiveDatabaseGrowth",
"annotations": {
"message": "etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow."
"description": "etcd cluster \"{{ $labels.job }}\": Observed surge in etcd writes leading to 50% increase in database size over the past four hours on etcd instance {{ $labels.instance }}, please check as it might be disruptive.",
"summary": "etcd cluster database growing very fast."
},
"expr": "histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))\n> 0.15\n",
"expr": "increase(((etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100)[240m:1m]) > 50\n",
"for": "10m",
"labels": {
"severity": "warning"
@ -146,135 +158,217 @@ data:
{
"groups": [
{
"name": "kube-apiserver-error",
"name": "kube-apiserver-burnrate.rules",
"rules": [
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[5m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1d]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate5m"
"record": "apiserver_request:burnrate1d"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[30m]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1h]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate30m"
"record": "apiserver_request:burnrate1h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[2h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[2h]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[2h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate1h"
"record": "apiserver_request:burnrate2h"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[2h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[30m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[30m]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[30m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate2h"
"record": "apiserver_request:burnrate30m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[6h]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[3d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[3d]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[3d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate6h"
"record": "apiserver_request:burnrate3d"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[1d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[5m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[5m]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[5m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate1d"
"record": "apiserver_request:burnrate5m"
},
{
"expr": "sum by (status_class) (\n label_replace(\n rate(apiserver_request_total{job=\"apiserver\"}[3d]\n ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[6h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[6h]))\n +\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[6h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
"labels": {
"job": "apiserver"
"verb": "read"
},
"record": "status_class:apiserver_request_total:rate3d"
"record": "apiserver_request:burnrate6h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate5m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate5m{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate5m"
"record": "apiserver_request:burnrate1d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate30m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate30m{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate30m"
"record": "apiserver_request:burnrate1h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1h{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[2h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1h"
"record": "apiserver_request:burnrate2h"
},
{
"expr": "sum(status_class:apiserver_request_total:rate2h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate2h{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[30m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate2h"
"record": "apiserver_request:burnrate30m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate6h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate6h{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[3d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate6h"
"record": "apiserver_request:burnrate3d"
},
{
"expr": "sum(status_class:apiserver_request_total:rate1d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1d{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[5m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate1d"
"record": "apiserver_request:burnrate5m"
},
{
"expr": "sum(status_class:apiserver_request_total:rate3d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate3d{job=\"apiserver\"})\n",
"expr": "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n sum by (cluster) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[6h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n",
"labels": {
"job": "apiserver"
"verb": "write"
},
"record": "status_class_5xx:apiserver_request_total:ratio_rate3d"
"record": "apiserver_request:burnrate6h"
}
]
},
{
"name": "kube-apiserver.rules",
"name": "kube-apiserver-histogram.rules",
"rules": [
{
"expr": "sum(rate(apiserver_request_duration_seconds_sum{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n/\nsum(rate(apiserver_request_duration_seconds_count{subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod)\n",
"record": "cluster:apiserver_request_duration_seconds:mean5m"
},
{
"expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"expr": "histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))) > 0\n",
"labels": {
"quantile": "0.99"
"quantile": "0.99",
"verb": "read"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"expr": "histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))) > 0\n",
"labels": {
"quantile": "0.9"
"quantile": "0.99",
"verb": "write"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
}
]
},
{
"interval": "3m",
"name": "kube-apiserver-availability.rules",
"rules": [
{
"expr": "avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30\n",
"record": "code_verb:apiserver_request_total:increase30d"
},
{
"expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT\"}[5m])) without(instance, pod))\n",
"expr": "sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~\"LIST|GET\"})\n",
"labels": {
"quantile": "0.5"
"verb": "read"
},
"record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
"record": "code:apiserver_request_total:increase30d"
},
{
"expr": "sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n",
"labels": {
"verb": "write"
},
"record": "code:apiserver_request_total:increase30d"
},
{
"expr": "sum by (cluster, verb, scope) (increase(apiserver_request_duration_seconds_count[1h]))\n",
"record": "cluster_verb_scope:apiserver_request_duration_seconds_count:increase1h"
},
{
"expr": "sum by (cluster, verb, scope) (avg_over_time(cluster_verb_scope:apiserver_request_duration_seconds_count:increase1h[30d]) * 24 * 30)\n",
"record": "cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d"
},
{
"expr": "sum by (cluster, verb, scope, le) (increase(apiserver_request_duration_seconds_bucket[1h]))\n",
"record": "cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase1h"
},
{
"expr": "sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase1h[30d]) * 24 * 30)\n",
"record": "cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d"
},
{
"expr": "1 - (\n (\n # write too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n ) +\n (\n # read too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n )\n ) +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n",
"labels": {
"verb": "all"
},
"record": "apiserver_request:availability30d"
},
{
"expr": "1 - (\n sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n # too slow\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n",
"labels": {
"verb": "read"
},
"record": "apiserver_request:availability30d"
},
{
"expr": "1 - (\n (\n # too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n",
"labels": {
"verb": "write"
},
"record": "apiserver_request:availability30d"
},
{
"expr": "sum by (cluster,code,resource) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
"labels": {
"verb": "read"
},
"record": "code_resource:apiserver_request_total:rate5m"
},
{
"expr": "sum by (cluster,code,resource) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
"labels": {
"verb": "write"
},
"record": "code_resource:apiserver_request_total:rate5m"
},
{
"expr": "sum by (cluster, code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET|POST|PUT|PATCH|DELETE\",code=~\"2..\"}[1h]))\n",
"record": "code_verb:apiserver_request_total:increase1h"
},
{
"expr": "sum by (cluster, code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET|POST|PUT|PATCH|DELETE\",code=~\"3..\"}[1h]))\n",
"record": "code_verb:apiserver_request_total:increase1h"
},
{
"expr": "sum by (cluster, code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET|POST|PUT|PATCH|DELETE\",code=~\"4..\"}[1h]))\n",
"record": "code_verb:apiserver_request_total:increase1h"
},
{
"expr": "sum by (cluster, code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET|POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n",
"record": "code_verb:apiserver_request_total:increase1h"
}
]
},
@ -282,61 +376,84 @@ data:
"name": "k8s.rules",
"rules": [
{
"expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])) by (namespace)\n",
"record": "namespace:container_cpu_usage_seconds_total:sum_rate"
"expr": "sum by (cluster, namespace, pod, container) (\n irate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate"
},
{
"expr": "sum by (cluster, namespace, pod, container) (\n rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info)\n)\n",
"record": "node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate"
},
{
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_working_set_bytes{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_working_set_bytes"
},
{
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_rss"
},
{
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_cache"
},
{
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info)\n)\n",
"expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) topk by(namespace, pod) (1,\n max by(namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n",
"record": "node_namespace_pod_container:container_memory_swap"
},
{
"expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}) by (namespace)\n",
"record": "namespace:container_memory_usage_bytes:sum"
"expr": "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
"record": "cluster:namespace:pod_memory:active:kube_pod_container_resource_requests"
},
{
"expr": "sum by (namespace) (\n sum by (namespace, pod) (\n max by (namespace, pod, container) (\n kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"}\n ) * on(namespace, pod) group_left() max by (namespace, pod) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace:kube_pod_container_resource_requests_memory_bytes:sum"
"expr": "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace_memory:kube_pod_container_resource_requests:sum"
},
{
"expr": "sum by (namespace) (\n sum by (namespace, pod) (\n max by (namespace, pod, container) (\n kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"}\n ) * on(namespace, pod) group_left() max by (namespace, pod) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace:kube_pod_container_resource_requests_cpu_cores:sum"
"expr": "kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
"record": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests"
},
{
"expr": "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace_cpu:kube_pod_container_resource_requests:sum"
},
{
"expr": "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n",
"record": "cluster:namespace:pod_memory:active:kube_pod_container_resource_limits"
},
{
"expr": "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace_memory:kube_pod_container_resource_limits:sum"
},
{
"expr": "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n )\n",
"record": "cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits"
},
{
"expr": "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n",
"record": "namespace_cpu:kube_pod_container_resource_limits:sum"
},
{
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"ReplicaSet\"},\n \"replicaset\", \"$1\", \"owner_name\", \"(.*)\"\n ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (\n 1, max by (replicaset, namespace, owner_name) (\n kube_replicaset_owner{job=\"kube-state-metrics\"}\n )\n ),\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "deployment"
},
"record": "mixin_pod_workload"
"record": "namespace_workload_pod:kube_pod_owner:relabel"
},
{
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "daemonset"
},
"record": "mixin_pod_workload"
"record": "namespace_workload_pod:kube_pod_owner:relabel"
},
{
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "statefulset"
},
"record": "mixin_pod_workload"
"record": "namespace_workload_pod:kube_pod_owner:relabel"
},
{
"expr": "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"Job\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n",
"labels": {
"workload_type": "job"
},
"record": "namespace_workload_pod:kube_pod_owner:relabel"
}
]
},
@ -412,20 +529,20 @@ data:
"name": "node.rules",
"rules": [
{
"expr": "sum(min(kube_pod_info) by (cluster, node))\n",
"record": ":kube_pod_info_node_count:"
},
{
"expr": "topk by(namespace, pod) (1,\n max by (node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n",
"expr": "topk by(namespace, pod) (1,\n max by (node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\",node!=\"\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n",
"record": "node_namespace_pod:kube_pod_info:"
},
{
"expr": "count by (cluster, node) (sum by (node, cpu) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n node_namespace_pod:kube_pod_info:\n))\n",
"expr": "count by (cluster, node) (sum by (node, cpu) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n* on (namespace, pod) group_left(node)\n topk by(namespace, pod) (1, node_namespace_pod:kube_pod_info:)\n))\n",
"record": "node:node_num_cpu:sum"
},
{
"expr": "sum(\n node_memory_MemAvailable_bytes{job=\"node-exporter\"} or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"} +\n node_memory_Cached_bytes{job=\"node-exporter\"} +\n node_memory_MemFree_bytes{job=\"node-exporter\"} +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n) by (cluster)\n",
"record": ":node_memory_MemAvailable_bytes:sum"
},
{
"expr": "sum(rate(node_cpu_seconds_total{job=\"node-exporter\",mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\"}[5m])) /\ncount(sum(node_cpu_seconds_total{job=\"node-exporter\"}) by (cluster, instance, cpu))\n",
"record": "cluster:node_cpu:ratio_rate5m"
}
]
},
@ -433,21 +550,21 @@ data:
"name": "kubelet.rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"labels": {
"quantile": "0.99"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"expr": "histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"labels": {
"quantile": "0.9"
},
"record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
},
{
"expr": "histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (instance, le) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"expr": "histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job=\"kubelet\"})\n",
"labels": {
"quantile": "0.5"
},
@ -461,104 +578,113 @@ data:
{
"alert": "KubePodCrashLooping",
"annotations": {
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf \"%.2f\" $value }} times / 5 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping"
"description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is in waiting state (reason: \"CrashLoopBackOff\").",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping",
"summary": "Pod is crash looping."
},
"expr": "rate(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\"}[15m]) * 60 * 5 > 0\n",
"expr": "max_over_time(kube_pod_container_status_waiting_reason{reason=\"CrashLoopBackOff\", job=\"kube-state-metrics\"}[5m]) >= 1\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubePodNotReady",
"annotations": {
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready"
"description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready",
"summary": "Pod has been in a non-ready state for more than 15 minutes."
},
"expr": "sum by (namespace, pod) (max by(namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}) * on(namespace, pod) group_left(owner_kind) max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})) > 0\n",
"expr": "sum by (namespace, pod) (\n max by(namespace, pod) (\n kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}\n ) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) (\n 1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})\n )\n) > 0\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeDeploymentGenerationMismatch",
"annotations": {
"message": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch"
"description": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch",
"summary": "Deployment generation mismatch due to possible roll-back"
},
"expr": "kube_deployment_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_deployment_metadata_generation{job=\"kube-state-metrics\"}\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeDeploymentReplicasMismatch",
"annotations": {
"message": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch"
"description": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch",
"summary": "Deployment has not matched the expected number of replicas."
},
"expr": "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n !=\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"expr": "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n >\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[10m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeStatefulSetReplicasMismatch",
"annotations": {
"message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch"
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch",
"summary": "Deployment has not matched the expected number of replicas."
},
"expr": "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"expr": "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[10m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeStatefulSetGenerationMismatch",
"annotations": {
"message": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch"
"description": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch",
"summary": "StatefulSet generation mismatch due to possible roll-back"
},
"expr": "kube_statefulset_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_statefulset_metadata_generation{job=\"kube-state-metrics\"}\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeStatefulSetUpdateNotRolledOut",
"annotations": {
"message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout"
"description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout",
"summary": "StatefulSet update has not been rolled out."
},
"expr": "max without (revision) (\n kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n unless\n kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n)\n *\n(\n kube_statefulset_replicas{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n)\n",
"expr": "(\n max without (revision) (\n kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n unless\n kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n )\n *\n (\n kube_statefulset_replicas{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeDaemonSetRolloutStuck",
"annotations": {
"message": "Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck"
"description": "DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck",
"summary": "DaemonSet rollout is stuck."
},
"expr": "kube_daemonset_status_number_ready{job=\"kube-state-metrics\"}\n /\nkube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"} < 1.00\n",
"expr": "(\n (\n kube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"}\n !=\n 0\n ) or (\n kube_daemonset_status_updated_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_available{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_daemonset_status_updated_number_scheduled{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubeContainerWaiting",
"annotations": {
"message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting"
"description": "pod/{{ $labels.pod }} in namespace {{ $labels.namespace }} on container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting",
"summary": "Pod container waiting longer than 1 hour"
},
"expr": "sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job=\"kube-state-metrics\"}) > 0\n",
"for": "1h",
@ -569,8 +695,9 @@ data:
{
"alert": "KubeDaemonSetNotScheduled",
"annotations": {
"message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled"
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled",
"summary": "DaemonSet pods are not scheduled."
},
"expr": "kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n -\nkube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"} > 0\n",
"for": "10m",
@ -581,23 +708,12 @@ data:
{
"alert": "KubeDaemonSetMisScheduled",
"annotations": {
"message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled"
"description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled",
"summary": "DaemonSet pods are misscheduled."
},
"expr": "kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"} > 0\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeCronJobRunning",
"annotations": {
"message": "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning"
},
"expr": "time() - kube_cronjob_next_schedule_time{job=\"kube-state-metrics\"} > 3600\n",
"for": "1h",
"for": "15m",
"labels": {
"severity": "warning"
}
@ -605,11 +721,12 @@ data:
{
"alert": "KubeJobCompletion",
"annotations": {
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than one hour to complete.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion"
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than 12 hours to complete.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion",
"summary": "Job did not complete in time"
},
"expr": "kube_job_spec_completions{job=\"kube-state-metrics\"} - kube_job_status_succeeded{job=\"kube-state-metrics\"} > 0\n",
"for": "1h",
"for": "12h",
"labels": {
"severity": "warning"
}
@ -617,8 +734,9 @@ data:
{
"alert": "KubeJobFailed",
"annotations": {
"message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed"
"description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed",
"summary": "Job failed to complete."
},
"expr": "kube_job_failed{job=\"kube-state-metrics\"} > 0\n",
"for": "15m",
@ -629,10 +747,11 @@ data:
{
"alert": "KubeHpaReplicasMismatch",
"annotations": {
"message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch"
"description": "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has not matched the desired number of replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch",
"summary": "HPA has not matched descired number of replicas."
},
"expr": "(kube_hpa_status_desired_replicas{job=\"kube-state-metrics\"}\n !=\nkube_hpa_status_current_replicas{job=\"kube-state-metrics\"})\n and\nchanges(kube_hpa_status_current_replicas[15m]) == 0\n",
"expr": "(kube_horizontalpodautoscaler_status_desired_replicas{job=\"kube-state-metrics\"}\n !=\nkube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"})\n and\n(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n >\nkube_horizontalpodautoscaler_spec_min_replicas{job=\"kube-state-metrics\"})\n and\n(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n <\nkube_horizontalpodautoscaler_spec_max_replicas{job=\"kube-state-metrics\"})\n and\nchanges(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}[15m]) == 0\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -641,10 +760,11 @@ data:
{
"alert": "KubeHpaMaxedOut",
"annotations": {
"message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout"
"description": "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has been running at max replicas for longer than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout",
"summary": "HPA is running at max replicas"
},
"expr": "kube_hpa_status_current_replicas{job=\"kube-state-metrics\"}\n ==\nkube_hpa_spec_max_replicas{job=\"kube-state-metrics\"}\n",
"expr": "kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n ==\nkube_horizontalpodautoscaler_spec_max_replicas{job=\"kube-state-metrics\"}\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -658,58 +778,89 @@ data:
{
"alert": "KubeCPUOvercommit",
"annotations": {
"message": "Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
"description": "Cluster has overcommitted CPU resource requests for Pods by {{ $value }} CPU shares and cannot tolerate node failure.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit",
"summary": "Cluster has overcommitted CPU resource requests."
},
"expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n >\n(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)\n",
"expr": "sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource=\"cpu\"}) - max(kube_node_status_allocatable{resource=\"cpu\"})) > 0\nand\n(sum(kube_node_status_allocatable{resource=\"cpu\"}) - max(kube_node_status_allocatable{resource=\"cpu\"})) > 0\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeMemoryOvercommit",
"annotations": {
"description": "Cluster has overcommitted memory resource requests for Pods by {{ $value | humanize }} bytes and cannot tolerate node failure.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit",
"summary": "Cluster has overcommitted memory resource requests."
},
"expr": "sum(namespace_memory:kube_pod_container_resource_requests:sum{}) - (sum(kube_node_status_allocatable{resource=\"memory\"}) - max(kube_node_status_allocatable{resource=\"memory\"})) > 0\nand\n(sum(kube_node_status_allocatable{resource=\"memory\"}) - max(kube_node_status_allocatable{resource=\"memory\"})) > 0\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeCPUQuotaOvercommit",
"annotations": {
"description": "Cluster has overcommitted CPU resource requests for Namespaces.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit",
"summary": "Cluster has overcommitted CPU resource requests."
},
"expr": "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(cpu|requests.cpu)\"}))\n /\nsum(kube_node_status_allocatable{resource=\"cpu\", job=\"kube-state-metrics\"})\n > 1.5\n",
"for": "5m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeMemOvercommit",
"alert": "KubeMemoryQuotaOvercommit",
"annotations": {
"message": "Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit"
"description": "Cluster has overcommitted memory resource requests for Namespaces.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit",
"summary": "Cluster has overcommitted memory resource requests."
},
"expr": "sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})\n /\nsum(kube_node_status_allocatable_memory_bytes)\n >\n(count(kube_node_status_allocatable_memory_bytes)-1)\n /\ncount(kube_node_status_allocatable_memory_bytes)\n",
"expr": "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(memory|requests.memory)\"}))\n /\nsum(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"})\n > 1.5\n",
"for": "5m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeCPUOvercommit",
"alert": "KubeQuotaAlmostFull",
"annotations": {
"message": "Cluster has overcommitted CPU resource requests for Namespaces.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaalmostfull",
"summary": "Namespace quota is going to be full."
},
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n /\nsum(kube_node_status_allocatable_cpu_cores)\n > 1.5\n",
"for": "5m",
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.9 < 1\n",
"for": "15m",
"labels": {
"severity": "warning"
"severity": "info"
}
},
{
"alert": "KubeMemOvercommit",
"alert": "KubeQuotaFullyUsed",
"annotations": {
"message": "Cluster has overcommitted memory resource requests for Namespaces.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit"
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotafullyused",
"summary": "Namespace quota is fully used."
},
"expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n /\nsum(kube_node_status_allocatable_memory_bytes{job=\"node-exporter\"})\n > 1.5\n",
"for": "5m",
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n == 1\n",
"for": "15m",
"labels": {
"severity": "warning"
"severity": "info"
}
},
{
"alert": "KubeQuotaExceeded",
"annotations": {
"message": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded"
"description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded",
"summary": "Namespace quota has exceeded the limits."
},
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.90\n",
"expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 1\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -718,13 +869,14 @@ data:
{
"alert": "CPUThrottlingHigh",
"annotations": {
"message": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh"
"description": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh",
"summary": "Processes experience elevated CPU throttling."
},
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n > ( 100 / 100 )\n",
"expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n > ( 80 / 100 )\n",
"for": "15m",
"labels": {
"severity": "warning"
"severity": "info"
}
}
]
@ -733,34 +885,37 @@ data:
"name": "kubernetes-storage",
"rules": [
{
"alert": "KubePersistentVolumeUsageCritical",
"alert": "KubePersistentVolumeFillingUp",
"annotations": {
"message": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeusagecritical"
"description": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup",
"summary": "PersistentVolume is filling up."
},
"expr": "kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\nkubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n < 0.03\n",
"expr": "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.03\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\"} > 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n",
"for": "1m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubePersistentVolumeFullInFourDays",
"alert": "KubePersistentVolumeFillingUp",
"annotations": {
"message": "Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
"description": "Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup",
"summary": "PersistentVolume is filling up."
},
"expr": "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.15\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\n",
"expr": "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.15\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\"} > 0\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n",
"for": "1h",
"labels": {
"severity": "critical"
"severity": "warning"
}
},
{
"alert": "KubePersistentVolumeErrors",
"annotations": {
"message": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors"
"description": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors",
"summary": "PersistentVolume is having issues with provisioning."
},
"expr": "kube_persistentvolume_status_phase{phase=~\"Failed|Pending\",job=\"kube-state-metrics\"} > 0\n",
"for": "5m",
@ -776,10 +931,11 @@ data:
{
"alert": "KubeVersionMismatch",
"annotations": {
"message": "There are {{ $value }} different semantic versions of Kubernetes components running.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch"
"description": "There are {{ $value }} different semantic versions of Kubernetes components running.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch",
"summary": "Different semantic versions of Kubernetes components running."
},
"expr": "count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~\"kube-dns|coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*.[0-9]*).*\"))) > 1\n",
"expr": "count(count by (git_version) (label_replace(kubernetes_build_info{job!~\"kube-dns|coredns\"},\"git_version\",\"$1\",\"git_version\",\"(v[0-9]*.[0-9]*).*\"))) > 1\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -788,10 +944,11 @@ data:
{
"alert": "KubeClientErrors",
"annotations": {
"message": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors"
"description": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors",
"summary": "Kubernetes API server client is experiencing errors."
},
"expr": "(sum(rate(rest_client_requests_total{code=~\"5..\"}[5m])) by (instance, job)\n /\nsum(rate(rest_client_requests_total[5m])) by (instance, job))\n> 0.01\n",
"expr": "(sum(rate(rest_client_requests_total{code=~\"5..\"}[5m])) by (instance, job, namespace)\n /\nsum(rate(rest_client_requests_total[5m])) by (instance, job, namespace))\n> 0.01\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -800,30 +957,66 @@ data:
]
},
{
"name": "kube-apiserver-error-alerts",
"name": "kube-apiserver-slos",
"rules": [
{
"alert": "ErrorBudgetBurn",
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
"description": "The API server is burning too much error budget.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
"summary": "The API server is burning too much error budget."
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1h{job=\"apiserver\"} > (14.4*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate5m{job=\"apiserver\"} > (14.4*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (6*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate30m{job=\"apiserver\"} > (6*0.010000)\n)\n",
"expr": "sum(apiserver_request:burnrate1h) > (14.40 * 0.01000)\nand\nsum(apiserver_request:burnrate5m) > (14.40 * 0.01000)\n",
"for": "2m",
"labels": {
"job": "apiserver",
"severity": "critical"
"long": "1h",
"severity": "critical",
"short": "5m"
}
},
{
"alert": "ErrorBudgetBurn",
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"message": "High requests error budget burn for job=apiserver (current value: {{ $value }})",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-errorbudgetburn"
"description": "The API server is burning too much error budget.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
"summary": "The API server is burning too much error budget."
},
"expr": "(\n status_class_5xx:apiserver_request_total:ratio_rate1d{job=\"apiserver\"} > (3*0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate2h{job=\"apiserver\"} > (3*0.010000)\n)\nor\n(\n status_class_5xx:apiserver_request_total:ratio_rate3d{job=\"apiserver\"} > (0.010000)\n and\n status_class_5xx:apiserver_request_total:ratio_rate6h{job=\"apiserver\"} > (0.010000)\n)\n",
"expr": "sum(apiserver_request:burnrate6h) > (6.00 * 0.01000)\nand\nsum(apiserver_request:burnrate30m) > (6.00 * 0.01000)\n",
"for": "15m",
"labels": {
"job": "apiserver",
"severity": "warning"
"long": "6h",
"severity": "critical",
"short": "30m"
}
},
{
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"description": "The API server is burning too much error budget.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
"summary": "The API server is burning too much error budget."
},
"expr": "sum(apiserver_request:burnrate1d) > (3.00 * 0.01000)\nand\nsum(apiserver_request:burnrate2h) > (3.00 * 0.01000)\n",
"for": "1h",
"labels": {
"long": "1d",
"severity": "warning",
"short": "2h"
}
},
{
"alert": "KubeAPIErrorBudgetBurn",
"annotations": {
"description": "The API server is burning too much error budget.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
"summary": "The API server is burning too much error budget."
},
"expr": "sum(apiserver_request:burnrate3d) > (1.00 * 0.01000)\nand\nsum(apiserver_request:burnrate6h) > (1.00 * 0.01000)\n",
"for": "3h",
"labels": {
"long": "3d",
"severity": "warning",
"short": "6h"
}
}
]
@ -831,59 +1024,12 @@ data:
{
"name": "kubernetes-system-apiserver",
"rules": [
{
"alert": "KubeAPILatencyHigh",
"annotations": {
"message": "The API server has an abnormal latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
"expr": "(\n cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"}\n >\n on (verb) group_left()\n (\n avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n +\n 2*stddev by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\n )\n) > on (verb) group_left()\n1.2 * avg by (verb) (cluster:apiserver_request_duration_seconds:mean5m{job=\"apiserver\"} >= 0)\nand on (verb,resource)\ncluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"}\n>\n1\n",
"for": "5m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeAPILatencyHigh",
"annotations": {
"message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
},
"expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\"} > 4\n",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.10\n",
"for": "10m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPIErrorsHigh",
"annotations": {
"message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
},
"expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (resource,subresource,verb)\n /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.05\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeClientCertificateExpiration",
"annotations": {
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 1.0 hours.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
"description": "A client certificate used to authenticate to kubernetes apiserver is expiring in less than 1.0 hours.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration",
"summary": "Client certificate is about to expire."
},
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 3600\n",
"labels": {
@ -893,8 +1039,9 @@ data:
{
"alert": "KubeClientCertificateExpiration",
"annotations": {
"message": "A client certificate used to authenticate to the apiserver is expiring in less than 0.1 hours.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
"description": "A client certificate used to authenticate to kubernetes apiserver is expiring in less than 0.1 hours.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration",
"summary": "Client certificate is about to expire."
},
"expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 300\n",
"labels": {
@ -902,23 +1049,25 @@ data:
}
},
{
"alert": "AggregatedAPIErrors",
"alert": "KubeAggregatedAPIErrors",
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. The number of errors have increased for it in the past five minutes. High values indicate that the availability of the service changes too often.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors"
"description": "Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeaggregatedapierrors",
"summary": "Kubernetes aggregated API has reported errors."
},
"expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2\n",
"expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_total[10m])) > 4\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "AggregatedAPIDown",
"alert": "KubeAggregatedAPIDown",
"annotations": {
"message": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} is down. It has not been available at least for the past five minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown"
"description": "Kubernetes aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeaggregatedapidown",
"summary": "Kubernetes aggregated API is down."
},
"expr": "sum by(name, namespace)(sum_over_time(aggregator_unavailable_apiservice[5m])) > 0\n",
"expr": "(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85\n",
"for": "5m",
"labels": {
"severity": "warning"
@ -927,14 +1076,28 @@ data:
{
"alert": "KubeAPIDown",
"annotations": {
"message": "KubeAPI has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown"
"description": "KubeAPI has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown",
"summary": "Target disappeared from Prometheus target discovery."
},
"expr": "absent(up{job=\"apiserver\"} == 1)\n",
"for": "15m",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeAPITerminatedRequests",
"annotations": {
"description": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapiterminatedrequests",
"summary": "The kubernetes apiserver has terminated {{ $value | humanizePercentage }} of its incoming requests."
},
"expr": "sum(rate(apiserver_request_terminations_total{job=\"apiserver\"}[10m])) / ( sum(rate(apiserver_request_total{job=\"apiserver\"}[10m])) + sum(rate(apiserver_request_terminations_total{job=\"apiserver\"}[10m])) ) > 0.20\n",
"for": "5m",
"labels": {
"severity": "warning"
}
}
]
},
@ -944,8 +1107,9 @@ data:
{
"alert": "KubeNodeNotReady",
"annotations": {
"message": "{{ $labels.node }} has been unready for more than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready"
"description": "{{ $labels.node }} has been unready for more than 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready",
"summary": "Node is not ready."
},
"expr": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\n",
"for": "15m",
@ -956,11 +1120,12 @@ data:
{
"alert": "KubeNodeUnreachable",
"annotations": {
"message": "{{ $labels.node }} is unreachable and some workloads may be rescheduled.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable"
"description": "{{ $labels.node }} is unreachable and some workloads may be rescheduled.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable",
"summary": "Node is unreachable."
},
"expr": "kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} == 1\n",
"for": "2m",
"expr": "(kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} unless ignoring(key,value) kube_node_spec_taint{job=\"kube-state-metrics\",key=~\"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn\"}) == 1\n",
"for": "15m",
"labels": {
"severity": "warning"
}
@ -968,20 +1133,22 @@ data:
{
"alert": "KubeletTooManyPods",
"annotations": {
"message": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods"
"description": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods",
"summary": "Kubelet is running at capacity."
},
"expr": "max(max(kubelet_running_pod_count{job=\"kubelet\"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"}) by(node) / max(kube_node_status_capacity_pods{job=\"kube-state-metrics\"} != 1) by(node) > 0.95\n",
"expr": "count by(node) (\n (kube_pod_status_phase{job=\"kube-state-metrics\",phase=\"Running\"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job=\"kube-state-metrics\"})\n)\n/\nmax by(node) (\n kube_node_status_capacity{job=\"kube-state-metrics\",resource=\"pods\"} != 1\n) > 0.95\n",
"for": "15m",
"labels": {
"severity": "warning"
"severity": "info"
}
},
{
"alert": "KubeNodeReadinessFlapping",
"annotations": {
"message": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping"
"description": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping",
"summary": "Node readiness status is flapping."
},
"expr": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 2\n",
"for": "15m",
@ -992,8 +1159,9 @@ data:
{
"alert": "KubeletPlegDurationHigh",
"annotations": {
"message": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh"
"description": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh",
"summary": "Kubelet Pod Lifecycle Event Generator is taking too long to relist."
},
"expr": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\n",
"for": "5m",
@ -1004,10 +1172,85 @@ data:
{
"alert": "KubeletPodStartUpLatencyHigh",
"annotations": {
"message": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh"
"description": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh",
"summary": "Kubelet Pod startup latency is too high."
},
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name > 60\n",
"expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"} > 60\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletClientCertificateExpiration",
"annotations": {
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration",
"summary": "Kubelet client certificate is about to expire."
},
"expr": "kubelet_certificate_manager_client_ttl_seconds < 3600\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletClientCertificateExpiration",
"annotations": {
"description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration",
"summary": "Kubelet client certificate is about to expire."
},
"expr": "kubelet_certificate_manager_client_ttl_seconds < 300\n",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeletServerCertificateExpiration",
"annotations": {
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration",
"summary": "Kubelet server certificate is about to expire."
},
"expr": "kubelet_certificate_manager_server_ttl_seconds < 3600\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletServerCertificateExpiration",
"annotations": {
"description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration",
"summary": "Kubelet server certificate is about to expire."
},
"expr": "kubelet_certificate_manager_server_ttl_seconds < 300\n",
"labels": {
"severity": "critical"
}
},
{
"alert": "KubeletClientCertificateRenewalErrors",
"annotations": {
"description": "Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificaterenewalerrors",
"summary": "Kubelet has failed to renew its client certificate."
},
"expr": "increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "KubeletServerCertificateRenewalErrors",
"annotations": {
"description": "Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificaterenewalerrors",
"summary": "Kubelet has failed to renew its server certificate."
},
"expr": "increase(kubelet_server_expiration_renew_errors[5m]) > 0\n",
"for": "15m",
"labels": {
"severity": "warning"
@ -1016,8 +1259,9 @@ data:
{
"alert": "KubeletDown",
"annotations": {
"message": "Kubelet has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown"
"description": "Kubelet has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown",
"summary": "Target disappeared from Prometheus target discovery."
},
"expr": "absent(up{job=\"kubelet\"} == 1)\n",
"for": "15m",
@ -1033,8 +1277,9 @@ data:
{
"alert": "KubeSchedulerDown",
"annotations": {
"message": "KubeScheduler has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown"
"description": "KubeScheduler has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown",
"summary": "Target disappeared from Prometheus target discovery."
},
"expr": "absent(up{job=\"kube-scheduler\"} == 1)\n",
"for": "15m",
@ -1050,8 +1295,9 @@ data:
{
"alert": "KubeControllerManagerDown",
"annotations": {
"message": "KubeControllerManager has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown"
"description": "KubeControllerManager has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown",
"summary": "Target disappeared from Prometheus target discovery."
},
"expr": "absent(up{job=\"kube-controller-manager\"} == 1)\n",
"for": "15m",
@ -1060,109 +1306,18 @@ data:
}
}
]
}
]
}
loki.yaml: |-
{
"groups": [
{
"name": "loki_rules",
"rules": [
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job))",
"record": "job:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job))",
"record": "job:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job) / sum(rate(loki_request_duration_seconds_count[1m])) by (job)",
"record": "job:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job)",
"record": "job:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job)",
"record": "job:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (job)",
"record": "job:loki_request_duration_seconds_count:sum_rate"
},
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route))",
"record": "job_route:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route))",
"record": "job_route:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (job, route)",
"record": "job_route:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, job, route)",
"record": "job_route:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (job, route)",
"record": "job_route:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (job, route)",
"record": "job_route:loki_request_duration_seconds_count:sum_rate"
},
{
"expr": "histogram_quantile(0.99, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route))",
"record": "namespace_job_route:loki_request_duration_seconds:99quantile"
},
{
"expr": "histogram_quantile(0.50, sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route))",
"record": "namespace_job_route:loki_request_duration_seconds:50quantile"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route) / sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds:avg"
},
{
"expr": "sum(rate(loki_request_duration_seconds_bucket[1m])) by (le, namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds_bucket:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_sum[1m])) by (namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds_sum:sum_rate"
},
{
"expr": "sum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)",
"record": "namespace_job_route:loki_request_duration_seconds_count:sum_rate"
}
]
},
{
"name": "loki_alerts",
"name": "kubernetes-system-kube-proxy",
"rules": [
{
"alert": "LokiRequestErrors",
"alert": "KubeProxyDown",
"annotations": {
"message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n"
"description": "KubeProxy has disappeared from Prometheus target discovery.",
"runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeproxydown",
"summary": "Target disappeared from Prometheus target discovery."
},
"expr": "100 * sum(rate(loki_request_duration_seconds_count{status_code=~\"5..\"}[1m])) by (namespace, job, route)\n /\nsum(rate(loki_request_duration_seconds_count[1m])) by (namespace, job, route)\n > 10\n",
"for": "15m",
"labels": {
"severity": "critical"
}
},
{
"alert": "LokiRequestLatency",
"annotations": {
"message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}s 99th percentile latency.\n"
},
"expr": "namespace_job_route:loki_request_duration_seconds:99quantile{route!~\"(?i).*tail.*\"} > 1\n",
"expr": "absent(up{job=\"kube-proxy\"} == 1)\n",
"for": "15m",
"labels": {
"severity": "critical"
@ -1179,48 +1334,48 @@ data:
"name": "node-exporter.rules",
"rules": [
{
"expr": "count without (cpu) (\n count without (mode) (\n node_cpu_seconds_total{job=\"node-exporter\"}\n )\n)\n",
"expr": "count without (cpu, mode) (\n node_cpu_seconds_total{job=\"node-exporter\",mode=\"idle\"}\n)\n",
"record": "instance:node_num_cpu:sum"
},
{
"expr": "1 - avg without (cpu, mode) (\n rate(node_cpu_seconds_total{job=\"node-exporter\", mode=\"idle\"}[1m])\n)\n",
"record": "instance:node_cpu_utilisation:rate1m"
"expr": "1 - avg without (cpu) (\n sum without (mode) (rate(node_cpu_seconds_total{job=\"node-exporter\", mode=~\"idle|iowait|steal\"}[5m]))\n)\n",
"record": "instance:node_cpu_utilisation:rate5m"
},
{
"expr": "(\n node_load1{job=\"node-exporter\"}\n/\n instance:node_num_cpu:sum{job=\"node-exporter\"}\n)\n",
"record": "instance:node_load1_per_cpu:ratio"
},
{
"expr": "1 - (\n node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n",
"expr": "1 - (\n (\n node_memory_MemAvailable_bytes{job=\"node-exporter\"}\n or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"}\n +\n node_memory_Cached_bytes{job=\"node-exporter\"}\n +\n node_memory_MemFree_bytes{job=\"node-exporter\"}\n +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n )\n/\n node_memory_MemTotal_bytes{job=\"node-exporter\"}\n)\n",
"record": "instance:node_memory_utilisation:ratio"
},
{
"expr": "rate(node_vmstat_pgmajfault{job=\"node-exporter\"}[1m])\n",
"record": "instance:node_vmstat_pgmajfault:rate1m"
"expr": "rate(node_vmstat_pgmajfault{job=\"node-exporter\"}[5m])\n",
"record": "instance:node_vmstat_pgmajfault:rate5m"
},
{
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n",
"record": "instance_device:node_disk_io_time_seconds:rate1m"
"expr": "rate(node_disk_io_time_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[5m])\n",
"record": "instance_device:node_disk_io_time_seconds:rate5m"
},
{
"expr": "rate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n",
"record": "instance_device:node_disk_io_time_weighted_seconds:rate1m"
"expr": "rate(node_disk_io_time_weighted_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[5m])\n",
"record": "instance_device:node_disk_io_time_weighted_seconds:rate5m"
},
{
"expr": "sum without (device) (\n rate(node_network_receive_bytes_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_receive_bytes_excluding_lo:rate1m"
"expr": "sum without (device) (\n rate(node_network_receive_bytes_total{job=\"node-exporter\", device!=\"lo\"}[5m])\n)\n",
"record": "instance:node_network_receive_bytes_excluding_lo:rate5m"
},
{
"expr": "sum without (device) (\n rate(node_network_transmit_bytes_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_transmit_bytes_excluding_lo:rate1m"
"expr": "sum without (device) (\n rate(node_network_transmit_bytes_total{job=\"node-exporter\", device!=\"lo\"}[5m])\n)\n",
"record": "instance:node_network_transmit_bytes_excluding_lo:rate5m"
},
{
"expr": "sum without (device) (\n rate(node_network_receive_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_receive_drop_excluding_lo:rate1m"
"expr": "sum without (device) (\n rate(node_network_receive_drop_total{job=\"node-exporter\", device!=\"lo\"}[5m])\n)\n",
"record": "instance:node_network_receive_drop_excluding_lo:rate5m"
},
{
"expr": "sum without (device) (\n rate(node_network_transmit_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
"record": "instance:node_network_transmit_drop_excluding_lo:rate1m"
"expr": "sum without (device) (\n rate(node_network_transmit_drop_total{job=\"node-exporter\", device!=\"lo\"}[5m])\n)\n",
"record": "instance:node_network_transmit_drop_excluding_lo:rate5m"
}
]
},
@ -1258,7 +1413,7 @@ data:
"summary": "Filesystem has less than 5% space left."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 5\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"for": "30m",
"labels": {
"severity": "warning"
}
@ -1270,7 +1425,7 @@ data:
"summary": "Filesystem has less than 3% space left."
},
"expr": "(\n node_filesystem_avail_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} / node_filesystem_size_bytes{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} * 100 < 3\nand\n node_filesystem_readonly{job=\"node-exporter\",fstype!~\"tmpfs|nsfs|vfat\"} == 0\n)\n",
"for": "1h",
"for": "30m",
"labels": {
"severity": "critical"
}
@ -1329,7 +1484,7 @@ data:
"description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.",
"summary": "Network interface is reporting many receive errors."
},
"expr": "increase(node_network_receive_errs_total[2m]) > 10\n",
"expr": "rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01\n",
"for": "1h",
"labels": {
"severity": "warning"
@ -1341,7 +1496,7 @@ data:
"description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.",
"summary": "Network interface is reporting many transmit errors."
},
"expr": "increase(node_network_transmit_errs_total[2m]) > 10\n",
"expr": "rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01\n",
"for": "1h",
"labels": {
"severity": "warning"
@ -1350,18 +1505,29 @@ data:
{
"alert": "NodeHighNumberConntrackEntriesUsed",
"annotations": {
"description": "{{ $value | humanizePercentage }} of conntrack entries are used",
"summary": "Number of conntrack are getting close to the limit"
"description": "{{ $value | humanizePercentage }} of conntrack entries are used.",
"summary": "Number of conntrack are getting close to the limit."
},
"expr": "(node_nf_conntrack_entries / node_nf_conntrack_entries_limit) > 0.75\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeTextFileCollectorScrapeError",
"annotations": {
"description": "Node Exporter text file collector failed to scrape.",
"summary": "Node Exporter text file collector failed to scrape."
},
"expr": "node_textfile_scrape_error{job=\"node-exporter\"} == 1\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeClockSkewDetected",
"annotations": {
"message": "Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.",
"description": "Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.",
"summary": "Clock skew detected."
},
"expr": "(\n node_timex_offset_seconds > 0.05\nand\n deriv(node_timex_offset_seconds[5m]) >= 0\n)\nor\n(\n node_timex_offset_seconds < -0.05\nand\n deriv(node_timex_offset_seconds[5m]) <= 0\n)\n",
@ -1373,14 +1539,61 @@ data:
{
"alert": "NodeClockNotSynchronising",
"annotations": {
"message": "Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.",
"description": "Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.",
"summary": "Clock not synchronising."
},
"expr": "min_over_time(node_timex_sync_status[5m]) == 0\n",
"expr": "min_over_time(node_timex_sync_status[5m]) == 0\nand\nnode_timex_maxerror_seconds >= 16\n",
"for": "10m",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeRAIDDegraded",
"annotations": {
"description": "RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.",
"summary": "RAID Array is degraded"
},
"expr": "node_md_disks_required - ignoring (state) (node_md_disks{state=\"active\"}) > 0\n",
"for": "15m",
"labels": {
"severity": "critical"
}
},
{
"alert": "NodeRAIDDiskFailure",
"annotations": {
"description": "At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.",
"summary": "Failed device in RAID array"
},
"expr": "node_md_disks{state=\"failed\"} > 0\n",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFileDescriptorLimit",
"annotations": {
"description": "File descriptors limit at {{ $labels.instance }} is currently at {{ printf \"%.2f\" $value }}%.",
"summary": "Kernel is predicted to exhaust file descriptors limit soon."
},
"expr": "(\n node_filefd_allocated{job=\"node-exporter\"} * 100 / node_filefd_maximum{job=\"node-exporter\"} > 70\n)\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "NodeFileDescriptorLimit",
"annotations": {
"description": "File descriptors limit at {{ $labels.instance }} is currently at {{ printf \"%.2f\" $value }}%.",
"summary": "Kernel is predicted to exhaust file descriptors limit soon."
},
"expr": "(\n node_filefd_allocated{job=\"node-exporter\"} * 100 / node_filefd_maximum{job=\"node-exporter\"} > 90\n)\n",
"for": "15m",
"labels": {
"severity": "critical"
}
}
]
}
@ -1428,18 +1641,6 @@ data:
"severity": "warning"
}
},
{
"alert": "PrometheusErrorSendingAlertsToAnyAlertmanager",
"annotations": {
"description": "{{ printf \"%.1f\" $value }}% minimum errors while sending alerts from Prometheus {{$labels.instance}} to any Alertmanager.",
"summary": "Prometheus encounters more than 3% errors sending alerts to any Alertmanager."
},
"expr": "min without(alertmanager) (\n rate(prometheus_notifications_errors_total{job=\"prometheus\"}[5m])\n/\n rate(prometheus_notifications_sent_total{job=\"prometheus\"}[5m])\n)\n* 100\n> 3\n",
"for": "15m",
"labels": {
"severity": "critical"
}
},
{
"alert": "PrometheusNotConnectedToAlertmanagers",
"annotations": {
@ -1482,7 +1683,7 @@ data:
"description": "Prometheus {{$labels.instance}} is not ingesting samples.",
"summary": "Prometheus is not ingesting samples."
},
"expr": "rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus\"}[5m]) <= 0\n",
"expr": "(\n rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus\"}[5m]) <= 0\nand\n (\n sum without(scrape_job) (prometheus_target_metadata_cache_entries{job=\"prometheus\"}) > 0\n or\n sum without(rule_group) (prometheus_rule_group_rules{job=\"prometheus\"}) > 0\n )\n)\n",
"for": "10m",
"labels": {
"severity": "warning"
@ -1515,10 +1716,10 @@ data:
{
"alert": "PrometheusRemoteStorageFailures",
"annotations": {
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
"description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ $labels.remote_name}}:{{ $labels.url }}",
"summary": "Prometheus fails to send samples to remote storage."
},
"expr": "(\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n (\n rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n +\n rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n )\n)\n* 100\n> 1\n",
"expr": "(\n (rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job=\"prometheus\"}[5m]))\n/\n (\n (rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{job=\"prometheus\"}[5m]))\n +\n (rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m]) or rate(prometheus_remote_storage_samples_total{job=\"prometheus\"}[5m]))\n )\n)\n* 100\n> 1\n",
"for": "15m",
"labels": {
"severity": "critical"
@ -1527,10 +1728,10 @@ data:
{
"alert": "PrometheusRemoteWriteBehind",
"annotations": {
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
"description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ $labels.remote_name}}:{{ $labels.url }}.",
"summary": "Prometheus remote write is behind."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- ignoring(remote_name, url) group_right\n max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
"for": "15m",
"labels": {
"severity": "critical"
@ -1539,7 +1740,7 @@ data:
{
"alert": "PrometheusRemoteWriteDesiredShards",
"annotations": {
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ $value }} shards, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
"description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ $value }} shards for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
"summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
},
"expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
@ -1571,6 +1772,54 @@ data:
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusTargetLimitHit",
"annotations": {
"description": "Prometheus {{$labels.instance}} has dropped {{ printf \"%.0f\" $value }} targets because the number of targets exceeded the configured target_limit.",
"summary": "Prometheus has dropped targets because some scrape configs have exceeded the targets limit."
},
"expr": "increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job=\"prometheus\"}[5m]) > 0\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusLabelLimitHit",
"annotations": {
"description": "Prometheus {{$labels.instance}} has dropped {{ printf \"%.0f\" $value }} targets because some samples exceeded the configured label_limit, label_name_length_limit or label_value_length_limit.",
"summary": "Prometheus has dropped targets because some scrape configs have exceeded the labels limit."
},
"expr": "increase(prometheus_target_scrape_pool_exceeded_label_limits_total{job=\"prometheus\"}[5m]) > 0\n",
"for": "15m",
"labels": {
"severity": "warning"
}
},
{
"alert": "PrometheusTargetSyncFailure",
"annotations": {
"description": "{{ printf \"%.0f\" $value }} targets in Prometheus {{$labels.instance}} have failed to sync because invalid configuration was supplied.",
"summary": "Prometheus has failed to sync targets."
},
"expr": "increase(prometheus_target_sync_failed_total{job=\"prometheus\"}[30m]) > 0\n",
"for": "5m",
"labels": {
"severity": "critical"
}
},
{
"alert": "PrometheusErrorSendingAlertsToAnyAlertmanager",
"annotations": {
"description": "{{ printf \"%.1f\" $value }}% minimum errors while sending alerts from Prometheus {{$labels.instance}} to any Alertmanager.",
"summary": "Prometheus encounters more than 3% errors sending alerts to any Alertmanager."
},
"expr": "min without (alertmanager) (\n rate(prometheus_notifications_errors_total{job=\"prometheus\",alertmanager!~``}[5m])\n/\n rate(prometheus_notifications_sent_total{job=\"prometheus\",alertmanager!~``}[5m])\n)\n* 100\n> 3\n",
"for": "15m",
"labels": {
"severity": "critical"
}
}
]
}

View File

@ -1,199 +0,0 @@
---
systemd:
units:
- name: etcd-member.service
enabled: true
dropins:
- name: 40-etcd-cluster.conf
contents: |
[Service]
Environment="ETCD_IMAGE_TAG=v3.4.9"
Environment="ETCD_IMAGE_URL=docker://quay.io/coreos/etcd"
Environment="RKT_RUN_ARGS=--insecure-options=image"
Environment="ETCD_NAME=${etcd_name}"
Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379"
Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380"
Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
Environment="ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381"
Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
Environment="ETCD_STRICT_RECONFIG_CHECK=true"
Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
Environment="ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt"
Environment="ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key"
Environment="ETCD_CLIENT_CERT_AUTH=true"
Environment="ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt"
Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
RequiredBy=etcd-member.service
- name: kubelet.service
enabled: true
contents: |
[Unit]
Description=Kubelet
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.18.6
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
ExecStart=/usr/bin/rkt run \
--uuid-file-save=/var/cache/kubelet-pod.uuid \
--stage1-from-dir=stage1-fly.aci \
--hosts-entry host \
--insecure-options=image \
--volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
--mount volume=etc-kubernetes,target=/etc/kubernetes \
--volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
--mount volume=etc-machine-id,target=/etc/machine-id \
--volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
--mount volume=etc-os-release,target=/etc/os-release \
--volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
--mount volume=etc-resolv,target=/etc/resolv.conf \
--volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
--mount volume=etc-ssl-certs,target=/etc/ssl/certs \
--volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
--mount volume=lib-modules,target=/lib/modules \
--volume run,kind=host,source=/run \
--mount volume=run,target=/run \
--volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
--mount volume=usr-share-certs,target=/usr/share/ca-certificates \
--volume var-lib-calico,kind=host,source=/var/lib/calico,readOnly=true \
--mount volume=var-lib-calico,target=/var/lib/calico \
--volume var-lib-docker,kind=host,source=/var/lib/docker \
--mount volume=var-lib-docker,target=/var/lib/docker \
--volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
--mount volume=var-lib-kubelet,target=/var/lib/kubelet \
--volume var-log,kind=host,source=/var/log \
--mount volume=var-log,target=/var/log \
--volume opt-cni-bin,kind=host,source=/opt/cni/bin \
--mount volume=opt-cni-bin,target=/opt/cni/bin \
$${KUBELET_IMAGE} -- \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=$${KUBELET_CGROUP_DRIVER} \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/controller="true" \
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: bootstrap.service
contents: |
[Unit]
Description=Kubernetes control plane
ConditionPathExists=!/opt/bootstrap/bootstrap.done
[Service]
Type=oneshot
RemainAfterExit=true
WorkingDirectory=/opt/bootstrap
ExecStart=/usr/bin/rkt run \
--trust-keys-from-https \
--volume config,kind=host,source=/etc/kubernetes/bootstrap-secrets \
--mount volume=config,target=/etc/kubernetes/secrets \
--volume assets,kind=host,source=/opt/bootstrap/assets \
--mount volume=assets,target=/assets \
--volume script,kind=host,source=/opt/bootstrap/apply \
--mount volume=script,target=/apply \
--insecure-options=image \
docker://quay.io/poseidon/kubelet:v1.18.6 \
--net=host \
--dns=host \
--exec=/apply
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
[Install]
WantedBy=multi-user.target
storage:
files:
- path: /etc/kubernetes/kubeconfig
filesystem: root
mode: 0644
contents:
inline: |
${kubeconfig}
- path: /opt/bootstrap/layout
filesystem: root
mode: 0544
contents:
inline: |
#!/bin/bash -e
mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
awk '/#####/ {filename=$2; next} {print > filename}' assets
mkdir -p /etc/ssl/etcd/etcd
mkdir -p /etc/kubernetes/bootstrap-secrets
mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
chown -R etcd:etcd /etc/ssl/etcd
chmod -R 500 /etc/ssl/etcd
mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
mkdir -p /etc/kubernetes/manifests
mv static-manifests/* /etc/kubernetes/manifests/
mkdir -p /opt/bootstrap/assets
mv manifests /opt/bootstrap/assets/manifests
mv manifests-networking/* /opt/bootstrap/assets/manifests/
rm -rf assets auth static-manifests tls manifests-networking
- path: /opt/bootstrap/apply
filesystem: root
mode: 0544
contents:
inline: |
#!/bin/bash -e
export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
until kubectl version; do
echo "Waiting for static pod control plane"
sleep 5
done
until kubectl apply -f /assets/manifests -R; do
echo "Retry applying manifests"
sleep 5
done
- path: /etc/sysctl.d/max-user-watches.conf
filesystem: root
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184
passwd:
users:
- name: core
ssh_authorized_keys:
- "${ssh_authorized_key}"

View File

@ -1,11 +0,0 @@
# Terraform version and plugin versions
terraform {
required_version = "~> 0.12.6"
required_providers {
aws = "~> 2.23"
ct = "~> 0.4"
template = "~> 2.1"
null = "~> 2.1"
}
}

View File

@ -1,140 +0,0 @@
---
systemd:
units:
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
- name: kubelet.service
enabled: true
contents: |
[Unit]
Description=Kubelet
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.18.6
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
ExecStart=/usr/bin/rkt run \
--uuid-file-save=/var/cache/kubelet-pod.uuid \
--stage1-from-dir=stage1-fly.aci \
--hosts-entry host \
--insecure-options=image \
--volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
--mount volume=etc-kubernetes,target=/etc/kubernetes \
--volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
--mount volume=etc-machine-id,target=/etc/machine-id \
--volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
--mount volume=etc-os-release,target=/etc/os-release \
--volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
--mount volume=etc-resolv,target=/etc/resolv.conf \
--volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
--mount volume=etc-ssl-certs,target=/etc/ssl/certs \
--volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
--mount volume=lib-modules,target=/lib/modules \
--volume run,kind=host,source=/run \
--mount volume=run,target=/run \
--volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
--mount volume=usr-share-certs,target=/usr/share/ca-certificates \
--volume var-lib-calico,kind=host,source=/var/lib/calico,readOnly=true \
--mount volume=var-lib-calico,target=/var/lib/calico \
--volume var-lib-docker,kind=host,source=/var/lib/docker \
--mount volume=var-lib-docker,target=/var/lib/docker \
--volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
--mount volume=var-lib-kubelet,target=/var/lib/kubelet \
--volume var-log,kind=host,source=/var/log \
--mount volume=var-log,target=/var/log \
--volume opt-cni-bin,kind=host,source=/opt/cni/bin \
--mount volume=opt-cni-bin,target=/opt/cni/bin \
$${KUBELET_IMAGE} -- \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=$${KUBELET_CGROUP_DRIVER} \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/node \
%{~ for label in split(",", node_labels) ~}
--node-labels=${label} \
%{~ endfor ~}
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
- name: delete-node.service
enable: true
contents: |
[Unit]
Description=Waiting to delete Kubernetes node on shutdown
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/true
ExecStop=/etc/kubernetes/delete-node
[Install]
WantedBy=multi-user.target
storage:
files:
- path: /etc/kubernetes/kubeconfig
filesystem: root
mode: 0644
contents:
inline: |
${kubeconfig}
- path: /etc/sysctl.d/max-user-watches.conf
filesystem: root
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184
- path: /etc/kubernetes/delete-node
filesystem: root
mode: 0744
contents:
inline: |
#!/bin/bash
set -e
exec /usr/bin/rkt run \
--trust-keys-from-https \
--volume config,kind=host,source=/etc/kubernetes \
--mount volume=config,target=/etc/kubernetes \
--insecure-options=image \
docker://quay.io/poseidon/kubelet:v1.18.6 \
--net=host \
--dns=host \
--exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
passwd:
users:
- name: core
ssh_authorized_keys:
- "${ssh_authorized_key}"

View File

@ -1,4 +0,0 @@
terraform {
required_version = ">= 0.12"
}

View File

@ -11,10 +11,10 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
* Kubernetes v1.18.6 (upstream)
* Kubernetes v1.26.1 (upstream)
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/cl/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/fedora-coreos/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
* Ready for Ingress, Prometheus, Grafana, CSI, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
## Docs

View File

@ -1,4 +1,3 @@
data "aws_ami" "fedora-coreos" {
most_recent = true
owners = ["125523088429"]
@ -18,3 +17,25 @@ data "aws_ami" "fedora-coreos" {
values = ["Fedora CoreOS ${var.os_stream} *"]
}
}
data "aws_ami" "fedora-coreos-arm" {
count = var.arch == "arm64" ? 1 : 0
most_recent = true
owners = ["125523088429"]
filter {
name = "architecture"
values = ["arm64"]
}
filter {
name = "virtualization-type"
values = ["hvm"]
}
filter {
name = "description"
values = ["Fedora CoreOS ${var.os_stream} *"]
}
}

View File

@ -1,11 +1,10 @@
# Kubernetes assets (kubeconfig, manifests)
module "bootstrap" {
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=835890025bfb3499aa0cd5a9704e9e7d3e7e5fe5"
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=4621c6b256129d1ede32ae1f72bcc1473664cb33"
cluster_name = var.cluster_name
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
etcd_servers = aws_route53_record.etcds.*.fqdn
asset_dir = var.asset_dir
networking = var.networking
network_mtu = var.network_mtu
pod_cidr = var.pod_cidr
@ -13,7 +12,6 @@ module "bootstrap" {
cluster_domain_suffix = var.cluster_domain_suffix
enable_reporting = var.enable_reporting
enable_aggregation = var.enable_aggregation
trusted_certs_dir = "/etc/pki/tls/certs"
daemonset_tolerations = var.daemonset_tolerations
}

View File

@ -1,6 +1,6 @@
---
variant: fcos
version: 1.0.0
version: 1.4.0
systemd:
units:
- name: etcd-member.service
@ -8,32 +8,32 @@ systemd:
contents: |
[Unit]
Description=etcd (System Container)
Documentation=https://github.com/coreos/etcd
Wants=network-online.target network.target
Documentation=https://github.com/etcd-io/etcd
Wants=network-online.target
After=network-online.target
[Service]
# https://github.com/opencontainers/runc/pull/1807
# Type=notify
# NotifyAccess=exec
Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.7
Type=exec
ExecStartPre=/bin/mkdir -p /var/lib/etcd
ExecStartPre=-/usr/bin/podman rm etcd
ExecStart=/usr/bin/podman run --name etcd \
--env-file /etc/etcd/etcd.env \
--log-driver k8s-file \
--network host \
--volume /var/lib/etcd:/var/lib/etcd:rw,Z \
--volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
$${ETCD_IMAGE}
ExecStop=/usr/bin/podman stop etcd
Restart=on-failure
RestartSec=10s
TimeoutStartSec=0
LimitNOFILE=40000
ExecStartPre=/bin/mkdir -p /var/lib/etcd
ExecStartPre=-/usr/bin/podman rm etcd
#--volume $${NOTIFY_SOCKET}:/run/systemd/notify \
ExecStart=/usr/bin/podman run --name etcd \
--env-file /etc/etcd/etcd.env \
--network host \
--volume /var/lib/etcd:/var/lib/etcd:rw,Z \
--volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
quay.io/coreos/etcd:v3.4.9
ExecStop=/usr/bin/podman stop etcd
[Install]
WantedBy=multi-user.target
- name: docker.service
- name: containerd.service
enabled: true
- name: docker.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
@ -53,10 +53,13 @@ systemd:
contents: |
[Unit]
Description=Kubelet (System Container)
Requires=afterburn.service
After=afterburn.service
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.18.6
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
EnvironmentFile=/run/metadata/afterburn
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
@ -64,44 +67,33 @@ systemd:
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/podman rm kubelet
ExecStart=/usr/bin/podman run --name kubelet \
--log-driver k8s-file \
--privileged \
--pid host \
--network host \
--volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
--volume /etc/kubernetes:/etc/kubernetes:ro,z \
--volume /etc/machine-id:/etc/machine-id:ro \
--volume /usr/lib/os-release:/etc/os-release:ro \
--volume /etc/ssl/certs:/etc/ssl/certs:ro \
--volume /lib/modules:/lib/modules:ro \
--volume /run:/run \
--volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
--volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
--volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
--volume /sys/fs/cgroup:/sys/fs/cgroup \
--volume /etc/selinux:/etc/selinux \
--volume /sys/fs/selinux:/sys/fs/selinux \
--volume /var/lib/calico:/var/lib/calico:ro \
--volume /var/lib/docker:/var/lib/docker \
--volume /var/lib/containerd:/var/lib/containerd \
--volume /var/lib/kubelet:/var/lib/kubelet:rshared,z \
--volume /var/log:/var/log \
--volume /var/run/lock:/var/run/lock:z \
--volume /opt/cni/bin:/opt/cni/bin:z \
$${KUBELET_IMAGE} \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=systemd \
--cgroups-per-qos=true \
--enforce-node-allocatable=pods \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/controller="true" \
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
--provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID} \
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
ExecStop=-/usr/bin/podman stop kubelet
Delegate=yes
Restart=always
@ -120,15 +112,17 @@ systemd:
ExecStartPre=-/usr/bin/podman rm bootstrap
ExecStart=/usr/bin/podman run --name bootstrap \
--network host \
--volume /etc/kubernetes/bootstrap-secrets:/etc/kubernetes/secrets:ro,z \
--volume /etc/kubernetes/pki:/etc/kubernetes/pki:ro,z \
--volume /opt/bootstrap/assets:/assets:ro,Z \
--volume /opt/bootstrap/apply:/apply:ro,Z \
--entrypoint=/apply \
quay.io/poseidon/kubelet:v1.18.6
quay.io/poseidon/kubelet:v1.26.1
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
ExecStartPost=-/usr/bin/podman stop bootstrap
storage:
directories:
- path: /var/lib/etcd
mode: 0700
- path: /etc/kubernetes
- path: /opt/bootstrap
files:
@ -137,6 +131,33 @@ storage:
contents:
inline: |
${kubeconfig}
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
rotateCertificates: true
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /opt/bootstrap/layout
mode: 0544
contents:
@ -145,25 +166,26 @@ storage:
mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
awk '/#####/ {filename=$2; next} {print > filename}' assets
mkdir -p /etc/ssl/etcd/etcd
mkdir -p /etc/kubernetes/bootstrap-secrets
mkdir -p /etc/kubernetes/pki
mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
mv tls/etcd/etcd-client* /etc/kubernetes/pki/
chown -R etcd:etcd /etc/ssl/etcd
chmod -R 500 /etc/ssl/etcd
mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
mv auth/* /etc/kubernetes/pki/
mv tls/k8s/* /etc/kubernetes/pki/
mkdir -p /etc/kubernetes/manifests
mv static-manifests/* /etc/kubernetes/manifests/
mkdir -p /opt/bootstrap/assets
mv manifests /opt/bootstrap/assets/manifests
mv manifests-networking/* /opt/bootstrap/assets/manifests/
rm -rf assets auth static-manifests tls manifests-networking
chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
- path: /opt/bootstrap/apply
mode: 0544
contents:
inline: |
#!/bin/bash -e
export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
export KUBECONFIG=/etc/kubernetes/pki/admin.conf
until kubectl version; do
echo "Waiting for static pod control plane"
sleep 5
@ -172,6 +194,11 @@ storage:
echo "Retry applying manifests"
sleep 5
done
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
contents:
inline: |
@ -181,6 +208,13 @@ storage:
inline: |
net.ipv4.conf.default.rp_filter=0
net.ipv4.conf.*.rp_filter=0
- path: /etc/systemd/network/50-flannel.link
contents:
inline: |
[Match]
OriginalName=flannel*
[Link]
MACAddressPolicy=none
- path: /etc/systemd/system.conf.d/accounting.conf
contents:
inline: |
@ -192,8 +226,6 @@ storage:
mode: 0644
contents:
inline: |
# TODO: Use a systemd dropin once podman v1.4.5 is avail.
NOTIFY_SOCKET=/run/systemd/notify
ETCD_NAME=${etcd_name}
ETCD_DATA_DIR=/var/lib/etcd
ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379
@ -211,6 +243,25 @@ storage:
ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
ETCD_PEER_CLIENT_CERT_AUTH=true
- path: /etc/containerd/config.toml
overwrite: true
contents:
inline: |
version = 2
root = "/var/lib/containerd"
state = "/run/containerd"
subreaper = true
oom_score = -999
[grpc]
address = "/run/containerd/containerd.sock"
uid = 0
gid = 0
[plugins."io.containerd.grpc.v1.cri"]
enable_selinux = true
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
SystemdCgroup = true
passwd:
users:
- name: core

View File

@ -22,9 +22,8 @@ resource "aws_instance" "controllers" {
}
instance_type = var.controller_type
ami = data.aws_ami.fedora-coreos.image_id
user_data = data.ct_config.controller-ignitions.*.rendered[count.index]
ami = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
user_data = data.ct_config.controllers.*.rendered[count.index]
# storage
root_block_device {
@ -32,6 +31,7 @@ resource "aws_instance" "controllers" {
volume_size = var.disk_size
iops = var.disk_iops
encrypted = true
tags = {}
}
# network
@ -47,41 +47,22 @@ resource "aws_instance" "controllers" {
}
}
# Controller Ignition configs
data "ct_config" "controller-ignitions" {
count = var.controller_count
content = data.template_file.controller-configs.*.rendered[count.index]
strict = true
snippets = var.controller_snippets
}
# Controller Fedora CoreOS configs
data "template_file" "controller-configs" {
# Fedora CoreOS controllers
data "ct_config" "controllers" {
count = var.controller_count
template = file("${path.module}/fcc/controller.yaml")
vars = {
content = templatefile("${path.module}/butane/controller.yaml", {
# Cannot use cyclic dependencies on controllers or their DNS records
etcd_name = "etcd${count.index}"
etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
# etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
etcd_initial_cluster = join(",", data.template_file.etcds.*.rendered)
etcd_initial_cluster = join(",", [
for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
])
kubeconfig = indent(10, module.bootstrap.kubeconfig-kubelet)
ssh_authorized_key = var.ssh_authorized_key
cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
cluster_domain_suffix = var.cluster_domain_suffix
}
})
strict = true
snippets = var.controller_snippets
}
data "template_file" "etcds" {
count = var.controller_count
template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
vars = {
index = count.index
cluster_name = var.cluster_name
dns_zone = var.dns_zone
}
}

View File

@ -17,6 +17,7 @@ resource "aws_route53_record" "apiserver" {
resource "aws_lb" "nlb" {
name = "${var.cluster_name}-nlb"
load_balancer_type = "network"
ip_address_type = "dualstack"
internal = false
subnets = aws_subnet.public.*.id

View File

@ -1,5 +1,6 @@
output "kubeconfig-admin" {
value = module.bootstrap.kubeconfig-admin
value = module.bootstrap.kubeconfig-admin
sensitive = true
}
# Outputs for Kubernetes Ingress
@ -32,7 +33,8 @@ output "worker_security_groups" {
}
output "kubeconfig" {
value = module.bootstrap.kubeconfig-kubelet
value = module.bootstrap.kubeconfig-kubelet
sensitive = true
}
# Outputs for custom load balancing
@ -52,3 +54,10 @@ output "worker_target_group_https" {
value = module.workers.target_group_https
}
# Outputs for debug
output "assets_dist" {
value = module.bootstrap.assets_dist
sensitive = true
}

View File

@ -201,8 +201,8 @@ resource "aws_security_group_rule" "controller-scheduler-metrics" {
type = "ingress"
protocol = "tcp"
from_port = 10251
to_port = 10251
from_port = 10259
to_port = 10259
source_security_group_id = aws_security_group.worker.id
}
@ -212,8 +212,8 @@ resource "aws_security_group_rule" "controller-manager-metrics" {
type = "ingress"
protocol = "tcp"
from_port = 10252
to_port = 10252
from_port = 10257
to_port = 10257
source_security_group_id = aws_security_group.worker.id
}

View File

@ -24,7 +24,7 @@ resource "null_resource" "copy-controller-secrets" {
provisioner "file" {
content = join("\n", local.assets_bundle)
destination = "$HOME/assets"
destination = "/home/core/assets"
}
provisioner "remote-exec" {

View File

@ -43,26 +43,31 @@ variable "worker_type" {
variable "os_stream" {
type = string
description = "Fedora CoreOs image stream for instances (e.g. stable, testing, next)"
description = "Fedora CoreOS image stream for instances (e.g. stable, testing, next)"
default = "stable"
validation {
condition = contains(["stable", "testing", "next"], var.os_stream)
error_message = "The os_stream must be stable, testing, or next."
}
}
variable "disk_size" {
type = number
description = "Size of the EBS volume in GB"
default = 40
default = 30
}
variable "disk_type" {
type = string
description = "Type of the EBS volume (e.g. standard, gp2, io1)"
default = "gp2"
description = "Type of the EBS volume (e.g. standard, gp2, gp3, io1)"
default = "gp3"
}
variable "disk_iops" {
type = number
description = "IOPS of the EBS volume (e.g. 100)"
default = 0
description = "IOPS of the EBS volume (e.g. 3000)"
default = 3000
}
variable "worker_price" {
@ -79,13 +84,13 @@ variable "worker_target_groups" {
variable "controller_snippets" {
type = list(string)
description = "Controller Fedora CoreOS Config snippets"
description = "Controller Butane snippets"
default = []
}
variable "worker_snippets" {
type = list(string)
description = "Worker Fedora CoreOS Config snippets"
description = "Worker Butane snippets"
default = []
}
@ -96,16 +101,10 @@ variable "ssh_authorized_key" {
description = "SSH public key for user 'core'"
}
variable "asset_dir" {
type = string
description = "Absolute path to a directory where generated assets should be placed (contains secrets)"
default = ""
}
variable "networking" {
type = string
description = "Choice of networking provider (calico or flannel)"
default = "calico"
description = "Choice of networking provider (flannel, calico, or cilium)"
default = "cilium"
}
variable "network_mtu" {
@ -143,8 +142,8 @@ variable "enable_reporting" {
variable "enable_aggregation" {
type = bool
description = "Enable the Kubernetes Aggregation Layer (defaults to false)"
default = false
description = "Enable the Kubernetes Aggregation Layer"
default = true
}
variable "worker_node_labels" {
@ -161,3 +160,19 @@ variable "cluster_domain_suffix" {
default = "cluster.local"
}
variable "arch" {
type = string
description = "Container architecture (amd64 or arm64)"
default = "amd64"
validation {
condition = var.arch == "amd64" || var.arch == "arm64"
error_message = "The arch must be amd64 or arm64."
}
}
variable "daemonset_tolerations" {
type = list(string)
description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
default = []
}

View File

@ -1,11 +1,13 @@
# Terraform version and plugin versions
terraform {
required_version = "~> 0.12.6"
required_version = ">= 0.13.0, < 2.0.0"
required_providers {
aws = "~> 2.23"
ct = "~> 0.4"
template = "~> 2.1"
null = "~> 2.1"
aws = ">= 2.23, <= 5.0"
null = ">= 2.1"
ct = {
source = "poseidon/ct"
version = "~> 0.9"
}
}
}

View File

@ -9,6 +9,7 @@ module "workers" {
worker_count = var.worker_count
instance_type = var.worker_type
os_stream = var.os_stream
arch = var.arch
disk_size = var.disk_size
spot_price = var.worker_price
target_groups = var.worker_target_groups

View File

@ -1,3 +1,6 @@
locals {
ami_id = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
}
data "aws_ami" "fedora-coreos" {
most_recent = true
@ -18,3 +21,25 @@ data "aws_ami" "fedora-coreos" {
values = ["Fedora CoreOS ${var.os_stream} *"]
}
}
data "aws_ami" "fedora-coreos-arm" {
count = var.arch == "arm64" ? 1 : 0
most_recent = true
owners = ["125523088429"]
filter {
name = "architecture"
values = ["arm64"]
}
filter {
name = "virtualization-type"
values = ["hvm"]
}
filter {
name = "description"
values = ["Fedora CoreOS ${var.os_stream} *"]
}
}

View File

@ -1,10 +1,12 @@
---
variant: fcos
version: 1.0.0
version: 1.4.0
systemd:
units:
- name: docker.service
- name: containerd.service
enabled: true
- name: docker.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
@ -23,10 +25,13 @@ systemd:
contents: |
[Unit]
Description=Kubelet (System Container)
Requires=afterburn.service
After=afterburn.service
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.18.6
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
EnvironmentFile=/run/metadata/afterburn
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
@ -34,64 +39,44 @@ systemd:
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/podman rm kubelet
ExecStart=/usr/bin/podman run --name kubelet \
--log-driver k8s-file \
--privileged \
--pid host \
--network host \
--volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
--volume /etc/kubernetes:/etc/kubernetes:ro,z \
--volume /etc/machine-id:/etc/machine-id:ro \
--volume /usr/lib/os-release:/etc/os-release:ro \
--volume /etc/ssl/certs:/etc/ssl/certs:ro \
--volume /lib/modules:/lib/modules:ro \
--volume /run:/run \
--volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
--volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
--volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
--volume /sys/fs/cgroup:/sys/fs/cgroup \
--volume /etc/selinux:/etc/selinux \
--volume /sys/fs/selinux:/sys/fs/selinux \
--volume /var/lib/calico:/var/lib/calico:ro \
--volume /var/lib/docker:/var/lib/docker \
--volume /var/lib/containerd:/var/lib/containerd \
--volume /var/lib/kubelet:/var/lib/kubelet:rshared,z \
--volume /var/log:/var/log \
--volume /var/run/lock:/var/run/lock:z \
--volume /opt/cni/bin:/opt/cni/bin:z \
$${KUBELET_IMAGE} \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=systemd \
--cgroups-per-qos=true \
--enforce-node-allocatable=pods \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/node \
%{~ for label in split(",", node_labels) ~}
--node-labels=${label} \
%{~ endfor ~}
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
%{~ for taint in split(",", node_taints) ~}
--register-with-taints=${taint} \
%{~ endfor ~}
--provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID}
ExecStop=-/usr/bin/podman stop kubelet
Delegate=yes
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: delete-node.service
enabled: true
contents: |
[Unit]
Description=Delete Kubernetes node on shutdown
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/true
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.18.6 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
[Install]
WantedBy=multi-user.target
storage:
directories:
- path: /etc/kubernetes
@ -101,6 +86,38 @@ storage:
contents:
inline: |
${kubeconfig}
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
rotateCertificates: true
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
contents:
inline: |
@ -110,6 +127,13 @@ storage:
inline: |
net.ipv4.conf.default.rp_filter=0
net.ipv4.conf.*.rp_filter=0
- path: /etc/systemd/network/50-flannel.link
contents:
inline: |
[Match]
OriginalName=flannel*
[Link]
MACAddressPolicy=none
- path: /etc/systemd/system.conf.d/accounting.conf
contents:
inline: |
@ -117,9 +141,27 @@ storage:
DefaultCPUAccounting=yes
DefaultMemoryAccounting=yes
DefaultBlockIOAccounting=yes
- path: /etc/containerd/config.toml
overwrite: true
contents:
inline: |
version = 2
root = "/var/lib/containerd"
state = "/run/containerd"
subreaper = true
oom_score = -999
[grpc]
address = "/run/containerd/containerd.sock"
uid = 0
gid = 0
[plugins."io.containerd.grpc.v1.cri"]
enable_selinux = true
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
SystemdCgroup = true
passwd:
users:
- name: core
ssh_authorized_keys:
- ${ssh_authorized_key}

View File

@ -36,20 +36,25 @@ variable "instance_type" {
variable "os_stream" {
type = string
description = "Fedora CoreOs image stream for instances (e.g. stable, testing, next)"
description = "Fedora CoreOS image stream for instances (e.g. stable, testing, next)"
default = "stable"
validation {
condition = contains(["stable", "testing", "next"], var.os_stream)
error_message = "The os_stream must be stable, testing, or next."
}
}
variable "disk_size" {
type = number
description = "Size of the EBS volume in GB"
default = 40
default = 30
}
variable "disk_type" {
type = string
description = "Type of the EBS volume (e.g. standard, gp2, io1)"
default = "gp2"
description = "Type of the EBS volume (e.g. standard, gp2, gp3, io1)"
default = "gp3"
}
variable "disk_iops" {
@ -72,7 +77,7 @@ variable "target_groups" {
variable "snippets" {
type = list(string)
description = "Fedora CoreOS Config snippets"
description = "Butane snippets"
default = []
}
@ -108,3 +113,22 @@ variable "node_labels" {
description = "List of initial node labels"
default = []
}
variable "node_taints" {
type = list(string)
description = "List of initial node taints"
default = []
}
# unofficial, undocumented, unsupported
variable "arch" {
type = string
description = "Container architecture (amd64 or arm64)"
default = "amd64"
validation {
condition = var.arch == "amd64" || var.arch == "arm64"
error_message = "The arch must be amd64 or arm64."
}
}

View File

@ -1,4 +1,12 @@
# Terraform version and plugin versions
terraform {
required_version = ">= 0.12"
required_version = ">= 0.13.0, < 2.0.0"
required_providers {
aws = ">= 2.23, <= 5.0"
ct = {
source = "poseidon/ct"
version = "~> 0.9"
}
}
}

View File

@ -1,6 +1,6 @@
# Workers AutoScaling Group
resource "aws_autoscaling_group" "workers" {
name = "${var.name}-worker ${aws_launch_configuration.worker.name}"
name = "${var.name}-worker"
# count
desired_capacity = var.worker_count
@ -13,7 +13,10 @@ resource "aws_autoscaling_group" "workers" {
vpc_zone_identifier = var.subnet_ids
# template
launch_configuration = aws_launch_configuration.worker.name
launch_template {
id = aws_launch_template.worker.id
version = aws_launch_template.worker.latest_version
}
# target groups to which instances should be added
target_group_arns = flatten([
@ -22,6 +25,14 @@ resource "aws_autoscaling_group" "workers" {
var.target_groups,
])
instance_refresh {
strategy = "Rolling"
preferences {
instance_warmup = 120
min_healthy_percentage = 90
}
}
lifecycle {
# override the default destroy and replace update behavior
create_before_destroy = true
@ -33,34 +44,50 @@ resource "aws_autoscaling_group" "workers" {
# used. Disable wait to avoid issues and align with other clouds.
wait_for_capacity_timeout = "0"
tags = [
{
key = "Name"
value = "${var.name}-worker"
propagate_at_launch = true
},
]
tag {
key = "Name"
value = "${var.name}-worker"
propagate_at_launch = true
}
}
# Worker template
resource "aws_launch_configuration" "worker" {
image_id = data.aws_ami.fedora-coreos.image_id
instance_type = var.instance_type
spot_price = var.spot_price > 0 ? var.spot_price : null
enable_monitoring = false
resource "aws_launch_template" "worker" {
name_prefix = "${var.name}-worker"
image_id = local.ami_id
instance_type = var.instance_type
monitoring {
enabled = false
}
user_data = data.ct_config.worker-ignition.rendered
user_data = sensitive(base64encode(data.ct_config.worker.rendered))
# storage
root_block_device {
volume_type = var.disk_type
volume_size = var.disk_size
iops = var.disk_iops
encrypted = true
ebs_optimized = true
block_device_mappings {
device_name = "/dev/xvda"
ebs {
volume_type = var.disk_type
volume_size = var.disk_size
iops = var.disk_iops
encrypted = true
delete_on_termination = true
}
}
# network
security_groups = var.security_groups
vpc_security_group_ids = var.security_groups
# spot
dynamic "instance_market_options" {
for_each = var.spot_price > 0 ? [1] : []
content {
market_type = "spot"
spot_options {
max_price = var.spot_price
}
}
}
lifecycle {
// Override the default destroy and replace update behavior
@ -69,23 +96,16 @@ resource "aws_launch_configuration" "worker" {
}
}
# Worker Ignition config
data "ct_config" "worker-ignition" {
content = data.template_file.worker-config.rendered
strict = true
snippets = var.snippets
}
# Worker Fedora CoreOS config
data "template_file" "worker-config" {
template = file("${path.module}/fcc/worker.yaml")
vars = {
# Fedora CoreOS worker
data "ct_config" "worker" {
content = templatefile("${path.module}/butane/worker.yaml", {
kubeconfig = indent(10, var.kubeconfig)
ssh_authorized_key = var.ssh_authorized_key
cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
cluster_domain_suffix = var.cluster_domain_suffix
node_labels = join(",", var.node_labels)
}
node_taints = join(",", var.node_taints)
})
strict = true
snippets = var.snippets
}

View File

@ -11,13 +11,13 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
* Kubernetes v1.18.6 (upstream)
* Kubernetes v1.26.1 (upstream)
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/)
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/cl/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/flatcar-linux/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
* Ready for Ingress, Prometheus, Grafana, CSI, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
## Docs
Please see the [official docs](https://typhoon.psdn.io) and the AWS [tutorial](https://typhoon.psdn.io/cl/aws/).
Please see the [official docs](https://typhoon.psdn.io) and the AWS [tutorial](https://typhoon.psdn.io/flatcar-linux/aws/).

View File

@ -1,33 +1,10 @@
locals {
# Pick a CoreOS Container Linux derivative
# coreos-stable -> Container Linux AMI
# Pick a Flatcar Linux AMI
# flatcar-stable -> Flatcar Linux AMI
ami_id = local.flavor == "flatcar" ? data.aws_ami.flatcar.image_id : data.aws_ami.coreos.image_id
flavor = split("-", var.os_image)[0]
ami_id = var.arch == "arm64" ? data.aws_ami.flatcar-arm64[0].image_id : data.aws_ami.flatcar.image_id
channel = split("-", var.os_image)[1]
}
data "aws_ami" "coreos" {
most_recent = true
owners = ["595879546273"]
filter {
name = "architecture"
values = ["x86_64"]
}
filter {
name = "virtualization-type"
values = ["hvm"]
}
filter {
name = "name"
values = ["CoreOS-${local.flavor == "coreos" ? local.channel : "stable"}-*"]
}
}
data "aws_ami" "flatcar" {
most_recent = true
owners = ["075585003325"]
@ -44,7 +21,29 @@ data "aws_ami" "flatcar" {
filter {
name = "name"
values = ["Flatcar-${local.flavor == "flatcar" ? local.channel : "stable"}-*"]
values = ["Flatcar-${local.channel}-*"]
}
}
data "aws_ami" "flatcar-arm64" {
count = var.arch == "arm64" ? 1 : 0
most_recent = true
owners = ["075585003325"]
filter {
name = "architecture"
values = ["arm64"]
}
filter {
name = "virtualization-type"
values = ["hvm"]
}
filter {
name = "name"
values = ["Flatcar-${local.channel}-*"]
}
}

View File

@ -1,11 +1,10 @@
# Kubernetes assets (kubeconfig, manifests)
module "bootstrap" {
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=835890025bfb3499aa0cd5a9704e9e7d3e7e5fe5"
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=4621c6b256129d1ede32ae1f72bcc1473664cb33"
cluster_name = var.cluster_name
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
etcd_servers = aws_route53_record.etcds.*.fqdn
asset_dir = var.asset_dir
networking = var.networking
network_mtu = var.network_mtu
pod_cidr = var.pod_cidr
@ -13,5 +12,6 @@ module "bootstrap" {
cluster_domain_suffix = var.cluster_domain_suffix
enable_reporting = var.enable_reporting
enable_aggregation = var.enable_aggregation
daemonset_tolerations = var.daemonset_tolerations
}

View File

@ -0,0 +1,231 @@
variant: flatcar
version: 1.0.0
systemd:
units:
- name: etcd-member.service
enabled: true
contents: |
[Unit]
Description=etcd (System Container)
Documentation=https://github.com/etcd-io/etcd
Requires=docker.service
After=docker.service
[Service]
Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.7
ExecStartPre=/usr/bin/docker run -d \
--name etcd \
--network host \
--env-file /etc/etcd/etcd.env \
--user 232:232 \
--volume /etc/ssl/etcd:/etc/ssl/certs:ro \
--volume /var/lib/etcd:/var/lib/etcd:rw \
$${ETCD_IMAGE}
ExecStart=docker logs -f etcd
ExecStop=docker stop etcd
ExecStopPost=docker rm etcd
Restart=always
RestartSec=10s
TimeoutStartSec=0
LimitNOFILE=40000
[Install]
WantedBy=multi-user.target
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
RequiredBy=etcd-member.service
- name: kubelet.service
enabled: true
contents: |
[Unit]
Description=Kubelet (System Container)
Requires=docker.service
After=docker.service
Requires=coreos-metadata.service
After=coreos-metadata.service
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
EnvironmentFile=/run/metadata/coreos
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=/usr/bin/docker run -d \
--name kubelet \
--privileged \
--pid host \
--network host \
-v /etc/cni/net.d:/etc/cni/net.d:ro \
-v /etc/kubernetes:/etc/kubernetes:ro \
-v /etc/machine-id:/etc/machine-id:ro \
-v /usr/lib/os-release:/etc/os-release:ro \
-v /lib/modules:/lib/modules:ro \
-v /run:/run \
-v /sys/fs/cgroup:/sys/fs/cgroup \
-v /var/lib/calico:/var/lib/calico:ro \
-v /var/lib/containerd:/var/lib/containerd \
-v /var/lib/kubelet:/var/lib/kubelet:rshared \
-v /var/log:/var/log \
-v /opt/cni/bin:/opt/cni/bin \
$${KUBELET_IMAGE} \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--node-labels=node.kubernetes.io/controller="true" \
--provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID} \
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
ExecStart=docker logs -f kubelet
ExecStop=docker stop kubelet
ExecStopPost=docker rm kubelet
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: bootstrap.service
contents: |
[Unit]
Description=Kubernetes control plane
Wants=docker.service
After=docker.service
ConditionPathExists=!/opt/bootstrap/bootstrap.done
[Service]
Type=oneshot
RemainAfterExit=true
WorkingDirectory=/opt/bootstrap
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
ExecStart=/usr/bin/docker run \
-v /etc/kubernetes/pki:/etc/kubernetes/pki:ro \
-v /opt/bootstrap/assets:/assets:ro \
-v /opt/bootstrap/apply:/apply:ro \
--entrypoint=/apply \
$${KUBELET_IMAGE}
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
[Install]
WantedBy=multi-user.target
storage:
directories:
- path: /var/lib/etcd
mode: 0700
overwrite: true
files:
- path: /etc/kubernetes/kubeconfig
mode: 0644
contents:
inline: |
${kubeconfig}
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
rotateCertificates: true
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /opt/bootstrap/layout
mode: 0544
contents:
inline: |
#!/bin/bash -e
mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
awk '/#####/ {filename=$2; next} {print > filename}' assets
mkdir -p /etc/ssl/etcd/etcd
mkdir -p /etc/kubernetes/pki
mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
mv tls/etcd/etcd-client* /etc/kubernetes/pki/
chown -R etcd:etcd /etc/ssl/etcd
chmod -R 500 /etc/ssl/etcd
chmod -R 700 /var/lib/etcd
mv auth/* /etc/kubernetes/pki/
mv tls/k8s/* /etc/kubernetes/pki/
mkdir -p /etc/kubernetes/manifests
mv static-manifests/* /etc/kubernetes/manifests/
mkdir -p /opt/bootstrap/assets
mv manifests /opt/bootstrap/assets/manifests
mv manifests-networking/* /opt/bootstrap/assets/manifests/
rm -rf assets auth static-manifests tls manifests-networking
- path: /opt/bootstrap/apply
mode: 0544
contents:
inline: |
#!/bin/bash -e
export KUBECONFIG=/etc/kubernetes/pki/admin.conf
until kubectl version; do
echo "Waiting for static pod control plane"
sleep 5
done
until kubectl apply -f /assets/manifests -R; do
echo "Retry applying manifests"
sleep 5
done
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184
- path: /etc/etcd/etcd.env
mode: 0644
contents:
inline: |
ETCD_NAME=${etcd_name}
ETCD_DATA_DIR=/var/lib/etcd
ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379
ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380
ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379
ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380
ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381
ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}
ETCD_STRICT_RECONFIG_CHECK=true
ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt
ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt
ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key
ETCD_CLIENT_CERT_AUTH=true
ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt
ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
ETCD_PEER_CLIENT_CERT_AUTH=true
passwd:
users:
- name: core
ssh_authorized_keys:
- "${ssh_authorized_key}"

View File

@ -24,7 +24,7 @@ resource "aws_instance" "controllers" {
instance_type = var.controller_type
ami = local.ami_id
user_data = data.ct_config.controller-ignitions.*.rendered[count.index]
user_data = data.ct_config.controllers.*.rendered[count.index]
# storage
root_block_device {
@ -32,6 +32,7 @@ resource "aws_instance" "controllers" {
volume_size = var.disk_size
iops = var.disk_iops
encrypted = true
tags = {}
}
# network
@ -47,42 +48,22 @@ resource "aws_instance" "controllers" {
}
}
# Controller Ignition configs
data "ct_config" "controller-ignitions" {
count = var.controller_count
content = data.template_file.controller-configs.*.rendered[count.index]
strict = true
snippets = var.controller_snippets
}
# Controller Container Linux configs
data "template_file" "controller-configs" {
# Flatcar Linux controllers
data "ct_config" "controllers" {
count = var.controller_count
template = file("${path.module}/cl/controller.yaml")
vars = {
content = templatefile("${path.module}/butane/controller.yaml", {
# Cannot use cyclic dependencies on controllers or their DNS records
etcd_name = "etcd${count.index}"
etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
# etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
etcd_initial_cluster = join(",", data.template_file.etcds.*.rendered)
cgroup_driver = local.flavor == "flatcar" && local.channel == "edge" ? "systemd" : "cgroupfs"
etcd_initial_cluster = join(",", [
for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
])
kubeconfig = indent(10, module.bootstrap.kubeconfig-kubelet)
ssh_authorized_key = var.ssh_authorized_key
cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
cluster_domain_suffix = var.cluster_domain_suffix
}
})
strict = true
snippets = var.controller_snippets
}
data "template_file" "etcds" {
count = var.controller_count
template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
vars = {
index = count.index
cluster_name = var.cluster_name
dns_zone = var.dns_zone
}
}

View File

@ -17,6 +17,7 @@ resource "aws_route53_record" "apiserver" {
resource "aws_lb" "nlb" {
name = "${var.cluster_name}-nlb"
load_balancer_type = "network"
ip_address_type = "dualstack"
internal = false
subnets = aws_subnet.public.*.id

View File

@ -1,5 +1,6 @@
output "kubeconfig-admin" {
value = module.bootstrap.kubeconfig-admin
value = module.bootstrap.kubeconfig-admin
sensitive = true
}
# Outputs for Kubernetes Ingress
@ -32,7 +33,8 @@ output "worker_security_groups" {
}
output "kubeconfig" {
value = module.bootstrap.kubeconfig-kubelet
value = module.bootstrap.kubeconfig-kubelet
sensitive = true
}
# Outputs for custom load balancing
@ -52,3 +54,10 @@ output "worker_target_group_https" {
value = module.workers.target_group_https
}
# Outputs for debug
output "assets_dist" {
value = module.bootstrap.assets_dist
sensitive = true
}

View File

@ -201,8 +201,8 @@ resource "aws_security_group_rule" "controller-scheduler-metrics" {
type = "ingress"
protocol = "tcp"
from_port = 10251
to_port = 10251
from_port = 10259
to_port = 10259
source_security_group_id = aws_security_group.worker.id
}
@ -212,8 +212,8 @@ resource "aws_security_group_rule" "controller-manager-metrics" {
type = "ingress"
protocol = "tcp"
from_port = 10252
to_port = 10252
from_port = 10257
to_port = 10257
source_security_group_id = aws_security_group.worker.id
}

View File

@ -24,7 +24,7 @@ resource "null_resource" "copy-controller-secrets" {
provisioner "file" {
content = join("\n", local.assets_bundle)
destination = "$HOME/assets"
destination = "/home/core/assets"
}
provisioner "remote-exec" {

View File

@ -43,26 +43,31 @@ variable "worker_type" {
variable "os_image" {
type = string
description = "AMI channel for a Container Linux derivative (coreos-stable, coreos-beta, coreos-alpha, flatcar-stable, flatcar-beta, flatcar-alpha, flatcar-edge)"
description = "AMI channel for a Container Linux derivative (flatcar-stable, flatcar-beta, flatcar-alpha)"
default = "flatcar-stable"
validation {
condition = contains(["flatcar-stable", "flatcar-beta", "flatcar-alpha"], var.os_image)
error_message = "The os_image must be flatcar-stable, flatcar-beta, or flatcar-alpha."
}
}
variable "disk_size" {
type = number
description = "Size of the EBS volume in GB"
default = 40
default = 30
}
variable "disk_type" {
type = string
description = "Type of the EBS volume (e.g. standard, gp2, io1)"
default = "gp2"
description = "Type of the EBS volume (e.g. standard, gp2, gp3, io1)"
default = "gp3"
}
variable "disk_iops" {
type = number
description = "IOPS of the EBS volume (e.g. 100)"
default = 0
description = "IOPS of the EBS volume (e.g. 3000)"
default = 3000
}
variable "worker_price" {
@ -98,8 +103,8 @@ variable "ssh_authorized_key" {
variable "networking" {
type = string
description = "Choice of networking provider (calico or flannel)"
default = "calico"
description = "Choice of networking provider (flannel, calico, or cilium)"
default = "cilium"
}
variable "network_mtu" {
@ -137,8 +142,8 @@ variable "enable_reporting" {
variable "enable_aggregation" {
type = bool
description = "Enable the Kubernetes Aggregation Layer (defaults to false)"
default = false
description = "Enable the Kubernetes Aggregation Layer"
default = true
}
variable "worker_node_labels" {
@ -149,15 +154,25 @@ variable "worker_node_labels" {
# unofficial, undocumented, unsupported
variable "asset_dir" {
type = string
description = "Absolute path to a directory where generated assets should be placed (contains secrets)"
default = ""
}
variable "cluster_domain_suffix" {
type = string
description = "Queries for domains with the suffix will be answered by CoreDNS. Default is cluster.local (e.g. foo.default.svc.cluster.local)"
default = "cluster.local"
}
variable "arch" {
type = string
description = "Container architecture (amd64 or arm64)"
default = "amd64"
validation {
condition = var.arch == "amd64" || var.arch == "arm64"
error_message = "The arch must be amd64 or arm64."
}
}
variable "daemonset_tolerations" {
type = list(string)
description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
default = []
}

View File

@ -0,0 +1,13 @@
# Terraform version and plugin versions
terraform {
required_version = ">= 0.13.0, < 2.0.0"
required_providers {
aws = ">= 2.23, <= 5.0"
null = ">= 2.1"
ct = {
source = "poseidon/ct"
version = "~> 0.11"
}
}
}

View File

@ -9,6 +9,7 @@ module "workers" {
worker_count = var.worker_count
instance_type = var.worker_type
os_image = var.os_image
arch = var.arch
disk_size = var.disk_size
spot_price = var.worker_price
target_groups = var.worker_target_groups

View File

@ -1,33 +1,10 @@
locals {
# Pick a CoreOS Container Linux derivative
# coreos-stable -> Container Linux AMI
# Pick a Flatcar Linux AMI
# flatcar-stable -> Flatcar Linux AMI
ami_id = local.flavor == "flatcar" ? data.aws_ami.flatcar.image_id : data.aws_ami.coreos.image_id
flavor = split("-", var.os_image)[0]
ami_id = var.arch == "arm64" ? data.aws_ami.flatcar-arm64[0].image_id : data.aws_ami.flatcar.image_id
channel = split("-", var.os_image)[1]
}
data "aws_ami" "coreos" {
most_recent = true
owners = ["595879546273"]
filter {
name = "architecture"
values = ["x86_64"]
}
filter {
name = "virtualization-type"
values = ["hvm"]
}
filter {
name = "name"
values = ["CoreOS-${local.flavor == "coreos" ? local.channel : "stable"}-*"]
}
}
data "aws_ami" "flatcar" {
most_recent = true
owners = ["075585003325"]
@ -44,7 +21,28 @@ data "aws_ami" "flatcar" {
filter {
name = "name"
values = ["Flatcar-${local.flavor == "flatcar" ? local.channel : "stable"}-*"]
values = ["Flatcar-${local.channel}-*"]
}
}
data "aws_ami" "flatcar-arm64" {
count = var.arch == "arm64" ? 1 : 0
most_recent = true
owners = ["075585003325"]
filter {
name = "architecture"
values = ["arm64"]
}
filter {
name = "virtualization-type"
values = ["hvm"]
}
filter {
name = "name"
values = ["Flatcar-${local.channel}-*"]
}
}

View File

@ -0,0 +1,129 @@
variant: flatcar
version: 1.0.0
systemd:
units:
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
- name: kubelet.service
enabled: true
contents: |
[Unit]
Description=Kubelet
Requires=docker.service
After=docker.service
Requires=coreos-metadata.service
After=coreos-metadata.service
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
EnvironmentFile=/run/metadata/coreos
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
# Podman, rkt, or runc run container processes, whereas docker run
# is a client to a daemon and requires workarounds to use within a
# systemd unit. https://github.com/moby/moby/issues/6791
ExecStartPre=/usr/bin/docker run -d \
--name kubelet \
--privileged \
--pid host \
--network host \
-v /etc/cni/net.d:/etc/cni/net.d:ro \
-v /etc/kubernetes:/etc/kubernetes:ro \
-v /etc/machine-id:/etc/machine-id:ro \
-v /usr/lib/os-release:/etc/os-release:ro \
-v /lib/modules:/lib/modules:ro \
-v /run:/run \
-v /sys/fs/cgroup:/sys/fs/cgroup \
-v /var/lib/calico:/var/lib/calico:ro \
-v /var/lib/containerd:/var/lib/containerd \
-v /var/lib/kubelet:/var/lib/kubelet:rshared \
-v /var/log:/var/log \
-v /opt/cni/bin:/opt/cni/bin \
$${KUBELET_IMAGE} \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--node-labels=node.kubernetes.io/node \
%{~ for label in split(",", node_labels) ~}
--node-labels=${label} \
%{~ endfor ~}
%{~ for taint in split(",", node_taints) ~}
--register-with-taints=${taint} \
%{~ endfor ~}
--provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID}
ExecStart=docker logs -f kubelet
ExecStop=docker stop kubelet
ExecStopPost=docker rm kubelet
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
storage:
files:
- path: /etc/kubernetes/kubeconfig
mode: 0644
contents:
inline: |
${kubeconfig}
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
rotateCertificates: true
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184
passwd:
users:
- name: core
ssh_authorized_keys:
- "${ssh_authorized_key}"

View File

@ -36,20 +36,25 @@ variable "instance_type" {
variable "os_image" {
type = string
description = "AMI channel for a Container Linux derivative (coreos-stable, coreos-beta, coreos-alpha, flatcar-stable, flatcar-beta, flatcar-alpha, flatcar-edge)"
description = "AMI channel for a Container Linux derivative (flatcar-stable, flatcar-beta, flatcar-alpha)"
default = "flatcar-stable"
validation {
condition = contains(["flatcar-stable", "flatcar-beta", "flatcar-alpha"], var.os_image)
error_message = "The os_image must be flatcar-stable, flatcar-beta, or flatcar-alpha."
}
}
variable "disk_size" {
type = number
description = "Size of the EBS volume in GB"
default = 40
default = 30
}
variable "disk_type" {
type = string
description = "Type of the EBS volume (e.g. standard, gp2, io1)"
default = "gp2"
description = "Type of the EBS volume (e.g. standard, gp2, gp3, io1)"
default = "gp3"
}
variable "disk_iops" {
@ -108,3 +113,22 @@ variable "node_labels" {
description = "List of initial node labels"
default = []
}
variable "node_taints" {
type = list(string)
description = "List of initial node taints"
default = []
}
# unofficial, undocumented, unsupported
variable "arch" {
type = string
description = "Container architecture (amd64 or arm64)"
default = "amd64"
validation {
condition = var.arch == "amd64" || var.arch == "arm64"
error_message = "The arch must be amd64 or arm64."
}
}

View File

@ -0,0 +1,12 @@
# Terraform version and plugin versions
terraform {
required_version = ">= 0.13.0, < 2.0.0"
required_providers {
aws = ">= 2.23, <= 5.0"
ct = {
source = "poseidon/ct"
version = "~> 0.11"
}
}
}

View File

@ -1,6 +1,6 @@
# Workers AutoScaling Group
resource "aws_autoscaling_group" "workers" {
name = "${var.name}-worker ${aws_launch_configuration.worker.name}"
name = "${var.name}-worker"
# count
desired_capacity = var.worker_count
@ -13,7 +13,10 @@ resource "aws_autoscaling_group" "workers" {
vpc_zone_identifier = var.subnet_ids
# template
launch_configuration = aws_launch_configuration.worker.name
launch_template {
id = aws_launch_template.worker.id
version = aws_launch_template.worker.latest_version
}
# target groups to which instances should be added
target_group_arns = flatten([
@ -22,6 +25,14 @@ resource "aws_autoscaling_group" "workers" {
var.target_groups,
])
instance_refresh {
strategy = "Rolling"
preferences {
instance_warmup = 120
min_healthy_percentage = 90
}
}
lifecycle {
# override the default destroy and replace update behavior
create_before_destroy = true
@ -33,34 +44,50 @@ resource "aws_autoscaling_group" "workers" {
# used. Disable wait to avoid issues and align with other clouds.
wait_for_capacity_timeout = "0"
tags = [
{
key = "Name"
value = "${var.name}-worker"
propagate_at_launch = true
},
]
tag {
key = "Name"
value = "${var.name}-worker"
propagate_at_launch = true
}
}
# Worker template
resource "aws_launch_configuration" "worker" {
image_id = local.ami_id
instance_type = var.instance_type
spot_price = var.spot_price > 0 ? var.spot_price : null
enable_monitoring = false
resource "aws_launch_template" "worker" {
name_prefix = "${var.name}-worker"
image_id = local.ami_id
instance_type = var.instance_type
monitoring {
enabled = false
}
user_data = data.ct_config.worker-ignition.rendered
user_data = sensitive(base64encode(data.ct_config.worker.rendered))
# storage
root_block_device {
volume_type = var.disk_type
volume_size = var.disk_size
iops = var.disk_iops
encrypted = true
ebs_optimized = true
block_device_mappings {
device_name = "/dev/xvda"
ebs {
volume_type = var.disk_type
volume_size = var.disk_size
iops = var.disk_iops
encrypted = true
delete_on_termination = true
}
}
# network
security_groups = var.security_groups
vpc_security_group_ids = var.security_groups
# spot
dynamic "instance_market_options" {
for_each = var.spot_price > 0 ? [1] : []
content {
market_type = "spot"
spot_options {
max_price = var.spot_price
}
}
}
lifecycle {
// Override the default destroy and replace update behavior
@ -69,24 +96,16 @@ resource "aws_launch_configuration" "worker" {
}
}
# Worker Ignition config
data "ct_config" "worker-ignition" {
content = data.template_file.worker-config.rendered
strict = true
snippets = var.snippets
}
# Worker Container Linux config
data "template_file" "worker-config" {
template = file("${path.module}/cl/worker.yaml")
vars = {
# Flatcar Linux worker
data "ct_config" "worker" {
content = templatefile("${path.module}/butane/worker.yaml", {
kubeconfig = indent(10, var.kubeconfig)
ssh_authorized_key = var.ssh_authorized_key
cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
cluster_domain_suffix = var.cluster_domain_suffix
cgroup_driver = local.flavor == "flatcar" && local.channel == "edge" ? "systemd" : "cgroupfs"
node_labels = join(",", var.node_labels)
}
node_taints = join(",", var.node_taints)
})
strict = true
snippets = var.snippets
}

View File

@ -1,199 +0,0 @@
---
systemd:
units:
- name: etcd-member.service
enabled: true
dropins:
- name: 40-etcd-cluster.conf
contents: |
[Service]
Environment="ETCD_IMAGE_TAG=v3.4.9"
Environment="ETCD_IMAGE_URL=docker://quay.io/coreos/etcd"
Environment="RKT_RUN_ARGS=--insecure-options=image"
Environment="ETCD_NAME=${etcd_name}"
Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379"
Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380"
Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
Environment="ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381"
Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
Environment="ETCD_STRICT_RECONFIG_CHECK=true"
Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
Environment="ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt"
Environment="ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key"
Environment="ETCD_CLIENT_CERT_AUTH=true"
Environment="ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt"
Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
RequiredBy=etcd-member.service
- name: kubelet.service
enabled: true
contents: |
[Unit]
Description=Kubelet
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.18.6
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
ExecStart=/usr/bin/rkt run \
--uuid-file-save=/var/cache/kubelet-pod.uuid \
--stage1-from-dir=stage1-fly.aci \
--hosts-entry host \
--insecure-options=image \
--volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
--mount volume=etc-kubernetes,target=/etc/kubernetes \
--volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
--mount volume=etc-machine-id,target=/etc/machine-id \
--volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
--mount volume=etc-os-release,target=/etc/os-release \
--volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
--mount volume=etc-resolv,target=/etc/resolv.conf \
--volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
--mount volume=etc-ssl-certs,target=/etc/ssl/certs \
--volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
--mount volume=lib-modules,target=/lib/modules \
--volume run,kind=host,source=/run \
--mount volume=run,target=/run \
--volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
--mount volume=usr-share-certs,target=/usr/share/ca-certificates \
--volume var-lib-calico,kind=host,source=/var/lib/calico,readOnly=true \
--mount volume=var-lib-calico,target=/var/lib/calico \
--volume var-lib-docker,kind=host,source=/var/lib/docker \
--mount volume=var-lib-docker,target=/var/lib/docker \
--volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
--mount volume=var-lib-kubelet,target=/var/lib/kubelet \
--volume var-log,kind=host,source=/var/log \
--mount volume=var-log,target=/var/log \
--volume opt-cni-bin,kind=host,source=/opt/cni/bin \
--mount volume=opt-cni-bin,target=/opt/cni/bin \
$${KUBELET_IMAGE} -- \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=$${KUBELET_CGROUP_DRIVER} \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/controller="true" \
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: bootstrap.service
contents: |
[Unit]
Description=Kubernetes control plane
ConditionPathExists=!/opt/bootstrap/bootstrap.done
[Service]
Type=oneshot
RemainAfterExit=true
WorkingDirectory=/opt/bootstrap
ExecStart=/usr/bin/rkt run \
--trust-keys-from-https \
--volume config,kind=host,source=/etc/kubernetes/bootstrap-secrets \
--mount volume=config,target=/etc/kubernetes/secrets \
--volume assets,kind=host,source=/opt/bootstrap/assets \
--mount volume=assets,target=/assets \
--volume script,kind=host,source=/opt/bootstrap/apply \
--mount volume=script,target=/apply \
--insecure-options=image \
docker://quay.io/poseidon/kubelet:v1.18.6 \
--net=host \
--dns=host \
--exec=/apply
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
[Install]
WantedBy=multi-user.target
storage:
files:
- path: /etc/kubernetes/kubeconfig
filesystem: root
mode: 0644
contents:
inline: |
${kubeconfig}
- path: /opt/bootstrap/layout
filesystem: root
mode: 0544
contents:
inline: |
#!/bin/bash -e
mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
awk '/#####/ {filename=$2; next} {print > filename}' assets
mkdir -p /etc/ssl/etcd/etcd
mkdir -p /etc/kubernetes/bootstrap-secrets
mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
chown -R etcd:etcd /etc/ssl/etcd
chmod -R 500 /etc/ssl/etcd
mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
mkdir -p /etc/kubernetes/manifests
mv static-manifests/* /etc/kubernetes/manifests/
mkdir -p /opt/bootstrap/assets
mv manifests /opt/bootstrap/assets/manifests
mv manifests-networking/* /opt/bootstrap/assets/manifests/
rm -rf assets auth static-manifests tls manifests-networking
- path: /opt/bootstrap/apply
filesystem: root
mode: 0544
contents:
inline: |
#!/bin/bash -e
export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
until kubectl version; do
echo "Waiting for static pod control plane"
sleep 5
done
until kubectl apply -f /assets/manifests -R; do
echo "Retry applying manifests"
sleep 5
done
- path: /etc/sysctl.d/max-user-watches.conf
filesystem: root
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184
passwd:
users:
- name: core
ssh_authorized_keys:
- "${ssh_authorized_key}"

View File

@ -1,428 +0,0 @@
# Controller security group
resource "azurerm_network_security_group" "controller" {
resource_group_name = azurerm_resource_group.cluster.name
name = "${var.cluster_name}-controller"
location = azurerm_resource_group.cluster.location
}
resource "azurerm_network_security_rule" "controller-icmp" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-icmp"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "1995"
access = "Allow"
direction = "Inbound"
protocol = "Icmp"
source_port_range = "*"
destination_port_range = "*"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
resource "azurerm_network_security_rule" "controller-ssh" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-ssh"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2000"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "22"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
resource "azurerm_network_security_rule" "controller-etcd" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-etcd"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2005"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "2379-2380"
source_address_prefix = azurerm_subnet.controller.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
# Allow Prometheus to scrape etcd metrics
resource "azurerm_network_security_rule" "controller-etcd-metrics" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-etcd-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2010"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "2381"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
# Allow Prometheus to scrape kube-proxy metrics
resource "azurerm_network_security_rule" "controller-kube-proxy" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kube-proxy-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2011"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10249"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
# Allow Prometheus to scrape kube-scheduler and kube-controller-manager metrics
resource "azurerm_network_security_rule" "controller-kube-metrics" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kube-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2012"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10251-10252"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
resource "azurerm_network_security_rule" "controller-apiserver" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-apiserver"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2015"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "6443"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
resource "azurerm_network_security_rule" "controller-cilium-health" {
resource_group_name = azurerm_resource_group.cluster.name
count = var.networking == "cilium" ? 1 : 0
name = "allow-cilium-health"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2019"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "4240"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
resource "azurerm_network_security_rule" "controller-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-vxlan"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2020"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "4789"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
resource "azurerm_network_security_rule" "controller-linux-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-linux-vxlan"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2021"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "8472"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
# Allow Prometheus to scrape node-exporter daemonset
resource "azurerm_network_security_rule" "controller-node-exporter" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-node-exporter"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2025"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "9100"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
# Allow apiserver to access kubelet's for exec, log, port-forward
resource "azurerm_network_security_rule" "controller-kubelet" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kubelet"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2030"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10250"
# allow Prometheus to scrape kubelet metrics too
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
}
# Override Azure AllowVNetInBound and AllowAzureLoadBalancerInBound
# https://docs.microsoft.com/en-us/azure/virtual-network/security-overview#default-security-rules
resource "azurerm_network_security_rule" "controller-allow-loadblancer" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-loadbalancer"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "3000"
access = "Allow"
direction = "Inbound"
protocol = "*"
source_port_range = "*"
destination_port_range = "*"
source_address_prefix = "AzureLoadBalancer"
destination_address_prefix = "*"
}
resource "azurerm_network_security_rule" "controller-deny-all" {
resource_group_name = azurerm_resource_group.cluster.name
name = "deny-all"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "3005"
access = "Deny"
direction = "Inbound"
protocol = "*"
source_port_range = "*"
destination_port_range = "*"
source_address_prefix = "*"
destination_address_prefix = "*"
}
# Worker security group
resource "azurerm_network_security_group" "worker" {
resource_group_name = azurerm_resource_group.cluster.name
name = "${var.cluster_name}-worker"
location = azurerm_resource_group.cluster.location
}
resource "azurerm_network_security_rule" "worker-icmp" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-icmp"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "1995"
access = "Allow"
direction = "Inbound"
protocol = "Icmp"
source_port_range = "*"
destination_port_range = "*"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
resource "azurerm_network_security_rule" "worker-ssh" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-ssh"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2000"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "22"
source_address_prefix = azurerm_subnet.controller.address_prefix
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
resource "azurerm_network_security_rule" "worker-http" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-http"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2005"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "80"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
resource "azurerm_network_security_rule" "worker-https" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-https"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2010"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "443"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
resource "azurerm_network_security_rule" "worker-cilium-health" {
resource_group_name = azurerm_resource_group.cluster.name
count = var.networking == "cilium" ? 1 : 0
name = "allow-cilium-health"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2014"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "4240"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
resource "azurerm_network_security_rule" "worker-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-vxlan"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2015"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "4789"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
resource "azurerm_network_security_rule" "worker-linux-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-linux-vxlan"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2016"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "8472"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
# Allow Prometheus to scrape node-exporter daemonset
resource "azurerm_network_security_rule" "worker-node-exporter" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-node-exporter"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2020"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "9100"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
# Allow Prometheus to scrape kube-proxy
resource "azurerm_network_security_rule" "worker-kube-proxy" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kube-proxy"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2024"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10249"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
# Allow apiserver to access kubelet's for exec, log, port-forward
resource "azurerm_network_security_rule" "worker-kubelet" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kubelet"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2025"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10250"
# allow Prometheus to scrape kubelet metrics too
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
}
# Override Azure AllowVNetInBound and AllowAzureLoadBalancerInBound
# https://docs.microsoft.com/en-us/azure/virtual-network/security-overview#default-security-rules
resource "azurerm_network_security_rule" "worker-allow-loadblancer" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-loadbalancer"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "3000"
access = "Allow"
direction = "Inbound"
protocol = "*"
source_port_range = "*"
destination_port_range = "*"
source_address_prefix = "AzureLoadBalancer"
destination_address_prefix = "*"
}
resource "azurerm_network_security_rule" "worker-deny-all" {
resource_group_name = azurerm_resource_group.cluster.name
name = "deny-all"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "3005"
access = "Deny"
direction = "Inbound"
protocol = "*"
source_port_range = "*"
destination_port_range = "*"
source_address_prefix = "*"
destination_address_prefix = "*"
}

View File

@ -1,12 +0,0 @@
# Terraform version and plugin versions
terraform {
required_version = "~> 0.12.6"
required_providers {
azurerm = "~> 2.8"
ct = "~> 0.4"
template = "~> 2.1"
null = "~> 2.1"
}
}

View File

@ -1,140 +0,0 @@
---
systemd:
units:
- name: docker.service
enabled: true
- name: locksmithd.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
[Unit]
Description=Wait for DNS entries
Wants=systemd-resolved.service
Before=kubelet.service
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
[Install]
RequiredBy=kubelet.service
- name: kubelet.service
enabled: true
contents: |
[Unit]
Description=Kubelet
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.18.6
Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
ExecStart=/usr/bin/rkt run \
--uuid-file-save=/var/cache/kubelet-pod.uuid \
--stage1-from-dir=stage1-fly.aci \
--hosts-entry host \
--insecure-options=image \
--volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
--mount volume=etc-kubernetes,target=/etc/kubernetes \
--volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
--mount volume=etc-machine-id,target=/etc/machine-id \
--volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
--mount volume=etc-os-release,target=/etc/os-release \
--volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
--mount volume=etc-resolv,target=/etc/resolv.conf \
--volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
--mount volume=etc-ssl-certs,target=/etc/ssl/certs \
--volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
--mount volume=lib-modules,target=/lib/modules \
--volume run,kind=host,source=/run \
--mount volume=run,target=/run \
--volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
--mount volume=usr-share-certs,target=/usr/share/ca-certificates \
--volume var-lib-calico,kind=host,source=/var/lib/calico,readOnly=true \
--mount volume=var-lib-calico,target=/var/lib/calico \
--volume var-lib-docker,kind=host,source=/var/lib/docker \
--mount volume=var-lib-docker,target=/var/lib/docker \
--volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
--mount volume=var-lib-kubelet,target=/var/lib/kubelet \
--volume var-log,kind=host,source=/var/log \
--mount volume=var-log,target=/var/log \
--volume opt-cni-bin,kind=host,source=/opt/cni/bin \
--mount volume=opt-cni-bin,target=/opt/cni/bin \
$${KUBELET_IMAGE} -- \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=$${KUBELET_CGROUP_DRIVER} \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/node \
%{~ for label in split(",", node_labels) ~}
--node-labels=${label} \
%{~ endfor ~}
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
Restart=always
RestartSec=5
[Install]
WantedBy=multi-user.target
- name: delete-node.service
enabled: true
contents: |
[Unit]
Description=Waiting to delete Kubernetes node on shutdown
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/true
ExecStop=/etc/kubernetes/delete-node
[Install]
WantedBy=multi-user.target
storage:
files:
- path: /etc/kubernetes/kubeconfig
filesystem: root
mode: 0644
contents:
inline: |
${kubeconfig}
- path: /etc/sysctl.d/max-user-watches.conf
filesystem: root
mode: 0644
contents:
inline: |
fs.inotify.max_user_watches=16184
- path: /etc/kubernetes/delete-node
filesystem: root
mode: 0744
contents:
inline: |
#!/bin/bash
set -e
exec /usr/bin/rkt run \
--trust-keys-from-https \
--volume config,kind=host,source=/etc/kubernetes \
--mount volume=config,target=/etc/kubernetes \
--insecure-options=image \
docker://quay.io/poseidon/kubelet:v1.18.6 \
--net=host \
--dns=host \
--exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname | tr '[:upper:]' '[:lower:]')
passwd:
users:
- name: core
ssh_authorized_keys:
- "${ssh_authorized_key}"

View File

@ -1,4 +0,0 @@
terraform {
required_version = ">= 0.12"
}

View File

@ -11,10 +11,10 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
* Kubernetes v1.18.6 (upstream)
* Kubernetes v1.26.1 (upstream)
* Single or multi-master, [Calico](https://www.projectcalico.org/) or [Cilium](https://github.com/cilium/cilium) or [flannel](https://github.com/coreos/flannel) networking
* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot priority](https://typhoon.psdn.io/fedora-coreos/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/) customization
* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot priority](https://typhoon.psdn.io/fedora-coreos/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
* Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
## Docs

View File

@ -1,11 +1,10 @@
# Kubernetes assets (kubeconfig, manifests)
module "bootstrap" {
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=835890025bfb3499aa0cd5a9704e9e7d3e7e5fe5"
source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=4621c6b256129d1ede32ae1f72bcc1473664cb33"
cluster_name = var.cluster_name
api_servers = [format("%s.%s", var.cluster_name, var.dns_zone)]
etcd_servers = formatlist("%s.%s", azurerm_dns_a_record.etcds.*.name, var.dns_zone)
asset_dir = var.asset_dir
networking = var.networking
@ -19,8 +18,6 @@ module "bootstrap" {
cluster_domain_suffix = var.cluster_domain_suffix
enable_reporting = var.enable_reporting
enable_aggregation = var.enable_aggregation
# Fedora CoreOS
trusted_certs_dir = "/etc/pki/tls/certs"
daemonset_tolerations = var.daemonset_tolerations
}

View File

@ -1,6 +1,6 @@
---
variant: fcos
version: 1.0.0
version: 1.4.0
systemd:
units:
- name: etcd-member.service
@ -8,32 +8,32 @@ systemd:
contents: |
[Unit]
Description=etcd (System Container)
Documentation=https://github.com/coreos/etcd
Wants=network-online.target network.target
Documentation=https://github.com/etcd-io/etcd
Wants=network-online.target
After=network-online.target
[Service]
# https://github.com/opencontainers/runc/pull/1807
# Type=notify
# NotifyAccess=exec
Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.5.7
Type=exec
ExecStartPre=/bin/mkdir -p /var/lib/etcd
ExecStartPre=-/usr/bin/podman rm etcd
ExecStart=/usr/bin/podman run --name etcd \
--env-file /etc/etcd/etcd.env \
--log-driver k8s-file \
--network host \
--volume /var/lib/etcd:/var/lib/etcd:rw,Z \
--volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
$${ETCD_IMAGE}
ExecStop=/usr/bin/podman stop etcd
Restart=on-failure
RestartSec=10s
TimeoutStartSec=0
LimitNOFILE=40000
ExecStartPre=/bin/mkdir -p /var/lib/etcd
ExecStartPre=-/usr/bin/podman rm etcd
#--volume $${NOTIFY_SOCKET}:/run/systemd/notify \
ExecStart=/usr/bin/podman run --name etcd \
--env-file /etc/etcd/etcd.env \
--network host \
--volume /var/lib/etcd:/var/lib/etcd:rw,Z \
--volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
quay.io/coreos/etcd:v3.4.9
ExecStop=/usr/bin/podman stop etcd
[Install]
WantedBy=multi-user.target
- name: docker.service
- name: containerd.service
enabled: true
- name: docker.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
@ -54,8 +54,8 @@ systemd:
Description=Kubelet (System Container)
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.18.6
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
@ -63,44 +63,32 @@ systemd:
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/podman rm kubelet
ExecStart=/usr/bin/podman run --name kubelet \
--log-driver k8s-file \
--privileged \
--pid host \
--network host \
--volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
--volume /etc/kubernetes:/etc/kubernetes:ro,z \
--volume /etc/machine-id:/etc/machine-id:ro \
--volume /usr/lib/os-release:/etc/os-release:ro \
--volume /etc/ssl/certs:/etc/ssl/certs:ro \
--volume /lib/modules:/lib/modules:ro \
--volume /run:/run \
--volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
--volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
--volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
--volume /sys/fs/cgroup:/sys/fs/cgroup \
--volume /etc/selinux:/etc/selinux \
--volume /sys/fs/selinux:/sys/fs/selinux \
--volume /var/lib/calico:/var/lib/calico:ro \
--volume /var/lib/docker:/var/lib/docker \
--volume /var/lib/containerd:/var/lib/containerd \
--volume /var/lib/kubelet:/var/lib/kubelet:rshared,z \
--volume /var/log:/var/log \
--volume /var/run/lock:/var/run/lock:z \
--volume /opt/cni/bin:/opt/cni/bin:z \
$${KUBELET_IMAGE} \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=systemd \
--cgroups-per-qos=true \
--enforce-node-allocatable=pods \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/controller="true" \
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
--register-with-taints=node-role.kubernetes.io/controller=:NoSchedule
ExecStop=-/usr/bin/podman stop kubelet
Delegate=yes
Restart=always
@ -119,15 +107,17 @@ systemd:
ExecStartPre=-/usr/bin/podman rm bootstrap
ExecStart=/usr/bin/podman run --name bootstrap \
--network host \
--volume /etc/kubernetes/bootstrap-secrets:/etc/kubernetes/secrets:ro,z \
--volume /etc/kubernetes/pki:/etc/kubernetes/pki:ro,z \
--volume /opt/bootstrap/assets:/assets:ro,Z \
--volume /opt/bootstrap/apply:/apply:ro,Z \
--entrypoint=/apply \
quay.io/poseidon/kubelet:v1.18.6
quay.io/poseidon/kubelet:v1.26.1
ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
ExecStartPost=-/usr/bin/podman stop bootstrap
storage:
directories:
- path: /var/lib/etcd
mode: 0700
- path: /etc/kubernetes
- path: /opt/bootstrap
files:
@ -136,6 +126,33 @@ storage:
contents:
inline: |
${kubeconfig}
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
rotateCertificates: true
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /opt/bootstrap/layout
mode: 0544
contents:
@ -144,25 +161,26 @@ storage:
mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
awk '/#####/ {filename=$2; next} {print > filename}' assets
mkdir -p /etc/ssl/etcd/etcd
mkdir -p /etc/kubernetes/bootstrap-secrets
mkdir -p /etc/kubernetes/pki
mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
mv tls/etcd/etcd-client* /etc/kubernetes/pki/
chown -R etcd:etcd /etc/ssl/etcd
chmod -R 500 /etc/ssl/etcd
mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
mv auth/* /etc/kubernetes/pki/
mv tls/k8s/* /etc/kubernetes/pki/
mkdir -p /etc/kubernetes/manifests
mv static-manifests/* /etc/kubernetes/manifests/
mkdir -p /opt/bootstrap/assets
mv manifests /opt/bootstrap/assets/manifests
mv manifests-networking/* /opt/bootstrap/assets/manifests/
rm -rf assets auth static-manifests tls manifests-networking
chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
- path: /opt/bootstrap/apply
mode: 0544
contents:
inline: |
#!/bin/bash -e
export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
export KUBECONFIG=/etc/kubernetes/pki/admin.conf
until kubectl version; do
echo "Waiting for static pod control plane"
sleep 5
@ -171,6 +189,11 @@ storage:
echo "Retry applying manifests"
sleep 5
done
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
contents:
inline: |
@ -180,6 +203,13 @@ storage:
inline: |
net.ipv4.conf.default.rp_filter=0
net.ipv4.conf.*.rp_filter=0
- path: /etc/systemd/network/50-flannel.link
contents:
inline: |
[Match]
OriginalName=flannel*
[Link]
MACAddressPolicy=none
- path: /etc/systemd/system.conf.d/accounting.conf
contents:
inline: |
@ -191,8 +221,6 @@ storage:
mode: 0644
contents:
inline: |
# TODO: Use a systemd dropin once podman v1.4.5 is avail.
NOTIFY_SOCKET=/run/systemd/notify
ETCD_NAME=${etcd_name}
ETCD_DATA_DIR=/var/lib/etcd
ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379
@ -210,6 +238,25 @@ storage:
ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
ETCD_PEER_CLIENT_CERT_AUTH=true
- path: /etc/containerd/config.toml
overwrite: true
contents:
inline: |
version = 2
root = "/var/lib/containerd"
state = "/run/containerd"
subreaper = true
oom_score = -999
[grpc]
address = "/run/containerd/containerd.sock"
uid = 0
gid = 0
[plugins."io.containerd.grpc.v1.cri"]
enable_selinux = true
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
SystemdCgroup = true
passwd:
users:
- name: core

View File

@ -35,7 +35,7 @@ resource "azurerm_linux_virtual_machine" "controllers" {
availability_set_id = azurerm_availability_set.controllers.id
size = var.controller_type
custom_data = base64encode(data.ct_config.controller-ignitions.*.rendered[count.index])
custom_data = base64encode(data.ct_config.controllers.*.rendered[count.index])
# storage
source_image_id = var.os_image
@ -111,41 +111,22 @@ resource "azurerm_network_interface_backend_address_pool_association" "controlle
backend_address_pool_id = azurerm_lb_backend_address_pool.controller.id
}
# Controller Ignition configs
data "ct_config" "controller-ignitions" {
count = var.controller_count
content = data.template_file.controller-configs.*.rendered[count.index]
strict = true
snippets = var.controller_snippets
}
# Controller Fedora CoreOS configs
data "template_file" "controller-configs" {
# Fedora CoreOS controllers
data "ct_config" "controllers" {
count = var.controller_count
template = file("${path.module}/fcc/controller.yaml")
vars = {
content = templatefile("${path.module}/butane/controller.yaml", {
# Cannot use cyclic dependencies on controllers or their DNS records
etcd_name = "etcd${count.index}"
etcd_domain = "${var.cluster_name}-etcd${count.index}.${var.dns_zone}"
# etcd0=https://cluster-etcd0.example.com,etcd1=https://cluster-etcd1.example.com,...
etcd_initial_cluster = join(",", data.template_file.etcds.*.rendered)
etcd_initial_cluster = join(",", [
for i in range(var.controller_count) : "etcd${i}=https://${var.cluster_name}-etcd${i}.${var.dns_zone}:2380"
])
kubeconfig = indent(10, module.bootstrap.kubeconfig-kubelet)
ssh_authorized_key = var.ssh_authorized_key
cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
cluster_domain_suffix = var.cluster_domain_suffix
}
})
strict = true
snippets = var.controller_snippets
}
data "template_file" "etcds" {
count = var.controller_count
template = "etcd$${index}=https://$${cluster_name}-etcd$${index}.$${dns_zone}:2380"
vars = {
index = count.index
cluster_name = var.cluster_name
dns_zone = var.dns_zone
}
}

View File

@ -53,53 +53,45 @@ resource "azurerm_lb" "cluster" {
}
resource "azurerm_lb_rule" "apiserver" {
resource_group_name = azurerm_resource_group.cluster.name
name = "apiserver"
loadbalancer_id = azurerm_lb.cluster.id
frontend_ip_configuration_name = "apiserver"
protocol = "Tcp"
frontend_port = 6443
backend_port = 6443
backend_address_pool_id = azurerm_lb_backend_address_pool.controller.id
probe_id = azurerm_lb_probe.apiserver.id
protocol = "Tcp"
frontend_port = 6443
backend_port = 6443
backend_address_pool_ids = [azurerm_lb_backend_address_pool.controller.id]
probe_id = azurerm_lb_probe.apiserver.id
}
resource "azurerm_lb_rule" "ingress-http" {
resource_group_name = azurerm_resource_group.cluster.name
name = "ingress-http"
loadbalancer_id = azurerm_lb.cluster.id
frontend_ip_configuration_name = "ingress"
disable_outbound_snat = true
protocol = "Tcp"
frontend_port = 80
backend_port = 80
backend_address_pool_id = azurerm_lb_backend_address_pool.worker.id
probe_id = azurerm_lb_probe.ingress.id
protocol = "Tcp"
frontend_port = 80
backend_port = 80
backend_address_pool_ids = [azurerm_lb_backend_address_pool.worker.id]
probe_id = azurerm_lb_probe.ingress.id
}
resource "azurerm_lb_rule" "ingress-https" {
resource_group_name = azurerm_resource_group.cluster.name
name = "ingress-https"
loadbalancer_id = azurerm_lb.cluster.id
frontend_ip_configuration_name = "ingress"
disable_outbound_snat = true
protocol = "Tcp"
frontend_port = 443
backend_port = 443
backend_address_pool_id = azurerm_lb_backend_address_pool.worker.id
probe_id = azurerm_lb_probe.ingress.id
protocol = "Tcp"
frontend_port = 443
backend_port = 443
backend_address_pool_ids = [azurerm_lb_backend_address_pool.worker.id]
probe_id = azurerm_lb_probe.ingress.id
}
# Worker outbound TCP/UDP SNAT
resource "azurerm_lb_outbound_rule" "worker-outbound" {
resource_group_name = azurerm_resource_group.cluster.name
name = "worker"
loadbalancer_id = azurerm_lb.cluster.id
frontend_ip_configuration {
@ -112,16 +104,12 @@ resource "azurerm_lb_outbound_rule" "worker-outbound" {
# Address pool of controllers
resource "azurerm_lb_backend_address_pool" "controller" {
resource_group_name = azurerm_resource_group.cluster.name
name = "controller"
loadbalancer_id = azurerm_lb.cluster.id
}
# Address pool of workers
resource "azurerm_lb_backend_address_pool" "worker" {
resource_group_name = azurerm_resource_group.cluster.name
name = "worker"
loadbalancer_id = azurerm_lb.cluster.id
}
@ -130,8 +118,6 @@ resource "azurerm_lb_backend_address_pool" "worker" {
# TCP health check for apiserver
resource "azurerm_lb_probe" "apiserver" {
resource_group_name = azurerm_resource_group.cluster.name
name = "apiserver"
loadbalancer_id = azurerm_lb.cluster.id
protocol = "Tcp"
@ -145,8 +131,6 @@ resource "azurerm_lb_probe" "apiserver" {
# HTTP health check for ingress
resource "azurerm_lb_probe" "ingress" {
resource_group_name = azurerm_resource_group.cluster.name
name = "ingress"
loadbalancer_id = azurerm_lb.cluster.id
protocol = "Http"

View File

@ -41,4 +41,3 @@ resource "azurerm_subnet_network_security_group_association" "worker" {
subnet_id = azurerm_subnet.worker.id
network_security_group_id = azurerm_network_security_group.worker.id
}

View File

@ -1,5 +1,6 @@
output "kubeconfig-admin" {
value = module.bootstrap.kubeconfig-admin
value = module.bootstrap.kubeconfig-admin
sensitive = true
}
# Outputs for Kubernetes Ingress
@ -32,7 +33,8 @@ output "security_group_id" {
}
output "kubeconfig" {
value = module.bootstrap.kubeconfig-kubelet
value = module.bootstrap.kubeconfig-kubelet
sensitive = true
}
# Outputs for custom firewalling
@ -41,9 +43,9 @@ output "worker_security_group_name" {
value = azurerm_network_security_group.worker.name
}
output "worker_address_prefix" {
description = "Worker network subnet CIDR address (for source/destination)"
value = azurerm_subnet.worker.address_prefix
output "worker_address_prefixes" {
description = "Worker network subnet CIDR addresses (for source/destination)"
value = azurerm_subnet.worker.address_prefixes
}
# Outputs for custom load balancing
@ -57,3 +59,11 @@ output "backend_address_pool_id" {
description = "ID of the worker backend address pool"
value = azurerm_lb_backend_address_pool.worker.id
}
# Outputs for debug
output "assets_dist" {
value = module.bootstrap.assets_dist
sensitive = true
}

View File

@ -10,171 +10,171 @@ resource "azurerm_network_security_group" "controller" {
resource "azurerm_network_security_rule" "controller-icmp" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-icmp"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "1995"
access = "Allow"
direction = "Inbound"
protocol = "Icmp"
source_port_range = "*"
destination_port_range = "*"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-icmp"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "1995"
access = "Allow"
direction = "Inbound"
protocol = "Icmp"
source_port_range = "*"
destination_port_range = "*"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
resource "azurerm_network_security_rule" "controller-ssh" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-ssh"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2000"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "22"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-ssh"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2000"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "22"
source_address_prefix = "*"
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
resource "azurerm_network_security_rule" "controller-etcd" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-etcd"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2005"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "2379-2380"
source_address_prefix = azurerm_subnet.controller.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-etcd"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2005"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "2379-2380"
source_address_prefixes = azurerm_subnet.controller.address_prefixes
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
# Allow Prometheus to scrape etcd metrics
resource "azurerm_network_security_rule" "controller-etcd-metrics" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-etcd-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2010"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "2381"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-etcd-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2010"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "2381"
source_address_prefixes = azurerm_subnet.worker.address_prefixes
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
# Allow Prometheus to scrape kube-proxy metrics
resource "azurerm_network_security_rule" "controller-kube-proxy" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kube-proxy-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2011"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10249"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-kube-proxy-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2011"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10249"
source_address_prefixes = azurerm_subnet.worker.address_prefixes
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
# Allow Prometheus to scrape kube-scheduler and kube-controller-manager metrics
resource "azurerm_network_security_rule" "controller-kube-metrics" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kube-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2012"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10251-10252"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-kube-metrics"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2012"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10257-10259"
source_address_prefixes = azurerm_subnet.worker.address_prefixes
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
resource "azurerm_network_security_rule" "controller-apiserver" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-apiserver"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2015"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "6443"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-apiserver"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2015"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "6443"
source_address_prefix = "*"
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
resource "azurerm_network_security_rule" "controller-cilium-health" {
resource_group_name = azurerm_resource_group.cluster.name
count = var.networking == "cilium" ? 1 : 0
name = "allow-cilium-health"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2019"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "4240"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-cilium-health"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2019"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "4240"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
resource "azurerm_network_security_rule" "controller-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-vxlan"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2020"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "4789"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-vxlan"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2020"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "4789"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
resource "azurerm_network_security_rule" "controller-linux-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-linux-vxlan"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2021"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "8472"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-linux-vxlan"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2021"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "8472"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
# Allow Prometheus to scrape node-exporter daemonset
resource "azurerm_network_security_rule" "controller-node-exporter" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-node-exporter"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2025"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "9100"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.controller.address_prefix
name = "allow-node-exporter"
network_security_group_name = azurerm_network_security_group.controller.name
priority = "2025"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "9100"
source_address_prefixes = azurerm_subnet.worker.address_prefixes
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
# Allow apiserver to access kubelet's for exec, log, port-forward
@ -191,8 +191,8 @@ resource "azurerm_network_security_rule" "controller-kubelet" {
destination_port_range = "10250"
# allow Prometheus to scrape kubelet metrics too
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.controller.address_prefix
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.controller.address_prefixes
}
# Override Azure AllowVNetInBound and AllowAzureLoadBalancerInBound
@ -240,139 +240,139 @@ resource "azurerm_network_security_group" "worker" {
resource "azurerm_network_security_rule" "worker-icmp" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-icmp"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "1995"
access = "Allow"
direction = "Inbound"
protocol = "Icmp"
source_port_range = "*"
destination_port_range = "*"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-icmp"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "1995"
access = "Allow"
direction = "Inbound"
protocol = "Icmp"
source_port_range = "*"
destination_port_range = "*"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
resource "azurerm_network_security_rule" "worker-ssh" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-ssh"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2000"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "22"
source_address_prefix = azurerm_subnet.controller.address_prefix
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-ssh"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2000"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "22"
source_address_prefixes = azurerm_subnet.controller.address_prefixes
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
resource "azurerm_network_security_rule" "worker-http" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-http"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2005"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "80"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-http"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2005"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "80"
source_address_prefix = "*"
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
resource "azurerm_network_security_rule" "worker-https" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-https"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2010"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "443"
source_address_prefix = "*"
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-https"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2010"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "443"
source_address_prefix = "*"
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
resource "azurerm_network_security_rule" "worker-cilium-health" {
resource_group_name = azurerm_resource_group.cluster.name
count = var.networking == "cilium" ? 1 : 0
name = "allow-cilium-health"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2014"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "4240"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-cilium-health"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2014"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "4240"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
resource "azurerm_network_security_rule" "worker-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-vxlan"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2015"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "4789"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-vxlan"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2015"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "4789"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
resource "azurerm_network_security_rule" "worker-linux-vxlan" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-linux-vxlan"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2016"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "8472"
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-linux-vxlan"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2016"
access = "Allow"
direction = "Inbound"
protocol = "Udp"
source_port_range = "*"
destination_port_range = "8472"
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
# Allow Prometheus to scrape node-exporter daemonset
resource "azurerm_network_security_rule" "worker-node-exporter" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-node-exporter"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2020"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "9100"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-node-exporter"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2020"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "9100"
source_address_prefixes = azurerm_subnet.worker.address_prefixes
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
# Allow Prometheus to scrape kube-proxy
resource "azurerm_network_security_rule" "worker-kube-proxy" {
resource_group_name = azurerm_resource_group.cluster.name
name = "allow-kube-proxy"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2024"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10249"
source_address_prefix = azurerm_subnet.worker.address_prefix
destination_address_prefix = azurerm_subnet.worker.address_prefix
name = "allow-kube-proxy"
network_security_group_name = azurerm_network_security_group.worker.name
priority = "2024"
access = "Allow"
direction = "Inbound"
protocol = "Tcp"
source_port_range = "*"
destination_port_range = "10249"
source_address_prefixes = azurerm_subnet.worker.address_prefixes
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
# Allow apiserver to access kubelet's for exec, log, port-forward
@ -389,8 +389,8 @@ resource "azurerm_network_security_rule" "worker-kubelet" {
destination_port_range = "10250"
# allow Prometheus to scrape kubelet metrics too
source_address_prefixes = [azurerm_subnet.controller.address_prefix, azurerm_subnet.worker.address_prefix]
destination_address_prefix = azurerm_subnet.worker.address_prefix
source_address_prefixes = concat(azurerm_subnet.controller.address_prefixes, azurerm_subnet.worker.address_prefixes)
destination_address_prefixes = azurerm_subnet.worker.address_prefixes
}
# Override Azure AllowVNetInBound and AllowAzureLoadBalancerInBound

View File

@ -25,7 +25,7 @@ resource "null_resource" "copy-controller-secrets" {
provisioner "file" {
content = join("\n", local.assets_bundle)
destination = "$HOME/assets"
destination = "/home/core/assets"
}
provisioner "remote-exec" {

View File

@ -43,7 +43,7 @@ variable "controller_type" {
variable "worker_type" {
type = string
description = "Machine type for workers (see `az vm list-skus --location centralus`)"
default = "Standard_DS1_v2"
default = "Standard_D2as_v5"
}
variable "os_image" {
@ -54,7 +54,7 @@ variable "os_image" {
variable "disk_size" {
type = number
description = "Size of the disk in GB"
default = 40
default = 30
}
variable "worker_priority" {
@ -65,13 +65,13 @@ variable "worker_priority" {
variable "controller_snippets" {
type = list(string)
description = "Controller Fedora CoreOS Config snippets"
description = "Controller Butane snippets"
default = []
}
variable "worker_snippets" {
type = list(string)
description = "Worker Fedora CoreOS Config snippets"
description = "Worker Butane snippets"
default = []
}
@ -84,8 +84,8 @@ variable "ssh_authorized_key" {
variable "networking" {
type = string
description = "Choice of networking provider (flannel or calico)"
default = "calico"
description = "Choice of networking provider (flannel, calico, or cilium)"
default = "cilium"
}
variable "host_cidr" {
@ -117,8 +117,8 @@ variable "enable_reporting" {
variable "enable_aggregation" {
type = bool
description = "Enable the Kubernetes Aggregation Layer (defaults to false)"
default = false
description = "Enable the Kubernetes Aggregation Layer"
default = true
}
variable "worker_node_labels" {
@ -129,15 +129,14 @@ variable "worker_node_labels" {
# unofficial, undocumented, unsupported
variable "asset_dir" {
type = string
description = "Absolute path to a directory where generated assets should be placed (contains secrets)"
default = ""
}
variable "cluster_domain_suffix" {
type = string
description = "Queries for domains with the suffix will be answered by coredns. Default is cluster.local (e.g. foo.default.svc.cluster.local) "
default = "cluster.local"
}
variable "daemonset_tolerations" {
type = list(string)
description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
default = []
}

View File

@ -1,12 +1,14 @@
# Terraform version and plugin versions
terraform {
required_version = "~> 0.12.6"
required_version = ">= 0.13.0, < 2.0.0"
required_providers {
azurerm = "~> 2.8"
ct = "~> 0.4"
template = "~> 2.1"
null = "~> 2.1"
azurerm = ">= 2.8, < 4.0"
null = ">= 2.1"
ct = {
source = "poseidon/ct"
version = "~> 0.9"
}
}
}

View File

@ -1,10 +1,12 @@
---
variant: fcos
version: 1.0.0
version: 1.4.0
systemd:
units:
- name: docker.service
- name: containerd.service
enabled: true
- name: docker.service
mask: true
- name: wait-for-dns.service
enabled: true
contents: |
@ -24,8 +26,8 @@ systemd:
Description=Kubelet (System Container)
Wants=rpc-statd.service
[Service]
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.18.6
ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.26.1
ExecStartPre=/bin/mkdir -p /etc/cni/net.d
ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
ExecStartPre=/bin/mkdir -p /opt/cni/bin
ExecStartPre=/bin/mkdir -p /var/lib/calico
@ -33,64 +35,43 @@ systemd:
ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
ExecStartPre=-/usr/bin/podman rm kubelet
ExecStart=/usr/bin/podman run --name kubelet \
--log-driver k8s-file \
--privileged \
--pid host \
--network host \
--volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
--volume /etc/kubernetes:/etc/kubernetes:ro,z \
--volume /usr/lib/os-release:/etc/os-release:ro \
--volume /etc/ssl/certs:/etc/ssl/certs:ro \
--volume /etc/machine-id:/etc/machine-id:ro \
--volume /lib/modules:/lib/modules:ro \
--volume /run:/run \
--volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
--volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
--volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
--volume /sys/fs/cgroup:/sys/fs/cgroup \
--volume /etc/selinux:/etc/selinux \
--volume /sys/fs/selinux:/sys/fs/selinux \
--volume /var/lib/calico:/var/lib/calico:ro \
--volume /var/lib/docker:/var/lib/docker \
--volume /var/lib/containerd:/var/lib/containerd \
--volume /var/lib/kubelet:/var/lib/kubelet:rshared,z \
--volume /var/log:/var/log \
--volume /var/run/lock:/var/run/lock:z \
--volume /opt/cni/bin:/opt/cni/bin:z \
$${KUBELET_IMAGE} \
--anonymous-auth=false \
--authentication-token-webhook \
--authorization-mode=Webhook \
--bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
--cgroup-driver=systemd \
--cgroups-per-qos=true \
--enforce-node-allocatable=pods \
--client-ca-file=/etc/kubernetes/ca.crt \
--cluster_dns=${cluster_dns_service_ip} \
--cluster_domain=${cluster_domain_suffix} \
--cni-conf-dir=/etc/kubernetes/cni/net.d \
--healthz-port=0 \
--config=/etc/kubernetes/kubelet.yaml \
--container-runtime-endpoint=unix:///run/containerd/containerd.sock \
--kubeconfig=/var/lib/kubelet/kubeconfig \
--network-plugin=cni \
--node-labels=node.kubernetes.io/node \
%{~ for label in split(",", node_labels) ~}
--node-labels=${label} \
%{~ endfor ~}
--pod-manifest-path=/etc/kubernetes/manifests \
--read-only-port=0 \
--rotate-certificates \
--volume-plugin-dir=/var/lib/kubelet/volumeplugins
%{~ for taint in split(",", node_taints) ~}
--register-with-taints=${taint} \
%{~ endfor ~}
--node-labels=node.kubernetes.io/node
ExecStop=-/usr/bin/podman stop kubelet
Delegate=yes
Restart=always
RestartSec=10
[Install]
WantedBy=multi-user.target
- name: delete-node.service
enabled: true
contents: |
[Unit]
Description=Delete Kubernetes node on shutdown
[Service]
Type=oneshot
RemainAfterExit=true
ExecStart=/bin/true
ExecStop=/bin/bash -c '/usr/bin/podman run --volume /etc/kubernetes:/etc/kubernetes:ro,z --entrypoint /usr/local/bin/kubectl quay.io/poseidon/kubelet:v1.18.6 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
[Install]
WantedBy=multi-user.target
storage:
directories:
- path: /etc/kubernetes
@ -100,6 +81,38 @@ storage:
contents:
inline: |
${kubeconfig}
- path: /etc/kubernetes/kubelet.yaml
mode: 0644
contents:
inline: |
apiVersion: kubelet.config.k8s.io/v1beta1
kind: KubeletConfiguration
authentication:
anonymous:
enabled: false
webhook:
enabled: true
x509:
clientCAFile: /etc/kubernetes/ca.crt
authorization:
mode: Webhook
cgroupDriver: systemd
clusterDNS:
- ${cluster_dns_service_ip}
clusterDomain: ${cluster_domain_suffix}
healthzPort: 0
rotateCertificates: true
shutdownGracePeriod: 45s
shutdownGracePeriodCriticalPods: 30s
staticPodPath: /etc/kubernetes/manifests
readOnlyPort: 0
resolvConf: /run/systemd/resolve/resolv.conf
volumePluginDir: /var/lib/kubelet/volumeplugins
- path: /etc/systemd/logind.conf.d/inhibitors.conf
contents:
inline: |
[Login]
InhibitDelayMaxSec=45s
- path: /etc/sysctl.d/max-user-watches.conf
contents:
inline: |
@ -109,6 +122,13 @@ storage:
inline: |
net.ipv4.conf.default.rp_filter=0
net.ipv4.conf.*.rp_filter=0
- path: /etc/systemd/network/50-flannel.link
contents:
inline: |
[Match]
OriginalName=flannel*
[Link]
MACAddressPolicy=none
- path: /etc/systemd/system.conf.d/accounting.conf
contents:
inline: |
@ -116,10 +136,28 @@ storage:
DefaultCPUAccounting=yes
DefaultMemoryAccounting=yes
DefaultBlockIOAccounting=yes
- path: /etc/containerd/config.toml
overwrite: true
contents:
inline: |
version = 2
root = "/var/lib/containerd"
state = "/run/containerd"
subreaper = true
oom_score = -999
[grpc]
address = "/run/containerd/containerd.sock"
uid = 0
gid = 0
[plugins."io.containerd.grpc.v1.cri"]
enable_selinux = true
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc]
runtime_type = "io.containerd.runc.v2"
[plugins."io.containerd.grpc.v1.cri".containerd.runtimes.runc.options]
SystemdCgroup = true
passwd:
users:
- name: core
ssh_authorized_keys:
- ${ssh_authorized_key}

View File

@ -41,7 +41,7 @@ variable "worker_count" {
variable "vm_type" {
type = string
description = "Machine type for instances (see `az vm list-skus --location centralus`)"
default = "Standard_DS1_v2"
default = "Standard_D2as_v5"
}
variable "os_image" {
@ -57,7 +57,7 @@ variable "priority" {
variable "snippets" {
type = list(string)
description = "Fedora CoreOS Config snippets"
description = "Butane snippets"
default = []
}
@ -88,6 +88,12 @@ variable "node_labels" {
default = []
}
variable "node_taints" {
type = list(string)
description = "List of initial node taints"
default = []
}
# unofficial, undocumented, unsupported
variable "cluster_domain_suffix" {

Some files were not shown because too many files have changed in this diff Show More