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

.github/ISSUE_TEMPLATE.md

@@ -1,33 +0,0 @@
-<!-- Fill in either the 'Bug' or 'Feature Request' section -->
-
-## Bug
-
-### Environment
-
-* Platform: aws, azure, bare-metal, google-cloud, digital-ocean
-* OS: container-linux, flatcar-linux
-* Release: Typhoon version or Git SHA (reporting latest is **not** helpful)
-* Terraform: `terraform version` (reporting latest is **not** helpful)
-* Plugins: Provider plugin versions (reporting latest is **not** helpful)
-
-### Problem
-
-Describe the problem.
-
-### Desired Behavior
-
-Describe the goal.
-
-### Steps to Reproduce
-
-Provide clear steps to reproduce the issue unless already covered.
-
-## Feature Request
-
-### Feature
-
-Describe the feature and what problem it solves.
-
-### Tradeoffs
-
-What are the pros and cons of this feature? How will it be exercised and maintained?

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,39 @@
+---
+name: Bug report
+about: Report a bug to improve the project
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+<!-- READ: Issues are used to receive focused bug reports from users and to track planned future enhancements by the authors. Topics like cluster operation, support, debugging help, advice, and Kubernetes concepts are out of scope and should not use issues-->
+
+**Description**
+
+A clear and concise description of what the bug is.
+
+**Steps to Reproduce**
+
+Provide clear steps to reproduce the bug.
+
+- [ ] Relevant error messages if appropriate (concise, not a dump of everything).
+- [ ] Explored using a vanilla cluster from the [tutorials](https://typhoon.psdn.io/#documentation). Ruled out [customizations](https://typhoon.psdn.io/advanced/customization/).
+
+**Expected behavior**
+
+A clear and concise description of what you expected to happen.
+
+**Environment**
+
+* Platform: aws, azure, bare-metal, google-cloud, digital-ocean
+* OS: fedora-coreos, flatcar-linux (include release version)
+* Release: Typhoon version or Git SHA (reporting latest is **not** helpful)
+* Terraform: `terraform version` (reporting latest is **not** helpful)
+* Plugins: Provider plugin versions (reporting latest is **not** helpful)
+
+**Possible Solution**
+
+<!-- Most bug reports should have some inkling about solutions. Otherwise, your report may be less of a bug and more of a support request (see top).-->
+
+Link to a PR or description.

.github/ISSUE_TEMPLATE/config.yml

@@ -0,0 +1,5 @@
+blank_issues_enabled: true
+contact_links:
+  - name: Security
+    url: https://typhoon.psdn.io/topics/security/
+    about: Report security vulnerabilities

.github/issue_template.md

@@ -0,0 +1,15 @@
+<!-- READ: Issues are used to receive focused bug reports from users and to track planned future enhancements by the authors. Topics like cluster operation, support, debugging help, advice, and Kubernetes concepts are out of scope and should not use issues-->
+
+## Enhancement
+
+### Overview
+
+One paragraph explanation of the enhancement.
+
+### Motivation
+
+Describe the motivation and what problem this solves.
+
+### Tradeoffs
+
+What are the pros and cons of this feature? How will it be exercised and maintained?

CHANGES.md

@@ -4,24 +4,410 @@ Notable changes between versions.
 
 ## Latest
 
+* 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)
+* Update Calico from v3.15.0 to [v3.15.1](https://docs.projectcalico.org/v3.15/release-notes/)
+* Update Cilium from v1.8.0 to [v1.8.1](https://github.com/cilium/cilium/releases/tag/v1.8.1)
+
+#### Addons
+
+* Update nginx-ingress from v0.33.0 to [v0.34.1](https://github.com/kubernetes/ingress-nginx/releases/tag/nginx-0.34.1)
+  * [ingress-nginx](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.34.0) will publish images only to gcr.io
+* Update Prometheus from v2.19.1 to [v2.19.2](https://github.com/prometheus/prometheus/releases/tag/v2.19.2)
+* Update Grafana from v7.0.4 to [v7.0.6](https://github.com/grafana/grafana/releases/tag/v7.0.6)
+
+## v1.18.5
+
+* Kubernetes [v1.18.5](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1185)
+* Add Cilium v1.8.0 as a (experimental) CNI provider option ([#760](https://github.com/poseidon/typhoon/pull/760))
+  * Set `networking` to "cilium" to enable
+* Update Calico from v3.14.1 to [v3.15.0](https://docs.projectcalico.org/v3.15/release-notes/)
+
+#### DigitalOcean
+
+* Isolate each cluster in an independent DigitalOcean VPC ([#776](https://github.com/poseidon/typhoon/pull/776))
+  * Create droplets in a VPC per cluster (matches Typhoon AWS, Azure, and GCP)
+  * Require `terraform-provider-digitalocean` v1.16.0+ (action required)
+  * Output `vpc_id` for use with an attached DigitalOcean [loadbalancer](https://github.com/poseidon/typhoon/blob/v1.18.5/docs/architecture/digitalocean.md#custom-load-balancer)
+
+### Fedora CoreOS
+
+#### Google Cloud
+
+* Promote Fedora CoreOS to stable
+* Remove `os_image` variable deprecated in v1.18.3 ([#777](https://github.com/poseidon/typhoon/pull/777))
+  * Use `os_stream` to select a Fedora CoreOS image stream
+
+### Flatcar Linux
+
+#### Azure
+
+* Allow using Flatcar Linux Edge by setting `os_image` to "flatcar-edge" ([#778](https://github.com/poseidon/typhoon/pull/778))
+
+#### Addons
+
+* Update Prometheus from v2.19.0 to [v2.19.1](https://github.com/prometheus/prometheus/releases/tag/v2.19.1)
+* Update Grafana from v7.0.3 to [v7.0.4](https://github.com/grafana/grafana/releases/tag/v7.0.4)
+
+## v1.18.4
+
+* Kubernetes [v1.18.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1184)
+* Update Kubelet image publishing ([#749](https://github.com/poseidon/typhoon/pull/749))
+  * Build Kubelet images internally and publish to Quay and Dockerhub
+    * [quay.io/poseidon/kubelet](https://quay.io/repository/poseidon/kubelet) (official)
+    * [docker.io/psdn/kubelet](https://hub.docker.com/r/psdn/kubelet) (fallback)
+  * Continue offering automated image builds with an alternate tag strategy (see [docs](https://typhoon.psdn.io/topics/security/#container-images))
+  * [Document](https://typhoon.psdn.io/advanced/customization/#kubelet) use of alternate Kubelet images during registry incidents
+* Update Calico from v3.14.0 to [v3.14.1](https://docs.projectcalico.org/v3.14/release-notes/)
+  * Fix [CVE-2020-13597](https://github.com/kubernetes/kubernetes/issues/91507)
+* Rename controller NoSchedule taint from `node-role.kubernetes.io/master` to `node-role.kubernetes.io/controller` ([#764](https://github.com/poseidon/typhoon/pull/764))
+  * Tolerate the new taint name for workloads that may run on controller nodes
+* Remove node label `node.kubernetes.io/master` from controller nodes ([#764](https://github.com/poseidon/typhoon/pull/764))
+  * Use `node.kubernetes.io/controller` (present since v1.9.5, [#160](https://github.com/poseidon/typhoon/pull/160)) to node select controllers
+* Remove unused Kubelet `-lock-file` and `-exit-on-lock-contention` ([#758](https://github.com/poseidon/typhoon/pull/758))
+
+### Fedora CoreOS
+
+#### Azure
+
+* Use `strict` Fedora CoreOS Config (FCC) snippet parsing ([#755](https://github.com/poseidon/typhoon/pull/755))
+* Reduce Calico vxlan interface MTU to maintain performance ([#767](https://github.com/poseidon/typhoon/pull/766))
+
+#### AWS
+
+* Fix Kubelet service race with hostname update ([#766](https://github.com/poseidon/typhoon/pull/766))
+  * Wait for a hostname to avoid Kubelet trying to register as `localhost`
+
+### Flatcar Linux
+
+* Use `strict` Container Linux Config (CLC) snippet parsing ([#755](https://github.com/poseidon/typhoon/pull/755))
+  * Require `terraform-provider-ct` v0.4+, recommend v0.5+ (**action required**)
+
+### Addons
+
+* Update nginx-ingress from v0.32.0 to [v0.33.0](https://github.com/kubernetes/ingress-nginx/releases/tag/nginx-0.33.0)
+* Update Prometheus from v2.18.1 to [v2.19.0](https://github.com/prometheus/prometheus/releases/tag/v2.19.0)
+* Update node-exporter from v1.0.0-rc.1 to [v1.0.1](https://github.com/prometheus/node_exporter/releases/tag/v1.0.1)
+* Update kube-state-metrics from v1.9.6 to v1.9.7
+* Update Grafana from v7.0.0 to v7.0.3
+
+## v1.18.3
+
+* Kubernetes [v1.18.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1183)
+* Use Kubelet [TLS bootstrap](https://kubernetes.io/docs/reference/command-line-tools-reference/kubelet-tls-bootstrapping/) with bootstrap token authentication ([#713](https://github.com/poseidon/typhoon/pull/713))
+  * Enable Node [Authorization](https://kubernetes.io/docs/reference/access-authn-authz/node/) and [NodeRestriction](https://kubernetes.io/docs/reference/access-authn-authz/admission-controllers/#noderestriction) to reduce authorization scope
+  * Renew Kubelet certificates every 72 hours
+* Update etcd from v3.4.7 to [v3.4.9](https://github.com/etcd-io/etcd/releases/tag/v3.4.9)
+* Update Calico from v3.13.1 to [v3.14.0](https://docs.projectcalico.org/v3.14/release-notes/)
+* Add CoreDNS node affinity preference for controller nodes ([#188](https://github.com/poseidon/terraform-render-bootstrap/pull/188))
+* Deprecate CoreOS Container Linux support (no OS [updates](https://coreos.com/os/eol/) after May 2020)
+  * Use a `fedora-coreos` module for Fedora CoreOS
+  * Use a `container-linux` module for Flatcar Linux
+
+### AWS
+
+* Fix Terraform plan error when `controller_count` exceeds AWS zones (e.g. 5 controllers) ([#714](https://github.com/poseidon/typhoon/pull/714))
+  * Regressed in v1.17.1 ([#605](https://github.com/poseidon/typhoon/pull/605))
+
+### Azure
+
+* Update Azure subnets to set `address_prefixes` list ([#730](https://github.com/poseidon/typhoon/pull/730))
+  * Fix warning that `address_prefix` is deprecated
+  * Require `terraform-provider-azurerm` v2.8.0+ (action required)
+
+### DigitalOcean
+
+* Promote DigitalOcean to beta on both Fedora CoreOS and Flatcar Linux
+
+### Fedora CoreOS
+
+* Fix Calico `install-cni` crashloop on Pod restarts ([#724](https://github.com/poseidon/typhoon/pull/724))
+  * SELinux enforcement requires consistent file context MCS level
+  * Restarting a node resolved the issue as a previous workaround
+
+#### AWS
+
+* Support Fedora CoreOS [image streams](https://docs.fedoraproject.org/en-US/fedora-coreos/update-streams/) ([#727](https://github.com/poseidon/typhoon/pull/727))
+  * Add `os_stream` variable to set the stream to `stable` (default), `testing`, or `next`
+  * Remove unused `os_image` variable
+
+#### Google
+
+* Support Fedora CoreOS [image streams](https://docs.fedoraproject.org/en-US/fedora-coreos/update-streams/) ([#723](https://github.com/poseidon/typhoon/pull/723))
+  * Add `os_stream` variable to set the stream to `stable` (default), `testing`, or `next`
+  * Deprecate `os_image` variable. Manual image uploads are no longer needed
+
+### Flatcar Linux
+
+#### Azure
+
+* Use the Flatcar Linux Azure Marketplace image
+  * Restore [#664](https://github.com/poseidon/typhoon/pull/664) (reverted in [#707](https://github.com/poseidon/typhoon/pull/707)) but use Flatcar Linux new free offer (not byol)
+* Change `os_image` to use a `flatcar-stable` default
+
+#### Google
+
+* Promote Flatcar Linux to beta
+
+### Addons
+
+* Update nginx-ingress from v0.30.0 to [v0.32.0](https://github.com/kubernetes/ingress-nginx/releases/tag/nginx-0.32.0)
+  * Add support for [IngressClass](https://kubernetes.io/docs/concepts/services-networking/ingress/#ingress-class)
+* Update Prometheus from v2.17.1 to v2.18.1
+  * Update kube-state-metrics from v1.9.5 to [v1.9.6](https://github.com/kubernetes/kube-state-metrics/releases/tag/v1.9.6)
+  * Update node-exporter from v1.0.0-rc.0 to [v1.0.0-rc.1](https://github.com/prometheus/node_exporter/releases/tag/v1.0.0-rc.1)
+* Update Grafana from v6.7.2 to [v7.0.0](https://grafana.com/docs/grafana/latest/guides/whats-new-in-v7-0/)
+
+## v1.18.2
+
+* Kubernetes [v1.18.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1182)
+* Choose Fedora CoreOS or Flatcar Linux (**action required**)
+  * Use a `fedora-coreos` module for Fedora CoreOS
+  * Use a `container-linux` module for Flatcar Linux
+* Change Container Linux modules' defaults from CoreOS Container Linux to [Flatcar Container Linux](https://typhoon.psdn.io/architecture/operating-systems/) ([#702](https://github.com/poseidon/typhoon/pull/702))
+  * CoreOS Container Linux [won't receive updates](https://coreos.com/os/eol/) after May 2020
+
+### Fedora CoreOS
+
+* Fix bootstrap race condition from SELinux unshared content label ([#708](https://github.com/poseidon/typhoon/pull/708))
+
+#### Azure
+
+* Add support for Fedora CoreOS ([#704](https://github.com/poseidon/typhoon/pull/704))
+
+#### DigitalOcean
+
+* Fix race condition creating firewall allow rules ([#709](https://github.com/poseidon/typhoon/pull/709))
+
+### Flatcar Linux
+
+#### AWS
+
+* Change `os_image` default from `coreos-stable` to `flatcar-stable` ([#702](https://github.com/poseidon/typhoon/pull/702))
+
+#### Azure
+
+* Change `os_image` to be required. Recommend uploading a Flatcar Linux image (**action required**) ([#702](https://github.com/poseidon/typhoon/pull/702))
+* Disable Flatcar Linux Azure Marketplace image [support](https://github.com/poseidon/typhoon/pull/664) (**breaking**, [#707](https://github.com/poseidon/typhoon/pull/707))
+  * Revert to manual uploading until marketplace issue is closed ([#703](https://github.com/poseidon/typhoon/issues/703))
+
+#### Bare-Metal
+
+* Recommend changing [os_channel](https://typhoon.psdn.io/cl/bare-metal/#required) from `coreos-stable` to `flatcar-stable`
+
+#### Google
+
+* Change `os_image` to be required. Recommend uploading a Flatcar Linux image (**action required**) ([#702](https://github.com/poseidon/typhoon/pull/702))
+
+#### DigitalOcean
+
+* Change `os_image` to be required. Recommend uploading a Flatcar Linux image (**action required**) ([#702](https://github.com/poseidon/typhoon/pull/702))
+* Fix race condition creating firewall allow rules ([#709](https://github.com/poseidon/typhoon/pull/709))
+
+## v1.18.1
+
+* Kubernetes [v1.18.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1181)
+* Choose Fedora CoreOS or Flatcar Linux (**action recommended**)
+  * Use a `fedora-coreos` module for Fedora CoreOS
+  * Use a `container-linux` module with OS set to Flatcar Linux
+* Update etcd from v3.4.5 to [v3.4.7](https://github.com/etcd-io/etcd/releases/tag/v3.4.7)
+* Change `kube-proxy` and `calico` or `flannel` to tolerate specific taints ([#682](https://github.com/poseidon/typhoon/pull/682))
+  * Tolerate master and not-ready taints, rather than tolerating all taints
+* Update flannel from v0.11.0 to v0.12.0 ([#690](https://github.com/poseidon/typhoon/pull/690))
+* Fix bootstrap when `networking` mode `flannel` (non-default) is chosen ([#689](https://github.com/poseidon/typhoon/pull/689))
+  * Regressed in v1.18.0 changes for Calico ([#675](https://github.com/poseidon/typhoon/pull/675))
+* Rename Container Linux `controller_clc_snippets` to `controller_snippets` for consistency ([#688](https://github.com/poseidon/typhoon/pull/688))
+* Rename Container Linux `worker_clc_snippets` to `worker_snippets` for consistency
+* Rename Container Linux `clc_snippets` (bare-metal) to `snippets` for consistency
+* Drop support for [gitRepo](https://kubernetes.io/docs/concepts/storage/volumes/#gitrepo) volumes ([kubelet#3](https://github.com/poseidon/kubelet/pull/3))
+
+#### Azure
+
+* Fix Azure worker UDP outbound connections ([#691](https://github.com/poseidon/typhoon/pull/691))
+  * Fix Azure worker clock sync timeouts
+
+#### DigitalOcean
+
+* Add support for Fedora CoreOS ([#699](https://github.com/poseidon/typhoon/pull/699))
+
+#### Addons
+
+* Refresh Prometheus rules/alerts and Grafana dashboards ([#692](https://github.com/poseidon/typhoon/pull/692))
+* Update Grafana from v6.7.1 to v6.7.2
+
+## v1.18.0
+
+* Kubernetes [v1.18.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1180)
+* Update etcd from v3.4.4 to [v3.4.5](https://github.com/etcd-io/etcd/releases/tag/v3.4.5)
+* Switch from upstream hyperkube image to individual images ([#669](https://github.com/poseidon/typhoon/pull/669))
+  * Use upstream k8s.gcr.io `kube-apiserver`, `kube-controller-manager`, `kube-scheduler`, and `kube-proxy` container images
+  * Use [poseidon/kubelet](https://github.com/poseidon/kubelet) to package the upstream Kubelet binary and dependencies as a container image (checksummed, automated build)
+  * Add [quay.io/poseidon/kubelet](https://quay.io/repository/poseidon/kubelet) as a Typhoon distributed artifact in the security policy
+  * Update base images from debian 9 to debian 10
+  * Background: Kubernetes will [stop releasing](https://github.com/kubernetes/kubernetes/pull/88676) the hyperkube container image and provide the Kubelet as a binary for packaging
+* Choose Fedora CoreOS or Flatcar Linux (**action recommended**)
+  * Use a `fedora-coreos` module for Fedora CoreOS
+  * Use a `container-linux` module with OS set for Flatcar Linux (varies, see docs)
+  * CoreOS Container Linux [won't receive updates](https://coreos.com/os/eol/) after May 2020
+* Add support for Fedora CoreOS snippets (`terraform-provider-ct` v0.5+) ([#686](https://github.com/poseidon/typhoon/pull/686))
+* Recommend updating `terraform-provider-ct` plugin from v0.4.0 to [v0.5.0](https://github.com/poseidon/terraform-provider-ct/releases/tag/v0.5.0)
+* Set Fedora CoreOS log driver back to the default `journald` ([#681](https://github.com/poseidon/typhoon/pull/681))
+* Deprecate `asset_dir` variable and remove docs ([#678](https://github.com/poseidon/typhoon/pull/678))
+* Deprecate support for [gitRepo](https://kubernetes.io/docs/concepts/storage/volumes/#gitrepo) volumes. A future release will drop support.
+
+#### AWS
+
+* Fix Fedora CoreOS AMI to filter for stable images ([#685](https://github.com/poseidon/typhoon/pull/685))
+  * Latest Fedora CoreOS `testing` or `bodhi-update` images could be chosen depending on the region
+
+#### Bare-Metal
+
+* Update Fedora CoreOS default `os_stream` from testing to stable
+
+#### Google Cloud
+
+* Known: Use of stale Fedora CoreOS image may require terraform re-apply during bootstrap ([#687](https://github.com/poseidon/typhoon/pull/687))
+
+#### DigitalOcean
+
+* Rename `image` variable to `os_image` for consistency ([#677](https://github.com/poseidon/typhoon/pull/677)) (action required)
+
+#### Addons
+
+* Update Prometheus from v2.16.0 to [v2.17.1](https://github.com/prometheus/prometheus/releases/tag/v2.17.1)
+* Update Grafana from v6.6.2 to [v6.7.1](https://github.com/grafana/grafana/releases/tag/v6.7.1)
+
+## v1.17.4
+
+* Kubernetes [v1.17.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.17.md#v1174)
+* Update etcd from v3.4.3 to [v3.4.4](https://github.com/etcd-io/etcd/releases/tag/v3.4.4)
+  * On Container Linux, fetch using the docker transport format ([#659](https://github.com/poseidon/typhoon/pull/659))
+* Update CoreDNS from v1.6.6 to v1.6.7 ([#648](https://github.com/poseidon/typhoon/pull/648))
+* Update Calico from v3.12.0 to [v3.13.1](https://docs.projectcalico.org/v3.13/release-notes/)
+
+#### AWS
+
+* Promote Fedora CoreOS to stable ([#668](https://github.com/poseidon/typhoon/pull/668))
+* Allow VPC route table extension via reference ([#654](https://github.com/poseidon/typhoon/pull/654))
+* Fix `worker_node_labels` on Fedora CoreOS ([#651](https://github.com/poseidon/typhoon/pull/651))
+* Fix automatic worker node delete on shutdown on Fedora CoreOS ([#657](https://github.com/poseidon/typhoon/pull/657))
+
+#### Azure
+
+* Upgrade to `terraform-provider-azurerm` [v2.0+](https://www.terraform.io/docs/providers/azurerm/guides/2.0-upgrade-guide.html) (action required)
+  * Change `worker_priority` from `Low` to `Spot` if used (action required)
+  * Switch to Azure's new Linux VM and Linux VM Scale Set resources
+  * Set controller's Azure disk caching to None
+  * Associate subnets (in addition to NICs) with security groups (aesthetic)
+* Add support for Flatcar Container Linux ([#664](https://github.com/poseidon/typhoon/pull/664))
+  * Requires accepting Flatcar Linux Azure Marketplace terms
+
+#### Bare-Metal
+
+* Add `worker_node_labels` map variable for per-worker node labels ([#663](https://github.com/poseidon/typhoon/pull/663))
+* Add `worker_node_taints` map variable for per-worker node taints ([#663](https://github.com/poseidon/typhoon/pull/663))
+
+#### DigitalOcean
+
+* Add support for Flatcar Container Linux ([#644](https://github.com/poseidon/typhoon/pull/644))
+
+#### Google Cloud
+
+* Promote Fedora CoreOS to beta ([#668](https://github.com/poseidon/typhoon/pull/668))
+* Fix `worker_node_labels` on Fedora CoreOS ([#651](https://github.com/poseidon/typhoon/pull/651))
+* Fix automatic worker node delete on shutdown on Fedora CoreOS ([#657](https://github.com/poseidon/typhoon/pull/657))
+
+#### Addons
+
+* Update nginx-ingress from v0.28.0 to [v0.30.0](https://github.com/kubernetes/ingress-nginx/releases/tag/nginx-0.30.0)
+* Update Prometheus from v2.15.2 to [v2.16.0](https://github.com/prometheus/prometheus/releases/tag/v2.16.0)
+  * Refresh Prometheus rules and alerts
+  * Add a BlackboxProbeFailure alert
+  * Update kube-state-metrics from v1.9.4 to v1.9.5
+  * Update node-exporter from v0.18.1 to [v1.0.0-rc.0](https://github.com/prometheus/node_exporter/releases/tag/v1.0.0-rc.0)
+* Update Grafana from v6.6.1 to v6.6.2
+  * Refresh Grafana dashboards
+* Remove Container Linux Update Operator (CLUO) addon example ([#667](https://github.com/poseidon/typhoon/pull/667))
+  * CLUO hasn't been in active use in our clusters and won't be relevant
+  beyond Container Linux. Requires patches for use on Kubernetes v1.16+
+
+## v1.17.3
+
 * Kubernetes [v1.17.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.17.md#v1173)
 * Update Calico from v3.11.2 to v3.12.0
 * Allow Fedora CoreOS clusters to pass CNCF conformance suite
   * Set Docker log driver to `json-file` as a workaround
+* Try Fedora CoreOS or Flatcar Linux alongside CoreOS [Container Linux](https://coreos.com/os/eol/) clusters (recommended)
 
 #### AWS
 
-* Promote Fedora CoreOS to beta
+* Promote Fedora CoreOS to beta ([#645](https://github.com/poseidon/typhoon/pull/645))
 
 #### Bare-Metal
 
-* Promote Fedora CoreOS to beta
+* Promote Fedora CoreOS to beta ([#645](https://github.com/poseidon/typhoon/pull/645))
 * Add Fedora CoreOS kernel arguments initrd and console ([#640](https://github.com/poseidon/typhoon/pull/640))
 
 #### Google Cloud
 
-* Add initial Terraform module for Fedora CoreOS ([#632](https://github.com/poseidon/typhoon/pull/632))
-* Add initial support for Flatcar Container Linux ([#639](https://github.com/poseidon/typhoon/pull/639))
+* Add Terraform module for Fedora CoreOS ([#632](https://github.com/poseidon/typhoon/pull/632))
+* Add support for Flatcar Container Linux ([#639](https://github.com/poseidon/typhoon/pull/639))
 
 #### Addons
 

README.md

@@ -11,9 +11,9 @@ 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 v1.17.3 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) 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/)
+* Kubernetes v1.19.0 (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
 * Ready for Ingress, Prometheus, Grafana, CSI, or other [addons](https://typhoon.psdn.io/addons/overview/)
 
@@ -21,35 +21,32 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 Typhoon provides a Terraform Module for each supported operating system and platform.
 
-| Platform      | Operating System | Terraform Module | Status |
-|---------------|------------------|------------------|--------|
-| AWS           | Container Linux  | [aws/container-linux/kubernetes](aws/container-linux/kubernetes) | stable |
-| Azure         | Container Linux  | [azure/container-linux/kubernetes](azure/container-linux/kubernetes) | alpha |
-| Bare-Metal    | Container Linux  | [bare-metal/container-linux/kubernetes](bare-metal/container-linux/kubernetes) | stable |
-| Digital Ocean | Container Linux  | [digital-ocean/container-linux/kubernetes](digital-ocean/container-linux/kubernetes) | beta |
-| Google Cloud  | Container Linux  | [google-cloud/container-linux/kubernetes](google-cloud/container-linux/kubernetes) | stable |
-
 Typhoon is available for [Fedora CoreOS](https://getfedora.org/coreos/).
 
 | Platform      | Operating System | Terraform Module | Status |
 |---------------|------------------|------------------|--------|
-| AWS           | Fedora CoreOS | [aws/fedora-coreos/kubernetes](aws/fedora-coreos/kubernetes) | beta |
+| 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 |
-| Google Cloud  | Fedora CoreOS | [google-cloud/fedora-coreos/kubernetes](google-cloud/fedora-coreos/kubernetes) | alpha |
+| 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 |
 
-Typhoon is available for [Flatcar Container Linux](https://www.flatcar-linux.org/releases/).
+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 |
-| Google Cloud  | Flatcar Linux  | [google-cloud/container-linux/kubernetes](google-cloud/container-linux/kubernetes) | alpha |
+| 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 |
 
 ## Documentation
 
 * [Docs](https://typhoon.psdn.io)
 * Architecture [concepts](https://typhoon.psdn.io/architecture/concepts/) and [operating systems](https://typhoon.psdn.io/architecture/operating-systems/)
-* Tutorials for [AWS](docs/cl/aws.md), [Azure](docs/cl/azure.md), [Bare-Metal](docs/cl/bare-metal.md), [Digital Ocean](docs/cl/digital-ocean.md), and [Google-Cloud](docs/cl/google-cloud.md)
+* Fedora CoreOS tutorials for [AWS](docs/fedora-coreos/aws.md), [Azure](docs/fedora-coreos/azure.md), [Bare-Metal](docs/fedora-coreos/bare-metal.md), [DigitalOcean](docs/fedora-coreos/digitalocean.md), and [Google Cloud](docs/fedora-coreos/google-cloud.md)
+* Flatcar Linux tutorials for [AWS](docs/flatcar-linux/aws.md), [Azure](docs/flatcar-linux/azure.md), [Bare-Metal](docs/flatcar-linux/bare-metal.md), [DigitalOcean](docs/flatcar-linux/digitalocean.md), and [Google Cloud](docs/flatcar-linux/google-cloud.md)
 
 ## Usage
 
@@ -57,7 +54,7 @@ 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/container-linux/kubernetes?ref=v1.17.3"
+  source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.19.0"
 
   # Google Cloud
   cluster_name  = "yavin"
@@ -96,9 +93,9 @@ 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   v1.17.3
-yavin-worker-jrbf.c.example-com.internal   <none>   Ready   5m   v1.17.3
-yavin-worker-mzdm.c.example-com.internal   <none>   Ready   5m   v1.17.3
+yavin-controller-0.c.example-com.internal  <none>   Ready   6m   v1.19.0
+yavin-worker-jrbf.c.example-com.internal   <none>   Ready   5m   v1.19.0
+yavin-worker-mzdm.c.example-com.internal   <none>   Ready   5m   v1.19.0
 ```
 
 List the pods.

addons/cluo/0-namespace.yaml

@@ -1,4 +0,0 @@
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: reboot-coordinator

addons/cluo/cluster-role-binding.yaml

@@ -1,12 +0,0 @@
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: reboot-coordinator
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: reboot-coordinator
-subjects:
-  - kind: ServiceAccount
-    namespace: reboot-coordinator
-    name: default

addons/cluo/cluster-role.yaml

@@ -1,45 +0,0 @@
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: reboot-coordinator
-rules:
-  - apiGroups:
-      - ""
-    resources:
-      - nodes
-    verbs:
-      - get
-      - list
-      - watch
-      - update
-  - apiGroups:
-      - ""
-    resources:
-      - configmaps
-    verbs:
-      - create
-      - get
-      - update
-      - list
-      - watch
-  - apiGroups:
-      - ""
-    resources:
-      - events
-    verbs:
-      - create
-      - watch
-  - apiGroups:
-      - ""
-    resources:
-      - pods
-    verbs:
-      - get
-      - list
-      - delete
-  - apiGroups:
-      - "extensions"
-    resources:
-      - daemonsets
-    verbs:
-      - get

addons/cluo/update-agent.yaml

@@ -1,68 +0,0 @@
-apiVersion: apps/v1
-kind: DaemonSet
-metadata:
-  name: container-linux-update-agent
-  namespace: reboot-coordinator
-spec:
-  updateStrategy:
-    type: RollingUpdate
-    rollingUpdate:
-      maxUnavailable: 1
-  selector:
-    matchLabels:
-      name: container-linux-update-agent
-  template:
-    metadata:
-      labels:
-        name: container-linux-update-agent
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
-    spec:
-      tolerations:
-        - key: node-role.kubernetes.io/master
-          operator: Exists
-          effect: NoSchedule
-      containers:
-        - name: update-agent
-          image: quay.io/coreos/container-linux-update-operator:v0.7.0
-          command:
-            - "/bin/update-agent"
-          env:
-            # read by update-agent as the node name to manage reboots for
-            - name: UPDATE_AGENT_NODE
-              valueFrom:
-                fieldRef:
-                  fieldPath: spec.nodeName
-            - name: POD_NAMESPACE
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.namespace
-          resources:
-            requests:
-              cpu: 10m
-              memory: 20Mi
-            limits:
-              cpu: 20m
-              memory: 40Mi
-          volumeMounts:
-            - mountPath: /var/run/dbus
-              name: var-run-dbus
-            - mountPath: /etc/coreos
-              name: etc-coreos
-            - mountPath: /usr/share/coreos
-              name: usr-share-coreos
-            - mountPath: /etc/os-release
-              name: etc-os-release
-      volumes:
-      - name: var-run-dbus
-        hostPath:
-          path: /var/run/dbus
-      - name: etc-coreos
-        hostPath:
-          path: /etc/coreos
-      - name: usr-share-coreos
-        hostPath:
-          path: /usr/share/coreos
-      - name: etc-os-release
-        hostPath:
-          path: /etc/os-release

addons/cluo/update-operator.yaml

@@ -1,39 +0,0 @@
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: container-linux-update-operator
-  namespace: reboot-coordinator
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      name: container-linux-update-operator
-  template:
-    metadata:
-      labels:
-        name: container-linux-update-operator
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
-    spec:
-      tolerations:
-      - key: node-role.kubernetes.io/master
-        operator: Exists
-        effect: NoSchedule
-      containers:
-        - name: update-operator
-          image: quay.io/coreos/container-linux-update-operator:v0.7.0
-          command:
-            - "/bin/update-operator"
-          env:
-            - name: POD_NAMESPACE
-              valueFrom:
-                fieldRef:
-                  fieldPath: metadata.namespace
-          resources:
-            requests:
-              cpu: 10m
-              memory: 20Mi
-            limits:
-              cpu: 20m
-              memory: 40Mi
-

addons/grafana/dashboards-coredns.yaml

@@ -72,7 +72,7 @@ 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}}",
@@ -163,7 +163,7 @@ 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}}",
@@ -254,7 +254,7 @@ 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}}",
@@ -463,7 +463,7 @@ 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}}",
@@ -790,7 +790,7 @@ 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}}",

addons/grafana/dashboards-k8s-nodes.yaml

@@ -21,7 +21,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -558,15 +558,15 @@ data:
               },
               "id": 8,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -649,15 +649,15 @@ data:
               },
               "id": 9,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -753,15 +753,15 @@ data:
               },
               "id": 10,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -857,15 +857,15 @@ data:
               },
               "id": 11,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -955,15 +955,15 @@ data:
               },
               "id": 12,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1066,17 +1066,17 @@ data:
               },
               "id": 13,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
-                "hideEmpty": "true",
-                "hideZero": "true",
+                "current": true,
+                "hideEmpty": true,
+                "hideZero": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1159,17 +1159,17 @@ data:
               },
               "id": 14,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
-                "hideEmpty": "true",
-                "hideZero": "true",
+                "current": true,
+                "hideEmpty": true,
+                "hideZero": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1265,17 +1265,17 @@ data:
               },
               "id": 15,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
-                "hideEmpty": "true",
-                "hideZero": "true",
+                "current": true,
+                "hideEmpty": true,
+                "hideZero": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
                 "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1371,15 +1371,15 @@ data:
               },
               "id": 16,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1462,15 +1462,15 @@ data:
               },
               "id": 17,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1567,15 +1567,15 @@ data:
               },
               "id": 18,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1658,15 +1658,15 @@ data:
               },
               "id": 19,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1762,15 +1762,15 @@ data:
               },
               "id": 20,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1991,15 +1991,15 @@ data:
               },
               "id": 22,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -2373,8 +2373,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2427,7 +2427,7 @@ data:
             "options": [
 
             ],
-            "query": "label_values(kubelet_runtime_operations{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
+            "query": "label_values(kubelet_runtime_operations_total{cluster=\"$cluster\", job=\"kubelet\"}, instance)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -2496,7 +2496,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -2691,15 +2691,15 @@ data:
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -2886,15 +2886,15 @@ data:
               },
               "id": 6,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -3206,15 +3206,15 @@ data:
               },
               "id": 9,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -3588,8 +3588,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,

addons/grafana/dashboards-k8s-resources-1.yaml

@@ -59,7 +59,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster=\"$cluster\"}[1m]))",
+                  "expr": "1 - avg(rate(node_cpu_seconds_total{mode=\"idle\", cluster=\"$cluster\"}[$__interval]))",
                   "format": "time_series",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1561,7 +1561,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1570,7 +1570,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1579,7 +1579,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1588,7 +1588,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1597,7 +1597,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1606,7 +1606,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1706,7 +1706,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -1804,7 +1804,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -1902,7 +1902,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2000,7 +2000,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2098,7 +2098,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2196,7 +2196,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2294,7 +2294,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2392,7 +2392,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2458,8 +2458,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2501,37 +2501,29 @@ data:
           },
           {
             "allValue": null,
-            "auto": false,
-            "auto_count": 30,
-            "auto_min": "10s",
             "current": {
-              "text": "5m",
-              "value": "5m"
+              "text": "",
+              "value": ""
             },
-            "datasource": "prometheus",
+            "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
             "label": null,
             "multi": false,
-            "name": "interval",
+            "name": "cluster",
             "options": [
-              {
-                "selected": true,
-                "text": "4h",
-                "value": "4h"
-              }
+
             ],
-            "query": "4h",
+            "query": "label_values(node_cpu_seconds_total, cluster)",
             "refresh": 2,
             "regex": "",
-            "skipUrlSync": false,
             "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
             ],
             "tagsQuery": "",
-            "type": "interval",
+            "type": "query",
             "useTags": false
           }
         ]
@@ -2586,6 +2578,354 @@ data:
       ],
       "refresh": "10s",
       "rows": [
+        {
+          "collapse": false,
+          "height": "100px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "format": "percentunit",
+              "id": 1,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"})",
+                  "format": "time_series",
+                  "instant": true,
+                  "intervalFactor": 2,
+                  "refId": "A"
+                }
+              ],
+              "thresholds": "70,80",
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "CPU Utilisation (from requests)",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "singlestat",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": 0,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": false
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "format": "percentunit",
+              "id": 2,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "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\"})",
+                  "format": "time_series",
+                  "instant": true,
+                  "intervalFactor": 2,
+                  "refId": "A"
+                }
+              ],
+              "thresholds": "70,80",
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "CPU Utilisation (from limits)",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "singlestat",
+              "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": "$datasource",
+              "fill": 1,
+              "format": "percentunit",
+              "id": 3,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"})",
+                  "format": "time_series",
+                  "instant": true,
+                  "intervalFactor": 2,
+                  "refId": "A"
+                }
+              ],
+              "thresholds": "70,80",
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Memory Utilization (from requests)",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "singlestat",
+              "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": "$datasource",
+              "fill": 1,
+              "format": "percentunit",
+              "id": 4,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"})",
+                  "format": "time_series",
+                  "instant": true,
+                  "intervalFactor": 2,
+                  "refId": "A"
+                }
+              ],
+              "thresholds": "70,80",
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Memory Utilisation (from limits)",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "singlestat",
+              "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": false,
+          "title": "Headlines",
+          "titleSize": "h6"
+        },
         {
           "collapse": false,
           "height": "250px",
@@ -2599,7 +2939,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 1,
+              "id": 5,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2620,7 +2960,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -2634,6 +2993,22 @@ data:
                   "legendFormat": "{{pod}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - requests",
+                  "legendLink": null,
+                  "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -2697,7 +3072,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 2,
+              "id": 6,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2964,7 +3339,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 3,
+              "id": 7,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2985,7 +3360,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -2999,6 +3393,22 @@ data:
                   "legendFormat": "{{pod}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - requests",
+                  "legendLink": null,
+                  "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -3062,7 +3472,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 4,
+              "id": 8,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -3410,7 +3820,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 5,
+              "id": 9,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -3588,7 +3998,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3597,7 +4007,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3606,7 +4016,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3615,7 +4025,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3624,7 +4034,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3633,7 +4043,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3698,398 +4108,6 @@ data:
             {
               "aliasColors": {
 
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 10,
-              "id": 6,
-              "legend": {
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 0,
-              "links": [
-
-              ],
-              "nullPointMode": "null as zero",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": true,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{pod}}",
-                  "legendLink": null,
-                  "step": 10
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Receive Bandwidth",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "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": "Network",
-          "titleSize": "h6"
-        },
-        {
-          "collapse": false,
-          "height": "250px",
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 10,
-              "id": 7,
-              "legend": {
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 0,
-              "links": [
-
-              ],
-              "nullPointMode": "null as zero",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": true,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{pod}}",
-                  "legendLink": null,
-                  "step": 10
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Transmit Bandwidth",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "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": "Network",
-          "titleSize": "h6"
-        },
-        {
-          "collapse": false,
-          "height": "250px",
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 10,
-              "id": 8,
-              "legend": {
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 0,
-              "links": [
-
-              ],
-              "nullPointMode": "null as zero",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": true,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{pod}}",
-                  "legendLink": null,
-                  "step": 10
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Rate of Received Packets",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "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": "Network",
-          "titleSize": "h6"
-        },
-        {
-          "collapse": false,
-          "height": "250px",
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 10,
-              "id": 9,
-              "legend": {
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 0,
-              "links": [
-
-              ],
-              "nullPointMode": "null as zero",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": true,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{pod}}",
-                  "legendLink": null,
-                  "step": 10
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Rate of Transmitted Packets",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "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": "Network",
-          "titleSize": "h6"
-        },
-        {
-          "collapse": false,
-          "height": "250px",
-          "panels": [
-            {
-              "aliasColors": {
-
               },
               "bars": false,
               "dashLength": 10,
@@ -4125,7 +4143,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -4138,7 +4156,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Rate of Received Packets Dropped",
+              "title": "Receive Bandwidth",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -4223,7 +4241,399 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{pod}}",
+                  "legendLink": null,
+                  "step": 10
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Transmit Bandwidth",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "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": "Network",
+          "titleSize": "h6"
+        },
+        {
+          "collapse": false,
+          "height": "250px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 10,
+              "id": 12,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{pod}}",
+                  "legendLink": null,
+                  "step": 10
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Rate of Received Packets",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "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": "Network",
+          "titleSize": "h6"
+        },
+        {
+          "collapse": false,
+          "height": "250px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 10,
+              "id": 13,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{pod}}",
+                  "legendLink": null,
+                  "step": 10
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Rate of Transmitted Packets",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "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": "Network",
+          "titleSize": "h6"
+        },
+        {
+          "collapse": false,
+          "height": "250px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 10,
+              "id": 14,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{pod}}",
+                  "legendLink": null,
+                  "step": 10
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Rate of Received Packets Dropped",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "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": "Network",
+          "titleSize": "h6"
+        },
+        {
+          "collapse": false,
+          "height": "250px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 10,
+              "id": 15,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -4289,8 +4699,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -4306,13 +4716,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -4321,7 +4731,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -4333,13 +4743,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "namespace",
+            "label": null,
             "multi": false,
             "name": "namespace",
             "options": [
@@ -4348,48 +4758,13 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "auto": false,
-            "auto_count": 30,
-            "auto_min": "10s",
-            "current": {
-              "text": "5m",
-              "value": "5m"
-            },
-            "datasource": "prometheus",
-            "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",
+            "type": "query",
             "useTags": false
           }
         ]
@@ -5265,8 +5640,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -5282,13 +5657,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -5297,7 +5672,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -5309,13 +5684,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "node",
+            "label": null,
             "multi": false,
             "name": "node",
             "options": [
@@ -5324,7 +5699,7 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 

addons/grafana/dashboards-k8s-resources-2.yaml

@@ -50,7 +50,24 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "requests",
+                  "color": "#F2495C",
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": true,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "limits",
+                  "color": "#FF9830",
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": true,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -64,6 +81,22 @@ data:
                   "legendFormat": "{{container}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "sum(\n    kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "requests",
+                  "legendLink": null,
+                  "step": 10
+                },
+                {
+                  "expr": "sum(\n    kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -126,8 +159,113 @@ data:
               "dashLength": 10,
               "dashes": false,
               "datasource": "$datasource",
-              "fill": 1,
+              "fill": 10,
               "id": 2,
+              "legend": {
+                "avg": false,
+                "current": true,
+                "max": true,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{namespace=\"$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)",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{container}}",
+                  "legendLink": null,
+                  "step": 10
+                }
+              ],
+              "thresholds": [
+                {
+                  "colorMode": "critical",
+                  "fill": true,
+                  "line": true,
+                  "op": "gt",
+                  "value": 1,
+                  "yaxis": "left"
+                }
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "CPU Throttling",
+              "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": 1,
+                  "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": "CPU Throttling",
+          "titleSize": "h6"
+        },
+        {
+          "collapse": false,
+          "height": "250px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "id": 3,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -394,7 +532,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 3,
+              "id": 4,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -415,7 +553,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -423,26 +580,26 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{container}} (RSS)",
+                  "legendFormat": "{{container}}",
                   "legendLink": null,
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_cache{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
+                  "expr": "sum(\n    kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{container}} (Cache)",
+                  "legendFormat": "requests",
                   "legendLink": null,
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_swap{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
+                  "expr": "sum(\n    kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"})\n",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{container}} (Swap)",
+                  "legendFormat": "limits",
                   "legendLink": null,
                   "step": 10
                 }
@@ -508,7 +665,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 4,
+              "id": 5,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -850,104 +1007,6 @@ data:
             {
               "aliasColors": {
 
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 10,
-              "id": 5,
-              "legend": {
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 0,
-              "links": [
-
-              ],
-              "nullPointMode": "null as zero",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": true,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{pod}}",
-                  "legendLink": null,
-                  "step": 10
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Receive Bandwidth",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "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": "Network",
-          "titleSize": "h6"
-        },
-        {
-          "collapse": false,
-          "height": "250px",
-          "panels": [
-            {
-              "aliasColors": {
-
               },
               "bars": false,
               "dashLength": 10,
@@ -983,7 +1042,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -996,7 +1055,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Transmit Bandwidth",
+              "title": "Receive Bandwidth",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -1081,7 +1140,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1094,7 +1153,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Rate of Received Packets",
+              "title": "Transmit Bandwidth",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -1179,7 +1238,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1192,7 +1251,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Rate of Transmitted Packets",
+              "title": "Rate of Received Packets",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -1277,7 +1336,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1290,7 +1349,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Rate of Received Packets Dropped",
+              "title": "Rate of Transmitted Packets",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -1375,7 +1434,105 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{pod}}",
+                  "legendLink": null,
+                  "step": 10
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Rate of Received Packets Dropped",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "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": "Network",
+          "titleSize": "h6"
+        },
+        {
+          "collapse": false,
+          "height": "250px",
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 10,
+              "id": 11,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1441,8 +1598,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -1458,13 +1615,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -1473,7 +1630,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -1485,13 +1642,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "namespace",
+            "label": null,
             "multi": false,
             "name": "namespace",
             "options": [
@@ -1500,75 +1657,40 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-              "text": "prod",
-              "value": "prod"
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "pod",
-            "multi": false,
-            "name": "pod",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
-            "refresh": 1,
-            "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "auto": false,
-            "auto_count": 30,
-            "auto_min": "10s",
-            "current": {
-              "text": "5m",
-              "value": "5m"
-            },
-            "datasource": "prometheus",
-            "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",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {
+              "text": "",
+              "value": ""
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "pod",
+            "options": [
+
+            ],
+            "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=\"$namespace\"}, pod)",
+            "refresh": 2,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
             "useTags": false
           }
         ]
@@ -2544,7 +2666,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2553,7 +2675,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2562,7 +2684,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2571,7 +2693,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2580,7 +2702,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2589,7 +2711,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2689,7 +2811,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2787,7 +2909,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2885,7 +3007,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2983,7 +3105,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3081,7 +3203,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3179,7 +3301,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3277,7 +3399,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3375,7 +3497,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$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{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=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3441,8 +3563,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -3458,13 +3580,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -3473,7 +3595,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -3485,13 +3607,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "namespace",
+            "label": null,
             "multi": false,
             "name": "namespace",
             "options": [
@@ -3500,7 +3622,7 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -3512,13 +3634,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "workload",
+            "label": null,
             "multi": false,
             "name": "workload",
             "options": [
@@ -3527,7 +3649,7 @@ data:
             "query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -3539,13 +3661,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
-              "value": "prod"
+              "text": "",
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "type",
+            "label": null,
             "multi": false,
             "name": "type",
             "options": [
@@ -3554,48 +3676,13 @@ data:
             "query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "auto": false,
-            "auto_count": 30,
-            "auto_min": "10s",
-            "current": {
-              "text": "5m",
-              "value": "5m"
-            },
-            "datasource": "prometheus",
-            "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",
+            "type": "query",
             "useTags": false
           }
         ]
@@ -3684,7 +3771,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -3698,6 +3804,22 @@ data:
                   "legendFormat": "{{workload}} - {{workload_type}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.cpu\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - requests",
+                  "legendLink": null,
+                  "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -4094,7 +4216,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -4108,6 +4249,22 @@ data:
                   "legendFormat": "{{workload}} - {{workload_type}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"requests.memory\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - requests",
+                  "legendLink": null,
+                  "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$cluster\", namespace=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -4679,7 +4836,7 @@ 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{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",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4688,7 +4845,7 @@ 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{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",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4697,7 +4854,7 @@ 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{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",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4706,7 +4863,7 @@ 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{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",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4715,7 +4872,7 @@ 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{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",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4724,7 +4881,7 @@ 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{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",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4824,7 +4981,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -4922,7 +5079,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5020,7 +5177,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5118,7 +5275,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5216,7 +5373,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5314,7 +5471,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5412,7 +5569,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5510,7 +5667,7 @@ data:
               "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{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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5576,8 +5733,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -5590,95 +5747,6 @@ data:
             "regex": "",
             "type": "datasource"
           },
-          {
-            "allValue": null,
-            "current": {
-              "text": "prod",
-              "value": "prod"
-            },
-            "datasource": "$datasource",
-            "hide": 2,
-            "includeAll": false,
-            "label": "cluster",
-            "multi": false,
-            "name": "cluster",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_info, cluster)",
-            "refresh": 1,
-            "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-              "text": "prod",
-              "value": "prod"
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "namespace",
-            "multi": false,
-            "name": "namespace",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
-            "refresh": 1,
-            "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "auto": false,
-            "auto_count": 30,
-            "auto_min": "10s",
-            "current": {
-              "text": "5m",
-              "value": "5m"
-            },
-            "datasource": "prometheus",
-            "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
-          },
           {
             "allValue": null,
             "auto": false,
@@ -5706,6 +5774,60 @@ data:
             "tagValuesQuery": "",
             "tags": [
 
+            ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {
+              "text": "",
+              "value": ""
+            },
+            "datasource": "$datasource",
+            "hide": 2,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "cluster",
+            "options": [
+
+            ],
+            "query": "label_values(kube_pod_info, cluster)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {
+              "text": "",
+              "value": ""
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "namespace",
+            "options": [
+
+            ],
+            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
             ],
             "tagsQuery": "",
             "type": "query",

addons/grafana/dashboards-k8s.yaml

@@ -21,7 +21,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -88,7 +88,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "sum(up{job=\"apiserver\"})",
+                  "expr": "sum(up{job=\"apiserver\", cluster=\"$cluster\"})",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -155,28 +155,28 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"2..\", cluster=\"$cluster\"}[5m]))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "2xx",
                   "refId": "A"
                 },
                 {
-                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
+                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$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..\"}[5m]))",
+                  "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=~\"$instance\",code=~\"5..\"}[5m]))",
+                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"5..\", cluster=\"$cluster\"}[5m]))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "5xx",
@@ -237,15 +237,15 @@ data:
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -267,7 +267,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\"}[5m])) by (verb, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", verb!=\"WATCH\", cluster=\"$cluster\"}[5m])) by (verb, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}}",
@@ -371,7 +371,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\"}[5m])) by (instance, name)",
+                  "expr": "sum(rate(workqueue_adds_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{name}}",
@@ -462,7 +462,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\"}[5m])) by (instance, name)",
+                  "expr": "sum(rate(workqueue_depth{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{name}}",
@@ -523,15 +523,15 @@ data:
               },
               "id": 7,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -553,7 +553,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\"}[5m])) by (instance, name, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(workqueue_queue_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}[5m])) by (instance, name, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{name}}",
@@ -657,7 +657,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "etcd_helper_cache_entry_total{job=\"apiserver\", instance=~\"$instance\"}",
+                  "expr": "etcd_helper_cache_entry_total{job=\"apiserver\", instance=~\"$instance\", cluster=\"$cluster\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -748,14 +748,14 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(rate(etcd_helper_cache_hit_total{job=\"apiserver\",instance=~\"$instance\"}[5m])) by (intance)",
+                  "expr": "sum(rate(etcd_helper_cache_hit_total{job=\"apiserver\",instance=~\"$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\"}[5m])) by (instance)",
+                  "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",
@@ -846,14 +846,14 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_get_duration_seconds_bucket{job=\"apiserver\",instance=~\"$instance\"}[5m])) by (instance, le))",
+                  "expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_get_duration_seconds_bucket{job=\"apiserver\",instance=~\"$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\"}[5m])) by (instance, le))",
+                  "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",
@@ -957,7 +957,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\"}",
+                  "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -1048,7 +1048,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\"}[5m])",
+                  "expr": "rate(process_cpu_seconds_total{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}[5m])",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -1139,7 +1139,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "go_goroutines{job=\"apiserver\",instance=~\"$instance\"}",
+                  "expr": "go_goroutines{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -1205,8 +1205,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -1219,6 +1219,33 @@ data:
             "regex": "",
             "type": "datasource"
           },
+          {
+            "allValue": null,
+            "current": {
+              "text": "prod",
+              "value": "prod"
+            },
+            "datasource": "$datasource",
+            "hide": 2,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "cluster",
+            "options": [
+
+            ],
+            "query": "label_values(apiserver_request_total, cluster)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
           {
             "allValue": null,
             "current": {
@@ -1233,7 +1260,7 @@ data:
             "options": [
 
             ],
-            "query": "label_values(apiserver_request_total{job=\"apiserver\"}, instance)",
+            "query": "label_values(apiserver_request_total{job=\"apiserver\", cluster=\"$cluster\"}, instance)",
             "refresh": 2,
             "regex": "",
             "sort": 1,
@@ -1302,7 +1329,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -1406,15 +1433,15 @@ data:
               },
               "id": 3,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1510,15 +1537,15 @@ data:
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1614,15 +1641,15 @@ data:
               },
               "id": 5,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1934,15 +1961,15 @@ data:
               },
               "id": 8,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -2316,8 +2343,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2413,7 +2440,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -2815,8 +2842,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2943,664 +2970,6 @@ data:
       "uid": "919b92a8e8041bd567af9edab12c840c",
       "version": 0
     }
-  pods.json: |-
-    {
-      "__inputs": [
-
-      ],
-      "__requires": [
-
-      ],
-      "annotations": {
-        "list": [
-          {
-            "builtIn": 1,
-            "datasource": "$datasource",
-            "enable": true,
-            "expr": "time() == BOOL timestamp(rate(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[2m]) > 0)",
-            "hide": false,
-            "iconColor": "rgba(215, 44, 44, 1)",
-            "name": "Restarts",
-            "showIn": 0,
-            "tags": [
-              "restart"
-            ],
-            "type": "rows"
-          }
-        ]
-      },
-      "editable": false,
-      "gnetId": null,
-      "graphTooltip": 0,
-      "hideControls": false,
-      "id": null,
-      "links": [
-
-      ],
-      "refresh": "",
-      "rows": [
-        {
-          "collapse": false,
-          "collapsed": false,
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 2,
-              "legend": {
-                "alignAsTable": true,
-                "avg": true,
-                "current": true,
-                "max": false,
-                "min": false,
-                "rightSide": true,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 1,
-              "links": [
-
-              ],
-              "nullPointMode": "null",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "repeat": null,
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": false,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum by(container) (container_memory_usage_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Current: {{ container }}",
-                  "refId": "A"
-                },
-                {
-                  "expr": "sum by(container) (kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\", pod=\"$pod\", container=~\"$container\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Requested: {{ container }}",
-                  "refId": "B"
-                },
-                {
-                  "expr": "sum by(container) (kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"memory\", pod=\"$pod\", container=~\"$container\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Limit: {{ container }}",
-                  "refId": "C"
-                },
-                {
-                  "expr": "sum by(container) (container_memory_cache{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$pod\", container=~\"$container\", container!=\"POD\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Cache: {{ container }}",
-                  "refId": "D"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Memory Usage",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "value_type": "individual"
-              },
-              "type": "graph",
-              "xaxis": {
-                "buckets": null,
-                "mode": "time",
-                "name": null,
-                "show": true,
-                "values": [
-
-                ]
-              },
-              "yaxes": [
-                {
-                  "format": "bytes",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                },
-                {
-                  "format": "bytes",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                }
-              ]
-            }
-          ],
-          "repeat": null,
-          "repeatIteration": null,
-          "repeatRowId": null,
-          "showTitle": false,
-          "title": "Dashboard Row",
-          "titleSize": "h6",
-          "type": "row"
-        },
-        {
-          "collapse": false,
-          "collapsed": false,
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 3,
-              "legend": {
-                "alignAsTable": true,
-                "avg": true,
-                "current": true,
-                "max": false,
-                "min": false,
-                "rightSide": true,
-                "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 by (container) (irate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", image!=\"\", pod=\"$pod\", container=~\"$container\", container!=\"POD\"}[4m]))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Current: {{ container }}",
-                  "refId": "A"
-                },
-                {
-                  "expr": "sum by(container) (kube_pod_container_resource_requests{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\", pod=\"$pod\", container=~\"$container\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Requested: {{ container }}",
-                  "refId": "B"
-                },
-                {
-                  "expr": "sum by(container) (kube_pod_container_resource_limits{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", resource=\"cpu\", pod=\"$pod\", container=~\"$container\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Limit: {{ container }}",
-                  "refId": "C"
-                }
-              ],
-              "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
-                }
-              ]
-            }
-          ],
-          "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": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 4,
-              "legend": {
-                "alignAsTable": true,
-                "avg": true,
-                "current": true,
-                "max": false,
-                "min": false,
-                "rightSide": true,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 1,
-              "links": [
-
-              ],
-              "nullPointMode": "null",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "repeat": null,
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 12,
-              "stack": false,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sort_desc(sum by (pod) (irate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[4m])))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "RX: {{ pod }}",
-                  "refId": "A"
-                },
-                {
-                  "expr": "sort_desc(sum by (pod) (irate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}[4m])))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "TX: {{ pod }}",
-                  "refId": "B"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Network I/O",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "value_type": "individual"
-              },
-              "type": "graph",
-              "xaxis": {
-                "buckets": null,
-                "mode": "time",
-                "name": null,
-                "show": true,
-                "values": [
-
-                ]
-              },
-              "yaxes": [
-                {
-                  "format": "bytes",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                },
-                {
-                  "format": "bytes",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                }
-              ]
-            }
-          ],
-          "repeat": null,
-          "repeatIteration": null,
-          "repeatRowId": null,
-          "showTitle": false,
-          "title": "Dashboard Row",
-          "titleSize": "h6",
-          "type": "row"
-        },
-        {
-          "collapse": false,
-          "collapsed": false,
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 5,
-              "legend": {
-                "alignAsTable": true,
-                "avg": true,
-                "current": true,
-                "max": false,
-                "min": false,
-                "rightSide": true,
-                "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": "max by (container) (kube_pod_container_status_restarts_total{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container=~\"$container\"})",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "Restarts: {{ container }}",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Total Restarts Per Container",
-              "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
-                }
-              ]
-            }
-          ],
-          "repeat": null,
-          "repeatIteration": null,
-          "repeatRowId": null,
-          "showTitle": false,
-          "title": "Dashboard Row",
-          "titleSize": "h6",
-          "type": "row"
-        }
-      ],
-      "schemaVersion": 14,
-      "style": "dark",
-      "tags": [
-        "kubernetes-mixin"
-      ],
-      "templating": {
-        "list": [
-          {
-            "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
-            },
-            "hide": 0,
-            "label": null,
-            "name": "datasource",
-            "options": [
-
-            ],
-            "query": "prometheus",
-            "refresh": 1,
-            "regex": "",
-            "type": "datasource"
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 2,
-            "includeAll": false,
-            "label": "cluster",
-            "multi": false,
-            "name": "cluster",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_info, cluster)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "Namespace",
-            "multi": false,
-            "name": "namespace",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "Pod",
-            "multi": false,
-            "name": "pod",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_info{cluster=\"$cluster\", namespace=~\"$namespace\"}, pod)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": true,
-            "label": "Container",
-            "multi": false,
-            "name": "container",
-            "options": [
-
-            ],
-            "query": "label_values(kube_pod_container_info{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}, container)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "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": "",
-      "title": "Kubernetes / Pods",
-      "uid": "ab4f13a9892a76a4d21ce8c2445bf4ea",
-      "version": 0
-    }
   scheduler.json: |-
     {
       "__inputs": [
@@ -3622,7 +2991,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -3726,15 +3095,15 @@ data:
               },
               "id": 3,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -3838,15 +3207,15 @@ data:
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -4179,15 +3548,15 @@ data:
               },
               "id": 7,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
-                "show": "true",
+                "rightSide": true,
+                "show": true,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -4561,8 +3930,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -4637,910 +4006,6 @@ data:
       "uid": "2e6b6a3b4bddf1427b3a55aa1311c656",
       "version": 0
     }
-  statefulset.json: |-
-    {
-      "__inputs": [
-
-      ],
-      "__requires": [
-
-      ],
-      "annotations": {
-        "list": [
-
-        ]
-      },
-      "editable": false,
-      "gnetId": null,
-      "graphTooltip": 0,
-      "hideControls": false,
-      "id": null,
-      "links": [
-
-      ],
-      "refresh": "",
-      "rows": [
-        {
-          "collapse": false,
-          "collapsed": false,
-          "panels": [
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$datasource",
-              "format": "none",
-              "gauge": {
-                "maxValue": 100,
-                "minValue": 0,
-                "show": false,
-                "thresholdLabels": false,
-                "thresholdMarkers": true
-              },
-              "gridPos": {
-
-              },
-              "id": 2,
-              "interval": null,
-              "links": [
-
-              ],
-              "mappingType": 1,
-              "mappingTypes": [
-                {
-                  "name": "value to text",
-                  "value": 1
-                },
-                {
-                  "name": "range to text",
-                  "value": 2
-                }
-              ],
-              "maxDataPoints": 100,
-              "nullPointMode": "connected",
-              "nullText": null,
-              "postfix": "cores",
-              "postfixFontSize": "50%",
-              "prefix": "",
-              "prefixFontSize": "50%",
-              "rangeMaps": [
-                {
-                  "from": "null",
-                  "text": "N/A",
-                  "to": "null"
-                }
-              ],
-              "span": 4,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "lineColor": "rgb(31, 120, 193)",
-                "show": true
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m]))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "CPU",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            },
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$datasource",
-              "format": "none",
-              "gauge": {
-                "maxValue": 100,
-                "minValue": 0,
-                "show": false,
-                "thresholdLabels": false,
-                "thresholdMarkers": true
-              },
-              "gridPos": {
-
-              },
-              "id": 3,
-              "interval": null,
-              "links": [
-
-              ],
-              "mappingType": 1,
-              "mappingTypes": [
-                {
-                  "name": "value to text",
-                  "value": 1
-                },
-                {
-                  "name": "range to text",
-                  "value": 2
-                }
-              ],
-              "maxDataPoints": 100,
-              "nullPointMode": "connected",
-              "nullText": null,
-              "postfix": "GB",
-              "postfixFontSize": "50%",
-              "prefix": "",
-              "prefixFontSize": "50%",
-              "rangeMaps": [
-                {
-                  "from": "null",
-                  "text": "N/A",
-                  "to": "null"
-                }
-              ],
-              "span": 4,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "lineColor": "rgb(31, 120, 193)",
-                "show": true
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}) / 1024^3",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "Memory",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            },
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$datasource",
-              "format": "none",
-              "gauge": {
-                "maxValue": 100,
-                "minValue": 0,
-                "show": false,
-                "thresholdLabels": false,
-                "thresholdMarkers": true
-              },
-              "gridPos": {
-
-              },
-              "id": 4,
-              "interval": null,
-              "links": [
-
-              ],
-              "mappingType": 1,
-              "mappingTypes": [
-                {
-                  "name": "value to text",
-                  "value": 1
-                },
-                {
-                  "name": "range to text",
-                  "value": 2
-                }
-              ],
-              "maxDataPoints": 100,
-              "nullPointMode": "connected",
-              "nullText": null,
-              "postfix": "Bps",
-              "postfixFontSize": "50%",
-              "prefix": "",
-              "prefixFontSize": "50%",
-              "rangeMaps": [
-                {
-                  "from": "null",
-                  "text": "N/A",
-                  "to": "null"
-                }
-              ],
-              "span": 4,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "lineColor": "rgb(31, 120, 193)",
-                "show": true
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=\"$namespace\",pod=~\"$statefulset.*\"}[3m]))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "Network",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            }
-          ],
-          "repeat": null,
-          "repeatIteration": null,
-          "repeatRowId": null,
-          "showTitle": false,
-          "title": "Dashboard Row",
-          "titleSize": "h6",
-          "type": "row"
-        },
-        {
-          "collapse": false,
-          "collapsed": false,
-          "height": "100px",
-          "panels": [
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$datasource",
-              "format": "none",
-              "gauge": {
-                "maxValue": 100,
-                "minValue": 0,
-                "show": false,
-                "thresholdLabels": false,
-                "thresholdMarkers": true
-              },
-              "gridPos": {
-
-              },
-              "id": 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": 3,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "full": false,
-                "lineColor": "rgb(31, 120, 193)",
-                "show": false
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "Desired Replicas",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            },
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$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": 3,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "full": false,
-                "lineColor": "rgb(31, 120, 193)",
-                "show": false
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "Replicas of current version",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            },
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$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": 3,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "full": false,
-                "lineColor": "rgb(31, 120, 193)",
-                "show": false
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "max(kube_statefulset_status_observed_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\", statefulset=\"$statefulset\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "Observed Generation",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            },
-            {
-              "cacheTimeout": null,
-              "colorBackground": false,
-              "colorValue": false,
-              "colors": [
-                "#299c46",
-                "rgba(237, 129, 40, 0.89)",
-                "#d44a3a"
-              ],
-              "datasource": "$datasource",
-              "format": "none",
-              "gauge": {
-                "maxValue": 100,
-                "minValue": 0,
-                "show": false,
-                "thresholdLabels": false,
-                "thresholdMarkers": true
-              },
-              "gridPos": {
-
-              },
-              "id": 8,
-              "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": 3,
-              "sparkline": {
-                "fillColor": "rgba(31, 118, 189, 0.18)",
-                "full": false,
-                "lineColor": "rgb(31, 120, 193)",
-                "show": false
-              },
-              "tableColumn": "",
-              "targets": [
-                {
-                  "expr": "max(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": "",
-              "title": "Metadata Generation",
-              "tooltip": {
-                "shared": false
-              },
-              "type": "singlestat",
-              "valueFontSize": "80%",
-              "valueMaps": [
-                {
-                  "op": "=",
-                  "text": "0",
-                  "value": "null"
-                }
-              ],
-              "valueName": "current"
-            }
-          ],
-          "repeat": null,
-          "repeatIteration": null,
-          "repeatRowId": null,
-          "showTitle": false,
-          "title": "Dashboard Row",
-          "titleSize": "h6",
-          "type": "row"
-        },
-        {
-          "collapse": false,
-          "collapsed": false,
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 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,
-              "stack": false,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "max(kube_statefulset_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "replicas specified",
-                  "refId": "A"
-                },
-                {
-                  "expr": "max(kube_statefulset_status_replicas{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "replicas created",
-                  "refId": "B"
-                },
-                {
-                  "expr": "min(kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "ready",
-                  "refId": "C"
-                },
-                {
-                  "expr": "min(kube_statefulset_status_replicas_current{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "replicas of current version",
-                  "refId": "D"
-                },
-                {
-                  "expr": "min(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\", statefulset=\"$statefulset\", cluster=\"$cluster\", namespace=\"$namespace\"}) without (instance, pod)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "updated",
-                  "refId": "E"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "Replicas",
-              "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",
-      "tags": [
-        "kubernetes-mixin"
-      ],
-      "templating": {
-        "list": [
-          {
-            "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
-            },
-            "hide": 0,
-            "label": null,
-            "name": "datasource",
-            "options": [
-
-            ],
-            "query": "prometheus",
-            "refresh": 1,
-            "regex": "",
-            "type": "datasource"
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 2,
-            "includeAll": false,
-            "label": "cluster",
-            "multi": false,
-            "name": "cluster",
-            "options": [
-
-            ],
-            "query": "label_values(kube_statefulset_metadata_generation, cluster)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "Namespace",
-            "multi": false,
-            "name": "namespace",
-            "options": [
-
-            ],
-            "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\"}, namespace)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "Name",
-            "multi": false,
-            "name": "statefulset",
-            "options": [
-
-            ],
-            "query": "label_values(kube_statefulset_metadata_generation{job=\"kube-state-metrics\", cluster=\"$cluster\", namespace=\"$namespace\"}, statefulset)",
-            "refresh": 2,
-            "regex": "",
-            "sort": 1,
-            "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": "",
-      "title": "Kubernetes / StatefulSets",
-      "uid": "a31c1f46e6f727cb37c0d731a7245005",
-      "version": 0
-    }
 kind: ConfigMap
 metadata:
   name: grafana-dashboards-k8s

addons/grafana/dashboards-prom.yaml

@@ -2,6 +2,12 @@ apiVersion: v1
 data:
   prometheus-remote-write.json: |-
     {
+      "__inputs": [
+
+      ],
+      "__requires": [
+
+      ],
       "annotations": {
         "list": [
 
@@ -11,14 +17,15 @@ data:
       "gnetId": null,
       "graphTooltip": 0,
       "hideControls": false,
+      "id": null,
       "links": [
 
       ],
-      "refresh": "10s",
+      "refresh": "",
       "rows": [
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -29,12 +36,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 1,
+              "gridPos": {
+
+              },
+              "id": 2,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -44,11 +56,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -58,12 +71,11 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} - ignoring(queue) group_right(instance) prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -89,11 +101,11 @@ data:
               },
               "yaxes": [
                 {
-                  "format": "s",
+                  "format": "short",
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -102,7 +114,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -115,12 +127,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 2,
+              "gridPos": {
+
+              },
+              "id": 3,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -130,11 +147,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -144,12 +162,11 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])  - ignoring (queue) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+                  "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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -179,7 +196,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -188,7 +205,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             }
@@ -198,11 +215,12 @@ data:
           "repeatRowId": null,
           "showTitle": true,
           "title": "Timestamps",
-          "titleSize": "h6"
+          "titleSize": "h6",
+          "type": "row"
         },
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -213,12 +231,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 3,
+              "gridPos": {
+
+              },
+              "id": 4,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -228,11 +251,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -242,12 +266,11 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "rate(prometheus_remote_storage_samples_in_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])- ignoring(queue) group_right(instance) rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) - rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+                  "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",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -277,7 +300,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -286,7 +309,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             }
@@ -296,11 +319,12 @@ data:
           "repeatRowId": null,
           "showTitle": true,
           "title": "Samples",
-          "titleSize": "h6"
+          "titleSize": "h6",
+          "type": "row"
         },
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -311,12 +335,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 4,
+              "gridPos": {
+
+              },
+              "id": 5,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -326,16 +355,18 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "minSpan": 6,
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
               "spaceLength": 10,
-              "span": 6,
+              "span": 12,
               "stack": false,
               "steppedLine": false,
               "targets": [
@@ -344,8 +375,7 @@ data:
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -353,7 +383,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Num. Shards",
+              "title": "Current Shards",
               "tooltip": {
                 "shared": true,
                 "sort": 0,
@@ -375,7 +405,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -384,7 +414,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -397,12 +427,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 5,
+              "gridPos": {
+
+              },
+              "id": 6,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -412,11 +447,298 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 4,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Max Shards",
+              "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": "$datasource",
+              "fill": 1,
+              "gridPos": {
+
+              },
+              "id": 7,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 4,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Min Shards",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "gridPos": {
+
+              },
+              "id": 8,
+              "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": "prometheus_remote_storage_shards_desired{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Desired Shards",
+              "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
+                }
+              ]
+            }
+          ],
+          "repeat": null,
+          "repeatIteration": null,
+          "repeatRowId": null,
+          "showTitle": true,
+          "title": "Shards",
+          "titleSize": "h6",
+          "type": "row"
+        },
+        {
+          "collapse": false,
+          "collapsed": false,
+          "panels": [
+            {
+              "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": [
 
               ],
@@ -430,8 +752,7 @@ data:
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -439,7 +760,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Capacity",
+              "title": "Shard Capacity",
               "tooltip": {
                 "shared": true,
                 "sort": 0,
@@ -461,7 +782,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -470,7 +791,98 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "gridPos": {
+
+              },
+              "id": 10,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 6,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Pending Samples",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
                 }
               ]
             }
@@ -479,12 +891,13 @@ data:
           "repeatIteration": null,
           "repeatRowId": null,
           "showTitle": true,
-          "title": "Shards",
-          "titleSize": "h6"
+          "title": "Shard Details",
+          "titleSize": "h6",
+          "type": "row"
         },
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -495,12 +908,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 6,
+              "gridPos": {
+
+              },
+              "id": 11,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -510,11 +928,207 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 6,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_tsdb_wal_segment_current{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "TSDB Current Segment",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "none",
+                  "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": "$datasource",
+              "fill": 1,
+              "gridPos": {
+
+              },
+              "id": 12,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 6,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Remote Write Current Segment",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "none",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            }
+          ],
+          "repeat": null,
+          "repeatIteration": null,
+          "repeatRowId": null,
+          "showTitle": true,
+          "title": "Segments",
+          "titleSize": "h6",
+          "type": "row"
+        },
+        {
+          "collapse": false,
+          "collapsed": false,
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "gridPos": {
+
+              },
+              "id": 13,
+              "legend": {
+                "alignAsTable": 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": [
 
               ],
@@ -528,8 +1142,7 @@ data:
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -559,7 +1172,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -568,7 +1181,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -581,12 +1194,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 7,
+              "gridPos": {
+
+              },
+              "id": 14,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -596,11 +1214,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -614,8 +1233,7 @@ data:
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -645,7 +1263,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -654,7 +1272,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -667,12 +1285,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 8,
+              "gridPos": {
+
+              },
+              "id": 15,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -682,11 +1305,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -700,8 +1324,7 @@ data:
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -731,7 +1354,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -740,7 +1363,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -753,12 +1376,17 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 9,
+              "gridPos": {
+
+              },
+              "id": 16,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
                 "total": false,
                 "values": false
@@ -768,11 +1396,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -786,8 +1415,7 @@ data:
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
-                  "legendLink": null,
-                  "step": 10
+                  "refId": "A"
                 }
               ],
               "thresholds": [
@@ -817,7 +1445,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -826,7 +1454,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             }
@@ -835,8 +1463,9 @@ data:
           "repeatIteration": null,
           "repeatRowId": null,
           "showTitle": true,
-          "title": "Misc Rates.",
-          "titleSize": "h6"
+          "title": "Misc. Rates",
+          "titleSize": "h6",
+          "type": "row"
         }
       ],
       "schemaVersion": 14,
@@ -847,10 +1476,6 @@ data:
       "templating": {
         "list": [
           {
-            "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
-            },
             "hide": 0,
             "label": null,
             "name": "datasource",
@@ -865,23 +1490,30 @@ data:
           {
             "allValue": null,
             "current": {
-              "selected": true,
-              "text": "All",
-              "value": "$__all"
+              "text": {
+                "selected": true,
+                "text": "All",
+                "value": "$__all"
+              },
+              "value": {
+                "selected": true,
+                "text": "All",
+                "value": "$__all"
+              }
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": true,
-            "label": "instance",
-            "multi": true,
+            "label": null,
+            "multi": false,
             "name": "instance",
             "options": [
 
             ],
             "query": "label_values(prometheus_build_info, instance)",
-            "refresh": 1,
+            "refresh": 2,
             "regex": "",
-            "sort": 2,
+            "sort": 0,
             "tagValuesQuery": "",
             "tags": [
 
@@ -893,23 +1525,56 @@ data:
           {
             "allValue": null,
             "current": {
-              "selected": true,
-              "text": "All",
-              "value": "$__all"
+              "text": {
+                "selected": true,
+                "text": "All",
+                "value": "$__all"
+              },
+              "value": {
+                "selected": true,
+                "text": "All",
+                "value": "$__all"
+              }
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": true,
-            "label": "cluster",
-            "multi": true,
+            "label": null,
+            "multi": false,
             "name": "cluster",
             "options": [
 
             ],
             "query": "label_values(kube_pod_container_info{image=~\".*prometheus.*\"}, cluster)",
-            "refresh": 1,
+            "refresh": 2,
             "regex": "",
-            "sort": 2,
+            "sort": 0,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {
+
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": null,
+            "multi": false,
+            "name": "queue",
+            "options": [
+
+            ],
+            "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, queue)",
+            "refresh": 2,
+            "regex": "",
+            "sort": 0,
             "tagValuesQuery": "",
             "tags": [
 
@@ -921,7 +1586,7 @@ data:
         ]
       },
       "time": {
-        "from": "now-1h",
+        "from": "now-6h",
         "to": "now"
       },
       "timepicker": {
@@ -949,9 +1614,8 @@ data:
           "30d"
         ]
       },
-      "timezone": "utc",
+      "timezone": "browser",
       "title": "Prometheus Remote Write",
-      "uid": "",
       "version": 0
     }
   prometheus.json: |-
@@ -2048,8 +2712,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
+              "text": "default",
+              "value": "default"
             },
             "hide": 0,
             "label": null,

addons/grafana/deployment.yaml

@@ -23,7 +23,7 @@ spec:
     spec:
       containers:
         - name: grafana
-          image: docker.io/grafana/grafana:6.6.1
+          image: docker.io/grafana/grafana:7.1.5
           env:
             - name: GF_PATHS_CONFIG
               value: "/etc/grafana/custom.ini"

addons/nginx-ingress/aws/class.yaml

@@ -0,0 +1,6 @@
+apiVersion: networking.k8s.io/v1beta1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/aws/deployment.yaml

@@ -22,7 +22,7 @@ spec:
     spec:
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.28.0
+          image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +47,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +54,16 @@ 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:

addons/nginx-ingress/aws/rbac/cluster-role.yaml

@@ -51,3 +51,12 @@ rules:
       - ingresses/status
     verbs:
       - update
+  - apiGroups:
+      - "networking.k8s.io"
+    resources:
+      - ingressclasses
+    verbs:
+      - get
+      - list
+      - watch
+

addons/nginx-ingress/azure/class.yaml

@@ -0,0 +1,6 @@
+apiVersion: networking.k8s.io/v1beta1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/azure/deployment.yaml

@@ -22,7 +22,7 @@ spec:
     spec:
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.28.0
+          image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +47,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +54,16 @@ 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:

addons/nginx-ingress/azure/rbac/cluster-role.yaml

@@ -51,3 +51,12 @@ rules:
       - ingresses/status
     verbs:
       - update
+  - apiGroups:
+      - "networking.k8s.io"
+    resources:
+      - ingressclasses
+    verbs:
+      - get
+      - list
+      - watch
+

addons/nginx-ingress/bare-metal/class.yaml

@@ -0,0 +1,6 @@
+apiVersion: networking.k8s.io/v1beta1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/bare-metal/deployment.yaml

@@ -1,7 +1,7 @@
 apiVersion: apps/v1
 kind: Deployment
 metadata:
-  name: ingress-controller-public
+  name: nginx-ingress-controller
   namespace: ingress
 spec:
   replicas: 2
@@ -10,19 +10,19 @@ 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:
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.28.0
+          image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -76,4 +76,3 @@ spec:
             runAsUser: 101 # www-data
       restartPolicy: Always
       terminationGracePeriodSeconds: 300
-

addons/nginx-ingress/bare-metal/rbac/cluster-role.yaml

@@ -51,3 +51,12 @@ rules:
       - ingresses/status
     verbs:
       - update
+  - apiGroups:
+      - "networking.k8s.io"
+    resources:
+      - ingressclasses
+    verbs:
+      - get
+      - list
+      - watch
+

addons/nginx-ingress/digital-ocean/class.yaml

@@ -0,0 +1,6 @@
+apiVersion: networking.k8s.io/v1beta1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/digital-ocean/daemonset.yaml

@@ -22,7 +22,7 @@ spec:
     spec:
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.28.0
+          image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +47,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +54,16 @@ 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:

addons/nginx-ingress/digital-ocean/rbac/cluster-role.yaml

@@ -51,3 +51,12 @@ rules:
       - ingresses/status
     verbs:
       - update
+  - apiGroups:
+      - "networking.k8s.io"
+    resources:
+      - ingressclasses
+    verbs:
+      - get
+      - list
+      - watch
+

addons/nginx-ingress/google-cloud/class.yaml

@@ -0,0 +1,6 @@
+apiVersion: networking.k8s.io/v1beta1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/google-cloud/deployment.yaml

@@ -22,7 +22,7 @@ spec:
     spec:
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.28.0
+          image: k8s.gcr.io/ingress-nginx/controller:v0.35.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +47,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +54,16 @@ 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:

addons/nginx-ingress/google-cloud/rbac/cluster-role.yaml

@@ -51,3 +51,12 @@ rules:
       - ingresses/status
     verbs:
       - update
+  - apiGroups:
+      - "networking.k8s.io"
+    resources:
+      - ingressclasses
+    verbs:
+      - get
+      - list
+      - watch
+

addons/prometheus/deployment.yaml

@@ -20,7 +20,7 @@ spec:
       serviceAccountName: prometheus
       containers:
         - name: prometheus
-          image: quay.io/prometheus/prometheus:v2.15.2
+          image: quay.io/prometheus/prometheus:v2.20.0
           args:
             - --web.listen-address=0.0.0.0:9090
             - --config.file=/etc/prometheus/prometheus.yaml

addons/prometheus/exporters/kube-state-metrics/deployment.yaml

@@ -24,7 +24,7 @@ spec:
       serviceAccountName: kube-state-metrics
       containers:
       - name: kube-state-metrics
-        image: quay.io/coreos/kube-state-metrics:v1.9.4
+        image: quay.io/coreos/kube-state-metrics:v1.9.7
         ports:
           - name: metrics
             containerPort: 8080

addons/prometheus/exporters/node-exporter/daemonset.yaml

@@ -28,7 +28,7 @@ spec:
       hostPID: true
       containers:
       - name: node-exporter
-        image: quay.io/prometheus/node-exporter:v0.18.1
+        image: quay.io/prometheus/node-exporter:v1.0.1
         args:
           - --path.procfs=/host/proc
           - --path.sysfs=/host/sys

addons/prometheus/rules.yaml

@@ -42,10 +42,10 @@ data:
             {
               "alert": "etcdHighNumberOfLeaderChanges",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last 30 minutes."
+                "message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated."
               },
-              "expr": "rate(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}[15m]) > 3\n",
-              "for": "15m",
+              "expr": "increase((max by (job) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 3\n",
+              "for": "5m",
               "labels": {
                 "severity": "warning"
               }
@@ -145,25 +145,132 @@ data:
   kube.yaml: |-
     {
       "groups": [
+        {
+          "name": "kube-apiserver-error",
+          "rules": [
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[5m]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate5m"
+            },
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[30m]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate30m"
+            },
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[1h]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate1h"
+            },
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[2h]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate2h"
+            },
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[6h]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate6h"
+            },
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[1d]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate1d"
+            },
+            {
+              "expr": "sum by (status_class) (\n  label_replace(\n    rate(apiserver_request_total{job=\"apiserver\"}[3d]\n  ), \"status_class\", \"${1}xx\", \"code\", \"([0-9])..\")\n)\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class:apiserver_request_total:rate3d"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate5m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate5m{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate5m"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate30m{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate30m{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate30m"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate1h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1h{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate1h"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate2h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate2h{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate2h"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate6h{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate6h{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate6h"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate1d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate1d{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate1d"
+            },
+            {
+              "expr": "sum(status_class:apiserver_request_total:rate3d{job=\"apiserver\",status_class=\"5xx\"})\n/\nsum(status_class:apiserver_request_total:rate3d{job=\"apiserver\"})\n",
+              "labels": {
+                "job": "apiserver"
+              },
+              "record": "status_class_5xx:apiserver_request_total:ratio_rate3d"
+            }
+          ]
+        },
         {
           "name": "kube-apiserver.rules",
           "rules": [
             {
-              "expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
+              "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",
               "labels": {
                 "quantile": "0.99"
               },
               "record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
             },
             {
-              "expr": "histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
+              "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",
               "labels": {
                 "quantile": "0.9"
               },
               "record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
             },
             {
-              "expr": "histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\"}[5m])) without(instance, pod))\n",
+              "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",
               "labels": {
                 "quantile": "0.5"
               },
@@ -179,23 +286,23 @@ data:
               "record": "namespace:container_cpu_usage_seconds_total:sum_rate"
             },
             {
-              "expr": "sum by (namespace, pod, container) (\n  rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])\n) * on (namespace, pod) group_left(node) max by(namespace, pod, node) (kube_pod_info)\n",
+              "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) max by(namespace, pod, node) (kube_pod_info)\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)\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) max by(namespace, pod, node) (kube_pod_info)\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)\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) max by(namespace, pod, node) (kube_pod_info)\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)\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) max by(namespace, pod, node) (kube_pod_info)\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)\n)\n",
               "record": "node_namespace_pod_container:container_memory_swap"
             },
             {
@@ -203,29 +310,29 @@ data:
               "record": "namespace:container_memory_usage_bytes:sum"
             },
             {
-              "expr": "sum by (namespace, label_name) (\n    sum(kube_pod_container_resource_requests_memory_bytes{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)) by (namespace, pod)\n  * on (namespace, pod)\n    group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
+              "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, label_name) (\n    sum(kube_pod_container_resource_requests_cpu_cores{job=\"kube-state-metrics\"} * on (endpoint, instance, job, namespace, pod, service) group_left(phase) (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)) by (namespace, pod)\n  * on (namespace, pod)\n    group_left(label_name) kube_pod_labels{job=\"kube-state-metrics\"}\n)\n",
+              "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": "sum(\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) kube_replicaset_owner{job=\"kube-state-metrics\"},\n    \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n  )\n) by (namespace, workload, pod)\n",
+              "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"
             },
             {
-              "expr": "sum(\n  label_replace(\n    kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n    \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n  )\n) by (namespace, workload, pod)\n",
+              "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"
             },
             {
-              "expr": "sum(\n  label_replace(\n    kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n    \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n  )\n) by (namespace, workload, pod)\n",
+              "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"
               },
@@ -305,23 +412,49 @@ data:
           "name": "node.rules",
           "rules": [
             {
-              "expr": "sum(min(kube_pod_info) by (node))",
+              "expr": "sum(min(kube_pod_info) by (cluster, node))\n",
               "record": ":kube_pod_info_node_count:"
             },
             {
-              "expr": "max(label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")) by (node, namespace, pod)\n",
+              "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",
               "record": "node_namespace_pod:kube_pod_info:"
             },
             {
-              "expr": "count by (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  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)\n",
+              "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"
             }
           ]
         },
+        {
+          "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",
+              "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",
+              "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",
+              "labels": {
+                "quantile": "0.5"
+              },
+              "record": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile"
+            }
+          ]
+        },
         {
           "name": "kubernetes-apps",
           "rules": [
@@ -343,7 +476,7 @@ data:
                 "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"
               },
-              "expr": "sum by (namespace, pod) (kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Failed|Pending|Unknown\"} * on(namespace, pod) group_left(owner_kind) kube_pod_owner{owner_kind!=\"Job\"}) > 0\n",
+              "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",
               "for": "15m",
               "labels": {
                 "severity": "critical"
@@ -367,7 +500,7 @@ data:
                 "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"
               },
-              "expr": "kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n  !=\nkube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\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\"}[5m])\n    ==\n  0\n)\n",
               "for": "15m",
               "labels": {
                 "severity": "critical"
@@ -379,7 +512,7 @@ data:
                 "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"
               },
-              "expr": "kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n  !=\nkube_statefulset_status_replicas{job=\"kube-state-metrics\"}\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\"}[5m])\n    ==\n  0\n)\n",
               "for": "15m",
               "labels": {
                 "severity": "critical"
@@ -528,7 +661,7 @@ data:
                 "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"
               },
-              "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: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",
               "for": "5m",
               "labels": {
                 "severity": "warning"
@@ -540,7 +673,7 @@ data:
                 "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"
               },
-              "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(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",
               "for": "5m",
               "labels": {
                 "severity": "warning"
@@ -618,7 +751,7 @@ data:
                 "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
               },
               "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",
-              "for": "5m",
+              "for": "1h",
               "labels": {
                 "severity": "critical"
               }
@@ -666,17 +799,46 @@ data:
             }
           ]
         },
+        {
+          "name": "kube-apiserver-error-alerts",
+          "rules": [
+            {
+              "alert": "ErrorBudgetBurn",
+              "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"
+              },
+              "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",
+              "labels": {
+                "job": "apiserver",
+                "severity": "critical"
+              }
+            },
+            {
+              "alert": "ErrorBudgetBurn",
+              "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"
+              },
+              "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",
+              "labels": {
+                "job": "apiserver",
+                "severity": "warning"
+              }
+            }
+          ]
+        },
         {
           "name": "kubernetes-system-apiserver",
           "rules": [
             {
               "alert": "KubeAPILatencyHigh",
               "annotations": {
-                "message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
+                "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": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 1\n",
-              "for": "10m",
+              "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"
               }
@@ -687,36 +849,12 @@ data:
                 "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\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 4\n",
+              "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.",
-                "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]))\n  /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.03\n",
-              "for": "10m",
-              "labels": {
-                "severity": "critical"
-              }
-            },
-            {
-              "alert": "KubeAPIErrorsHigh",
-              "annotations": {
-                "message": "API server is returning errors for {{ $value | humanizePercentage }} of requests.",
-                "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]))\n  /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) > 0.01\n",
-              "for": "10m",
-              "labels": {
-                "severity": "warning"
-              }
-            },
             {
               "alert": "KubeAPIErrorsHigh",
               "annotations": {
@@ -744,10 +882,10 @@ data:
             {
               "alert": "KubeClientCertificateExpiration",
               "annotations": {
-                "message": "A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.",
+                "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"
               },
-              "expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 604800\n",
+              "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": {
                 "severity": "warning"
               }
@@ -755,14 +893,37 @@ data:
             {
               "alert": "KubeClientCertificateExpiration",
               "annotations": {
-                "message": "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.",
+                "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"
               },
-              "expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job=\"apiserver\"}[5m]))) < 86400\n",
+              "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": {
                 "severity": "critical"
               }
             },
+            {
+              "alert": "AggregatedAPIErrors",
+              "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"
+              },
+              "expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[5m])) > 2\n",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "AggregatedAPIDown",
+              "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"
+              },
+              "expr": "sum by(name, namespace)(sum_over_time(aggregator_unavailable_apiservice[5m])) > 0\n",
+              "for": "5m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
             {
               "alert": "KubeAPIDown",
               "annotations": {
@@ -799,6 +960,7 @@ data:
                 "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable"
               },
               "expr": "kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} == 1\n",
+              "for": "2m",
               "labels": {
                 "severity": "warning"
               }
@@ -809,7 +971,43 @@ data:
                 "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"
               },
-              "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\"}) by(node) > 0.95\n",
+              "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",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "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"
+              },
+              "expr": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 2\n",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "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"
+              },
+              "expr": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\n",
+              "for": "5m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "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"
+              },
+              "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",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -865,9 +1063,167 @@ 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",
+          "rules": [
+            {
+              "alert": "LokiRequestErrors",
+              "annotations": {
+                "message": "{{ $labels.job }} {{ $labels.route }} is experiencing {{ printf \"%.2f\" $value }}% errors.\n"
+              },
+              "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",
+              "for": "15m",
+              "labels": {
+                "severity": "critical"
+              }
+            }
+          ]
+        }
+      ]
+    }
   node-exporter.yaml: |-
     {
       "groups": [
+        {
+          "name": "node-exporter.rules",
+          "rules": [
+            {
+              "expr": "count without (cpu) (\n  count without (mode) (\n    node_cpu_seconds_total{job=\"node-exporter\"}\n  )\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": "(\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",
+              "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_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_weighted_seconds_total{job=\"node-exporter\", device!~\"dm.*\"}[1m])\n",
+              "record": "instance_device:node_disk_io_time_weighted_seconds:rate1m"
+            },
+            {
+              "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_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_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_transmit_drop_total{job=\"node-exporter\", device!=\"lo\"}[1m])\n)\n",
+              "record": "instance:node_network_transmit_drop_excluding_lo:rate1m"
+            }
+          ]
+        },
         {
           "name": "node-exporter",
           "rules": [
@@ -990,6 +1346,41 @@ data:
               "labels": {
                 "severity": "warning"
               }
+            },
+            {
+              "alert": "NodeHighNumberConntrackEntriesUsed",
+              "annotations": {
+                "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": "NodeClockSkewDetected",
+              "annotations": {
+                "message": "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",
+              "for": "10m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "NodeClockNotSynchronising",
+              "annotations": {
+                "message": "Clock on {{ $labels.instance }} is not synchronising. Ensure NTP is configured on this host.",
+                "summary": "Clock not synchronising."
+              },
+              "expr": "min_over_time(node_timex_sync_status[5m]) == 0\n",
+              "for": "10m",
+              "labels": {
+                "severity": "warning"
+              }
             }
           ]
         }
@@ -1124,7 +1515,7 @@ data:
             {
               "alert": "PrometheusRemoteStorageFailures",
               "annotations": {
-                "description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to queue {{$labels.queue}}.",
+                "description": "Prometheus {{$labels.instance}} failed to send {{ printf \"%.1f\" $value }}% of the samples to {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
                 "summary": "Prometheus fails to send samples to remote storage."
               },
               "expr": "(\n  rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n  (\n    rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n  +\n    rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n  )\n)\n* 100\n> 1\n",
@@ -1136,7 +1527,7 @@ data:
             {
               "alert": "PrometheusRemoteWriteBehind",
               "annotations": {
-                "description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for queue {{$labels.queue}}.",
+                "description": "Prometheus {{$labels.instance}} remote write is {{ printf \"%.1f\" $value }}s behind for {{ if $labels.queue }}{{ $labels.queue }}{{ else }}{{ $labels.url }}{{ end }}.",
                 "summary": "Prometheus remote write is behind."
               },
               "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n  max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
@@ -1148,10 +1539,10 @@ data:
             {
               "alert": "PrometheusRemoteWriteDesiredShards",
               "annotations": {
-                "description": "Prometheus {{$labels.instance}} remote write desired shards calculation wants to run {{ printf $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, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
                 "summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
               },
-              "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n> on(job, instance) group_right\n  max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
+              "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n  max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -1201,6 +1592,17 @@ data:
               "labels": {
                 "severity": "warning"
               }
+            },
+            {
+              "alert": "BlackboxProbeFailure",
+              "annotations": {
+                "message": "Blackbox probe {{$labels.instance}} failed"
+              },
+              "expr": "probe_success == 0",
+              "for": "2m",
+              "labels": {
+                "severity": "critical"
+              }
             }
           ]
         },
@@ -1212,7 +1614,7 @@ data:
               "annotations": {
                 "message": "{{ $value }} RAID disk(s) on node {{ $labels.instance }} are inactive."
               },
-              "expr": "node_md_disks - node_md_disks_active > 0",
+              "expr": "node_md_disks{state=\"failed\"} > 0",
               "for": "10m",
               "labels": {
                 "severity": "warning"

aws/container-linux/kubernetes/README.md

@@ -11,11 +11,11 @@ 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 v1.17.3 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* Kubernetes v1.19.0 (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
-* Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+* Ready for Ingress, Prometheus, Grafana, CSI, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
 
 ## Docs
 

aws/container-linux/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=796194583426593d1a62b6f1bf3f7ffed8fca140"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
 
   cluster_name          = var.cluster_name
   api_servers           = [format("%s.%s", var.cluster_name, var.dns_zone)]

aws/container-linux/kubernetes/cl/controller.yaml

@@ -2,12 +2,14 @@
 systemd:
   units:
     - name: etcd-member.service
-      enable: true
+      enabled: true
       dropins:
         - name: 40-etcd-cluster.conf
           contents: |
             [Service]
-            Environment="ETCD_IMAGE_TAG=v3.4.3"
+            Environment="ETCD_IMAGE_TAG=v3.4.12"
+            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://${etcd_domain}:2380"
@@ -26,11 +28,11 @@ systemd:
             Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
             Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
     - name: docker.service
-      enable: true
+      enabled: true
     - name: locksmithd.service
       mask: true
     - name: wait-for-dns.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Wait for DNS entries
@@ -44,12 +46,13 @@ systemd:
         RequiredBy=kubelet.service
         RequiredBy=etcd-member.service
     - name: kubelet.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube
+        Description=Kubelet
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
         Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -79,7 +82,7 @@ systemd:
           --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 \
+          --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 \
@@ -89,26 +92,24 @@ systemd:
           --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 \
-          docker://k8s.gcr.io/hyperkube:v1.17.3 \
-          --exec=/usr/local/bin/kubelet -- \
+          $${KUBELET_IMAGE} -- \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
           --cgroup-driver=$${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 \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
-          --node-labels=node.kubernetes.io/master \
           --node-labels=node.kubernetes.io/controller="true" \
           --pod-manifest-path=/etc/kubernetes/manifests \
           --read-only-port=0 \
-          --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
+          --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
@@ -124,7 +125,6 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        ExecStartPre=-/usr/bin/bash -c 'set -x && [ -n "$(ls /opt/bootstrap/assets/manifests-*/* 2>/dev/null)" ] && mv /opt/bootstrap/assets/manifests-*/* /opt/bootstrap/assets/manifests && rm -rf /opt/bootstrap/assets/manifests-*'
         ExecStart=/usr/bin/rkt run \
             --trust-keys-from-https \
             --volume config,kind=host,source=/etc/kubernetes/bootstrap-secrets \
@@ -134,7 +134,7 @@ systemd:
             --volume script,kind=host,source=/opt/bootstrap/apply \
             --mount volume=script,target=/apply \
             --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.3 \
+            docker://quay.io/poseidon/kubelet:v1.19.0 \
             --net=host \
             --dns=host \
             --exec=/apply
@@ -142,6 +142,11 @@ systemd:
         [Install]
         WantedBy=multi-user.target
 storage:
+  directories:
+    - path: /var/lib/etcd
+      filesystem: root
+      mode: 0700
+      overwrite: true
   files:
     - path: /etc/kubernetes/kubeconfig
       filesystem: root
@@ -163,14 +168,15 @@ storage:
           mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
           chown -R etcd:etcd /etc/ssl/etcd
           chmod -R 500 /etc/ssl/etcd
+          chmod -R 700 /var/lib/etcd
           mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
           mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
-          sudo mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
-          rm -rf assets auth static-manifests tls
+          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
@@ -188,6 +194,7 @@ storage:
           done
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
+      mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184

aws/container-linux/kubernetes/controllers.tf

@@ -36,7 +36,7 @@ resource "aws_instance" "controllers" {
 
   # network
   associate_public_ip_address = true
-  subnet_id                   = aws_subnet.public.*.id[count.index]
+  subnet_id                   = element(aws_subnet.public.*.id, count.index)
   vpc_security_group_ids      = [aws_security_group.controller.id]
 
   lifecycle {
@@ -49,10 +49,10 @@ 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]
-  pretty_print = false
-  snippets     = var.controller_clc_snippets
+  count    = var.controller_count
+  content  = data.template_file.controller-configs.*.rendered[count.index]
+  strict   = true
+  snippets = var.controller_snippets
 }
 
 # Controller Container Linux configs

aws/container-linux/kubernetes/network.tf

@@ -25,21 +25,23 @@ resource "aws_internet_gateway" "gateway" {
 resource "aws_route_table" "default" {
   vpc_id = aws_vpc.network.id
 
-  route {
-    cidr_block = "0.0.0.0/0"
-    gateway_id = aws_internet_gateway.gateway.id
-  }
-
-  route {
-    ipv6_cidr_block = "::/0"
-    gateway_id      = aws_internet_gateway.gateway.id
-  }
-
   tags = {
     "Name" = var.cluster_name
   }
 }
 
+resource "aws_route" "egress-ipv4" {
+  route_table_id         = aws_route_table.default.id
+  destination_cidr_block = "0.0.0.0/0"
+  gateway_id             = aws_internet_gateway.gateway.id
+}
+
+resource "aws_route" "egress-ipv6" {
+  route_table_id              = aws_route_table.default.id
+  destination_ipv6_cidr_block = "::/0"
+  gateway_id                  = aws_internet_gateway.gateway.id
+}
+
 # Subnets (one per availability zone)
 
 resource "aws_subnet" "public" {

aws/container-linux/kubernetes/security.tf

@@ -13,6 +13,30 @@ resource "aws_security_group" "controller" {
   }
 }
 
+resource "aws_security_group_rule" "controller-icmp" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "icmp"
+  from_port                = 8
+  to_port                  = 0
+  source_security_group_id = aws_security_group.worker.id
+}
+
+resource "aws_security_group_rule" "controller-icmp-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type      = "ingress"
+  protocol  = "icmp"
+  from_port = 8
+  to_port   = 0
+  self      = true
+}
+
 resource "aws_security_group_rule" "controller-ssh" {
   security_group_id = aws_security_group.controller.id
 
@@ -44,39 +68,31 @@ resource "aws_security_group_rule" "controller-etcd-metrics" {
   source_security_group_id = aws_security_group.worker.id
 }
 
-# Allow Prometheus to scrape kube-proxy
-resource "aws_security_group_rule" "kube-proxy-metrics" {
+resource "aws_security_group_rule" "controller-cilium-health" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
   type                     = "ingress"
   protocol                 = "tcp"
-  from_port                = 10249
-  to_port                  = 10249
+  from_port                = 4240
+  to_port                  = 4240
   source_security_group_id = aws_security_group.worker.id
 }
 
-# Allow Prometheus to scrape kube-scheduler
-resource "aws_security_group_rule" "controller-scheduler-metrics" {
+resource "aws_security_group_rule" "controller-cilium-health-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
-  type                     = "ingress"
-  protocol                 = "tcp"
-  from_port                = 10251
-  to_port                  = 10251
-  source_security_group_id = aws_security_group.worker.id
-}
-
-# Allow Prometheus to scrape kube-controller-manager
-resource "aws_security_group_rule" "controller-manager-metrics" {
-  security_group_id = aws_security_group.controller.id
-
-  type                     = "ingress"
-  protocol                 = "tcp"
-  from_port                = 10252
-  to_port                  = 10252
-  source_security_group_id = aws_security_group.worker.id
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 4240
+  to_port   = 4240
+  self      = true
 }
 
+# IANA VXLAN default
 resource "aws_security_group_rule" "controller-vxlan" {
   count = var.networking == "flannel" ? 1 : 0
 
@@ -111,6 +127,31 @@ resource "aws_security_group_rule" "controller-apiserver" {
   cidr_blocks = ["0.0.0.0/0"]
 }
 
+# Linux VXLAN default
+resource "aws_security_group_rule" "controller-linux-vxlan" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "udp"
+  from_port                = 8472
+  to_port                  = 8472
+  source_security_group_id = aws_security_group.worker.id
+}
+
+resource "aws_security_group_rule" "controller-linux-vxlan-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type      = "ingress"
+  protocol  = "udp"
+  from_port = 8472
+  to_port   = 8472
+  self      = true
+}
+
 # Allow Prometheus to scrape node-exporter daemonset
 resource "aws_security_group_rule" "controller-node-exporter" {
   security_group_id = aws_security_group.controller.id
@@ -122,6 +163,17 @@ resource "aws_security_group_rule" "controller-node-exporter" {
   source_security_group_id = aws_security_group.worker.id
 }
 
+# Allow Prometheus to scrape kube-proxy
+resource "aws_security_group_rule" "kube-proxy-metrics" {
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10249
+  to_port                  = 10249
+  source_security_group_id = aws_security_group.worker.id
+}
+
 # Allow apiserver to access kubelets for exec, log, port-forward
 resource "aws_security_group_rule" "controller-kubelet" {
   security_group_id = aws_security_group.controller.id
@@ -143,6 +195,28 @@ resource "aws_security_group_rule" "controller-kubelet-self" {
   self      = true
 }
 
+# Allow Prometheus to scrape kube-scheduler
+resource "aws_security_group_rule" "controller-scheduler-metrics" {
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10251
+  to_port                  = 10251
+  source_security_group_id = aws_security_group.worker.id
+}
+
+# Allow Prometheus to scrape kube-controller-manager
+resource "aws_security_group_rule" "controller-manager-metrics" {
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10252
+  to_port                  = 10252
+  source_security_group_id = aws_security_group.worker.id
+}
+
 resource "aws_security_group_rule" "controller-bgp" {
   security_group_id = aws_security_group.controller.id
 
@@ -227,6 +301,30 @@ resource "aws_security_group" "worker" {
   }
 }
 
+resource "aws_security_group_rule" "worker-icmp" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "icmp"
+  from_port                = 8
+  to_port                  = 0
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-icmp-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "icmp"
+  from_port = 8
+  to_port   = 0
+  self      = true
+}
+
 resource "aws_security_group_rule" "worker-ssh" {
   security_group_id = aws_security_group.worker.id
 
@@ -257,6 +355,31 @@ resource "aws_security_group_rule" "worker-https" {
   cidr_blocks = ["0.0.0.0/0"]
 }
 
+resource "aws_security_group_rule" "worker-cilium-health" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 4240
+  to_port                  = 4240
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-cilium-health-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 4240
+  to_port   = 4240
+  self      = true
+}
+
+# IANA VXLAN default
 resource "aws_security_group_rule" "worker-vxlan" {
   count = var.networking == "flannel" ? 1 : 0
 
@@ -281,6 +404,31 @@ resource "aws_security_group_rule" "worker-vxlan-self" {
   self      = true
 }
 
+# Linux VXLAN default
+resource "aws_security_group_rule" "worker-linux-vxlan" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "udp"
+  from_port                = 8472
+  to_port                  = 8472
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-linux-vxlan-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "udp"
+  from_port = 8472
+  to_port   = 8472
+  self      = true
+}
+
 # Allow Prometheus to scrape node-exporter daemonset
 resource "aws_security_group_rule" "worker-node-exporter" {
   security_group_id = aws_security_group.worker.id

aws/container-linux/kubernetes/variables.tf

@@ -44,7 +44,7 @@ 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)"
-  default     = "coreos-stable"
+  default     = "flatcar-stable"
 }
 
 variable "disk_size" {
@@ -77,13 +77,13 @@ variable "worker_target_groups" {
   default     = []
 }
 
-variable "controller_clc_snippets" {
+variable "controller_snippets" {
   type        = list(string)
   description = "Controller Container Linux Config snippets"
   default     = []
 }
 
-variable "worker_clc_snippets" {
+variable "worker_snippets" {
   type        = list(string)
   description = "Worker Container Linux Config snippets"
   default     = []
@@ -96,12 +96,6 @@ 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)"
@@ -155,6 +149,12 @@ 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)"

aws/container-linux/kubernetes/versions.tf

@@ -1,11 +1,15 @@
 # Terraform version and plugin versions
 
 terraform {
-  required_version = "~> 0.12.6"
+  required_version = ">= 0.12.26, < 0.14.0"
   required_providers {
-    aws      = "~> 2.23"
-    ct       = "~> 0.3"
+    aws      = ">= 2.23, <= 4.0"
     template = "~> 2.1"
     null     = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
   }
 }

aws/container-linux/kubernetes/workers.tf

@@ -18,7 +18,7 @@ module "workers" {
   ssh_authorized_key    = var.ssh_authorized_key
   service_cidr          = var.service_cidr
   cluster_domain_suffix = var.cluster_domain_suffix
-  clc_snippets          = var.worker_clc_snippets
+  snippets              = var.worker_snippets
   node_labels           = var.worker_node_labels
 }
 

aws/container-linux/kubernetes/workers/cl/worker.yaml

@@ -2,11 +2,11 @@
 systemd:
   units:
     - name: docker.service
-      enable: true
+      enabled: true
     - name: locksmithd.service
       mask: true
     - name: wait-for-dns.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Wait for DNS entries
@@ -19,12 +19,13 @@ systemd:
         [Install]
         RequiredBy=kubelet.service
     - name: kubelet.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube
+        Description=Kubelet
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
         Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -54,7 +55,7 @@ systemd:
           --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 \
+          --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 \
@@ -64,27 +65,26 @@ systemd:
           --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 \
-          docker://k8s.gcr.io/hyperkube:v1.17.3 \
-          --exec=/usr/local/bin/kubelet -- \
+          $${KUBELET_IMAGE} -- \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
           --cgroup-driver=$${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 \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
           --node-labels=node.kubernetes.io/node \
-          %{ for label in split(",", node_labels) }
+          %{~ for label in split(",", node_labels) ~}
           --node-labels=${label} \
-          %{ endfor ~}
+          %{~ 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
@@ -113,6 +113,7 @@ storage:
           ${kubeconfig}
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
+      mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
@@ -128,11 +129,10 @@ storage:
             --volume config,kind=host,source=/etc/kubernetes \
             --mount volume=config,target=/etc/kubernetes \
             --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.3 \
+            docker://quay.io/poseidon/kubelet:v1.19.0 \
             --net=host \
             --dns=host \
-            -- \
-            kubectl --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
+            --exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
 passwd:
   users:
     - name: core

aws/container-linux/kubernetes/workers/variables.tf

@@ -37,7 +37,7 @@ 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)"
-  default     = "coreos-stable"
+  default     = "flatcar-stable"
 }
 
 variable "disk_size" {
@@ -70,7 +70,7 @@ variable "target_groups" {
   default     = []
 }
 
-variable "clc_snippets" {
+variable "snippets" {
   type        = list(string)
   description = "Container Linux Config snippets"
   default     = []

aws/container-linux/kubernetes/workers/versions.tf

@@ -1,4 +1,14 @@
+# Terraform version and plugin versions
 
 terraform {
-  required_version = ">= 0.12"
+  required_version = ">= 0.12.26, < 0.14.0"
+  required_providers {
+    aws      = ">= 2.23, <= 4.0"
+    template = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
+  }
 }

aws/container-linux/kubernetes/workers/workers.tf

@@ -71,9 +71,9 @@ resource "aws_launch_configuration" "worker" {
 
 # Worker Ignition config
 data "ct_config" "worker-ignition" {
-  content      = data.template_file.worker-config.rendered
-  pretty_print = false
-  snippets     = var.clc_snippets
+  content  = data.template_file.worker-config.rendered
+  strict   = true
+  snippets = var.snippets
 }
 
 # Worker Container Linux config

aws/fedora-coreos/kubernetes/README.md

@@ -11,11 +11,11 @@ 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 v1.17.3 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) 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/)
+* Kubernetes v1.19.0 (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
-* Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+* Ready for Ingress, Prometheus, Grafana, CSI, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
 
 ## Docs
 

aws/fedora-coreos/kubernetes/ami.tf

@@ -14,10 +14,7 @@ data "aws_ami" "fedora-coreos" {
   }
 
   filter {
-    name   = "name"
-    values = ["fedora-coreos-31.*.*.*-hvm"]
+    name   = "description"
+    values = ["Fedora CoreOS ${var.os_stream} *"]
   }
-
-  # try to filter out dev images (AWS filters can't)
-  name_regex = "^fedora-coreos-31.[0-9]*.[0-9]*.[0-9]*-hvm*"
 }

aws/fedora-coreos/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=796194583426593d1a62b6f1bf3f7ffed8fca140"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
 
   cluster_name          = var.cluster_name
   api_servers           = [format("%s.%s", var.cluster_name, var.dns_zone)]

aws/fedora-coreos/kubernetes/controllers.tf

@@ -36,7 +36,7 @@ resource "aws_instance" "controllers" {
 
   # network
   associate_public_ip_address = true
-  subnet_id                   = aws_subnet.public.*.id[count.index]
+  subnet_id                   = element(aws_subnet.public.*.id, count.index)
   vpc_security_group_ids      = [aws_security_group.controller.id]
 
   lifecycle {

aws/fedora-coreos/kubernetes/fcc/controller.yaml

@@ -28,7 +28,7 @@ systemd:
           --network host \
           --volume /var/lib/etcd:/var/lib/etcd:rw,Z \
           --volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
-          quay.io/coreos/etcd:v3.4.3
+          quay.io/coreos/etcd:v3.4.12
         ExecStop=/usr/bin/podman stop etcd
         [Install]
         WantedBy=multi-user.target
@@ -38,11 +38,12 @@ systemd:
       enabled: true
       contents: |
         [Unit]
-        Description=Wait for DNS entries
+        Description=Wait for DNS and hostname
         Before=kubelet.service
         [Service]
         Type=oneshot
         RemainAfterExit=true
+        ExecStartPre=/bin/sh -c 'while [ `hostname -s` == "localhost" ]; do sleep 1; done;'
         ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
         [Install]
         RequiredBy=kubelet.service
@@ -51,9 +52,10 @@ systemd:
       enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube (System Container)
+        Description=Kubelet (System Container)
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -73,16 +75,17 @@ systemd:
           --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 /var/lib/calico:/var/lib/calico \
+          --volume /var/lib/calico:/var/lib/calico:ro \
           --volume /var/lib/docker:/var/lib/docker \
           --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 \
-          k8s.gcr.io/hyperkube:v1.17.3 kubelet \
+          $${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 \
@@ -90,16 +93,14 @@ systemd:
           --cluster_dns=${cluster_dns_service_ip} \
           --cluster_domain=${cluster_domain_suffix} \
           --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
-          --node-labels=node.kubernetes.io/master \
           --node-labels=node.kubernetes.io/controller="true" \
           --pod-manifest-path=/etc/kubernetes/manifests \
           --read-only-port=0 \
-          --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
+          --rotate-certificates \
           --volume-plugin-dir=/var/lib/kubelet/volumeplugins
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
@@ -116,18 +117,20 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        ExecStartPre=-/usr/bin/bash -c 'set -x && [ -n "$(ls /opt/bootstrap/assets/manifests-*/* 2>/dev/null)" ] && mv /opt/bootstrap/assets/manifests-*/* /opt/bootstrap/assets/manifests && rm -rf /opt/bootstrap/assets/manifests-*'
+        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/bootstrap-secrets:/etc/kubernetes/secrets:ro,z \
             --volume /opt/bootstrap/assets:/assets:ro,Z \
             --volume /opt/bootstrap/apply:/apply:ro,Z \
             --entrypoint=/apply \
-            k8s.gcr.io/hyperkube:v1.17.3
+            quay.io/poseidon/kubelet:v1.19.0
         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:
@@ -151,12 +154,13 @@ storage:
           chmod -R 500 /etc/ssl/etcd
           mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
           mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
-          sudo mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
-          rm -rf assets auth static-manifests tls
+          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/bootstrap-secrets
     - path: /opt/bootstrap/apply
       mode: 0544
       contents:
@@ -175,6 +179,18 @@ storage:
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
+    - path: /etc/sysctl.d/reverse-path-filter.conf
+      contents:
+        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: |
@@ -182,19 +198,6 @@ storage:
           DefaultCPUAccounting=yes
           DefaultMemoryAccounting=yes
           DefaultBlockIOAccounting=yes
-    - path: /etc/sysconfig/docker
-      mode: 0644
-      overwrite: true
-      contents:
-        inline: |
-          # Modify these options if you want to change the way the docker daemon runs
-          OPTIONS="--selinux-enabled \
-            --log-driver=json-file \
-            --live-restore \
-            --default-ulimit nofile=1024:1024 \
-            --init-path /usr/libexec/docker/docker-init \
-            --userland-proxy-path /usr/libexec/docker/docker-proxy \
-          "
     - path: /etc/etcd/etcd.env
       mode: 0644
       contents:

aws/fedora-coreos/kubernetes/network.tf

@@ -25,21 +25,23 @@ resource "aws_internet_gateway" "gateway" {
 resource "aws_route_table" "default" {
   vpc_id = aws_vpc.network.id
 
-  route {
-    cidr_block = "0.0.0.0/0"
-    gateway_id = aws_internet_gateway.gateway.id
-  }
-
-  route {
-    ipv6_cidr_block = "::/0"
-    gateway_id      = aws_internet_gateway.gateway.id
-  }
-
   tags = {
     "Name" = var.cluster_name
   }
 }
 
+resource "aws_route" "egress-ipv4" {
+  route_table_id         = aws_route_table.default.id
+  destination_cidr_block = "0.0.0.0/0"
+  gateway_id             = aws_internet_gateway.gateway.id
+}
+
+resource "aws_route" "egress-ipv6" {
+  route_table_id              = aws_route_table.default.id
+  destination_ipv6_cidr_block = "::/0"
+  gateway_id                  = aws_internet_gateway.gateway.id
+}
+
 # Subnets (one per availability zone)
 
 resource "aws_subnet" "public" {

aws/fedora-coreos/kubernetes/security.tf

@@ -13,6 +13,30 @@ resource "aws_security_group" "controller" {
   }
 }
 
+resource "aws_security_group_rule" "controller-icmp" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "icmp"
+  from_port                = 8
+  to_port                  = 0
+  source_security_group_id = aws_security_group.worker.id
+}
+
+resource "aws_security_group_rule" "controller-icmp-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type      = "ingress"
+  protocol  = "icmp"
+  from_port = 8
+  to_port   = 0
+  self      = true
+}
+
 resource "aws_security_group_rule" "controller-ssh" {
   security_group_id = aws_security_group.controller.id
 
@@ -44,39 +68,31 @@ resource "aws_security_group_rule" "controller-etcd-metrics" {
   source_security_group_id = aws_security_group.worker.id
 }
 
-# Allow Prometheus to scrape kube-proxy
-resource "aws_security_group_rule" "kube-proxy-metrics" {
+resource "aws_security_group_rule" "controller-cilium-health" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
   type                     = "ingress"
   protocol                 = "tcp"
-  from_port                = 10249
-  to_port                  = 10249
+  from_port                = 4240
+  to_port                  = 4240
   source_security_group_id = aws_security_group.worker.id
 }
 
-# Allow Prometheus to scrape kube-scheduler
-resource "aws_security_group_rule" "controller-scheduler-metrics" {
+resource "aws_security_group_rule" "controller-cilium-health-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
-  type                     = "ingress"
-  protocol                 = "tcp"
-  from_port                = 10251
-  to_port                  = 10251
-  source_security_group_id = aws_security_group.worker.id
-}
-
-# Allow Prometheus to scrape kube-controller-manager
-resource "aws_security_group_rule" "controller-manager-metrics" {
-  security_group_id = aws_security_group.controller.id
-
-  type                     = "ingress"
-  protocol                 = "tcp"
-  from_port                = 10252
-  to_port                  = 10252
-  source_security_group_id = aws_security_group.worker.id
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 4240
+  to_port   = 4240
+  self      = true
 }
 
+# IANA VXLAN default
 resource "aws_security_group_rule" "controller-vxlan" {
   count = var.networking == "flannel" ? 1 : 0
 
@@ -111,6 +127,31 @@ resource "aws_security_group_rule" "controller-apiserver" {
   cidr_blocks = ["0.0.0.0/0"]
 }
 
+# Linux VXLAN default
+resource "aws_security_group_rule" "controller-linux-vxlan" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "udp"
+  from_port                = 8472
+  to_port                  = 8472
+  source_security_group_id = aws_security_group.worker.id
+}
+
+resource "aws_security_group_rule" "controller-linux-vxlan-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.controller.id
+
+  type      = "ingress"
+  protocol  = "udp"
+  from_port = 8472
+  to_port   = 8472
+  self      = true
+}
+
 # Allow Prometheus to scrape node-exporter daemonset
 resource "aws_security_group_rule" "controller-node-exporter" {
   security_group_id = aws_security_group.controller.id
@@ -122,6 +163,17 @@ resource "aws_security_group_rule" "controller-node-exporter" {
   source_security_group_id = aws_security_group.worker.id
 }
 
+# Allow Prometheus to scrape kube-proxy
+resource "aws_security_group_rule" "kube-proxy-metrics" {
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10249
+  to_port                  = 10249
+  source_security_group_id = aws_security_group.worker.id
+}
+
 # Allow apiserver to access kubelets for exec, log, port-forward
 resource "aws_security_group_rule" "controller-kubelet" {
   security_group_id = aws_security_group.controller.id
@@ -143,6 +195,28 @@ resource "aws_security_group_rule" "controller-kubelet-self" {
   self      = true
 }
 
+# Allow Prometheus to scrape kube-scheduler
+resource "aws_security_group_rule" "controller-scheduler-metrics" {
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10251
+  to_port                  = 10251
+  source_security_group_id = aws_security_group.worker.id
+}
+
+# Allow Prometheus to scrape kube-controller-manager
+resource "aws_security_group_rule" "controller-manager-metrics" {
+  security_group_id = aws_security_group.controller.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 10252
+  to_port                  = 10252
+  source_security_group_id = aws_security_group.worker.id
+}
+
 resource "aws_security_group_rule" "controller-bgp" {
   security_group_id = aws_security_group.controller.id
 
@@ -227,6 +301,30 @@ resource "aws_security_group" "worker" {
   }
 }
 
+resource "aws_security_group_rule" "worker-icmp" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "icmp"
+  from_port                = 8
+  to_port                  = 0
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-icmp-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "icmp"
+  from_port = 8
+  to_port   = 0
+  self      = true
+}
+
 resource "aws_security_group_rule" "worker-ssh" {
   security_group_id = aws_security_group.worker.id
 
@@ -257,6 +355,31 @@ resource "aws_security_group_rule" "worker-https" {
   cidr_blocks = ["0.0.0.0/0"]
 }
 
+resource "aws_security_group_rule" "worker-cilium-health" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "tcp"
+  from_port                = 4240
+  to_port                  = 4240
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-cilium-health-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "tcp"
+  from_port = 4240
+  to_port   = 4240
+  self      = true
+}
+
+# IANA VXLAN default
 resource "aws_security_group_rule" "worker-vxlan" {
   count = var.networking == "flannel" ? 1 : 0
 
@@ -281,6 +404,31 @@ resource "aws_security_group_rule" "worker-vxlan-self" {
   self      = true
 }
 
+# Linux VXLAN default
+resource "aws_security_group_rule" "worker-linux-vxlan" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type                     = "ingress"
+  protocol                 = "udp"
+  from_port                = 8472
+  to_port                  = 8472
+  source_security_group_id = aws_security_group.controller.id
+}
+
+resource "aws_security_group_rule" "worker-linux-vxlan-self" {
+  count = var.networking == "cilium" ? 1 : 0
+
+  security_group_id = aws_security_group.worker.id
+
+  type      = "ingress"
+  protocol  = "udp"
+  from_port = 8472
+  to_port   = 8472
+  self      = true
+}
+
 # Allow Prometheus to scrape node-exporter daemonset
 resource "aws_security_group_rule" "worker-node-exporter" {
   security_group_id = aws_security_group.worker.id

aws/fedora-coreos/kubernetes/variables.tf

@@ -41,10 +41,10 @@ variable "worker_type" {
   default     = "t3.small"
 }
 
-variable "os_image" {
+variable "os_stream" {
   type        = string
-  description = "AMI channel for Fedora CoreOS (not yet used)"
-  default     = "coreos-stable"
+  description = "Fedora CoreOs image stream for instances (e.g. stable, testing, next)"
+  default     = "stable"
 }
 
 variable "disk_size" {

aws/fedora-coreos/kubernetes/versions.tf

@@ -1,11 +1,15 @@
 # Terraform version and plugin versions
 
 terraform {
-  required_version = "~> 0.12.6"
+  required_version = ">= 0.12.26, < 0.14.0"
   required_providers {
-    aws      = "~> 2.23"
-    ct       = "~> 0.4"
+    aws      = ">= 2.23, <= 4.0"
     template = "~> 2.1"
     null     = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
   }
 }

aws/fedora-coreos/kubernetes/workers.tf

@@ -8,7 +8,7 @@ module "workers" {
   security_groups = [aws_security_group.worker.id]
   worker_count    = var.worker_count
   instance_type   = var.worker_type
-  os_image        = var.os_image
+  os_stream       = var.os_stream
   disk_size       = var.disk_size
   spot_price      = var.worker_price
   target_groups   = var.worker_target_groups

aws/fedora-coreos/kubernetes/workers/ami.tf

@@ -14,10 +14,7 @@ data "aws_ami" "fedora-coreos" {
   }
 
   filter {
-    name   = "name"
-    values = ["fedora-coreos-31.*.*.*-hvm"]
+    name   = "description"
+    values = ["Fedora CoreOS ${var.os_stream} *"]
   }
-
-  # try to filter out dev images (AWS filters can't)
-  name_regex = "^fedora-coreos-31.[0-9]*.[0-9]*.[0-9]*-hvm*"
 }

aws/fedora-coreos/kubernetes/workers/fcc/worker.yaml

@@ -9,11 +9,12 @@ systemd:
       enabled: true
       contents: |
         [Unit]
-        Description=Wait for DNS entries
+        Description=Wait for DNS and hostname
         Before=kubelet.service
         [Service]
         Type=oneshot
         RemainAfterExit=true
+        ExecStartPre=/bin/sh -c 'while [ `hostname -s` == "localhost" ]; do sleep 1; done;'
         ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
         [Install]
         RequiredBy=kubelet.service
@@ -21,9 +22,10 @@ systemd:
       enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube (System Container)
+        Description=Kubelet (System Container)
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
@@ -43,16 +45,17 @@ systemd:
           --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 /var/lib/calico:/var/lib/calico \
+          --volume /var/lib/calico:/var/lib/calico:ro \
           --volume /var/lib/docker:/var/lib/docker \
           --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 \
-          k8s.gcr.io/hyperkube:v1.17.3 kubelet \
+          $${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 \
@@ -60,17 +63,16 @@ systemd:
           --cluster_dns=${cluster_dns_service_ip} \
           --cluster_domain=${cluster_domain_suffix} \
           --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
           --node-labels=node.kubernetes.io/node \
-          %{ for label in split(",", node_labels) }
+          %{~ for label in split(",", node_labels) ~}
           --node-labels=${label} \
-          %{ endfor ~}
+          %{~ endfor ~}
           --pod-manifest-path=/etc/kubernetes/manifests \
           --read-only-port=0 \
+          --rotate-certificates \
           --volume-plugin-dir=/var/lib/kubelet/volumeplugins
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
@@ -78,6 +80,18 @@ systemd:
         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:v1.19.0 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
+        [Install]
+        WantedBy=multi-user.target
 storage:
   directories:
     - path: /etc/kubernetes
@@ -91,6 +105,18 @@ storage:
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
+    - path: /etc/sysctl.d/reverse-path-filter.conf
+      contents:
+        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: |
@@ -98,19 +124,6 @@ storage:
           DefaultCPUAccounting=yes
           DefaultMemoryAccounting=yes
           DefaultBlockIOAccounting=yes
-    - path: /etc/sysconfig/docker
-      mode: 0644
-      overwrite: true
-      contents:
-        inline: |
-          # Modify these options if you want to change the way the docker daemon runs
-          OPTIONS="--selinux-enabled \
-            --log-driver=json-file \
-            --live-restore \
-            --default-ulimit nofile=1024:1024 \
-            --init-path /usr/libexec/docker/docker-init \
-            --userland-proxy-path /usr/libexec/docker/docker-proxy \
-          "
 passwd:
   users:
     - name: core

aws/fedora-coreos/kubernetes/workers/variables.tf

@@ -34,10 +34,10 @@ variable "instance_type" {
   default     = "t3.small"
 }
 
-variable "os_image" {
+variable "os_stream" {
   type        = string
-  description = "AMI channel for Fedora CoreOS (not yet used)"
-  default     = "coreos-stable"
+  description = "Fedora CoreOs image stream for instances (e.g. stable, testing, next)"
+  default     = "stable"
 }
 
 variable "disk_size" {

aws/fedora-coreos/kubernetes/workers/versions.tf

@@ -1,4 +1,14 @@
+# Terraform version and plugin versions
 
 terraform {
-  required_version = ">= 0.12"
+  required_version = ">= 0.12.26, < 0.14.0"
+  required_providers {
+    aws      = ">= 2.23, <= 4.0"
+    template = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
+  }
 }

azure/container-linux/kubernetes/README.md

@@ -11,8 +11,8 @@ 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 v1.17.3 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* Kubernetes v1.19.0 (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/), [low-priority](https://typhoon.psdn.io/cl/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
 * Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)

azure/container-linux/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=796194583426593d1a62b6f1bf3f7ffed8fca140"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
 
   cluster_name = var.cluster_name
   api_servers  = [format("%s.%s", var.cluster_name, var.dns_zone)]

azure/container-linux/kubernetes/cl/controller.yaml

@@ -2,12 +2,14 @@
 systemd:
   units:
     - name: etcd-member.service
-      enable: true
+      enabled: true
       dropins:
         - name: 40-etcd-cluster.conf
           contents: |
             [Service]
-            Environment="ETCD_IMAGE_TAG=v3.4.3"
+            Environment="ETCD_IMAGE_TAG=v3.4.12"
+            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://${etcd_domain}:2380"
@@ -26,11 +28,11 @@ systemd:
             Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
             Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
     - name: docker.service
-      enable: true
+      enabled: true
     - name: locksmithd.service
       mask: true
     - name: wait-for-dns.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Wait for DNS entries
@@ -44,12 +46,14 @@ systemd:
         RequiredBy=kubelet.service
         RequiredBy=etcd-member.service
     - name: kubelet.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube
+        Description=Kubelet
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
+        Environment=KUBELET_CGROUP_DRIVER=${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
@@ -78,7 +82,7 @@ systemd:
           --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 \
+          --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 \
@@ -88,25 +92,24 @@ systemd:
           --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 \
-          docker://k8s.gcr.io/hyperkube:v1.17.3 \
-          --exec=/usr/local/bin/kubelet -- \
+          $${KUBELET_IMAGE} -- \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
+          --cgroup-driver=$${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 \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
-          --node-labels=node.kubernetes.io/master \
           --node-labels=node.kubernetes.io/controller="true" \
           --pod-manifest-path=/etc/kubernetes/manifests \
           --read-only-port=0 \
-          --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
+          --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
@@ -122,7 +125,6 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        ExecStartPre=-/usr/bin/bash -c 'set -x && [ -n "$(ls /opt/bootstrap/assets/manifests-*/* 2>/dev/null)" ] && mv /opt/bootstrap/assets/manifests-*/* /opt/bootstrap/assets/manifests && rm -rf /opt/bootstrap/assets/manifests-*'
         ExecStart=/usr/bin/rkt run \
             --trust-keys-from-https \
             --volume config,kind=host,source=/etc/kubernetes/bootstrap-secrets \
@@ -132,7 +134,7 @@ systemd:
             --volume script,kind=host,source=/opt/bootstrap/apply \
             --mount volume=script,target=/apply \
             --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.3 \
+            docker://quay.io/poseidon/kubelet:v1.19.0 \
             --net=host \
             --dns=host \
             --exec=/apply
@@ -140,6 +142,11 @@ systemd:
         [Install]
         WantedBy=multi-user.target
 storage:
+  directories:
+    - path: /var/lib/etcd
+      filesystem: root
+      mode: 0700
+      overwrite: true
   files:
     - path: /etc/kubernetes/kubeconfig
       filesystem: root
@@ -161,14 +168,15 @@ storage:
           mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
           chown -R etcd:etcd /etc/ssl/etcd
           chmod -R 500 /etc/ssl/etcd
+          chmod -R 700 /var/lib/etcd
           mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
           mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
-          sudo mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
-          rm -rf assets auth static-manifests tls
+          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
@@ -186,6 +194,7 @@ storage:
           done
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
+      mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184

azure/container-linux/kubernetes/controllers.tf

@@ -15,8 +15,10 @@ resource "azurerm_dns_a_record" "etcds" {
 }
 
 locals {
-  # Channel for a Container Linux derivative
+  # Container Linux derivative
   # coreos-stable -> Container Linux Stable
+  # flatcar-stable -> Flatcar Linux Stable
+  flavor  = split("-", var.os_image)[0]
   channel = split("-", var.os_image)[1]
 }
 
@@ -32,92 +34,64 @@ resource "azurerm_availability_set" "controllers" {
 }
 
 # Controller instances
-resource "azurerm_virtual_machine" "controllers" {
+resource "azurerm_linux_virtual_machine" "controllers" {
   count               = var.controller_count
   resource_group_name = azurerm_resource_group.cluster.name
 
   name                = "${var.cluster_name}-controller-${count.index}"
   location            = var.region
   availability_set_id = azurerm_availability_set.controllers.id
-  vm_size             = var.controller_type
 
-  # boot
-  storage_image_reference {
-    publisher = "CoreOS"
-    offer     = "CoreOS"
+  size        = var.controller_type
+  custom_data = base64encode(data.ct_config.controller-ignitions.*.rendered[count.index])
+
+  # storage
+  os_disk {
+    name                 = "${var.cluster_name}-controller-${count.index}"
+    caching              = "None"
+    disk_size_gb         = var.disk_size
+    storage_account_type = "Premium_LRS"
+  }
+
+  # CoreOS Container Linux or Flatcar Container Linux
+  source_image_reference {
+    publisher = local.flavor == "flatcar" ? "Kinvolk" : "CoreOS"
+    offer     = local.flavor == "flatcar" ? "flatcar-container-linux-free" : "CoreOS"
     sku       = local.channel
     version   = "latest"
   }
 
-  # storage
-  storage_os_disk {
-    name              = "${var.cluster_name}-controller-${count.index}"
-    create_option     = "FromImage"
-    caching           = "ReadWrite"
-    disk_size_gb      = var.disk_size
-    os_type           = "Linux"
-    managed_disk_type = "Premium_LRS"
-  }
+  # Gross hack for Flatcar Linux
+  dynamic "plan" {
+    for_each = local.flavor == "flatcar" ? [1] : []
 
-  # network
-  network_interface_ids = [azurerm_network_interface.controllers.*.id[count.index]]
-
-  os_profile {
-    computer_name  = "${var.cluster_name}-controller-${count.index}"
-    admin_username = "core"
-    custom_data    = data.ct_config.controller-ignitions.*.rendered[count.index]
-  }
-
-  # Azure mandates setting an ssh_key, even though Ignition custom_data handles it too
-  os_profile_linux_config {
-    disable_password_authentication = true
-
-    ssh_keys {
-      path     = "/home/core/.ssh/authorized_keys"
-      key_data = var.ssh_authorized_key
+    content {
+      name      = local.channel
+      publisher = "kinvolk"
+      product   = "flatcar-container-linux-free"
     }
   }
 
-  # lifecycle
-  delete_os_disk_on_termination    = true
-  delete_data_disks_on_termination = true
+  # network
+  network_interface_ids = [
+    azurerm_network_interface.controllers.*.id[count.index]
+  ]
+
+  # Azure requires setting admin_ssh_key, though Ignition custom_data handles it too
+  admin_username = "core"
+  admin_ssh_key {
+    username   = "core"
+    public_key = var.ssh_authorized_key
+  }
 
   lifecycle {
     ignore_changes = [
-      storage_os_disk,
-      os_profile,
+      os_disk,
+      custom_data,
     ]
   }
 }
 
-# Controller NICs with public and private IPv4
-resource "azurerm_network_interface" "controllers" {
-  count               = var.controller_count
-  resource_group_name = azurerm_resource_group.cluster.name
-
-  name                      = "${var.cluster_name}-controller-${count.index}"
-  location                  = azurerm_resource_group.cluster.location
-  network_security_group_id = azurerm_network_security_group.controller.id
-
-  ip_configuration {
-    name                          = "ip0"
-    subnet_id                     = azurerm_subnet.controller.id
-    private_ip_address_allocation = "dynamic"
-
-    # public IPv4
-    public_ip_address_id = azurerm_public_ip.controllers.*.id[count.index]
-  }
-}
-
-# Add controller NICs to the controller backend address pool
-resource "azurerm_network_interface_backend_address_pool_association" "controllers" {
-  count = var.controller_count
-
-  network_interface_id    = azurerm_network_interface.controllers[count.index].id
-  ip_configuration_name   = "ip0"
-  backend_address_pool_id = azurerm_lb_backend_address_pool.controller.id
-}
-
 # Controller public IPv4 addresses
 resource "azurerm_public_ip" "controllers" {
   count               = var.controller_count
@@ -129,12 +103,46 @@ resource "azurerm_public_ip" "controllers" {
   allocation_method = "Static"
 }
 
+# Controller NICs with public and private IPv4
+resource "azurerm_network_interface" "controllers" {
+  count               = var.controller_count
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name     = "${var.cluster_name}-controller-${count.index}"
+  location = azurerm_resource_group.cluster.location
+
+  ip_configuration {
+    name                          = "ip0"
+    subnet_id                     = azurerm_subnet.controller.id
+    private_ip_address_allocation = "Dynamic"
+    # instance public IPv4
+    public_ip_address_id = azurerm_public_ip.controllers.*.id[count.index]
+  }
+}
+
+# Associate controller network interface with controller security group
+resource "azurerm_network_interface_security_group_association" "controllers" {
+  count = var.controller_count
+
+  network_interface_id      = azurerm_network_interface.controllers[count.index].id
+  network_security_group_id = azurerm_network_security_group.controller.id
+}
+
+# Associate controller network interface with controller backend address pool
+resource "azurerm_network_interface_backend_address_pool_association" "controllers" {
+  count = var.controller_count
+
+  network_interface_id    = azurerm_network_interface.controllers[count.index].id
+  ip_configuration_name   = "ip0"
+  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]
-  pretty_print = false
-  snippets     = var.controller_clc_snippets
+  count    = var.controller_count
+  content  = data.template_file.controller-configs.*.rendered[count.index]
+  strict   = true
+  snippets = var.controller_snippets
 }
 
 # Controller Container Linux configs
@@ -149,6 +157,7 @@ data "template_file" "controller-configs" {
     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"
     kubeconfig             = indent(10, module.bootstrap.kubeconfig-kubelet)
     ssh_authorized_key     = var.ssh_authorized_key
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)

azure/container-linux/kubernetes/lb.tf

@@ -72,6 +72,7 @@ resource "azurerm_lb_rule" "ingress-http" {
   name                           = "ingress-http"
   loadbalancer_id                = azurerm_lb.cluster.id
   frontend_ip_configuration_name = "ingress"
+  disable_outbound_snat          = true
 
   protocol                = "Tcp"
   frontend_port           = 80
@@ -86,6 +87,7 @@ resource "azurerm_lb_rule" "ingress-https" {
   name                           = "ingress-https"
   loadbalancer_id                = azurerm_lb.cluster.id
   frontend_ip_configuration_name = "ingress"
+  disable_outbound_snat          = true
 
   protocol                = "Tcp"
   frontend_port           = 443
@@ -94,6 +96,20 @@ resource "azurerm_lb_rule" "ingress-https" {
   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 {
+    name = "ingress"
+  }
+
+  protocol                = "All"
+  backend_address_pool_id = azurerm_lb_backend_address_pool.worker.id
+}
+
 # Address pool of controllers
 resource "azurerm_lb_backend_address_pool" "controller" {
   resource_group_name = azurerm_resource_group.cluster.name

azure/container-linux/kubernetes/network.tf

@@ -21,7 +21,12 @@ resource "azurerm_subnet" "controller" {
 
   name                 = "controller"
   virtual_network_name = azurerm_virtual_network.network.name
-  address_prefix       = cidrsubnet(var.host_cidr, 1, 0)
+  address_prefixes     = [cidrsubnet(var.host_cidr, 1, 0)]
+}
+
+resource "azurerm_subnet_network_security_group_association" "controller" {
+  subnet_id                 = azurerm_subnet.controller.id
+  network_security_group_id = azurerm_network_security_group.controller.id
 }
 
 resource "azurerm_subnet" "worker" {
@@ -29,6 +34,11 @@ resource "azurerm_subnet" "worker" {
 
   name                 = "worker"
   virtual_network_name = azurerm_virtual_network.network.name
-  address_prefix       = cidrsubnet(var.host_cidr, 1, 1)
+  address_prefixes     = [cidrsubnet(var.host_cidr, 1, 1)]
+}
+
+resource "azurerm_subnet_network_security_group_association" "worker" {
+  subnet_id                 = azurerm_subnet.worker.id
+  network_security_group_id = azurerm_network_security_group.worker.id
 }
 

azure/container-linux/kubernetes/security.tf

@@ -7,6 +7,21 @@ resource "azurerm_network_security_group" "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
 
@@ -100,6 +115,22 @@ resource "azurerm_network_security_rule" "controller-apiserver" {
   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
 
@@ -115,6 +146,21 @@ resource "azurerm_network_security_rule" "controller-vxlan" {
   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
@@ -191,6 +237,21 @@ resource "azurerm_network_security_group" "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
 
@@ -236,6 +297,22 @@ resource "azurerm_network_security_rule" "worker-https" {
   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
 
@@ -251,6 +328,21 @@ resource "azurerm_network_security_rule" "worker-vxlan" {
   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

azure/container-linux/kubernetes/ssh.tf

@@ -13,7 +13,7 @@ resource "null_resource" "copy-controller-secrets" {
 
   depends_on = [
     module.bootstrap,
-    azurerm_virtual_machine.controllers
+    azurerm_linux_virtual_machine.controllers
   ]
 
   connection {

azure/container-linux/kubernetes/variables.tf

@@ -48,8 +48,8 @@ variable "worker_type" {
 
 variable "os_image" {
   type        = string
-  default     = "coreos-stable"
-  description = "Channel for a Container Linux derivative (coreos-stable, coreos-beta, coreos-alpha)"
+  description = "Channel for a Container Linux derivative (flatcar-stable, flatcar-beta, flatcar-alpha, flatcar-edge, coreos-stable, coreos-beta, coreos-alpha)"
+  default     = "flatcar-stable"
 }
 
 variable "disk_size" {
@@ -60,17 +60,17 @@ variable "disk_size" {
 
 variable "worker_priority" {
   type        = string
-  description = "Set worker priority to Low to use reduced cost surplus capacity, with the tradeoff that instances can be deallocated at any time."
+  description = "Set worker priority to Spot to use reduced cost surplus capacity, with the tradeoff that instances can be deallocated at any time."
   default     = "Regular"
 }
 
-variable "controller_clc_snippets" {
+variable "controller_snippets" {
   type        = list(string)
   description = "Controller Container Linux Config snippets"
   default     = []
 }
 
-variable "worker_clc_snippets" {
+variable "worker_snippets" {
   type        = list(string)
   description = "Worker Container Linux Config snippets"
   default     = []
@@ -83,12 +83,6 @@ 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 (flannel or calico)"
@@ -136,6 +130,12 @@ 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) "

azure/container-linux/kubernetes/versions.tf

@@ -1,12 +1,16 @@
 # Terraform version and plugin versions
 
 terraform {
-  required_version = "~> 0.12.6"
+  required_version = ">= 0.12.26, < 0.14.0"
   required_providers {
-    azurerm  = "~> 1.27"
-    ct       = "~> 0.3"
+    azurerm  = "~> 2.8"
     template = "~> 2.1"
     null     = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
   }
 }
 

azure/container-linux/kubernetes/workers.tf

@@ -19,7 +19,6 @@ module "workers" {
   ssh_authorized_key    = var.ssh_authorized_key
   service_cidr          = var.service_cidr
   cluster_domain_suffix = var.cluster_domain_suffix
-  clc_snippets          = var.worker_clc_snippets
+  snippets              = var.worker_snippets
   node_labels           = var.worker_node_labels
 }
-

azure/container-linux/kubernetes/workers/cl/worker.yaml

@@ -2,11 +2,11 @@
 systemd:
   units:
     - name: docker.service
-      enable: true
+      enabled: true
     - name: locksmithd.service
       mask: true
     - name: wait-for-dns.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Wait for DNS entries
@@ -19,12 +19,14 @@ systemd:
         [Install]
         RequiredBy=kubelet.service
     - name: kubelet.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube
+        Description=Kubelet
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
+        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
@@ -53,7 +55,7 @@ systemd:
           --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 \
+          --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 \
@@ -63,26 +65,26 @@ systemd:
           --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 \
-          docker://k8s.gcr.io/hyperkube:v1.17.3 \
-          --exec=/usr/local/bin/kubelet -- \
+          $${KUBELET_IMAGE} -- \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
+          --cgroup-driver=$${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 \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
           --node-labels=node.kubernetes.io/node \
-          %{ for label in split(",", node_labels) }
+          %{~ for label in split(",", node_labels) ~}
           --node-labels=${label} \
-          %{ endfor ~}
+          %{~ 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
@@ -90,7 +92,7 @@ systemd:
         [Install]
         WantedBy=multi-user.target
     - name: delete-node.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Waiting to delete Kubernetes node on shutdown
@@ -111,6 +113,7 @@ storage:
           ${kubeconfig}
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
+      mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184
@@ -126,11 +129,10 @@ storage:
             --volume config,kind=host,source=/etc/kubernetes \
             --mount volume=config,target=/etc/kubernetes \
             --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.3 \
+            docker://quay.io/poseidon/kubelet:v1.19.0 \
             --net=host \
             --dns=host \
-            -- \
-            kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname | tr '[:upper:]' '[:lower:]')
+            --exec=/usr/local/bin/kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname | tr '[:upper:]' '[:lower:]')
 passwd:
   users:
     - name: core

azure/container-linux/kubernetes/workers/variables.tf

@@ -46,17 +46,17 @@ variable "vm_type" {
 
 variable "os_image" {
   type        = string
-  description = "Channel for a Container Linux derivative (coreos-stable, coreos-beta, coreos-alpha)"
-  default     = "coreos-stable"
+  description = "Channel for a Container Linux derivative (flatcar-stable, flatcar-beta, flatcar-alpha, flatcar-edge, coreos-stable, coreos-beta, coreos-alpha)"
+  default     = "flatcar-stable"
 }
 
 variable "priority" {
   type        = string
-  description = "Set priority to Low to use reduced cost surplus capacity, with the tradeoff that instances can be evicted at any time."
+  description = "Set priority to Spot to use reduced cost surplus capacity, with the tradeoff that instances can be evicted at any time."
   default     = "Regular"
 }
 
-variable "clc_snippets" {
+variable "snippets" {
   type        = list(string)
   description = "Container Linux Config snippets"
   default     = []

azure/container-linux/kubernetes/workers/versions.tf

@@ -1,4 +1,14 @@
+# Terraform version and plugin versions
 
 terraform {
-  required_version = ">= 0.12"
+  required_version = ">= 0.12.26, < 0.14.0"
+  required_providers {
+    azurerm  = "~> 2.8"
+    template = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
+  }
 }

azure/container-linux/kubernetes/workers/workers.tf

@@ -1,57 +1,57 @@
 locals {
-  # Channel for a Container Linux derivative
   # coreos-stable -> Container Linux Stable
+  # flatcar-stable -> Flatcar Linux Stable
+  flavor  = split("-", var.os_image)[0]
   channel = split("-", var.os_image)[1]
 }
 
 # Workers scale set
-resource "azurerm_virtual_machine_scale_set" "workers" {
+resource "azurerm_linux_virtual_machine_scale_set" "workers" {
   resource_group_name = var.resource_group_name
 
-  name                   = "${var.name}-workers"
-  location               = var.region
+  name      = "${var.name}-worker"
+  location  = var.region
+  sku       = var.vm_type
+  instances = var.worker_count
+  # instance name prefix for instances in the set
+  computer_name_prefix   = "${var.name}-worker"
   single_placement_group = false
+  custom_data            = base64encode(data.ct_config.worker-ignition.rendered)
 
-  sku {
-    name     = var.vm_type
-    tier     = "standard"
-    capacity = var.worker_count
+  # storage
+  os_disk {
+    storage_account_type = "Standard_LRS"
+    caching              = "ReadWrite"
   }
 
-  # boot
-  storage_profile_image_reference {
-    publisher = "CoreOS"
-    offer     = "CoreOS"
+  # CoreOS Container Linux or Flatcar Container Linux
+  source_image_reference {
+    publisher = local.flavor == "flatcar" ? "Kinvolk" : "CoreOS"
+    offer     = local.flavor == "flatcar" ? "flatcar-container-linux-free" : "CoreOS"
     sku       = local.channel
     version   = "latest"
   }
 
-  # storage
-  storage_profile_os_disk {
-    create_option     = "FromImage"
-    caching           = "ReadWrite"
-    os_type           = "linux"
-    managed_disk_type = "Standard_LRS"
-  }
+  # Gross hack for Flatcar Linux
+  dynamic "plan" {
+    for_each = local.flavor == "flatcar" ? [1] : []
 
-  os_profile {
-    computer_name_prefix = "${var.name}-worker-"
-    admin_username       = "core"
-    custom_data          = data.ct_config.worker-ignition.rendered
-  }
-
-  # Azure mandates setting an ssh_key, even though Ignition custom_data handles it too
-  os_profile_linux_config {
-    disable_password_authentication = true
-
-    ssh_keys {
-      path     = "/home/core/.ssh/authorized_keys"
-      key_data = var.ssh_authorized_key
+    content {
+      name      = local.channel
+      publisher = "kinvolk"
+      product   = "flatcar-container-linux-free"
     }
   }
 
+  # Azure requires setting admin_ssh_key, though Ignition custom_data handles it too
+  admin_username = "core"
+  admin_ssh_key {
+    username   = "core"
+    public_key = var.ssh_authorized_key
+  }
+
   # network
-  network_profile {
+  network_interface {
     name                      = "nic0"
     primary                   = true
     network_security_group_id = var.security_group_id
@@ -67,10 +67,10 @@ resource "azurerm_virtual_machine_scale_set" "workers" {
   }
 
   # lifecycle
-  upgrade_policy_mode = "Manual"
-  # eviction policy may only be set when priority is Low
+  upgrade_mode = "Manual"
+  # eviction policy may only be set when priority is Spot
   priority        = var.priority
-  eviction_policy = var.priority == "Low" ? "Delete" : null
+  eviction_policy = var.priority == "Spot" ? "Delete" : null
 }
 
 # Scale up or down to maintain desired number, tolerating deallocations.
@@ -82,7 +82,7 @@ resource "azurerm_monitor_autoscale_setting" "workers" {
 
   # autoscale
   enabled            = true
-  target_resource_id = azurerm_virtual_machine_scale_set.workers.id
+  target_resource_id = azurerm_linux_virtual_machine_scale_set.workers.id
 
   profile {
     name = "default"
@@ -97,9 +97,9 @@ resource "azurerm_monitor_autoscale_setting" "workers" {
 
 # Worker Ignition configs
 data "ct_config" "worker-ignition" {
-  content      = data.template_file.worker-config.rendered
-  pretty_print = false
-  snippets     = var.clc_snippets
+  content  = data.template_file.worker-config.rendered
+  strict   = true
+  snippets = var.snippets
 }
 
 # Worker Container Linux configs
@@ -111,6 +111,7 @@ data "template_file" "worker-config" {
     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)
   }
 }

azure/fedora-coreos/kubernetes/LICENSE

@@ -0,0 +1,23 @@
+The MIT License (MIT)
+
+Copyright (c) 2020 Typhoon Authors
+Copyright (c) 2020 Dalton Hubble
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+

azure/fedora-coreos/kubernetes/README.md

@@ -0,0 +1,23 @@
+# Typhoon <img align="right" src="https://storage.googleapis.com/poseidon/typhoon-logo.png">
+
+Typhoon is a minimal and free Kubernetes distribution.
+
+* Minimal, stable base Kubernetes distribution
+* Declarative infrastructure and configuration
+* Free (freedom and cost) and privacy-respecting
+* Practical for labs, datacenters, and clouds
+
+Typhoon distributes upstream Kubernetes, architectural conventions, and cluster addons, much like a GNU/Linux distribution provides the Linux kernel and userspace components.
+
+## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
+
+* Kubernetes v1.19.0 (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
+* Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
+
+## Docs
+
+Please see the [official docs](https://typhoon.psdn.io) and the Azure [tutorial](https://typhoon.psdn.io/fedora-coreos/azure/).
+

azure/fedora-coreos/kubernetes/bootstrap.tf

@@ -0,0 +1,26 @@
+# Kubernetes assets (kubeconfig, manifests)
+module "bootstrap" {
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
+
+  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
+
+  # only effective with Calico networking
+  # we should be able to use 1450 MTU, but in practice, 1410 was needed
+  network_encapsulation = "vxlan"
+  network_mtu           = "1410"
+
+  pod_cidr              = var.pod_cidr
+  service_cidr          = var.service_cidr
+  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"
+}
+

azure/fedora-coreos/kubernetes/controllers.tf

@@ -0,0 +1,151 @@
+# Discrete DNS records for each controller's private IPv4 for etcd usage
+resource "azurerm_dns_a_record" "etcds" {
+  count               = var.controller_count
+  resource_group_name = var.dns_zone_group
+
+  # DNS Zone name where record should be created
+  zone_name = var.dns_zone
+
+  # DNS record
+  name = format("%s-etcd%d", var.cluster_name, count.index)
+  ttl  = 300
+
+  # private IPv4 address for etcd
+  records = [azurerm_network_interface.controllers.*.private_ip_address[count.index]]
+}
+
+# Controller availability set to spread controllers
+resource "azurerm_availability_set" "controllers" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name                         = "${var.cluster_name}-controllers"
+  location                     = var.region
+  platform_fault_domain_count  = 2
+  platform_update_domain_count = 4
+  managed                      = true
+}
+
+# Controller instances
+resource "azurerm_linux_virtual_machine" "controllers" {
+  count               = var.controller_count
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name                = "${var.cluster_name}-controller-${count.index}"
+  location            = var.region
+  availability_set_id = azurerm_availability_set.controllers.id
+
+  size        = var.controller_type
+  custom_data = base64encode(data.ct_config.controller-ignitions.*.rendered[count.index])
+
+  # storage
+  source_image_id = var.os_image
+  os_disk {
+    name                 = "${var.cluster_name}-controller-${count.index}"
+    caching              = "None"
+    disk_size_gb         = var.disk_size
+    storage_account_type = "Premium_LRS"
+  }
+
+  # network
+  network_interface_ids = [
+    azurerm_network_interface.controllers.*.id[count.index]
+  ]
+
+  # Azure requires setting admin_ssh_key, though Ignition custom_data handles it too
+  admin_username = "core"
+  admin_ssh_key {
+    username   = "core"
+    public_key = var.ssh_authorized_key
+  }
+
+  lifecycle {
+    ignore_changes = [
+      os_disk,
+      custom_data,
+    ]
+  }
+}
+
+# Controller public IPv4 addresses
+resource "azurerm_public_ip" "controllers" {
+  count               = var.controller_count
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name              = "${var.cluster_name}-controller-${count.index}"
+  location          = azurerm_resource_group.cluster.location
+  sku               = "Standard"
+  allocation_method = "Static"
+}
+
+# Controller NICs with public and private IPv4
+resource "azurerm_network_interface" "controllers" {
+  count               = var.controller_count
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name     = "${var.cluster_name}-controller-${count.index}"
+  location = azurerm_resource_group.cluster.location
+
+  ip_configuration {
+    name                          = "ip0"
+    subnet_id                     = azurerm_subnet.controller.id
+    private_ip_address_allocation = "Dynamic"
+    # instance public IPv4
+    public_ip_address_id = azurerm_public_ip.controllers.*.id[count.index]
+  }
+}
+
+# Associate controller network interface with controller security group
+resource "azurerm_network_interface_security_group_association" "controllers" {
+  count = var.controller_count
+
+  network_interface_id      = azurerm_network_interface.controllers[count.index].id
+  network_security_group_id = azurerm_network_security_group.controller.id
+}
+
+# Associate controller network interface with controller backend address pool
+resource "azurerm_network_interface_backend_address_pool_association" "controllers" {
+  count = var.controller_count
+
+  network_interface_id    = azurerm_network_interface.controllers[count.index].id
+  ip_configuration_name   = "ip0"
+  backend_address_pool_id = azurerm_lb_backend_address_pool.controller.id
+}
+
+# Controller Ignition configs
+data "ct_config" "controller-ignitions" {
+  count    = var.controller_count
+  content  = data.template_file.controller-configs.*.rendered[count.index]
+  strict   = true
+  snippets = var.controller_snippets
+}
+
+# Controller Fedora CoreOS configs
+data "template_file" "controller-configs" {
+  count = var.controller_count
+
+  template = file("${path.module}/fcc/controller.yaml")
+
+  vars = {
+    # 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)
+    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
+  }
+}
+
+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
+  }
+}
+

azure/fedora-coreos/kubernetes/fcc/controller.yaml

@@ -0,0 +1,228 @@
+---
+variant: fcos
+version: 1.0.0
+systemd:
+  units:
+    - name: etcd-member.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=etcd (System Container)
+        Documentation=https://github.com/coreos/etcd
+        Wants=network-online.target network.target
+        After=network-online.target
+        [Service]
+        # https://github.com/opencontainers/runc/pull/1807
+        # Type=notify
+        # NotifyAccess=exec
+        Type=exec
+        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:v3.4.12
+        ExecStop=/usr/bin/podman stop etcd
+        [Install]
+        WantedBy=multi-user.target
+    - name: docker.service
+      enabled: true
+    - name: wait-for-dns.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Wait for DNS entries
+        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)
+        Wants=rpc-statd.service
+        [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
+        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/podman rm kubelet
+        ExecStart=/usr/bin/podman run --name kubelet \
+          --privileged \
+          --pid host \
+          --network host \
+          --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 /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 /var/lib/calico:/var/lib/calico:ro \
+          --volume /var/lib/docker:/var/lib/docker \
+          --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 \
+          --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/podman stop kubelet
+        Delegate=yes
+        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
+        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 /opt/bootstrap/assets:/assets:ro,Z \
+            --volume /opt/bootstrap/apply:/apply:ro,Z \
+            --entrypoint=/apply \
+            quay.io/poseidon/kubelet:v1.19.0
+        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:
+    - path: /etc/kubernetes/kubeconfig
+      mode: 0644
+      contents:
+        inline: |
+          ${kubeconfig}
+    - 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/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
+          chcon -R -u system_u -t container_file_t /etc/kubernetes/bootstrap-secrets
+    - path: /opt/bootstrap/apply
+      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
+      contents:
+        inline: |
+          fs.inotify.max_user_watches=16184
+    - path: /etc/sysctl.d/reverse-path-filter.conf
+      contents:
+        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: |
+          [Manager]
+          DefaultCPUAccounting=yes
+          DefaultMemoryAccounting=yes
+          DefaultBlockIOAccounting=yes
+    - path: /etc/etcd/etcd.env
+      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://${etcd_domain}:2379
+          ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${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}
+

azure/fedora-coreos/kubernetes/lb.tf

@@ -0,0 +1,161 @@
+# DNS record for the apiserver load balancer
+resource "azurerm_dns_a_record" "apiserver" {
+  resource_group_name = var.dns_zone_group
+
+  # DNS Zone name where record should be created
+  zone_name = var.dns_zone
+
+  # DNS record
+  name = var.cluster_name
+  ttl  = 300
+
+  # IPv4 address of apiserver load balancer
+  records = [azurerm_public_ip.apiserver-ipv4.ip_address]
+}
+
+# Static IPv4 address for the apiserver frontend
+resource "azurerm_public_ip" "apiserver-ipv4" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name              = "${var.cluster_name}-apiserver-ipv4"
+  location          = var.region
+  sku               = "Standard"
+  allocation_method = "Static"
+}
+
+# Static IPv4 address for the ingress frontend
+resource "azurerm_public_ip" "ingress-ipv4" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name              = "${var.cluster_name}-ingress-ipv4"
+  location          = var.region
+  sku               = "Standard"
+  allocation_method = "Static"
+}
+
+# Network Load Balancer for apiservers and ingress
+resource "azurerm_lb" "cluster" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name     = var.cluster_name
+  location = var.region
+  sku      = "Standard"
+
+  frontend_ip_configuration {
+    name                 = "apiserver"
+    public_ip_address_id = azurerm_public_ip.apiserver-ipv4.id
+  }
+
+  frontend_ip_configuration {
+    name                 = "ingress"
+    public_ip_address_id = azurerm_public_ip.ingress-ipv4.id
+  }
+}
+
+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
+}
+
+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
+}
+
+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
+}
+
+# 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 {
+    name = "ingress"
+  }
+
+  protocol                = "All"
+  backend_address_pool_id = azurerm_lb_backend_address_pool.worker.id
+}
+
+# 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
+}
+
+# Health checks / probes
+
+# 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"
+  port            = 6443
+
+  # unhealthy threshold
+  number_of_probes = 3
+
+  interval_in_seconds = 5
+}
+
+# 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"
+  port            = 10254
+  request_path    = "/healthz"
+
+  # unhealthy threshold
+  number_of_probes = 3
+
+  interval_in_seconds = 5
+}
+

azure/fedora-coreos/kubernetes/network.tf

@@ -0,0 +1,44 @@
+# Organize cluster into a resource group
+resource "azurerm_resource_group" "cluster" {
+  name     = var.cluster_name
+  location = var.region
+}
+
+resource "azurerm_virtual_network" "network" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name          = var.cluster_name
+  location      = azurerm_resource_group.cluster.location
+  address_space = [var.host_cidr]
+}
+
+# Subnets - separate subnets for controller and workers because Azure
+# network security groups are based on IPv4 CIDR rather than instance
+# tags like GCP or security group membership like AWS
+
+resource "azurerm_subnet" "controller" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name                 = "controller"
+  virtual_network_name = azurerm_virtual_network.network.name
+  address_prefixes     = [cidrsubnet(var.host_cidr, 1, 0)]
+}
+
+resource "azurerm_subnet_network_security_group_association" "controller" {
+  subnet_id                 = azurerm_subnet.controller.id
+  network_security_group_id = azurerm_network_security_group.controller.id
+}
+
+resource "azurerm_subnet" "worker" {
+  resource_group_name = azurerm_resource_group.cluster.name
+
+  name                 = "worker"
+  virtual_network_name = azurerm_virtual_network.network.name
+  address_prefixes     = [cidrsubnet(var.host_cidr, 1, 1)]
+}
+
+resource "azurerm_subnet_network_security_group_association" "worker" {
+  subnet_id                 = azurerm_subnet.worker.id
+  network_security_group_id = azurerm_network_security_group.worker.id
+}
+

azure/fedora-coreos/kubernetes/outputs.tf

@@ -0,0 +1,59 @@
+output "kubeconfig-admin" {
+  value = module.bootstrap.kubeconfig-admin
+}
+
+# Outputs for Kubernetes Ingress
+
+output "ingress_static_ipv4" {
+  value       = azurerm_public_ip.ingress-ipv4.ip_address
+  description = "IPv4 address of the load balancer for distributing traffic to Ingress controllers"
+}
+
+# Outputs for worker pools
+
+output "region" {
+  value = azurerm_resource_group.cluster.location
+}
+
+output "resource_group_name" {
+  value = azurerm_resource_group.cluster.name
+}
+
+output "resource_group_id" {
+  value = azurerm_resource_group.cluster.id
+}
+
+output "subnet_id" {
+  value = azurerm_subnet.worker.id
+}
+
+output "security_group_id" {
+  value = azurerm_network_security_group.worker.id
+}
+
+output "kubeconfig" {
+  value = module.bootstrap.kubeconfig-kubelet
+}
+
+# Outputs for custom firewalling
+
+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
+}
+
+# Outputs for custom load balancing
+
+output "loadbalancer_id" {
+  description = "ID of the cluster load balancer"
+  value       = azurerm_lb.cluster.id
+}
+
+output "backend_address_pool_id" {
+  description = "ID of the worker backend address pool"
+  value       = azurerm_lb_backend_address_pool.worker.id
+}

azure/fedora-coreos/kubernetes/security.tf

@@ -0,0 +1,428 @@
+# 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  = "*"
+}
+

azure/fedora-coreos/kubernetes/ssh.tf

@@ -0,0 +1,59 @@
+locals {
+  # format assets for distribution
+  assets_bundle = [
+    # header with the unpack location
+    for key, value in module.bootstrap.assets_dist :
+    format("##### %s\n%s", key, value)
+  ]
+}
+
+# Secure copy assets to controllers.
+resource "null_resource" "copy-controller-secrets" {
+  count = var.controller_count
+
+  depends_on = [
+    module.bootstrap,
+    azurerm_linux_virtual_machine.controllers
+  ]
+
+  connection {
+    type    = "ssh"
+    host    = azurerm_public_ip.controllers.*.ip_address[count.index]
+    user    = "core"
+    timeout = "15m"
+  }
+
+  provisioner "file" {
+    content     = join("\n", local.assets_bundle)
+    destination = "$HOME/assets"
+  }
+
+  provisioner "remote-exec" {
+    inline = [
+      "sudo /opt/bootstrap/layout",
+    ]
+  }
+}
+
+# Connect to a controller to perform one-time cluster bootstrap.
+resource "null_resource" "bootstrap" {
+  depends_on = [
+    null_resource.copy-controller-secrets,
+    module.workers,
+    azurerm_dns_a_record.apiserver,
+  ]
+
+  connection {
+    type    = "ssh"
+    host    = azurerm_public_ip.controllers.*.ip_address[0]
+    user    = "core"
+    timeout = "15m"
+  }
+
+  provisioner "remote-exec" {
+    inline = [
+      "sudo systemctl start bootstrap",
+    ]
+  }
+}
+

azure/fedora-coreos/kubernetes/variables.tf

@@ -0,0 +1,143 @@
+variable "cluster_name" {
+  type        = string
+  description = "Unique cluster name (prepended to dns_zone)"
+}
+
+# Azure
+
+variable "region" {
+  type        = string
+  description = "Azure Region (e.g. centralus , see `az account list-locations --output table`)"
+}
+
+variable "dns_zone" {
+  type        = string
+  description = "Azure DNS Zone (e.g. azure.example.com)"
+}
+
+variable "dns_zone_group" {
+  type        = string
+  description = "Resource group where the Azure DNS Zone resides (e.g. global)"
+}
+
+# instances
+
+variable "controller_count" {
+  type        = number
+  description = "Number of controllers (i.e. masters)"
+  default     = 1
+}
+
+variable "worker_count" {
+  type        = number
+  description = "Number of workers"
+  default     = 1
+}
+
+variable "controller_type" {
+  type        = string
+  description = "Machine type for controllers (see `az vm list-skus --location centralus`)"
+  default     = "Standard_B2s"
+}
+
+variable "worker_type" {
+  type        = string
+  description = "Machine type for workers (see `az vm list-skus --location centralus`)"
+  default     = "Standard_DS1_v2"
+}
+
+variable "os_image" {
+  type        = string
+  description = "Fedora CoreOS image for instances"
+}
+
+variable "disk_size" {
+  type        = number
+  description = "Size of the disk in GB"
+  default     = 40
+}
+
+variable "worker_priority" {
+  type        = string
+  description = "Set worker priority to Spot to use reduced cost surplus capacity, with the tradeoff that instances can be deallocated at any time."
+  default     = "Regular"
+}
+
+variable "controller_snippets" {
+  type        = list(string)
+  description = "Controller Fedora CoreOS Config snippets"
+  default     = []
+}
+
+variable "worker_snippets" {
+  type        = list(string)
+  description = "Worker Fedora CoreOS Config snippets"
+  default     = []
+}
+
+# configuration
+
+variable "ssh_authorized_key" {
+  type        = string
+  description = "SSH public key for user 'core'"
+}
+
+variable "networking" {
+  type        = string
+  description = "Choice of networking provider (flannel or calico)"
+  default     = "calico"
+}
+
+variable "host_cidr" {
+  type        = string
+  description = "CIDR IPv4 range to assign to instances"
+  default     = "10.0.0.0/16"
+}
+
+variable "pod_cidr" {
+  type        = string
+  description = "CIDR IPv4 range to assign Kubernetes pods"
+  default     = "10.2.0.0/16"
+}
+
+variable "service_cidr" {
+  type        = string
+  description = <<EOD
+CIDR IPv4 range to assign Kubernetes services.
+The 1st IP will be reserved for kube_apiserver, the 10th IP will be reserved for coredns.
+EOD
+  default     = "10.3.0.0/16"
+}
+
+variable "enable_reporting" {
+  type        = bool
+  description = "Enable usage or analytics reporting to upstreams (Calico)"
+  default     = false
+}
+
+variable "enable_aggregation" {
+  type        = bool
+  description = "Enable the Kubernetes Aggregation Layer (defaults to false)"
+  default     = false
+}
+
+variable "worker_node_labels" {
+  type        = list(string)
+  description = "List of initial worker node labels"
+  default     = []
+}
+
+# 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"
+}
+

azure/fedora-coreos/kubernetes/versions.tf

@@ -0,0 +1,16 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.12.26, < 0.14.0"
+  required_providers {
+    azurerm  = "~> 2.8"
+    template = "~> 2.1"
+    null     = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
+  }
+}
+

azure/fedora-coreos/kubernetes/workers.tf

@@ -0,0 +1,24 @@
+module "workers" {
+  source = "./workers"
+  name   = var.cluster_name
+
+  # Azure
+  resource_group_name     = azurerm_resource_group.cluster.name
+  region                  = azurerm_resource_group.cluster.location
+  subnet_id               = azurerm_subnet.worker.id
+  security_group_id       = azurerm_network_security_group.worker.id
+  backend_address_pool_id = azurerm_lb_backend_address_pool.worker.id
+
+  worker_count = var.worker_count
+  vm_type      = var.worker_type
+  os_image     = var.os_image
+  priority     = var.worker_priority
+
+  # configuration
+  kubeconfig            = module.bootstrap.kubeconfig-kubelet
+  ssh_authorized_key    = var.ssh_authorized_key
+  service_cidr          = var.service_cidr
+  cluster_domain_suffix = var.cluster_domain_suffix
+  snippets              = var.worker_snippets
+  node_labels           = var.worker_node_labels
+}

azure/fedora-coreos/kubernetes/workers/fcc/worker.yaml

@@ -0,0 +1,132 @@
+---
+variant: fcos
+version: 1.0.0
+systemd:
+  units:
+    - name: docker.service
+      enabled: true
+    - name: wait-for-dns.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Wait for DNS entries
+        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 (System Container)
+        Wants=rpc-statd.service
+        [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.19.0
+        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/podman rm kubelet
+        ExecStart=/usr/bin/podman run --name kubelet \
+          --privileged \
+          --pid host \
+          --network host \
+          --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 /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 /var/lib/calico:/var/lib/calico:ro \
+          --volume /var/lib/docker:/var/lib/docker \
+          --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 \
+          --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/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:v1.19.0 --kubeconfig=/etc/kubernetes/kubeconfig delete node $HOSTNAME'
+        [Install]
+        WantedBy=multi-user.target
+storage:
+  directories:
+    - path: /etc/kubernetes
+  files:
+    - path: /etc/kubernetes/kubeconfig
+      mode: 0644
+      contents:
+        inline: |
+          ${kubeconfig}
+    - path: /etc/sysctl.d/max-user-watches.conf
+      contents:
+        inline: |
+          fs.inotify.max_user_watches=16184
+    - path: /etc/sysctl.d/reverse-path-filter.conf
+      contents:
+        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: |
+          [Manager]
+          DefaultCPUAccounting=yes
+          DefaultMemoryAccounting=yes
+          DefaultBlockIOAccounting=yes
+passwd:
+  users:
+    - name: core
+      ssh_authorized_keys:
+        - ${ssh_authorized_key}
+
+

azure/fedora-coreos/kubernetes/workers/variables.tf

@@ -0,0 +1,98 @@
+variable "name" {
+  type        = string
+  description = "Unique name for the worker pool"
+}
+
+# Azure
+
+variable "region" {
+  type        = string
+  description = "Must be set to the Azure Region of cluster"
+}
+
+variable "resource_group_name" {
+  type        = string
+  description = "Must be set to the resource group name of cluster"
+}
+
+variable "subnet_id" {
+  type        = string
+  description = "Must be set to the `worker_subnet_id` output by cluster"
+}
+
+variable "security_group_id" {
+  type        = string
+  description = "Must be set to the `worker_security_group_id` output by cluster"
+}
+
+variable "backend_address_pool_id" {
+  type        = string
+  description = "Must be set to the `worker_backend_address_pool_id` output by cluster"
+}
+
+# instances
+
+variable "worker_count" {
+  type        = number
+  description = "Number of instances"
+  default     = 1
+}
+
+variable "vm_type" {
+  type        = string
+  description = "Machine type for instances (see `az vm list-skus --location centralus`)"
+  default     = "Standard_DS1_v2"
+}
+
+variable "os_image" {
+  type        = string
+  description = "Fedora CoreOS image for instances"
+}
+
+variable "priority" {
+  type        = string
+  description = "Set priority to Spot to use reduced cost surplus capacity, with the tradeoff that instances can be evicted at any time."
+  default     = "Regular"
+}
+
+variable "snippets" {
+  type        = list(string)
+  description = "Fedora CoreOS Config snippets"
+  default     = []
+}
+
+# configuration
+
+variable "kubeconfig" {
+  type        = string
+  description = "Must be set to `kubeconfig` output by cluster"
+}
+
+variable "ssh_authorized_key" {
+  type        = string
+  description = "SSH public key for user 'core'"
+}
+
+variable "service_cidr" {
+  type        = string
+  description = <<EOD
+CIDR IPv4 range to assign Kubernetes services.
+The 1st IP will be reserved for kube_apiserver, the 10th IP will be reserved for coredns.
+EOD
+  default     = "10.3.0.0/16"
+}
+
+variable "node_labels" {
+  type        = list(string)
+  description = "List of initial node labels"
+  default     = []
+}
+
+# unofficial, undocumented, unsupported
+
+variable "cluster_domain_suffix" {
+  description = "Queries for domains with the suffix will be answered by coredns. Default is cluster.local (e.g. foo.default.svc.cluster.local) "
+  type        = string
+  default     = "cluster.local"
+}
+

azure/fedora-coreos/kubernetes/workers/versions.tf

@@ -0,0 +1,14 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.12.26, < 0.14.0"
+  required_providers {
+    azurerm  = "~> 2.8"
+    template = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.6.1"
+    }
+  }
+}

azure/fedora-coreos/kubernetes/workers/workers.tf

@@ -0,0 +1,92 @@
+# Workers scale set
+resource "azurerm_linux_virtual_machine_scale_set" "workers" {
+  resource_group_name = var.resource_group_name
+
+  name      = "${var.name}-worker"
+  location  = var.region
+  sku       = var.vm_type
+  instances = var.worker_count
+  # instance name prefix for instances in the set
+  computer_name_prefix   = "${var.name}-worker"
+  single_placement_group = false
+  custom_data            = base64encode(data.ct_config.worker-ignition.rendered)
+
+  # storage
+  source_image_id = var.os_image
+  os_disk {
+    storage_account_type = "Standard_LRS"
+    caching              = "ReadWrite"
+  }
+
+  # Azure requires setting admin_ssh_key, though Ignition custom_data handles it too
+  admin_username = "core"
+  admin_ssh_key {
+    username   = "core"
+    public_key = var.ssh_authorized_key
+  }
+
+  # network
+  network_interface {
+    name                      = "nic0"
+    primary                   = true
+    network_security_group_id = var.security_group_id
+
+    ip_configuration {
+      name      = "ip0"
+      primary   = true
+      subnet_id = var.subnet_id
+
+      # backend address pool to which the NIC should be added
+      load_balancer_backend_address_pool_ids = [var.backend_address_pool_id]
+    }
+  }
+
+  # lifecycle
+  upgrade_mode = "Manual"
+  # eviction policy may only be set when priority is Spot
+  priority        = var.priority
+  eviction_policy = var.priority == "Spot" ? "Delete" : null
+}
+
+# Scale up or down to maintain desired number, tolerating deallocations.
+resource "azurerm_monitor_autoscale_setting" "workers" {
+  resource_group_name = var.resource_group_name
+
+  name     = "${var.name}-maintain-desired"
+  location = var.region
+
+  # autoscale
+  enabled            = true
+  target_resource_id = azurerm_linux_virtual_machine_scale_set.workers.id
+
+  profile {
+    name = "default"
+
+    capacity {
+      minimum = var.worker_count
+      default = var.worker_count
+      maximum = var.worker_count
+    }
+  }
+}
+
+# Worker Ignition configs
+data "ct_config" "worker-ignition" {
+  content  = data.template_file.worker-config.rendered
+  strict   = true
+  snippets = var.snippets
+}
+
+# Worker Fedora CoreOS configs
+data "template_file" "worker-config" {
+  template = file("${path.module}/fcc/worker.yaml")
+
+  vars = {
+    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)
+  }
+}
+

bare-metal/container-linux/kubernetes/README.md

@@ -11,8 +11,8 @@ 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 v1.17.3 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* Kubernetes v1.19.0 (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 [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
 * Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)

bare-metal/container-linux/kubernetes/bootstrap.tf

@@ -1,6 +1,6 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=796194583426593d1a62b6f1bf3f7ffed8fca140"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=79343f02aea7c69bb03dab2051aa95248c0471d7"
 
   cluster_name                    = var.cluster_name
   api_servers                     = [var.k8s_domain_name]

bare-metal/container-linux/kubernetes/cl/controller.yaml

@@ -2,12 +2,14 @@
 systemd:
   units:
     - name: etcd-member.service
-      enable: true
+      enabled: true
       dropins:
         - name: 40-etcd-cluster.conf
           contents: |
             [Service]
-            Environment="ETCD_IMAGE_TAG=v3.4.3"
+            Environment="ETCD_IMAGE_TAG=v3.4.12"
+            Environment="ETCD_IMAGE_URL=docker://quay.io/coreos/etcd"
+            Environment="RKT_RUN_ARGS=--insecure-options=image"
             Environment="ETCD_NAME=${etcd_name}"
             Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${domain_name}:2379"
             Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${domain_name}:2380"
@@ -26,11 +28,11 @@ systemd:
             Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
             Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
     - name: docker.service
-      enable: true
+      enabled: true
     - name: locksmithd.service
       mask: true
     - name: kubelet.path
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Watch for kubeconfig
@@ -39,7 +41,7 @@ systemd:
         [Install]
         WantedBy=multi-user.target
     - name: wait-for-dns.service
-      enable: true
+      enabled: true
       contents: |
         [Unit]
         Description=Wait for DNS entries
@@ -55,9 +57,10 @@ systemd:
     - name: kubelet.service
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube
+        Description=Kubelet
         Wants=rpc-statd.service
         [Service]
+        Environment=KUBELET_IMAGE=docker://quay.io/poseidon/kubelet:v1.19.0
         Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
@@ -87,7 +90,7 @@ systemd:
           --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 \
+          --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 \
@@ -101,27 +104,25 @@ systemd:
           --mount volume=etc-iscsi,target=/etc/iscsi \
           --volume usr-sbin-iscsiadm,kind=host,source=/usr/sbin/iscsiadm \
           --mount volume=usr-sbin-iscsiadm,target=/sbin/iscsiadm \
-          docker://k8s.gcr.io/hyperkube:v1.17.3 \
-          --exec=/usr/local/bin/kubelet -- \
+          $${KUBELET_IMAGE} -- \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
           --cgroup-driver=$${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 \
-          --exit-on-lock-contention \
           --healthz-port=0 \
           --hostname-override=${domain_name} \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
           --network-plugin=cni \
-          --node-labels=node.kubernetes.io/master \
           --node-labels=node.kubernetes.io/controller="true" \
           --pod-manifest-path=/etc/kubernetes/manifests \
           --read-only-port=0 \
-          --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
+          --rotate-certificates \
           --volume-plugin-dir=/var/lib/kubelet/volumeplugins
         ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
         Restart=always
@@ -137,7 +138,6 @@ systemd:
         Type=oneshot
         RemainAfterExit=true
         WorkingDirectory=/opt/bootstrap
-        ExecStartPre=-/usr/bin/bash -c 'set -x && [ -n "$(ls /opt/bootstrap/assets/manifests-*/* 2>/dev/null)" ] && mv /opt/bootstrap/assets/manifests-*/* /opt/bootstrap/assets/manifests && rm -rf /opt/bootstrap/assets/manifests-*'
         ExecStart=/usr/bin/rkt run \
             --trust-keys-from-https \
             --volume config,kind=host,source=/etc/kubernetes/bootstrap-secrets \
@@ -147,7 +147,7 @@ systemd:
             --volume script,kind=host,source=/opt/bootstrap/apply \
             --mount volume=script,target=/apply \
             --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.3 \
+            docker://quay.io/poseidon/kubelet:v1.19.0 \
             --net=host \
             --dns=host \
             --exec=/apply
@@ -156,8 +156,13 @@ systemd:
         WantedBy=multi-user.target
 storage:
   directories:
+    - path: /var/lib/etcd
+      filesystem: root
+      mode: 0700
+      overwrite: true
     - path: /etc/kubernetes
       filesystem: root
+      mode: 0755
   files:
     - path: /etc/hostname
       filesystem: root
@@ -179,14 +184,15 @@ storage:
           mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
           chown -R etcd:etcd /etc/ssl/etcd
           chmod -R 500 /etc/ssl/etcd
+          chmod -R 700 /var/lib/etcd
           mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
           mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
-          sudo mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
-          rm -rf assets auth static-manifests tls
+          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
@@ -204,6 +210,7 @@ storage:
           done
     - path: /etc/sysctl.d/max-user-watches.conf
       filesystem: root
+      mode: 0644
       contents:
         inline: |
           fs.inotify.max_user_watches=16184