Update docs for Kubernetes v1.21.1 and Terraform v0.15.x

* https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1211

.github/FUNDING.yml

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

.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/dependabot.yaml

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

.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

@@ -4,6 +4,720 @@ Notable changes between versions.
 
 ## Latest
 
+## Kubernetes v1.21.0
+
+* Kubernetes [v1.21.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1211)
+* Add Terraform v0.15.x support ([#974](https://github.com/poseidon/typhoon/pull/974))
+  * Continue to support Terraform v0.13.x and v0.14.4+
+* Update etcd from v3.4.15 to [v3.4.16](https://github.com/etcd-io/etcd/releases/tag/v3.4.16)
+* Update Cilium from v1.9.5 to [v1.9.6](https://github.com/cilium/cilium/releases/tag/v1.9.6)
+* Update Calico from v3.18.1 to [v3.19.0](https://github.com/projectcalico/calico/releases/tag/v3.19.0)
+
+### AWS
+
+* Reduce the default `disk_size` from 40GB to 30GB ([#983](https://github.com/poseidon/typhoon/pull/983))
+
+### Azure
+
+* Reduce the default `disk_size` from 40GB to 30GB ([#983](https://github.com/poseidon/typhoon/pull/983))
+
+### Google Cloud
+
+* Reduce the default `disk_size` from 40GB to 30GB ([#983](https://github.com/poseidon/typhoon/pull/983))
+
+### Fedora CoreOS
+
+* Update Kubelet mounts for cgroups v2 ([#978](https://github.com/poseidon/typhoon/pull/978))
+
+### Addons
+
+* Update kube-state-metrics from v2.0.0-rc.1 to [v2.0.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0)
+* Update Prometheus from v2.25.2 to [v2.27.0](https://github.com/prometheus/prometheus/releases/tag/v2.27.0)
+* Update Grafana from v7.5.3 to [v7.5.6](https://github.com/grafana/grafana/releases/tag/v7.5.6)
+* Update nginx-ingress from v0.45.0 to [v0.46.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.46.0)
+
+## v1.21.0
+
+* Kubernetes [v1.21.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.21.md#v1210)
+  * Enable `tokencleaner` controller ([#969](https://github.com/poseidon/typhoon/pull/969))
+  * Enable `kube-scheduler` and `kube-controller-manager` separate authn/z kubeconfig
+  * Change CNI config location from /etc/kubernetes/cni/net.d to /etc/cni/net.d ([#965](https://github.com/poseidon/typhoon/pull/965))
+  * Change `kube-controller-manager` to mount `/var/lib/kubelet/volumeplugins` directly
+  * Remove unused `cloud-provider` flags
+* Update Fedora CoreOS Config version from v1.1.0 to v1.2.0 ([#970](https://github.com/poseidon/typhoon/pull/970))
+  * Require [poseidon/ct](https://github.com/poseidon/terraform-provider-ct) Terraform provider v0.8+ ([notes](https://typhoon.psdn.io/topics/maintenance/#upgrade-terraform-provider-ct))
+  * Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customizations to update to v1.2.0
+
+### AWS
+
+* Allow setting custom initial node taints on worker pools ([#968](https://github.com/poseidon/typhoon/pull/968))
+  * Add `node_taints` variable to internal `workers` pool module to set initial node taints
+  * Add `daemonset_tolerations` so `kube-system` DaemonSets can tolerate custom taints
+
+### Azure
+
+* Allow setting custom initial node taints on worker pools ([#968](https://github.com/poseidon/typhoon/pull/968))
+  * Add `node_taints` variable to internal `workers` pool module to set initial node taints
+  * Add `daemonset_tolerations` so `kube-system` DaemonSets can tolerate custom taints
+* Remove deprecated `azurerm_lb_backend_address_pool` field `resource_group_name` ([#972](https://github.com/poseidon/typhoon/pull/972))
+
+### Google Cloud
+
+* Allow setting custom initial node taints on worker pools ([#968](https://github.com/poseidon/typhoon/pull/968))
+  * Add `node_taints` variable to internal `workers` pool module to set initial node taints
+  * Add `daemonset_tolerations` so `kube-system` DaemonSets can tolerate custom taints
+
+### Addons
+
+* Update nginx-ingress from v0.44.0 to [v0.45.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.45.0)
+* Update kube-state-metrics from v2.0.0-rc.0 to [v2.0.0-rc.1](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-rc.1)
+* Update Grafana from v7.4.5 to [v7.5.3](https://github.com/grafana/grafana/releases/tag/v7.5.3)
+
+## v1.20.5
+
+* Kubernetes [v1.20.5](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1205)
+* Update etcd from v3.4.14 to [v3.4.15](https://github.com/etcd-io/etcd/releases/tag/v3.4.15)
+* Update Cilium from v1.9.4 to [v1.9.5](https://github.com/cilium/cilium/releases/tag/v1.9.5)
+* Update Calico from v3.17.3 to [v3.18.1](https://github.com/projectcalico/calico/releases/tag/v3.18.1)
+* Update CoreDNS from v1.7.0 to [v1.8.0](https://coredns.io/2020/10/22/coredns-1.8.0-release/)
+* Mark bootstrap token as sensitive in Terraform plans ([#949](https://github.com/poseidon/typhoon/pull/949))
+
+### Fedora CoreOS
+
+* Set Kubelet `provider-id` ([#951](https://github.com/poseidon/typhoon/pull/951))
+
+### Flatcar Linux
+
+#### AWS
+
+* Set Kubelet `provider-id` ([#951](https://github.com/poseidon/typhoon/pull/951))
+* Remove `os_image` option `flatcar-edge` ([#943](https://github.com/poseidon/typhoon/pull/943))
+
+#### Azure
+
+* Remove `os_image` option `flatcar-edge` ([#943](https://github.com/poseidon/typhoon/pull/943))
+
+#### Bare-Metal
+
+* Remove `os_channel` option `flatcar-edge` ([#943](https://github.com/poseidon/typhoon/pull/943))
+
+### Addons
+
+* Update Prometheus from v2.25.0 to [v2.25.2](https://github.com/prometheus/prometheus/releases/tag/v2.25.2)
+* Update kube-state-metrics from v2.0.0-alpha.3 to [v2.0.0-rc.0](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-rc.0)
+  * Switch image from `quay.io` to `k8s.gcr.io` ([#946](https://github.com/poseidon/typhoon/pull/946))
+* Update node-exporter from v1.1.1 to [v1.1.2](https://github.com/prometheus/node_exporter/releases/tag/v1.1.2)
+* Update Grafana from v7.4.2 to [v7.4.5](https://github.com/grafana/grafana/releases/tag/v7.4.5)
+
+## v1.20.4
+
+* Kubernetes [v1.20.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1204)
+* Update Cilium from v1.9.1 to [v1.9.4](https://github.com/cilium/cilium/releases/tag/v1.9.4)
+* Update Calico from v3.17.1 to [v3.17.3](https://github.com/projectcalico/calico/releases/tag/v3.17.3)
+* Update flannel-cni from v0.4.1 to [v0.4.2](https://github.com/poseidon/flannel-cni/releases/tag/v0.4.2)
+
+### Addons
+
+* Update nginx-ingress from v0.43.0 to [v0.44.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.44.0)
+* Update Prometheus from v2.24.0 to [v2.25.0](https://github.com/prometheus/prometheus/releases/tag/v2.25.0)
+  * Update node-exporter from v1.0.1 to [v1.1.1](https://github.com/prometheus/node_exporter/releases/tag/v1.1.1)
+* Update Grafana from v7.3.7 to [v7.4.2](https://github.com/grafana/grafana/releases/tag/v7.4.2)
+
+## v1.20.2
+
+* Kubernetes [v1.20.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1202)
+* Support Terraform v0.13.x and v0.14.4+ ([#924](https://github.com/poseidon/typhoon/pull/923))
+
+### Addons
+
+* Update nginx-ingress from v0.41.2 to [v0.43.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.43.0)
+* Update Prometheus from v2.23.0 to [v2.24.0](https://github.com/prometheus/prometheus/releases/tag/v2.24.0)
+* Update Grafana from v7.3.6 to [v7.3.7](https://github.com/grafana/grafana/releases/tag/v7.3.7)
+
+## v1.20.1
+
+* Kubernetes [v1.20.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1201)
+
+### Fedora CoreOS
+
+* Fedora CoreOS 33 has stronger crypto defaults ([**notice**](https://docs.fedoraproject.org/en-US/fedora-coreos/faq/#_why_does_ssh_stop_working_after_upgrading_to_fedora_33), [#915](https://github.com/poseidon/typhoon/issues/915))
+  * Use a non-RSA SSH key or add the workaround provided in upstream [Fedora docs](https://docs.fedoraproject.org/en-US/fedora-coreos/faq/#_why_does_ssh_stop_working_after_upgrading_to_fedora_33) as a [snippet](https://typhoon.psdn.io/advanced/customization/#fedora-coreos) (**action required**)
+
+### Addons
+
+* Update Grafana from v7.3.5 to [v7.3.6](https://github.com/grafana/grafana/releases/tag/v7.3.6)
+
+## v1.20.0
+
+* Kubernetes [v1.20.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.20.md#v1200)
+* Add input variable validations ([#880](https://github.com/poseidon/typhoon/pull/880))
+  * Require Terraform v0.13+ ([migration guide](https://typhoon.psdn.io/topics/maintenance/#terraform-versions))
+* Set output sensitive to suppress console display for some cases ([#885](https://github.com/poseidon/typhoon/pull/885))
+* Add service account token [volume projection](https://kubernetes.io/docs/tasks/configure-pod-container/configure-service-account/#service-account-token-volume-projection) ([#897](https://github.com/poseidon/typhoon/pull/897))
+* Scope kube-scheduler and kube-controller-manager permissions ([#898](https://github.com/poseidon/typhoon/pull/898))
+* Update etcd from v3.4.12 to [v3.4.14](https://github.com/etcd-io/etcd/releases/tag/v3.4.14)
+* Update Calico from v3.16.5 to v3.17.1 ([#890](https://github.com/poseidon/typhoon/pull/890))
+  * Enable Calico MTU auto-detection
+  * Remove [workaround](https://github.com/poseidon/typhoon/pull/724) to Calico cni-plugin [issue](https://github.com/projectcalico/cni-plugin/issues/874)
+* Update Cilium from v1.9.0 to [v1.9.1](https://github.com/cilium/cilium/releases/tag/v1.9.1)
+* Relax `terraform-provider-ct` version constraint to v0.6+ ([#893](https://github.com/poseidon/typhoon/pull/893))
+  * Allow upgrading `terraform-provider-ct` to v0.7.x ([warn](https://typhoon.psdn.io/topics/maintenance/#upgrade-terraform-provider-ct))
+
+### AWS
+
+* Enable Network Load Balancer (NLB) dualstack ([#883](https://github.com/poseidon/typhoon/pull/883))
+  * NLB subnets assigned both IPv4 and IPv6 addresses
+  * NLB DNS name has both A and AAAA records
+  * NLB to target node traffic is IPv4 (no change)
+
+### Bare-Metal
+
+* Remove iSCSI `/etc/iscsi` and `iscsadm` mounts from Kubelet ([#912](https://github.com/poseidon/typhoon/pull/912))
+
+### Fedora CoreOS
+
+#### AWS
+
+* Fix AMI query for which could fail in some regions ([#887](https://github.com/poseidon/typhoon/pull/887))
+
+#### Bare-Metal
+
+* Promote Fedora CoreOS to stable
+* Use initramfs and rootfs images as initrd's ([#889](https://github.com/poseidon/typhoon/pull/889))
+  * Requires Fedora CoreOS version with rootfs images (e.g. 32.20200923.3.0+)
+
+### Addons
+
+* Update Prometheus from v2.22.2 to [v2.23.0](https://github.com/prometheus/prometheus/releases/tag/v2.23.0)
+* Update kube-state-metrics from v2.0.0-alpha.2 to [v2.0.0-alpha.3](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.3)
+* Update Grafana from v7.3.2 to [v7.3.5](https://github.com/grafana/grafana/releases/tag/v7.3.5)
+
+## v1.19.4
+
+* Kubernetes [v1.19.4](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1194)
+* Update Cilium from v1.8.4 to [v1.9.0](https://github.com/cilium/cilium/releases/tag/v1.9.0)
+* Update Calico from v3.16.3 to [v3.16.5](https://github.com/projectcalico/calico/releases/tag/v3.16.5)
+* Remove `asset_dir` variable (defaulted off in [v1.17.0](https://github.com/poseidon/typhoon/pull/595), deprecated in [v1.18.0](https://github.com/poseidon/typhoon/pull/678))
+
+### Fedora CoreOS
+
+* Improve `etcd-member.service` systemd unit ([#868](https://github.com/poseidon/typhoon/pull/868))
+  * Allow a snippet with a systemd dropin to set an alternate image (e.g. mirror)
+* Fix local node delete oneshot on node shutdown ([#856](https://github.com/poseidon/typhoon/pull/855))
+
+#### AWS
+
+* Add experimental Fedora CoreOS arm64 support ([docs](https://typhoon.psdn.io/advanced/arm64/), [#875](https://github.com/poseidon/typhoon/pull/875))
+  * Allow arm64 full-cluster or mixed/hybrid cluster with worker pools
+  * Add `arch` variable to cluster module
+  * Add `daemonset_tolerations` variable to cluster module
+  * Add `node_taints` variable to workers module
+  * Requires flannel CNI provider and use of experimental AMI (see docs)
+
+### Flatcar Linux
+
+* Rename `container-linux` modules to `flatcar-linux` ([#858](https://github.com/poseidon/typhoon/issues/858)) (**action required**)
+* Change on-host system containers from rkt to docker
+  * Change `etcd-member.service` container runnner from rkt to docker ([#867](https://github.com/poseidon/typhoon/pull/867))
+  * Change `kubelet.service` container runner from rkt-fly to docker ([#855](https://github.com/poseidon/typhoon/pull/855))
+  * Change `bootstrap.service` container runner from rkt to docker ([#873](https://github.com/poseidon/typhoon/pull/873))
+  * Change `delete-node.service` to use docker and an inline ExecStart ([#855](https://github.com/poseidon/typhoon/pull/855))
+* Fix local node delete oneshot on node shutdown ([#855](https://github.com/poseidon/typhoon/pull/855))
+* Remove CoreOS Container Linux Matchbox profiles ([#859](https://github.com/poseidon/typhoon/pull/858))
+
+### Addons
+
+* Update nginx-ingress from v0.40.2 to [v0.41.2](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.41.2)
+* Update Prometheus from v2.22.0 to [v2.22.1](https://github.com/prometheus/prometheus/releases/tag/v2.22.1)
+* Update kube-state-metrics from v2.0.0-alpha.1 to [v2.0.0-alpha.2](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.2)
+* Update Grafana from v7.2.1 to [v7.3.2](https://github.com/grafana/grafana/releases/tag/v7.3.2)
+
+## v1.19.3
+
+* Kubernetes [v1.19.3](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1193)
+* Update Cilium from v1.8.3 to [v1.8.4](https://github.com/cilium/cilium/releases/tag/v1.8.4)
+* Update Calico from v1.15.3 to [v1.16.3](https://github.com/projectcalico/calico/releases/tag/v3.16.3) ([#851](https://github.com/poseidon/typhoon/pull/851))
+* Update flannel from v0.13.0-rc2 to v0.13.0 ([#219](https://github.com/poseidon/terraform-render-bootstrap/pull/219))
+
+### Flatcar Linux
+
+* Remove references to CoreOS Container Linux ([#839](https://github.com/poseidon/typhoon/pull/839))
+  * Fix error querying for coreos AMI on AWS ([#838](https://github.com/poseidon/typhoon/issues/838))
+
+### Addons
+
+* Update nginx-ingress from v0.35.0 to [v0.40.2](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.40.2)
+* Update Grafana from v7.1.5 to [v7.2.1](https://github.com/grafana/grafana/releases/tag/v7.2.1)
+* Update Prometheus from v2.21.0 to [v2.22.0](https://github.com/prometheus/prometheus/releases/tag/v2.22.0)
+  * Update kube-state-metrics from v1.9.7 to [v2.0.0-alpha.1](https://github.com/kubernetes/kube-state-metrics/releases/tag/v2.0.0-alpha.1)
+
+## v1.19.2
+
+* Kubernetes [v1.19.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1192)
+* Update flannel from v0.12.0 to v0.13.0-rc2 ([#216](https://github.com/poseidon/terraform-render-bootstrap/pull/216))
+  * Update flannel-cni from v0.4.0 to v0.4.1
+  * Update CNI plugins from v0.8.6 to v0.8.7
+
+### Addons
+
+* Refresh Prometheus rules/alerts and Grafana dashboards ([#831](https://github.com/poseidon/typhoon/pull/831))
+* Reduce apiserver metrics cardinality for non-core APIs ([#830](https://github.com/poseidon/typhoon/pull/830))
+
+## v1.19.1
+
+* Kubernetes [v1.19.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1191)
+  * Change control plane seccomp annotations to GA `seccompProfile` ([#822](https://github.com/poseidon/typhoon/pull/822))
+* Update Cilium from v1.8.2 to [v1.8.3](https://github.com/cilium/cilium/releases/tag/v1.8.3)
+  * Promote Cilium from experimental to general availability ([#827](https://github.com/poseidon/typhoon/pull/827))
+* Update Calico from v1.15.2 to [v1.15.3](https://github.com/projectcalico/calico/releases/tag/v3.15.3)
+
+### Fedora CoreOS
+
+* Update Fedora CoreOS Config version from v1.0.0 to v1.1.0
+  * Require any [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customizations to update to v1.1.0
+
+### Addons
+
+* Update IngressClass resources to `networking.k8s.io/v1` ([#824](https://github.com/poseidon/typhoon/pull/824))
+* Update Prometheus from v2.20.0 to [v2.21.0](https://github.com/prometheus/prometheus/releases/tag/v2.21.0)
+  * Remove Kubernetes node name labelmap `relabel_config` from etcd, Kubelet, and CAdvisor scrape config ([#828](https://github.com/poseidon/typhoon/pull/828))
+
+## v1.19.0
+
+* Kubernetes [v1.19.0](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.19.md#v1190)
+* Update etcd from v3.4.10 to [v3.4.12](https://github.com/etcd-io/etcd/releases/tag/v3.4.12)
+* Update Calico from v3.15.1 to [v3.15.2](https://docs.projectcalico.org/v3.15/release-notes/)
+
+### Fedora CoreOS
+
+* Fix race condition during bootstrap of multi-controller clusters ([#808](https://github.com/poseidon/typhoon/pull/808))
+  * Fix SELinux label of bootstrap-secrets on non-bootstrap controllers
+
+### Addons
+
+* Introduce [fleetlock](https://github.com/poseidon/fleetlock) for Fedora CoreOS reboot coordination ([#814](https://github.com/poseidon/typhoon/pull/814))
+* Update nginx-ingress from v0.34.1 to [v0.35.0](https://github.com/kubernetes/ingress-nginx/releases/tag/controller-v0.35.0)
+  * Repository changed to `k8s.gcr.io/ingress-nginx/controller`
+* Update Grafana from v7.1.3 to [v7.1.5](https://github.com/grafana/grafana/releases/tag/v7.1.5)
+
+## v1.18.8
+
+* Kubernetes [v1.18.8](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1188)
+* Migrate from Terraform v0.12.x to v0.13.x ([#804](https://github.com/poseidon/typhoon/pull/804)) (**action required**)
+  * Recommend Terraform v0.13.x ([migration guide](https://typhoon.psdn.io/topics/maintenance/#terraform-versions))
+  * Support automatic install of poseidon's provider plugins ([poseidon/ct](https://registry.terraform.io/providers/poseidon/ct/latest), [poseidon/matchbox](https://registry.terraform.io/providers/poseidon/matchbox/latest))
+  * Require Terraform v0.12.26+ (migration compatibility)
+  * Require `terraform-provider-ct` v0.6.1
+  * Require `terraform-provider-matchbox` v0.4.1
+* Update etcd from v3.4.9 to [v3.4.10](https://github.com/etcd-io/etcd/releases/tag/v3.4.10)
+* Update CoreDNS from v1.6.7 to [v1.7.0](https://coredns.io/2020/06/15/coredns-1.7.0-release/)
+* Update Cilium from v1.8.1 to [v1.8.2](https://github.com/cilium/cilium/releases/tag/v1.8.2)
+* Update [coreos/flannel-cni](https://github.com/coreos/flannel-cni) to [poseidon/flannel-cni](https://github.com/poseidon/flannel-cni) ([#798](https://github.com/poseidon/typhoon/pull/798))
+  * Update CNI plugins and fix CVEs with Flannel CNI (non-default)
+  * Transition to a poseidon maintained container image
+
+### AWS
+
+* Allow `terraform-provider-aws` v3.0+ ([#803](https://github.com/poseidon/typhoon/pull/803))
+  * Recommend updating `terraform-provider-aws` to v3.0+
+  * Continue to allow v2.23+, no v3.x specific features are used
+
+### DigitalOcean
+
+* Require `terraform-provider-digitalocean` v1.21+ for Terraform v0.13.x (unenforced)
+* Require `terraform-provider-digitalocean` v1.20+ for Terraform v0.12.x
+
+### Fedora CoreOS
+
+* Fix support for Flannel with Fedora CoreOS ([#795](https://github.com/poseidon/typhoon/pull/795))
+  * Configure `flannel.1` link to select its own MAC address to solve flannel
+  pod-to-pod traffic drops starting with default link changes in Fedora CoreOS
+  32.20200629.3.0 ([details](https://github.com/coreos/fedora-coreos-tracker/issues/574#issuecomment-665487296))
+
+#### Addons
+
+* Update Prometheus from v2.19.2 to [v2.20.0](https://github.com/prometheus/prometheus/releases/tag/v2.20.0)
+* Update Grafana from v7.0.6 to [v7.1.3](https://github.com/grafana/grafana/releases/tag/v7.1.3)
+
+## v1.18.6
+
+* Kubernetes [v1.18.6](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG/CHANGELOG-1.18.md#v1186)
+* 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 ([#645](https://github.com/poseidon/typhoon/pull/645))
+
+#### Bare-Metal
+
+* 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 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
+
+* Update nginx-ingress from v0.27.1 to v0.28.0
+* Update kube-state-metrics from v1.9.3 to v1.9.4
+* Update Grafana from v6.5.3 to v6.6.1
+
+## v1.17.2
+
+* Kubernetes [v1.17.2](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG-1.17.md#v1172)
+
+#### AWS
+
+* Promote Fedora CoreOS from preview to alpha
+
+#### Bare-Metal
+
+* Promote Fedora CoreOS from preview to alpha
+* Update Fedora CoreOS images location
+  * Use Fedora CoreOS production [download](https://getfedora.org/coreos/download/) streams
+  * Use live PXE kernel and initramfs images
+
+#### Addons
+
+* Update nginx-ingress from v0.26.1 to [v0.27.1](https://github.com/kubernetes/ingress-nginx/releases/tag/nginx-0.27.1) ([#625](https://github.com/poseidon/typhoon/pull/625))
+  * Change runAsUser from 33 to 101 for alpine-based image
+* Update kube-state-metrics from v1.9.2 to v1.9.3
+
+## v1.17.1
+
 * Kubernetes [v1.17.1](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG-1.17.md#v1171)
 * Update CoreDNS from v1.6.5 to [v1.6.6](https://coredns.io/2019/12/11/coredns-1.6.6-release/) ([#602](https://github.com/poseidon/typhoon/pull/602))
 * Update Calico from v3.10.2 to v3.11.2 ([#604](https://github.com/poseidon/typhoon/pull/604))
@@ -12,6 +726,10 @@ Notable changes between versions.
 * Enable kube-proxy metrics and allow Prometheus scrapes
   * Allow TCP/10249 traffic with worker node sources
 
+#### AWS
+
+* Update Fedora CoreOS AMI filter for fedora-coreos-31 ([#620](https://github.com/poseidon/typhoon/pull/620))
+
 #### Google
 
 * Allow `terraform-provider-google` v3.0+ ([#617](https://github.com/poseidon/typhoon/pull/617))

README.md

@@ -11,36 +11,46 @@ 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 v1.17.1 (upstream)
+* Kubernetes v1.21.1 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* 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/)
+* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
-* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/cl/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
+* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [preemptible](https://typhoon.psdn.io/flatcar-linux/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
 * Ready for Ingress, Prometheus, Grafana, CSI, or other [addons](https://typhoon.psdn.io/addons/overview/)
 
 ## Modules
 
 Typhoon provides a Terraform Module for each supported operating system and platform.
 
-| Platform      | Operating System | Terraform Module | Status |
+Typhoon is available for [Fedora CoreOS](https://getfedora.org/coreos/).
-|---------------|------------------|------------------|--------|
-| AWS           | Container Linux / Flatcar 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 / Flatcar 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 |
-
-A preview of Typhoon for [Fedora CoreOS](https://getfedora.org/coreos/) is available for testing.
 
 | Platform      | Operating System | Terraform Module | Status |
 |---------------|------------------|------------------|--------|
-| AWS           | Fedora CoreOS | [aws/fedora-coreos/kubernetes](aws/fedora-coreos/kubernetes) | preview |
+| AWS           | Fedora CoreOS | [aws/fedora-coreos/kubernetes](aws/fedora-coreos/kubernetes) | stable |
-| Bare-Metal    | Fedora CoreOS | [bare-metal/fedora-coreos/kubernetes](bare-metal/fedora-coreos/kubernetes) | preview |
+| 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) | stable |
+| DigitalOcean  | Fedora CoreOS | [digital-ocean/fedora-coreos/kubernetes](digital-ocean/fedora-coreos/kubernetes) | beta |
+| Google Cloud  | Fedora CoreOS | [google-cloud/fedora-coreos/kubernetes](google-cloud/fedora-coreos/kubernetes) | stable |
+
+| Platform      | Operating System | Terraform Module | Status |
+|---------------|------------------|------------------|--------|
+| AWS           | Fedora CoreOS (ARM64) | [aws/fedora-coreos/kubernetes](aws/fedora-coreos/kubernetes) | alpha |
+
+Typhoon is available for [Flatcar Linux](https://www.flatcar-linux.org/releases/).
+
+| Platform      | Operating System | Terraform Module | Status |
+|---------------|------------------|------------------|--------|
+| AWS           | Flatcar Linux    | [aws/flatcar-linux/kubernetes](aws/flatcar-linux/kubernetes) | stable |
+| Azure         | Flatcar Linux    | [azure/flatcar-linux/kubernetes](azure/flatcar-linux/kubernetes) | alpha |
+| Bare-Metal    | Flatcar Linux    | [bare-metal/flatcar-linux/kubernetes](bare-metal/flatcar-linux/kubernetes) | stable |
+| DigitalOcean | Flatcar Linux  | [digital-ocean/flatcar-linux/kubernetes](digital-ocean/flatcar-linux/kubernetes) | beta |
+| Google Cloud  | Flatcar Linux  | [google-cloud/flatcar-linux/kubernetes](google-cloud/flatcar-linux/kubernetes) | 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
 
@@ -48,7 +58,7 @@ 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=v1.17.1"
+  source = "git::https://github.com/poseidon/typhoon//google-cloud/fedora-coreos/kubernetes?ref=v1.21.1"
 
   # Google Cloud
   cluster_name  = "yavin"
@@ -87,9 +97,9 @@ 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   v1.17.1
+yavin-controller-0.c.example-com.internal  <none>   Ready   6m   v1.21.1
-yavin-worker-jrbf.c.example-com.internal   <none>   Ready   5m   v1.17.1
+yavin-worker-jrbf.c.example-com.internal   <none>   Ready   5m   v1.21.1
-yavin-worker-mzdm.c.example-com.internal   <none>   Ready   5m   v1.17.1
+yavin-worker-mzdm.c.example-com.internal   <none>   Ready   5m   v1.21.1
 ```
 
 List the pods.
@@ -120,7 +130,7 @@ Typhoon is strict about minimalism, maturity, and scope. These are not in scope:
 
 ## Help
 
-Ask questions on the IRC #typhoon channel on [freenode.net](http://freenode.net/).
+Schedule a meeting via [Github Sponsors](https://github.com/sponsors/poseidon?frequency=one-time) to discuss your use case. You can also ask questions on the IRC #typhoon channel on [freenode.net](http://freenode.net/) (unmonitored).
 
 ## Motivation
 
@@ -130,12 +140,17 @@ Typhoon addresses real world needs, which you may share. It is honest about limi
 
 ## Social Contract
 
-Typhoon is not a product, trial, or free-tier. It is not run by a company, does not offer support or services, and does not accept or make any money. It is not associated with any operating system or platform vendor.
+Typhoon is not a product, trial, or free-tier. Typhoon does not offer support, services, or charge money. And Typhoon is independent of operating system or platform vendors.
 
 Typhoon clusters will contain only [free](https://www.debian.org/intro/free) components. Cluster components will not collect data on users without their permission.
 
-## Donations
+## Sponsors
 
-Typhoon does not accept money donations. Instead, we encourage you to donate to one of [these organizations](https://github.com/poseidon/typhoon/wiki/Donations) to show your appreciation.
+Poseidon's Github [Sponsors](https://github.com/sponsors/poseidon) support the infrastructure and operational costs of providing Typhoon.
 
-* [DigitalOcean](https://www.digitalocean.com/) kindly provides credits to support Typhoon test clusters.
+<a href="https://www.digitalocean.com/">
+    <img src="https://opensource.nyc3.cdn.digitaloceanspaces.com/attribution/assets/SVG/DO_Logo_horizontal_blue.svg" width="201px">
+</a>
+<br>
+
+If you'd like your company here, please contact dghubble at psdn.io.

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

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

addons/grafana/dashboards-etcd.yaml

@@ -11,7 +11,6 @@ data:
       "editable": true,
       "gnetId": null,
       "hideControls": false,
-      "id": 6,
       "links": [
 
       ],
@@ -343,7 +342,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "etcd_debugging_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
+                  "expr": "etcd_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
                   "hide": false,
                   "interval": "",
                   "intervalFactor": 2,

addons/grafana/dashboards-k8s-nodes.yaml

@@ -21,7 +21,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -172,7 +172,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
+                  "expr": "sum(kubelet_running_pods{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}) OR sum(kubelet_running_pod_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -256,7 +256,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
+                  "expr": "sum(kubelet_running_containers{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"}) OR sum(kubelet_running_container_count{cluster=\"$cluster\", job=\"kubelet\", instance=~\"$instance\"})",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -553,20 +553,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 8,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -644,20 +646,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 9,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -748,20 +752,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 10,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -852,20 +858,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 11,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -950,20 +958,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 12,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1061,22 +1071,24 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 13,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
-                "hideEmpty": "true",
+                "hideEmpty": true,
-                "hideZero": "true",
+                "hideZero": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1154,22 +1166,24 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 14,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
-                "hideEmpty": "true",
+                "hideEmpty": true,
-                "hideZero": "true",
+                "hideZero": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1260,22 +1274,24 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 15,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
-                "hideEmpty": "true",
+                "hideEmpty": true,
-                "hideZero": "true",
+                "hideZero": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1366,20 +1382,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 16,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1457,20 +1475,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 17,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1562,20 +1582,22 @@ data:
               "datasource": "$datasource",
               "description": "Pod lifecycle event generator",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 18,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1653,20 +1675,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 19,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1757,20 +1781,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 20,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1861,6 +1887,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -1873,6 +1900,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -1986,20 +2014,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 22,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -2021,7 +2051,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{cluster=\"$cluster\",job=\"kubelet\", instance=~\"$instance\"}[5m])) by (instance, verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{verb}} {{url}}",
@@ -2090,6 +2120,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2102,6 +2133,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2181,6 +2213,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2193,6 +2226,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2272,6 +2306,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2284,6 +2319,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2373,8 +2409,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2427,7 +2463,7 @@ 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,
@@ -2470,7 +2506,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Kubelet",
       "uid": "3138fa155d5915769fbded898ac09fd9",
       "version": 0
@@ -2496,7 +2532,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -2595,6 +2631,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2607,6 +2644,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2686,20 +2724,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -2790,6 +2830,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2802,6 +2843,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2881,20 +2923,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 6,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -2985,6 +3029,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2997,6 +3042,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -3097,6 +3143,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -3109,6 +3156,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -3132,7 +3180,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-proxy\",instance=~\"$instance\",verb=\"POST\"}[5m])) by (verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}} {{url}}",
@@ -3201,20 +3249,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 9,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -3236,7 +3286,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-proxy\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}} {{url}}",
@@ -3305,6 +3355,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -3317,6 +3368,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -3396,6 +3448,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -3408,6 +3461,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -3487,6 +3541,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -3499,6 +3554,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -3588,8 +3644,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -3659,7 +3715,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Proxy",
       "uid": "632e265de029684c40b21cb76bca4f94",
       "version": 0

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

@@ -31,6 +31,7 @@ data:
               "fill": 1,
               "format": "percentunit",
               "id": 1,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -59,7 +60,7 @@ 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\"}[$__rate_interval]))",
                   "format": "time_series",
                   "instant": true,
                   "intervalFactor": 2,
@@ -686,6 +687,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 0,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
                   "pattern": "Value #A",
@@ -704,6 +706,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 0,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to workloads",
                   "linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
                   "pattern": "Value #B",
@@ -722,6 +725,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -740,6 +744,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -758,6 +763,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -776,6 +782,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -794,6 +801,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #G",
@@ -812,6 +820,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
                   "pattern": "namespace",
@@ -839,7 +848,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)",
+                  "expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -848,7 +857,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
+                  "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1105,6 +1114,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 0,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
                   "pattern": "Value #A",
@@ -1123,6 +1133,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 0,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to workloads",
                   "linkUrl": "./d/a87fb0d919ec0ea5f6543124e16c42a5/k8s-resources-workloads-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell_1",
                   "pattern": "Value #B",
@@ -1141,6 +1152,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -1159,6 +1171,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -1177,6 +1190,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -1195,6 +1209,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -1213,6 +1228,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #G",
@@ -1231,6 +1247,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
                   "pattern": "namespace",
@@ -1258,7 +1275,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "count(mixin_pod_workload{cluster=\"$cluster\"}) by (namespace)",
+                  "expr": "sum(kube_pod_owner{cluster=\"$cluster\"}) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1267,7 +1284,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "count(avg(mixin_pod_workload{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
+                  "expr": "count(avg(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\"}) by (workload, namespace)) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1384,6 +1401,7 @@ data:
               "datasource": "$datasource",
               "fill": 1,
               "id": 11,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -1426,6 +1444,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -1444,6 +1463,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -1462,6 +1482,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -1480,6 +1501,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -1498,6 +1520,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -1516,6 +1539,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -1534,6 +1558,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/85a562078cdf77779eaa1add43ccec1e/k8s-resources-namespace?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$__cell",
                   "pattern": "namespace",
@@ -1561,7 +1586,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1570,7 +1595,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1579,7 +1604,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1588,7 +1613,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1597,7 +1622,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1606,7 +1631,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1706,7 +1731,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -1804,7 +1829,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -1902,7 +1927,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "avg(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2000,7 +2025,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "avg(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2098,7 +2123,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2196,7 +2221,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2294,7 +2319,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2392,7 +2417,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$interval])) by (namespace)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\".+\"}[$__rate_interval])) by (namespace)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{namespace}}",
@@ -2458,8 +2483,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2475,63 +2500,28 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
 
             ],
             "query": "label_values(node_cpu_seconds_total, cluster)",
-            "refresh": 1,
-            "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "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
           }
         ]
@@ -2565,7 +2555,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Compute Resources / Cluster",
       "uid": "efa86fd1d0c121a26444b636a3f509a8",
       "version": 0
@@ -2586,6 +2576,354 @@ 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=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$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=\"$namespace\",container!=\"\", image!=\"\"}) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$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 +2937,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 1,
+              "id": 5,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2620,7 +2958,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -2634,6 +2991,22 @@ data:
                   "legendFormat": "{{pod}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$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=\"$namespace\", type=\"hard\",resource=\"limits.cpu\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -2697,7 +3070,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 2,
+              "id": 6,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2740,6 +3113,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -2758,6 +3132,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -2776,6 +3151,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -2794,6 +3170,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -2812,6 +3189,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -2830,6 +3208,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
                   "pattern": "pod",
@@ -2964,7 +3343,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 3,
+              "id": 7,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2985,7 +3364,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -2993,12 +3391,28 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}) by (pod)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$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=\"$namespace\", type=\"hard\",resource=\"limits.memory\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "quota - limits",
+                  "legendLink": null,
+                  "step": 10
                 }
               ],
               "thresholds": [
@@ -3062,7 +3476,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 4,
+              "id": 8,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -3105,6 +3519,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -3123,6 +3538,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -3141,6 +3557,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -3159,6 +3576,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -3177,6 +3595,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -3195,6 +3614,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -3213,6 +3633,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #G",
@@ -3231,6 +3652,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #H",
@@ -3249,6 +3671,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
                   "pattern": "pod",
@@ -3276,7 +3699,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3294,7 +3717,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3312,7 +3735,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\",container!=\"\", image!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3410,7 +3833,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 5,
+              "id": 9,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -3453,6 +3877,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -3471,6 +3896,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -3489,6 +3915,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -3507,6 +3934,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -3525,6 +3953,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -3543,6 +3972,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -3561,6 +3991,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
                   "pattern": "pod",
@@ -3588,7 +4019,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3597,7 +4028,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3606,7 +4037,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3615,7 +4046,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3624,7 +4055,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3633,7 +4064,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3698,398 +4129,6 @@ 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 +4164,7 @@ 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=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -4138,7 +4177,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Rate of Received Packets Dropped",
+              "title": "Receive Bandwidth",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -4223,7 +4262,399 @@ 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=~\"$namespace\"}[$__rate_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=~\"$namespace\"}[$__rate_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": "$datasource",
+              "fill": 10,
+              "id": 13,
+              "legend": {
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "show": true,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 0,
+              "links": [
+
+              ],
+              "nullPointMode": "null as zero",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 12,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum(irate(container_network_transmit_packets_total{cluster=\"$cluster\", namespace=~\"$namespace\"}[$__rate_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=~\"$namespace\"}[$__rate_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=~\"$namespace\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -4289,8 +4720,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -4306,13 +4737,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -4321,7 +4752,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -4333,13 +4764,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "namespace",
+            "label": null,
             "multi": false,
             "name": "namespace",
             "options": [
@@ -4348,48 +4779,13 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$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
           }
         ]
@@ -4423,7 +4819,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Compute Resources / Namespace (Pods)",
       "uid": "85a562078cdf77779eaa1add43ccec1e",
       "version": 0
@@ -4486,7 +4882,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -4598,6 +4994,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -4616,6 +5013,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -4634,6 +5032,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -4652,6 +5051,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -4670,6 +5070,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -4688,6 +5089,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "pod",
@@ -4715,7 +5117,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4724,7 +5126,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4733,7 +5135,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4742,7 +5144,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4751,7 +5153,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", node=~\"$node\"}) by (pod) / sum(kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4851,7 +5253,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\", container!=\"\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\", container!=\"\"}) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -4963,6 +5365,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -4981,6 +5384,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -4999,6 +5403,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -5017,6 +5422,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -5035,6 +5441,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -5053,6 +5460,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -5071,6 +5479,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #G",
@@ -5089,6 +5498,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #H",
@@ -5107,6 +5517,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "pod",
@@ -5134,7 +5545,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5143,7 +5554,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5152,7 +5563,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=\"$node\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_requests_memory_bytes{node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5161,7 +5572,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", node=\"$node\"}) by (pod)",
+                  "expr": "sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5170,7 +5581,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=\"$node\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_working_set_bytes{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod) / sum(kube_pod_container_resource_limits_memory_bytes{node=~\"$node\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5179,7 +5590,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_rss{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5188,7 +5599,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_cache{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5197,7 +5608,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=\"$node\",container!=\"\"}) by (pod)",
+                  "expr": "sum(node_namespace_pod_container:container_memory_swap{cluster=\"$cluster\", node=~\"$node\",container!=\"\"}) by (pod)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -5265,8 +5676,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -5282,13 +5693,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -5297,7 +5708,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -5309,14 +5720,14 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "node",
+            "label": null,
-            "multi": false,
+            "multi": true,
             "name": "node",
             "options": [
 
@@ -5324,7 +5735,7 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, node)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -5364,7 +5775,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Compute Resources / Node (Pods)",
       "uid": "200ac8fdbfbb74b39aff88118e4d1c2c",
       "version": 0

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=\"$pod\", container!=\"POD\", container!=\"\", cluster=\"$cluster\"}[5m])) by (container) /sum(increase(container_cpu_cfs_periods_total{namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", 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": 0.80000000000000004,
+                  "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,
@@ -170,6 +308,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -188,6 +327,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -206,6 +346,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -224,6 +365,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -242,6 +384,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -260,6 +403,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "container",
@@ -394,7 +538,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 3,
+              "id": 4,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -415,7 +559,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -423,26 +586,26 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(container_memory_rss{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", image!=\"\"}) by (container)",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{container}} (RSS)",
+                  "legendFormat": "{{container}}",
                   "legendLink": null,
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_cache{cluster=\"$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=\"$pod\"})\n",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{container}} (Swap)",
+                  "legendFormat": "limits",
                   "legendLink": null,
                   "step": 10
                 }
@@ -508,7 +671,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 4,
+              "id": 5,
               "legend": {
                 "avg": false,
                 "current": false,
@@ -551,6 +714,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -569,6 +733,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -587,6 +752,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -605,6 +771,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -623,6 +790,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -641,6 +809,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -659,6 +828,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #G",
@@ -677,6 +847,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #H",
@@ -695,6 +866,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "container",
@@ -722,7 +894,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\"}) by (container)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"POD\", container!=\"\", image!=\"\"}) by (container)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -740,7 +912,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -758,7 +930,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\"}) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
+                  "expr": "sum(container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\", container!=\"\", image!=\"\"}) by (container) / sum(kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\", pod=\"$pod\"}) by (container)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -856,7 +1028,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 5,
+              "id": 6,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -885,7 +1058,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -954,7 +1127,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 6,
+              "id": 7,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -983,7 +1157,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_bytes_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1052,7 +1226,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 7,
+              "id": 8,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -1081,7 +1256,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1150,7 +1325,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 8,
+              "id": 9,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -1179,7 +1355,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1248,7 +1424,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 9,
+              "id": 10,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -1277,7 +1454,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_receive_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1346,7 +1523,8 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 10,
-              "id": 10,
+              "id": 11,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -1375,7 +1553,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$interval])) by (pod)",
+                  "expr": "sum(irate(container_network_transmit_packets_dropped_total{namespace=~\"$namespace\", pod=~\"$pod\"}[$__rate_interval])) by (pod)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1441,8 +1619,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -1458,13 +1636,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -1473,7 +1651,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -1485,13 +1663,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "namespace",
+            "label": null,
             "multi": false,
             "name": "namespace",
             "options": [
@@ -1500,75 +1678,40 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$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=\"$namespace\"}, pod)",
+            "refresh": 2,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
             "useTags": false
           }
         ]
@@ -1602,7 +1745,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Compute Resources / Pod",
       "uid": "6581e46e4e5c7ba40a07646395ef7b23",
       "version": 0
@@ -1665,7 +1808,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -1777,6 +1920,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -1795,6 +1939,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -1813,6 +1958,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -1831,6 +1977,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -1849,6 +1996,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -1867,6 +2015,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
                   "pattern": "pod",
@@ -1894,7 +2043,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1903,7 +2052,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1912,7 +2061,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1921,7 +2070,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -1930,7 +2079,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2030,7 +2179,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2142,6 +2291,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -2160,6 +2310,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -2178,6 +2329,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -2196,6 +2348,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -2214,6 +2367,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -2232,6 +2386,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
                   "pattern": "pod",
@@ -2259,7 +2414,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2268,7 +2423,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2277,7 +2432,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2286,7 +2441,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2295,7 +2450,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n/sum(\n    kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\", workload_type=\"$type\"}\n) by (pod)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2367,6 +2522,7 @@ data:
               "datasource": "$datasource",
               "fill": 1,
               "id": 5,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -2409,6 +2565,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -2427,6 +2584,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -2445,6 +2603,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -2463,6 +2622,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -2481,6 +2641,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -2499,6 +2660,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -2517,6 +2679,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/6581e46e4e5c7ba40a07646395ef7b23/k8s-resources-pod?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-pod=$__cell",
                   "pattern": "pod",
@@ -2544,7 +2707,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2553,7 +2716,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2562,7 +2725,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2571,7 +2734,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2580,7 +2743,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2589,7 +2752,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -2689,7 +2852,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2787,7 +2950,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2885,7 +3048,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -2983,7 +3146,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3081,7 +3244,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3179,7 +3342,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3277,7 +3440,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3375,7 +3538,7 @@ 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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\"$workload\", workload_type=\"$type\"}) by (pod))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{pod}}",
@@ -3441,8 +3604,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -3458,13 +3621,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 2,
             "includeAll": false,
-            "label": "cluster",
+            "label": null,
             "multi": false,
             "name": "cluster",
             "options": [
@@ -3473,7 +3636,7 @@ data:
             "query": "label_values(kube_pod_info, cluster)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
+            "sort": 1,
             "tagValuesQuery": "",
             "tags": [
 
@@ -3485,13 +3648,13 @@ data:
           {
             "allValue": null,
             "current": {
-              "text": "prod",
+              "text": "",
-              "value": "prod"
+              "value": ""
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": false,
-            "label": "namespace",
+            "label": null,
             "multi": false,
             "name": "namespace",
             "options": [
@@ -3500,102 +3663,67 @@ data:
             "query": "label_values(kube_pod_info{cluster=\"$cluster\"}, namespace)",
             "refresh": 1,
             "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-              "text": "prod",
-              "value": "prod"
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "workload",
-            "multi": false,
-            "name": "workload",
-            "options": [
-
-            ],
-            "query": "label_values(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
-            "refresh": 1,
-            "regex": "",
-            "sort": 2,
-            "tagValuesQuery": "",
-            "tags": [
-
-            ],
-            "tagsQuery": "",
-            "type": "query",
-            "useTags": false
-          },
-          {
-            "allValue": null,
-            "current": {
-              "text": "prod",
-              "value": "prod"
-            },
-            "datasource": "$datasource",
-            "hide": 0,
-            "includeAll": false,
-            "label": "type",
-            "multi": false,
-            "name": "type",
-            "options": [
-
-            ],
-            "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
+          },
+          {
+            "allValue": null,
+            "current": {
+              "text": "",
+              "value": ""
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "workload",
+            "options": [
+
+            ],
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\"}, workload)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {
+              "text": "",
+              "value": ""
+            },
+            "datasource": "$datasource",
+            "hide": 0,
+            "includeAll": false,
+            "label": null,
+            "multi": false,
+            "name": "type",
+            "options": [
+
+            ],
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload=\"$workload\"}, workload_type)",
+            "refresh": 1,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
             "useTags": false
           }
         ]
@@ -3629,7 +3757,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Compute Resources / Workload",
       "uid": "a164a7f0339f99e89cea5cb47e9be617",
       "version": 0
@@ -3684,7 +3812,26 @@ data:
               "points": false,
               "renderer": "flot",
               "seriesOverrides": [
-
+                {
+                  "alias": "quota - requests",
+                  "color": "#F2495C",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                },
+                {
+                  "alias": "quota - limits",
+                  "color": "#FF9830",
+                  "dashes": true,
+                  "fill": 0,
+                  "hideTooltip": true,
+                  "legend": false,
+                  "linewidth": 2,
+                  "stack": false
+                }
               ],
               "spaceLength": 10,
               "span": 12,
@@ -3692,12 +3839,28 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}} - {{workload_type}}",
                   "legendLink": null,
                   "step": 10
+                },
+                {
+                  "expr": "scalar(kube_resourcequota{cluster=\"$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": [
@@ -3804,6 +3967,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 0,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -3822,6 +3986,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -3840,6 +4005,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -3858,6 +4024,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -3876,6 +4043,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -3894,6 +4062,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -3912,6 +4081,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
                   "pattern": "workload",
@@ -3930,6 +4100,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "workload_type",
@@ -3957,7 +4128,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
+                  "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3966,7 +4137,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3975,7 +4146,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3984,7 +4155,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -3993,7 +4164,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4002,7 +4173,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits_cpu_cores{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4094,7 +4265,26 @@ 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,
@@ -4102,12 +4292,28 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}} - {{workload_type}}",
                   "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": [
@@ -4214,6 +4420,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 0,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -4232,6 +4439,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -4250,6 +4458,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -4268,6 +4477,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -4286,6 +4496,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -4304,6 +4515,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -4322,6 +4534,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$__cell_2",
                   "pattern": "workload",
@@ -4340,6 +4553,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "workload_type",
@@ -4367,7 +4581,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "count(mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
+                  "expr": "count(namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}) by (workload, workload_type)",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4376,7 +4590,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4385,7 +4599,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4394,7 +4608,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_requests_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4403,7 +4617,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n  kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n  kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4412,7 +4626,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) mixin_pod_workload{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
+                  "expr": "sum(\n    container_memory_working_set_bytes{cluster=\"$cluster\", namespace=\"$namespace\", container!=\"\", image!=\"\"}\n  * on(namespace,pod)\n    group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n/sum(\n  kube_pod_container_resource_limits_memory_bytes{cluster=\"$cluster\", namespace=\"$namespace\"}\n* on(namespace,pod)\n  group_left(workload, workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=\"$namespace\", workload_type=\"$type\"}\n) by (workload, workload_type)\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4484,6 +4698,7 @@ data:
               "datasource": "$datasource",
               "fill": 1,
               "id": 5,
+              "interval": "1m",
               "legend": {
                 "avg": false,
                 "current": false,
@@ -4526,6 +4741,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -4544,6 +4760,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -4562,6 +4779,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #C",
@@ -4580,6 +4798,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #D",
@@ -4598,6 +4817,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #E",
@@ -4616,6 +4836,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #F",
@@ -4634,6 +4855,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": true,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down to pods",
                   "linkUrl": "./d/a164a7f0339f99e89cea5cb47e9be617/k8s-resources-workload?var-datasource=$datasource&var-cluster=$cluster&var-namespace=$namespace&var-workload=$__cell&var-type=$type",
                   "pattern": "workload",
@@ -4652,6 +4874,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "workload_type",
@@ -4679,7 +4902,7 @@ data:
               ],
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4688,7 +4911,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4697,7 +4920,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4706,7 +4929,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4715,7 +4938,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4724,7 +4947,7 @@ data:
                   "step": 10
                 },
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "table",
                   "instant": true,
                   "intervalFactor": 2,
@@ -4824,7 +5047,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_bytes_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -4922,7 +5145,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_transmit_bytes_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5020,7 +5243,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(avg(irate(container_network_receive_bytes_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5118,7 +5341,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(avg(irate(container_network_transmit_bytes_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5216,7 +5439,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5314,7 +5537,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5412,7 +5635,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_receive_packets_dropped_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5510,7 +5733,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "(sum(irate(container_network_transmit_packets_dropped_total{cluster=\"$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=~\"$namespace\"}[$__rate_interval])\n* on (namespace,pod)\ngroup_left(workload,workload_type) namespace_workload_pod:kube_pod_owner:relabel{cluster=\"$cluster\", namespace=~\"$namespace\", workload=~\".+\", workload_type=\"$type\"}) by (workload))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{workload}}",
@@ -5576,8 +5799,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -5590,95 +5813,6 @@ data:
             "regex": "",
             "type": "datasource"
           },
-          {
-            "allValue": null,
-            "current": {
-              "text": "prod",
-              "value": "prod"
-            },
-            "datasource": "$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,
@@ -5689,7 +5823,7 @@ data:
               "value": "deployment"
             },
             "datasource": "$datasource",
-            "definition": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+            "definition": "label_values(namespace_workload_pod:kube_pod_owner:relabel{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
             "hide": 0,
             "includeAll": false,
             "label": null,
@@ -5698,7 +5832,7 @@ data:
             "options": [
 
             ],
-            "query": "label_values(mixin_pod_workload{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
+            "query": "label_values(namespace_workload_pod:kube_pod_owner:relabel{namespace=~\"$namespace\", workload=~\".+\"}, workload_type)",
             "refresh": 1,
             "regex": "",
             "skipUrlSync": false,
@@ -5706,6 +5840,60 @@ 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",
@@ -5742,7 +5930,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Compute Resources / Namespace (Workloads)",
       "uid": "a87fb0d919ec0ea5f6543124e16c42a5",
       "version": 0

addons/grafana/dashboards-k8s.yaml

@@ -21,7 +21,25 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "panels": [
+        {
+          "content": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.",
+          "datasource": null,
+          "description": "The SLO (service level objective) and other metrics displayed on this dashboard are for informational purposes only.",
+          "gridPos": {
+            "h": 2,
+            "w": 24,
+            "x": 0,
+            "y": 0
+          },
+          "id": 2,
+          "mode": "markdown",
+          "span": 12,
+          "title": "Notice",
+          "type": "text"
+        }
+      ],
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -37,7 +55,9 @@ data:
                 "#d44a3a"
               ],
               "datasource": "$datasource",
-              "format": "none",
+              "decimals": 3,
+              "description": "How many percent of requests (both read and write) in 30 days have been answered successfully and fast enough?",
+              "format": "percentunit",
               "gauge": {
                 "maxValue": 100,
                 "minValue": 0,
@@ -48,7 +68,7 @@ data:
               "gridPos": {
 
               },
-              "id": 2,
+              "id": 3,
               "interval": null,
               "links": [
 
@@ -78,7 +98,7 @@ data:
                   "to": "null"
                 }
               ],
-              "span": 2,
+              "span": 4,
               "sparkline": {
                 "fillColor": "rgba(31, 118, 189, 0.18)",
                 "full": false,
@@ -88,7 +108,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "sum(up{job=\"apiserver\"})",
+                  "expr": "apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -96,7 +116,7 @@ data:
                 }
               ],
               "thresholds": "",
-              "title": "Up",
+              "title": "Availability (30d) > 99.000%",
               "tooltip": {
                 "shared": false
               },
@@ -109,7 +129,7 @@ data:
                   "value": "null"
                 }
               ],
-              "valueName": "min"
+              "valueName": "avg"
             },
             {
               "aliasColors": {
@@ -119,11 +139,14 @@ data:
               "dashLength": 10,
               "dashes": false,
               "datasource": "$datasource",
-              "fill": 1,
+              "decimals": 3,
+              "description": "How much error budget is left looking at our 0.990% availability guarantees?",
+              "fill": 10,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 3,
+              "id": 4,
               "legend": {
                 "alignAsTable": false,
                 "avg": false,
@@ -132,6 +155,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -150,37 +174,16 @@ data:
 
               ],
               "spaceLength": 10,
-              "span": 5,
+              "span": 8,
               "stack": false,
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"2..\"}[5m]))",
+                  "expr": "100 * (apiserver_request:availability30d{verb=\"all\", cluster=\"$cluster\"} - 0.990000)",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "2xx",
+                  "legendFormat": "errorbudget",
                   "refId": "A"
-                },
-                {
-                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"3..\"}[5m]))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "3xx",
-                  "refId": "B"
-                },
-                {
-                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"4..\"}[5m]))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "4xx",
-                  "refId": "C"
-                },
-                {
-                  "expr": "sum(rate(apiserver_request_total{job=\"apiserver\", instance=~\"$instance\",code=~\"5..\"}[5m]))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "5xx",
-                  "refId": "D"
                 }
               ],
               "thresholds": [
@@ -188,7 +191,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "RPC Rate",
+              "title": "ErrorBudget (30d) > 99.000%",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -206,7 +209,8 @@ data:
               },
               "yaxes": [
                 {
-                  "format": "ops",
+                  "decimals": 3,
+                  "format": "percentunit",
                   "label": null,
                   "logBase": 1,
                   "max": null,
@@ -214,7 +218,216 @@ data:
                   "show": true
                 },
                 {
-                  "format": "ops",
+                  "decimals": 3,
+                  "format": "percentunit",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            }
+          ],
+          "repeat": null,
+          "repeatIteration": null,
+          "repeatRowId": null,
+          "showTitle": false,
+          "title": "Dashboard Row",
+          "titleSize": "h6",
+          "type": "row"
+        },
+        {
+          "collapse": false,
+          "collapsed": false,
+          "panels": [
+            {
+              "cacheTimeout": null,
+              "colorBackground": false,
+              "colorValue": false,
+              "colors": [
+                "#299c46",
+                "rgba(237, 129, 40, 0.89)",
+                "#d44a3a"
+              ],
+              "datasource": "$datasource",
+              "decimals": 3,
+              "description": "How many percent of read requests (LIST,GET) in 30 days have been answered successfully and fast enough?",
+              "format": "percentunit",
+              "gauge": {
+                "maxValue": 100,
+                "minValue": 0,
+                "show": false,
+                "thresholdLabels": false,
+                "thresholdMarkers": true
+              },
+              "gridPos": {
+
+              },
+              "id": 5,
+              "interval": 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": "apiserver_request:availability30d{verb=\"read\", cluster=\"$cluster\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": "",
+              "title": "Read Availability (30d)",
+              "tooltip": {
+                "shared": false
+              },
+              "type": "singlestat",
+              "valueFontSize": "80%",
+              "valueMaps": [
+                {
+                  "op": "=",
+                  "text": "N/A",
+                  "value": "null"
+                }
+              ],
+              "valueName": "avg"
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "description": "How many read requests (LIST,GET) per second do the apiservers get by code?",
+              "fill": 10,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 6,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+                {
+                  "alias": "/2../i",
+                  "color": "#56A64B"
+                },
+                {
+                  "alias": "/3../i",
+                  "color": "#F2CC0C"
+                },
+                {
+                  "alias": "/4../i",
+                  "color": "#3274D9"
+                },
+                {
+                  "alias": "/5../i",
+                  "color": "#E02F44"
+                }
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{ code }}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Read SLI - Requests",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "reqps",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "reqps",
                   "label": null,
                   "logBase": 1,
                   "max": null,
@@ -231,21 +444,24 @@ data:
               "dashLength": 10,
               "dashes": false,
               "datasource": "$datasource",
+              "description": "How many percent of read requests (LIST,GET) per second are returned with errors (5xx)?",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 4,
+              "id": 7,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": false,
                 "avg": false,
-                "current": "true",
+                "current": false,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": false,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": false
               },
               "lines": true,
               "linewidth": 1,
@@ -262,15 +478,15 @@ data:
 
               ],
               "spaceLength": 10,
-              "span": 5,
+              "span": 3,
               "stack": false,
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\", instance=~\"$instance\"}[5m])) by (verb, le))",
+                  "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"read\", cluster=\"$cluster\"})",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{verb}}",
+                  "legendFormat": "{{ resource }}",
                   "refId": "A"
                 }
               ],
@@ -279,7 +495,497 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Request duration 99th quantile",
+              "title": "Read SLI - Errors",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "percentunit",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": 0,
+                  "show": true
+                },
+                {
+                  "format": "percentunit",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": 0,
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "description": "How many seconds is the 99th percentile for reading (LIST|GET) a given resource?",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 8,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"read\", cluster=\"$cluster\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{ resource }}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Read SLI - Duration",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "s",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "s",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            }
+          ],
+          "repeat": null,
+          "repeatIteration": null,
+          "repeatRowId": null,
+          "showTitle": false,
+          "title": "Dashboard Row",
+          "titleSize": "h6",
+          "type": "row"
+        },
+        {
+          "collapse": false,
+          "collapsed": false,
+          "panels": [
+            {
+              "cacheTimeout": null,
+              "colorBackground": false,
+              "colorValue": false,
+              "colors": [
+                "#299c46",
+                "rgba(237, 129, 40, 0.89)",
+                "#d44a3a"
+              ],
+              "datasource": "$datasource",
+              "decimals": 3,
+              "description": "How many percent of write requests (POST|PUT|PATCH|DELETE) in 30 days have been answered successfully and fast enough?",
+              "format": "percentunit",
+              "gauge": {
+                "maxValue": 100,
+                "minValue": 0,
+                "show": false,
+                "thresholdLabels": false,
+                "thresholdMarkers": true
+              },
+              "gridPos": {
+
+              },
+              "id": 9,
+              "interval": 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": "apiserver_request:availability30d{verb=\"write\", cluster=\"$cluster\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": "",
+              "title": "Write Availability (30d)",
+              "tooltip": {
+                "shared": false
+              },
+              "type": "singlestat",
+              "valueFontSize": "80%",
+              "valueMaps": [
+                {
+                  "op": "=",
+                  "text": "N/A",
+                  "value": "null"
+                }
+              ],
+              "valueName": "avg"
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "description": "How many write requests (POST|PUT|PATCH|DELETE) per second do the apiservers get by code?",
+              "fill": 10,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 10,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+                {
+                  "alias": "/2../i",
+                  "color": "#56A64B"
+                },
+                {
+                  "alias": "/3../i",
+                  "color": "#F2CC0C"
+                },
+                {
+                  "alias": "/4../i",
+                  "color": "#3274D9"
+                },
+                {
+                  "alias": "/5../i",
+                  "color": "#E02F44"
+                }
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": true,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum by (code) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{ code }}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Write SLI - Requests",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "reqps",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "reqps",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "description": "How many percent of write requests (POST|PUT|PATCH|DELETE) per second are returned with errors (5xx)?",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 11,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\",code=~\"5..\", cluster=\"$cluster\"}) / sum by (resource) (code_resource:apiserver_request_total:rate5m{verb=\"write\", cluster=\"$cluster\"})",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{ resource }}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Write SLI - Errors",
+              "tooltip": {
+                "shared": false,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "percentunit",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": 0,
+                  "show": true
+                },
+                {
+                  "format": "percentunit",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": 0,
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "description": "How many seconds is the 99th percentile for writing (POST|PUT|PATCH|DELETE) a given resource?",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 12,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 3,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{verb=\"write\", cluster=\"$cluster\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{ resource }}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Write SLI - Duration",
               "tooltip": {
                 "shared": false,
                 "sort": 0,
@@ -336,10 +1042,11 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 5,
+              "id": 13,
               "legend": {
                 "alignAsTable": false,
                 "avg": false,
@@ -348,6 +1055,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": false,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -371,7 +1079,7 @@ 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=\"$cluster\"}[5m])) by (instance, name)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{name}}",
@@ -427,10 +1135,11 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 6,
+              "id": 14,
               "legend": {
                 "alignAsTable": false,
                 "avg": false,
@@ -439,6 +1148,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": false,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -462,7 +1172,7 @@ 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=\"$cluster\"}[5m])) by (instance, name)",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{name}}",
@@ -518,20 +1228,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 7,
+              "id": 15,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -553,7 +1265,7 @@ 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=\"$cluster\"}[5m])) by (instance, name, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}} {{name}}",
@@ -622,10 +1334,11 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 8,
+              "id": 16,
               "legend": {
                 "alignAsTable": false,
                 "avg": false,
@@ -634,6 +1347,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -657,307 +1371,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "etcd_helper_cache_entry_total{job=\"apiserver\", instance=~\"$instance\"}",
+                  "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\", cluster=\"$cluster\"}",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{instance}}",
-                  "refId": "A"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "ETCD Cache Entry Total",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "value_type": "individual"
-              },
-              "type": "graph",
-              "xaxis": {
-                "buckets": null,
-                "mode": "time",
-                "name": null,
-                "show": true,
-                "values": [
-
-                ]
-              },
-              "yaxes": [
-                {
-                  "format": "short",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                },
-                {
-                  "format": "short",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                }
-              ]
-            },
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 9,
-              "legend": {
-                "alignAsTable": false,
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "rightSide": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 1,
-              "links": [
-
-              ],
-              "nullPointMode": "null",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "repeat": null,
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 4,
-              "stack": false,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "sum(rate(etcd_helper_cache_hit_total{job=\"apiserver\",instance=~\"$instance\"}[5m])) by (intance)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{instance}} hit",
-                  "refId": "A"
-                },
-                {
-                  "expr": "sum(rate(etcd_helper_cache_miss_total{job=\"apiserver\",instance=~\"$instance\"}[5m])) by (instance)",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{instance}} miss",
-                  "refId": "B"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "ETCD Cache Hit/Miss Rate",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "value_type": "individual"
-              },
-              "type": "graph",
-              "xaxis": {
-                "buckets": null,
-                "mode": "time",
-                "name": null,
-                "show": true,
-                "values": [
-
-                ]
-              },
-              "yaxes": [
-                {
-                  "format": "ops",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                },
-                {
-                  "format": "ops",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                }
-              ]
-            },
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 10,
-              "legend": {
-                "alignAsTable": false,
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "rightSide": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 1,
-              "links": [
-
-              ],
-              "nullPointMode": "null",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "repeat": null,
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 4,
-              "stack": false,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "histogram_quantile(0.99,sum(rate(etcd_request_cache_get_duration_seconds_bucket{job=\"apiserver\",instance=~\"$instance\"}[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=~\"$instance\"}[5m])) by (instance, le))",
-                  "format": "time_series",
-                  "intervalFactor": 2,
-                  "legendFormat": "{{instance}} miss",
-                  "refId": "B"
-                }
-              ],
-              "thresholds": [
-
-              ],
-              "timeFrom": null,
-              "timeShift": null,
-              "title": "ETCD Cache Duration 99th Quantile",
-              "tooltip": {
-                "shared": false,
-                "sort": 0,
-                "value_type": "individual"
-              },
-              "type": "graph",
-              "xaxis": {
-                "buckets": null,
-                "mode": "time",
-                "name": null,
-                "show": true,
-                "values": [
-
-                ]
-              },
-              "yaxes": [
-                {
-                  "format": "s",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                },
-                {
-                  "format": "s",
-                  "label": null,
-                  "logBase": 1,
-                  "max": null,
-                  "min": 0,
-                  "show": true
-                }
-              ]
-            }
-          ],
-          "repeat": null,
-          "repeatIteration": null,
-          "repeatRowId": null,
-          "showTitle": false,
-          "title": "Dashboard Row",
-          "titleSize": "h6",
-          "type": "row"
-        },
-        {
-          "collapse": false,
-          "collapsed": false,
-          "panels": [
-            {
-              "aliasColors": {
-
-              },
-              "bars": false,
-              "dashLength": 10,
-              "dashes": false,
-              "datasource": "$datasource",
-              "fill": 1,
-              "gridPos": {
-
-              },
-              "id": 11,
-              "legend": {
-                "alignAsTable": false,
-                "avg": false,
-                "current": false,
-                "max": false,
-                "min": false,
-                "rightSide": false,
-                "show": true,
-                "total": false,
-                "values": false
-              },
-              "lines": true,
-              "linewidth": 1,
-              "links": [
-
-              ],
-              "nullPointMode": "null",
-              "percentage": false,
-              "pointradius": 5,
-              "points": false,
-              "renderer": "flot",
-              "repeat": null,
-              "seriesOverrides": [
-
-              ],
-              "spaceLength": 10,
-              "span": 4,
-              "stack": false,
-              "steppedLine": false,
-              "targets": [
-                {
-                  "expr": "process_resident_memory_bytes{job=\"apiserver\",instance=~\"$instance\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -1013,10 +1427,11 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 12,
+              "id": 17,
               "legend": {
                 "alignAsTable": false,
                 "avg": false,
@@ -1025,6 +1440,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -1048,7 +1464,7 @@ 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=\"$cluster\"}[5m])",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{instance}}",
@@ -1104,10 +1520,11 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
-              "id": 13,
+              "id": 18,
               "legend": {
                 "alignAsTable": false,
                 "avg": false,
@@ -1116,6 +1533,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -1139,7 +1557,7 @@ 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 +1623,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -1223,6 +1641,32 @@ data:
             "allValue": null,
             "current": {
 
+            },
+            "datasource": "$datasource",
+            "hide": 2,
+            "includeAll": false,
+            "label": "cluster",
+            "multi": false,
+            "name": "cluster",
+            "options": [
+
+            ],
+            "query": "label_values(apiserver_request_total, cluster)",
+            "refresh": 2,
+            "regex": "",
+            "sort": 1,
+            "tagValuesQuery": "",
+            "tags": [
+
+            ],
+            "tagsQuery": "",
+            "type": "query",
+            "useTags": false
+          },
+          {
+            "allValue": null,
+            "current": {
+
             },
             "datasource": "$datasource",
             "hide": 0,
@@ -1233,7 +1677,7 @@ 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,
@@ -1276,7 +1720,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / API server",
       "uid": "09ec8aa1e996d6ffcd6817bbaff4db1b",
       "version": 0
@@ -1302,7 +1746,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -1401,20 +1845,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 3,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1505,20 +1951,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1609,20 +2057,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 5,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1713,6 +2163,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -1725,6 +2176,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -1825,6 +2277,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -1837,6 +2290,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -1860,7 +2314,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}} {{url}}",
@@ -1929,20 +2383,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 8,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -1964,7 +2420,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-controller-manager\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}} {{url}}",
@@ -2033,6 +2489,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2045,6 +2502,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2124,6 +2582,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2136,6 +2595,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2215,6 +2675,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2227,6 +2688,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -2316,8 +2778,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2387,7 +2849,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Controller Manager",
       "uid": "72e0e05bef5099e5f049b05fdc429ed4",
       "version": 0
@@ -2413,7 +2875,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -2428,6 +2890,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2440,6 +2903,7 @@ data:
                 "min": true,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": true
               },
@@ -2578,7 +3042,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "(\n  kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n  -\n  kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n)\n/\nkubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n",
+                  "expr": "max without(instance,node) (\n(\n  kubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n  -\n  kubelet_volume_stats_available_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n)\n/\nkubelet_volume_stats_capacity_bytes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -2623,6 +3087,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -2635,6 +3100,7 @@ data:
                 "min": true,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": true
               },
@@ -2773,7 +3239,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "kubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n/\nkubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100\n",
+                  "expr": "max without(instance,node) (\nkubelet_volume_stats_inodes_used{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n/\nkubelet_volume_stats_inodes{cluster=\"$cluster\", job=\"kubelet\", namespace=\"$namespace\", persistentvolumeclaim=\"$volume\"}\n* 100)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -2815,8 +3281,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2938,669 +3404,11 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Persistent Volumes",
       "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 +3430,7 @@ data:
       "links": [
 
       ],
-      "refresh": "",
+      "refresh": "10s",
       "rows": [
         {
           "collapse": false,
@@ -3721,20 +3529,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 3,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -3833,20 +3643,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 4,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -3958,6 +3770,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -3970,6 +3783,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -4070,6 +3884,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -4082,6 +3897,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -4105,7 +3921,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"POST\"}[5m])) by (verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}} {{url}}",
@@ -4174,20 +3990,22 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
               "id": 7,
               "legend": {
-                "alignAsTable": "true",
+                "alignAsTable": true,
                 "avg": false,
-                "current": "true",
+                "current": true,
                 "max": false,
                 "min": false,
-                "rightSide": "true",
+                "rightSide": true,
-                "show": "true",
+                "show": true,
+                "sideWidth": null,
                 "total": false,
-                "values": "true"
+                "values": true
               },
               "lines": true,
               "linewidth": 1,
@@ -4209,7 +4027,7 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_latency_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
+                  "expr": "histogram_quantile(0.99, sum(rate(rest_client_request_duration_seconds_bucket{job=\"kube-scheduler\", instance=~\"$instance\", verb=\"GET\"}[5m])) by (verb, url, le))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "{{verb}} {{url}}",
@@ -4278,6 +4096,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -4290,6 +4109,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -4369,6 +4189,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -4381,6 +4202,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -4460,6 +4282,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -4472,6 +4295,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -4561,8 +4385,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -4632,7 +4456,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / Scheduler",
       "uid": "2e6b6a3b4bddf1427b3a55aa1311c656",
       "version": 0
@@ -4724,7 +4548,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m]))",
+                  "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", container!=\"\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m]))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -4807,7 +4631,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}) / 1024^3",
+                  "expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", container!=\"\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}) / 1024^3",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -4890,7 +4714,7 @@ data:
               "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]))",
+                  "expr": "sum(rate(container_network_transmit_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\", pod=~\"$statefulset.*\"}[3m])) + sum(rate(container_network_receive_bytes_total{job=\"kubernetes-cadvisor\", cluster=\"$cluster\", namespace=\"$namespace\",pod=~\"$statefulset.*\"}[3m]))",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -5285,6 +5109,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -5297,6 +5122,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -5413,8 +5239,8 @@ data:
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -5536,7 +5362,7 @@ data:
           "30d"
         ]
       },
-      "timezone": "",
+      "timezone": "UTC",
       "title": "Kubernetes / StatefulSets",
       "uid": "a31c1f46e6f727cb37c0d731a7245005",
       "version": 0

addons/grafana/dashboards-nginx-ingress.yaml

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

addons/grafana/dashboards-node-exporter.yaml

@@ -36,6 +36,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -48,6 +49,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -128,6 +130,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 0,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -140,6 +143,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -253,6 +257,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -265,6 +270,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -417,7 +423,7 @@ data:
               "tableColumn": "",
               "targets": [
                 {
-                  "expr": "100 -\n(\n  node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"}\n/\n  node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"}\n* 100\n)\n",
+                  "expr": "100 -\n(\n  avg(node_memory_MemAvailable_bytes{job=\"node-exporter\", instance=\"$instance\"})\n/\n  avg(node_memory_MemTotal_bytes{job=\"node-exporter\", instance=\"$instance\"})\n* 100\n)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
                   "legendFormat": "",
@@ -459,6 +465,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 0,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -471,6 +478,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -574,6 +582,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -586,6 +595,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -692,6 +702,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 0,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -704,6 +715,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -784,6 +796,7 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 0,
+              "fillGradient": 0,
               "gridPos": {
 
               },
@@ -796,6 +809,7 @@ data:
                 "min": false,
                 "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },

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": "60s",
       "rows": [
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -29,13 +36,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 2,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -44,11 +58,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -58,12 +73,11 @@ 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(remote_name, url) group_right(instance) (prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"} != 0)\n)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -89,11 +103,11 @@ data:
               },
               "yaxes": [
                 {
-                  "format": "s",
+                  "format": "short",
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -102,7 +116,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -115,13 +129,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 2,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 3,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -130,11 +151,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -144,12 +166,11 @@ 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": "clamp_min(\n  rate(prometheus_remote_storage_highest_timestamp_in_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])  \n- \n  ignoring (remote_name, url) group_right(instance) rate(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])\n, 0)\n",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -179,7 +200,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -188,7 +209,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             }
@@ -198,11 +219,12 @@ data:
           "repeatRowId": null,
           "showTitle": true,
           "title": "Timestamps",
-          "titleSize": "h6"
+          "titleSize": "h6",
+          "type": "row"
         },
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -213,13 +235,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 3,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 4,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -228,11 +257,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -242,12 +272,11 @@ 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(remote_name, url) group_right(instance) (rate(prometheus_remote_storage_succeeded_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n- \n  (rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]))\n",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -277,7 +306,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -286,7 +315,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             }
@@ -296,11 +325,12 @@ data:
           "repeatRowId": null,
           "showTitle": true,
           "title": "Samples",
-          "titleSize": "h6"
+          "titleSize": "h6",
+          "type": "row"
         },
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -311,13 +341,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 4,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 5,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -326,16 +363,18 @@ 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": [
@@ -343,9 +382,8 @@ data:
                   "expr": "prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -353,7 +391,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Num. Shards",
+              "title": "Current Shards",
               "tooltip": {
                 "shared": true,
                 "sort": 0,
@@ -375,7 +413,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -384,7 +422,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -397,13 +435,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 5,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 6,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -412,26 +457,26 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
               "spaceLength": 10,
-              "span": 6,
+              "span": 4,
               "stack": false,
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "prometheus_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "expr": "prometheus_remote_storage_shards_max{cluster=~\"$cluster\", instance=~\"$instance\"}",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -439,7 +484,7 @@ data:
               ],
               "timeFrom": null,
               "timeShift": null,
-              "title": "Capacity",
+              "title": "Max Shards",
               "tooltip": {
                 "shared": true,
                 "sort": 0,
@@ -461,7 +506,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -470,7 +515,193 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 7,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 4,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_remote_storage_shards_min{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Min Shards",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 8,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "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}} {{remote_name}}:{{url}}",
+                  "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
                 }
               ]
             }
@@ -480,11 +711,12 @@ data:
           "repeatRowId": null,
           "showTitle": true,
           "title": "Shards",
-          "titleSize": "h6"
+          "titleSize": "h6",
+          "type": "row"
         },
         {
           "collapse": false,
-          "height": "250px",
+          "collapsed": false,
           "panels": [
             {
               "aliasColors": {
@@ -495,13 +727,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 6,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 9,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -510,11 +749,410 @@ 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_remote_storage_shard_capacity{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Shard Capacity",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            },
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 10,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 6,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_remote_storage_pending_samples{cluster=~\"$cluster\", instance=~\"$instance\"} or prometheus_remote_storage_samples_pending{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Pending Samples",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            }
+          ],
+          "repeat": null,
+          "repeatIteration": null,
+          "repeatRowId": null,
+          "showTitle": true,
+          "title": "Shard Details",
+          "titleSize": "h6",
+          "type": "row"
+        },
+        {
+          "collapse": false,
+          "collapsed": false,
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 11,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "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": "$datasource",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 12,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
+              "seriesOverrides": [
+
+              ],
+              "spaceLength": 10,
+              "span": 6,
+              "stack": false,
+              "steppedLine": false,
+              "targets": [
+                {
+                  "expr": "prometheus_wal_watcher_current_segment{cluster=~\"$cluster\", instance=~\"$instance\"}",
+                  "format": "time_series",
+                  "intervalFactor": 2,
+                  "legendFormat": "{{cluster}}:{{instance}} {{consumer}}",
+                  "refId": "A"
+                }
+              ],
+              "thresholds": [
+
+              ],
+              "timeFrom": null,
+              "timeShift": null,
+              "title": "Remote Write Current Segment",
+              "tooltip": {
+                "shared": true,
+                "sort": 0,
+                "value_type": "individual"
+              },
+              "type": "graph",
+              "xaxis": {
+                "buckets": null,
+                "mode": "time",
+                "name": null,
+                "show": true,
+                "values": [
+
+                ]
+              },
+              "yaxes": [
+                {
+                  "format": "none",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                },
+                {
+                  "format": "short",
+                  "label": null,
+                  "logBase": 1,
+                  "max": null,
+                  "min": null,
+                  "show": true
+                }
+              ]
+            }
+          ],
+          "repeat": null,
+          "repeatIteration": null,
+          "repeatRowId": null,
+          "showTitle": true,
+          "title": "Segments",
+          "titleSize": "h6",
+          "type": "row"
+        },
+        {
+          "collapse": false,
+          "collapsed": false,
+          "panels": [
+            {
+              "aliasColors": {
+
+              },
+              "bars": false,
+              "dashLength": 10,
+              "dashes": false,
+              "datasource": "$datasource",
+              "fill": 1,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 13,
+              "legend": {
+                "alignAsTable": false,
+                "avg": false,
+                "current": false,
+                "max": false,
+                "min": false,
+                "rightSide": false,
+                "show": true,
+                "sideWidth": null,
+                "total": false,
+                "values": false
+              },
+              "lines": true,
+              "linewidth": 1,
+              "links": [
+
+              ],
+              "nullPointMode": "null",
+              "percentage": false,
+              "pointradius": 5,
+              "points": false,
+              "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -524,12 +1162,11 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+                  "expr": "rate(prometheus_remote_storage_dropped_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_dropped_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -559,7 +1196,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -568,7 +1205,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -581,13 +1218,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 7,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 14,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -596,11 +1240,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -610,12 +1255,11 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+                  "expr": "rate(prometheus_remote_storage_failed_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_failed_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -645,7 +1289,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -654,7 +1298,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -667,13 +1311,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 8,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 15,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -682,11 +1333,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -696,12 +1348,11 @@ data:
               "steppedLine": false,
               "targets": [
                 {
-                  "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
+                  "expr": "rate(prometheus_remote_storage_retried_samples_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m]) or rate(prometheus_remote_storage_samples_retried_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -731,7 +1382,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -740,7 +1391,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             },
@@ -753,13 +1404,20 @@ data:
               "dashes": false,
               "datasource": "$datasource",
               "fill": 1,
-              "id": 9,
+              "fillGradient": 0,
+              "gridPos": {
+
+              },
+              "id": 16,
               "legend": {
+                "alignAsTable": false,
                 "avg": false,
                 "current": false,
                 "max": false,
                 "min": false,
+                "rightSide": false,
                 "show": true,
+                "sideWidth": null,
                 "total": false,
                 "values": false
               },
@@ -768,11 +1426,12 @@ data:
               "links": [
 
               ],
-              "nullPointMode": "null as zero",
+              "nullPointMode": "null",
               "percentage": false,
               "pointradius": 5,
               "points": false,
               "renderer": "flot",
+              "repeat": null,
               "seriesOverrides": [
 
               ],
@@ -785,9 +1444,8 @@ data:
                   "expr": "rate(prometheus_remote_storage_enqueue_retries_total{cluster=~\"$cluster\", instance=~\"$instance\"}[5m])",
                   "format": "time_series",
                   "intervalFactor": 2,
-                  "legendFormat": "{{cluster}}:{{instance}}-{{queue}}",
+                  "legendFormat": "{{cluster}}:{{instance}} {{remote_name}}:{{url}}",
-                  "legendLink": null,
+                  "refId": "A"
-                  "step": 10
                 }
               ],
               "thresholds": [
@@ -817,7 +1475,7 @@ data:
                   "label": null,
                   "logBase": 1,
                   "max": null,
-                  "min": 0,
+                  "min": null,
                   "show": true
                 },
                 {
@@ -826,7 +1484,7 @@ data:
                   "logBase": 1,
                   "max": null,
                   "min": null,
-                  "show": false
+                  "show": true
                 }
               ]
             }
@@ -835,22 +1493,19 @@ data:
           "repeatIteration": null,
           "repeatRowId": null,
           "showTitle": true,
-          "title": "Misc Rates.",
+          "title": "Misc. Rates",
-          "titleSize": "h6"
+          "titleSize": "h6",
+          "type": "row"
         }
       ],
       "schemaVersion": 14,
       "style": "dark",
       "tags": [
-
+        "prometheus-mixin"
       ],
       "templating": {
         "list": [
           {
-            "current": {
-              "text": "Prometheus",
-              "value": "Prometheus"
-            },
             "hide": 0,
             "label": null,
             "name": "datasource",
@@ -865,23 +1520,30 @@ data:
           {
             "allValue": null,
             "current": {
-              "selected": true,
+              "text": {
-              "text": "All",
+                "selected": true,
-              "value": "$__all"
+                "text": "All",
+                "value": "$__all"
+              },
+              "value": {
+                "selected": true,
+                "text": "All",
+                "value": "$__all"
+              }
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": true,
-            "label": "instance",
+            "label": null,
-            "multi": true,
+            "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 +1555,56 @@ data:
           {
             "allValue": null,
             "current": {
-              "selected": true,
+              "text": {
-              "text": "All",
+                "selected": true,
-              "value": "$__all"
+                "text": "All",
+                "value": "$__all"
+              },
+              "value": {
+                "selected": true,
+                "text": "All",
+                "value": "$__all"
+              }
             },
             "datasource": "$datasource",
             "hide": 0,
             "includeAll": true,
-            "label": "cluster",
+            "label": null,
-            "multi": true,
+            "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": "$datasource",
+            "hide": 0,
+            "includeAll": true,
+            "label": null,
+            "multi": false,
+            "name": "url",
+            "options": [
+
+            ],
+            "query": "label_values(prometheus_remote_storage_shards{cluster=~\"$cluster\", instance=~\"$instance\"}, url)",
+            "refresh": 2,
+            "regex": "",
+            "sort": 0,
             "tagValuesQuery": "",
             "tags": [
 
@@ -921,7 +1616,7 @@ data:
         ]
       },
       "time": {
-        "from": "now-1h",
+        "from": "now-6h",
         "to": "now"
       },
       "timepicker": {
@@ -949,9 +1644,8 @@ data:
           "30d"
         ]
       },
-      "timezone": "utc",
+      "timezone": "browser",
-      "title": "Prometheus Remote Write",
+      "title": "Prometheus / Remote Write",
-      "uid": "",
       "version": 0
     }
   prometheus.json: |-
@@ -968,7 +1662,7 @@ data:
       "links": [
 
       ],
-      "refresh": "10s",
+      "refresh": "60s",
       "rows": [
         {
           "collapse": false,
@@ -1026,6 +1720,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #A",
@@ -1044,6 +1739,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "Value #B",
@@ -1062,6 +1758,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "instance",
@@ -1080,6 +1777,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "job",
@@ -1098,6 +1796,7 @@ data:
                   "dateFormat": "YYYY-MM-DD HH:mm:ss",
                   "decimals": 2,
                   "link": false,
+                  "linkTargetBlank": false,
                   "linkTooltip": "Drill down",
                   "linkUrl": "",
                   "pattern": "version",
@@ -2042,14 +2741,14 @@ data:
       "schemaVersion": 14,
       "style": "dark",
       "tags": [
-
+        "prometheus-mixin"
       ],
       "templating": {
         "list": [
           {
             "current": {
-              "text": "Prometheus",
+              "text": "default",
-              "value": "Prometheus"
+              "value": "default"
             },
             "hide": 0,
             "label": null,
@@ -2150,7 +2849,7 @@ data:
         ]
       },
       "timezone": "utc",
-      "title": "Prometheus",
+      "title": "Prometheus / Overview",
       "uid": "",
       "version": 0
     }

addons/grafana/deployment.yaml

@@ -18,12 +18,13 @@ spec:
       labels:
         name: grafana
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       containers:
         - name: grafana
-          image: docker.io/grafana/grafana:6.5.3
+          image: docker.io/grafana/grafana:7.5.6
           env:
             - name: GF_PATHS_CONFIG
               value: "/etc/grafana/custom.ini"

addons/nginx-ingress/aws/class.yaml

@@ -0,0 +1,6 @@
+apiVersion: networking.k8s.io/v1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/aws/deployment.yaml

@@ -17,12 +17,13 @@ spec:
       labels:
         name: nginx-ingress-controller
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.26.1
+          image: k8s.gcr.io/ingress-nginx/controller:v0.46.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +48,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +55,16 @@ 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:
@@ -76,6 +77,6 @@ spec:
               - NET_BIND_SERVICE
               drop:
               - ALL
-            runAsUser: 33 # www-data
+            runAsUser: 101 # www-data
       restartPolicy: Always
       terminationGracePeriodSeconds: 300

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/v1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

addons/nginx-ingress/azure/deployment.yaml

@@ -17,12 +17,13 @@ spec:
       labels:
         name: nginx-ingress-controller
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.26.1
+          image: k8s.gcr.io/ingress-nginx/controller:v0.46.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +48,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +55,16 @@ 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:
@@ -76,6 +77,6 @@ spec:
               - NET_BIND_SERVICE
               drop:
               - ALL
-            runAsUser: 33 # www-data
+            runAsUser: 101 # www-data
       restartPolicy: Always
       terminationGracePeriodSeconds: 300

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/v1
+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 +10,20 @@ spec:
       maxUnavailable: 1
   selector:
     matchLabels:
-      name: ingress-controller-public
+      name: nginx-ingress-controller
       phase: prod
   template:
     metadata:
       labels:
-        name: ingress-controller-public
+        name: nginx-ingress-controller
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.26.1
+          image: k8s.gcr.io/ingress-nginx/controller:v0.46.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -73,7 +74,6 @@ spec:
               - NET_BIND_SERVICE
               drop:
               - ALL
-            runAsUser: 33 # www-data
+            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/v1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

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

@@ -17,12 +17,13 @@ spec:
       labels:
         name: nginx-ingress-controller
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.26.1
+          image: k8s.gcr.io/ingress-nginx/controller:v0.46.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +48,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +55,16 @@ 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:
@@ -76,6 +77,6 @@ spec:
               - NET_BIND_SERVICE
               drop:
               - ALL
-            runAsUser: 33 # www-data
+            runAsUser: 101 # www-data
       restartPolicy: Always
       terminationGracePeriodSeconds: 300

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/v1
+kind: IngressClass
+metadata:
+  name: public
+spec:
+  controller: k8s.io/ingress-nginx

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

@@ -17,12 +17,13 @@ spec:
       labels:
         name: nginx-ingress-controller
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       containers:
         - name: nginx-ingress-controller
-          image: quay.io/kubernetes-ingress-controller/nginx-ingress-controller:0.26.1
+          image: k8s.gcr.io/ingress-nginx/controller:v0.46.0
           args:
             - /nginx-ingress-controller
             - --ingress-class=public
@@ -47,7 +48,6 @@ spec:
               containerPort: 10254
               hostPort: 10254
           livenessProbe:
-            failureThreshold: 3
             httpGet:
               path: /healthz
               port: 10254
@@ -55,15 +55,16 @@ 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:
@@ -76,6 +77,6 @@ spec:
               - NET_BIND_SERVICE
               drop:
               - ALL
-            runAsUser: 33 # www-data
+            runAsUser: 101 # www-data
       restartPolicy: Always
       terminationGracePeriodSeconds: 300

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/config.yaml

@@ -68,6 +68,9 @@ data:
       - source_labels: [__name__, group]
         regex: apiserver_request_duration_seconds_bucket;.+
         action: drop
+      - source_labels: [__name__, group]
+        regex: apiserver_request_duration_seconds_count;.+
+        action: drop
 
     # Scrape config for node (i.e. kubelet) /metrics (e.g. 'kubelet_'). Explore
     # metrics from a node by scraping kubelet (127.0.0.1:10250/metrics).
@@ -82,10 +85,6 @@ data:
         insecure_skip_verify: true
       bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
 
-      relabel_configs:
-      - action: labelmap
-        regex: __meta_kubernetes_node_name
-
     # Scrape config for Kubelet cAdvisor. Explore metrics from a node by
     # scraping kubelet (127.0.0.1:10250/metrics/cadvisor).
     - job_name: 'kubernetes-cadvisor'
@@ -100,9 +99,6 @@ data:
         ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
       bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
 
-      relabel_configs:
-      - action: labelmap
-        regex: __meta_kubernetes_node_name
       metric_relabel_configs:
       - source_labels: [__name__, image]
         action: drop
@@ -121,8 +117,6 @@ data:
       - source_labels: [__meta_kubernetes_node_label_node_kubernetes_io_controller]
         action: keep
         regex: 'true'
-      - action: labelmap
-        regex: __meta_kubernetes_node_name
       - source_labels: [__meta_kubernetes_node_address_InternalIP]
         action: replace
         target_label: __address__

addons/prometheus/deployment.yaml

@@ -14,13 +14,14 @@ spec:
       labels:
         name: prometheus
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       serviceAccountName: prometheus
       containers:
         - name: prometheus
-          image: quay.io/prometheus/prometheus:v2.15.2
+          image: quay.io/prometheus/prometheus:v2.27.0
           args:
             - --web.listen-address=0.0.0.0:9090
             - --config.file=/etc/prometheus/prometheus.yaml

addons/prometheus/exporters/kube-state-metrics/cluster-role.yaml

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

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

@@ -18,16 +18,19 @@ spec:
       labels:
         name: kube-state-metrics
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
+      securityContext:
+        seccompProfile:
+          type: RuntimeDefault
       serviceAccountName: kube-state-metrics
       containers:
       - name: kube-state-metrics
-        image: quay.io/coreos/kube-state-metrics:v1.9.2
+        image: k8s.gcr.io/kube-state-metrics/kube-state-metrics:v2.0.0
         ports:
           - name: metrics
             containerPort: 8080
+          - name: telemetry
+            containerPort: 8081
         livenessProbe:
           httpGet:
             path: /healthz
@@ -40,3 +43,5 @@ spec:
             port: 8081
           initialDelaySeconds: 5
           timeoutSeconds: 5
+        securityContext:
+          runAsUser: 65534

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

@@ -17,18 +17,18 @@ spec:
       labels:
         name: node-exporter
         phase: prod
-      annotations:
-        seccomp.security.alpha.kubernetes.io/pod: 'docker/default'
     spec:
       serviceAccountName: node-exporter
       securityContext:
         runAsNonRoot: true
         runAsUser: 65534
+        seccompProfile:
+          type: RuntimeDefault
       hostNetwork: true
       hostPID: true
       containers:
       - name: node-exporter
-        image: quay.io/prometheus/node-exporter:v0.18.1
+        image: quay.io/prometheus/node-exporter:v1.1.2
         args:
           - --path.procfs=/host/proc
           - --path.sysfs=/host/sys

addons/prometheus/rules.yaml

@@ -9,10 +9,11 @@ data:
             {
               "alert": "etcdMembersDown",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": members are down ({{ $value }})."
+                "description": "etcd cluster \"{{ $labels.job }}\": members are down ({{ $value }}).",
+                "summary": "etcd cluster members are down."
               },
-              "expr": "max by (job) (\n  sum by (job) (up{job=~\".*etcd.*\"} == bool 0)\nor\n  count by (job,endpoint) (\n    sum by (job,endpoint,To) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[3m])) > 0.01\n  )\n)\n> 0\n",
+              "expr": "max without (endpoint) (\n  sum without (instance) (up{job=~\".*etcd.*\"} == bool 0)\nor\n  count without (To) (\n    sum without (instance) (rate(etcd_network_peer_sent_failures_total{job=~\".*etcd.*\"}[120s])) > 0.01\n  )\n)\n> 0\n",
-              "for": "3m",
+              "for": "10m",
               "labels": {
                 "severity": "critical"
               }
@@ -20,9 +21,10 @@ data:
             {
               "alert": "etcdInsufficientMembers",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": insufficient members ({{ $value }})."
+                "description": "etcd cluster \"{{ $labels.job }}\": insufficient members ({{ $value }}).",
+                "summary": "etcd cluster has insufficient number of members."
               },
-              "expr": "sum(up{job=~\".*etcd.*\"} == bool 1) by (job) < ((count(up{job=~\".*etcd.*\"}) by (job) + 1) / 2)\n",
+              "expr": "sum(up{job=~\".*etcd.*\"} == bool 1) without (instance) < ((count(up{job=~\".*etcd.*\"}) without (instance) + 1) / 2)\n",
               "for": "3m",
               "labels": {
                 "severity": "critical"
@@ -31,7 +33,8 @@ data:
             {
               "alert": "etcdNoLeader",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": member {{ $labels.instance }} has no leader."
+                "description": "etcd cluster \"{{ $labels.job }}\": member {{ $labels.instance }} has no leader.",
+                "summary": "etcd cluster has no leader."
               },
               "expr": "etcd_server_has_leader{job=~\".*etcd.*\"} == 0\n",
               "for": "1m",
@@ -42,10 +45,11 @@ data:
             {
               "alert": "etcdHighNumberOfLeaderChanges",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last 30 minutes."
+                "description": "etcd cluster \"{{ $labels.job }}\": {{ $value }} leader changes within the last 15 minutes. Frequent elections may be a sign of insufficient resources, high network latency, or disruptions by other components and should be investigated.",
+                "summary": "etcd cluster has high number of leader changes."
               },
-              "expr": "rate(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}[15m]) > 3\n",
+              "expr": "increase((max without (instance) (etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}) or 0*absent(etcd_server_leader_changes_seen_total{job=~\".*etcd.*\"}))[15m:1m]) >= 4\n",
-              "for": "15m",
+              "for": "5m",
               "labels": {
                 "severity": "warning"
               }
@@ -53,9 +57,10 @@ data:
             {
               "alert": "etcdGRPCRequestsSlow",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}."
+                "description": "etcd cluster \"{{ $labels.job }}\": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.",
+                "summary": "etcd grpc requests are slow"
               },
-              "expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_type=\"unary\"}[5m])) by (job, instance, grpc_service, grpc_method, le))\n> 0.15\n",
+              "expr": "histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{job=~\".*etcd.*\", grpc_type=\"unary\"}[5m])) without(grpc_type))\n> 0.15\n",
               "for": "10m",
               "labels": {
                 "severity": "critical"
@@ -64,7 +69,8 @@ data:
             {
               "alert": "etcdMemberCommunicationSlow",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}."
+                "description": "etcd cluster \"{{ $labels.job }}\": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.",
+                "summary": "etcd cluster member communication is slow."
               },
               "expr": "histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.15\n",
               "for": "10m",
@@ -75,7 +81,8 @@ data:
             {
               "alert": "etcdHighNumberOfFailedProposals",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}."
+                "description": "etcd cluster \"{{ $labels.job }}\": {{ $value }} proposal failures within the last 30 minutes on etcd instance {{ $labels.instance }}.",
+                "summary": "etcd cluster has high number of proposal failures."
               },
               "expr": "rate(etcd_server_proposals_failed_total{job=~\".*etcd.*\"}[15m]) > 5\n",
               "for": "15m",
@@ -86,7 +93,8 @@ data:
             {
               "alert": "etcdHighFsyncDurations",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": 99th percentile fync durations are {{ $value }}s on etcd instance {{ $labels.instance }}."
+                "description": "etcd cluster \"{{ $labels.job }}\": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.",
+                "summary": "etcd cluster 99th percentile fsync durations are too high."
               },
               "expr": "histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.5\n",
               "for": "10m",
@@ -94,10 +102,22 @@ data:
                 "severity": "warning"
               }
             },
+            {
+              "alert": "etcdHighFsyncDurations",
+              "annotations": {
+                "message": "etcd cluster \"{{ $labels.job }}\": 99th percentile fsync durations are {{ $value }}s on etcd instance {{ $labels.instance }}."
+              },
+              "expr": "histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 1\n",
+              "for": "10m",
+              "labels": {
+                "severity": "critical"
+              }
+            },
             {
               "alert": "etcdHighCommitDurations",
               "annotations": {
-                "message": "etcd cluster \"{{ $labels.job }}\": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}."
+                "description": "etcd cluster \"{{ $labels.job }}\": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.",
+                "summary": "etcd cluster 99th percentile commit durations are too high."
               },
               "expr": "histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{job=~\".*etcd.*\"}[5m]))\n> 0.25\n",
               "for": "10m",
@@ -108,9 +128,10 @@ data:
             {
               "alert": "etcdHighNumberOfFailedHTTPRequests",
               "annotations": {
-                "message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}"
+                "description": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}",
+                "summary": "etcd has high number of failed HTTP requests."
               },
-              "expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.01\n",
+              "expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nwithout (code) > 0.01\n",
               "for": "10m",
               "labels": {
                 "severity": "warning"
@@ -119,9 +140,10 @@ data:
             {
               "alert": "etcdHighNumberOfFailedHTTPRequests",
               "annotations": {
-                "message": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}."
+                "description": "{{ $value }}% of requests for {{ $labels.method }} failed on etcd instance {{ $labels.instance }}.",
+                "summary": "etcd has high number of failed HTTP requests."
               },
-              "expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) BY (method) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nBY (method) > 0.05\n",
+              "expr": "sum(rate(etcd_http_failed_total{job=~\".*etcd.*\", code!=\"404\"}[5m])) without (code) / sum(rate(etcd_http_received_total{job=~\".*etcd.*\"}[5m]))\nwithout (code) > 0.05\n",
               "for": "10m",
               "labels": {
                 "severity": "critical"
@@ -130,13 +152,36 @@ data:
             {
               "alert": "etcdHTTPRequestsSlow",
               "annotations": {
-                "message": "etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow."
+                "description": "etcd instance {{ $labels.instance }} HTTP requests to {{ $labels.method }} are slow.",
+                "summary": "etcd instance HTTP requests are slow."
               },
               "expr": "histogram_quantile(0.99, rate(etcd_http_successful_duration_seconds_bucket[5m]))\n> 0.15\n",
               "for": "10m",
               "labels": {
                 "severity": "warning"
               }
+            },
+            {
+              "alert": "etcdBackendQuotaLowSpace",
+              "annotations": {
+                "message": "etcd cluster \"{{ $labels.job }}\": database size exceeds the defined quota on etcd instance {{ $labels.instance }}, please defrag or increase the quota as the writes to etcd will be disabled when it is full."
+              },
+              "expr": "(etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100 > 95\n",
+              "for": "10m",
+              "labels": {
+                "severity": "critical"
+              }
+            },
+            {
+              "alert": "etcdExcessiveDatabaseGrowth",
+              "annotations": {
+                "message": "etcd cluster \"{{ $labels.job }}\": Observed surge in etcd writes leading to 50% increase in database size over the past four hours on etcd instance {{ $labels.instance }}, please check as it might be disruptive."
+              },
+              "expr": "increase(((etcd_mvcc_db_total_size_in_bytes/etcd_server_quota_backend_bytes)*100)[240m:1m]) > 50\n",
+              "for": "10m",
+              "labels": {
+                "severity": "warning"
+              }
             }
           ]
         }
@@ -149,21 +194,149 @@ data:
           "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": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[1d]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[1d]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[1d]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate1d"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[1h]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[1h]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[1h]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[1h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate1h"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[2h]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[2h]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[2h]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[2h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate2h"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[30m]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[30m]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[30m]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[30m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate30m"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[3d]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[3d]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[3d]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[3d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate3d"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[5m]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[5m]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[5m]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[5m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate5m"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n    -\n    (\n      (\n        sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[6h]))\n        or\n        vector(0)\n      )\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[6h]))\n      +\n      sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[6h]))\n    )\n  )\n  +\n  # errors\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"5..\"}[6h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:burnrate6h"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[1d]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate1d"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[1h]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate1h"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[2h]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate2h"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[30m]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate30m"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[3d]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate3d"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[5m]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate5m"
+            },
+            {
+              "expr": "(\n  (\n    # too slow\n    sum(rate(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n    -\n    sum(rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[6h]))\n  )\n  +\n  sum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum(rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:burnrate6h"
+            },
+            {
+              "expr": "sum by (code,resource) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "code_resource:apiserver_request_total:rate5m"
+            },
+            {
+              "expr": "sum by (code,resource) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "code_resource:apiserver_request_total:rate5m"
+            },
+            {
+              "expr": "histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))) > 0\n",
+              "labels": {
+                "quantile": "0.99",
+                "verb": "read"
+              },
+              "record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
+            },
+            {
+              "expr": "histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))) > 0\n",
+              "labels": {
+                "quantile": "0.99",
+                "verb": "write"
+              },
+              "record": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile"
+            },
+            {
+              "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"
               },
@@ -171,65 +344,194 @@ data:
             }
           ]
         },
+        {
+          "interval": "3m",
+          "name": "kube-apiserver-availability.rules",
+          "rules": [
+            {
+              "expr": "1 - (\n  (\n    # write too slow\n    sum(increase(apiserver_request_duration_seconds_count{verb=~\"POST|PUT|PATCH|DELETE\"}[30d]))\n    -\n    sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[30d]))\n  ) +\n  (\n    # read too slow\n    sum(increase(apiserver_request_duration_seconds_count{verb=~\"LIST|GET\"}[30d]))\n    -\n    (\n      (\n        sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[30d]))\n        or\n        vector(0)\n      )\n      +\n      sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[30d]))\n      +\n      sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[30d]))\n    )\n  ) +\n  # errors\n  sum(code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum(code:apiserver_request_total:increase30d)\n",
+              "labels": {
+                "verb": "all"
+              },
+              "record": "apiserver_request:availability30d"
+            },
+            {
+              "expr": "1 - (\n  sum(increase(apiserver_request_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\"}[30d]))\n  -\n  (\n    # too slow\n    (\n      sum(increase(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=~\"resource|\",le=\"0.1\"}[30d]))\n      or\n      vector(0)\n    )\n    +\n    sum(increase(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"namespace\",le=\"0.5\"}[30d]))\n    +\n    sum(increase(apiserver_request_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",scope=\"cluster\",le=\"5\"}[30d]))\n  )\n  +\n  # errors\n  sum(code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum(code:apiserver_request_total:increase30d{verb=\"read\"})\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "apiserver_request:availability30d"
+            },
+            {
+              "expr": "1 - (\n  (\n    # too slow\n    sum(increase(apiserver_request_duration_seconds_count{verb=~\"POST|PUT|PATCH|DELETE\"}[30d]))\n    -\n    sum(increase(apiserver_request_duration_seconds_bucket{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"}[30d]))\n  )\n  +\n  # errors\n  sum(code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum(code:apiserver_request_total:increase30d{verb=\"write\"})\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "apiserver_request:availability30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"2..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"2..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"2..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"2..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"2..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"2..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"3..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"3..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"3..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"3..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"3..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"3..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"4..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"4..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"4..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"4..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"4..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"4..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"LIST\",code=~\"5..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"GET\",code=~\"5..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"POST\",code=~\"5..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PUT\",code=~\"5..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"PATCH\",code=~\"5..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code, verb) (increase(apiserver_request_total{job=\"apiserver\",verb=\"DELETE\",code=~\"5..\"}[30d]))\n",
+              "record": "code_verb:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~\"LIST|GET\"})\n",
+              "labels": {
+                "verb": "read"
+              },
+              "record": "code:apiserver_request_total:increase30d"
+            },
+            {
+              "expr": "sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n",
+              "labels": {
+                "verb": "write"
+              },
+              "record": "code:apiserver_request_total:increase30d"
+            }
+          ]
+        },
         {
           "name": "k8s.rules",
           "rules": [
             {
-              "expr": "sum(rate(container_cpu_usage_seconds_total{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}[5m])) by (namespace)\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{node!=\"\"})\n)\n",
-              "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",
               "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{node!=\"\"})\n)\n",
               "record": "node_namespace_pod_container:container_memory_working_set_bytes"
             },
             {
-              "expr": "container_memory_rss{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) 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{node!=\"\"})\n)\n",
               "record": "node_namespace_pod_container:container_memory_rss"
             },
             {
-              "expr": "container_memory_cache{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) 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{node!=\"\"})\n)\n",
               "record": "node_namespace_pod_container:container_memory_cache"
             },
             {
-              "expr": "container_memory_swap{job=\"kubernetes-cadvisor\", image!=\"\"}\n* on (namespace, pod) group_left(node) 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{node!=\"\"})\n)\n",
               "record": "node_namespace_pod_container:container_memory_swap"
             },
             {
-              "expr": "sum(container_memory_usage_bytes{job=\"kubernetes-cadvisor\", image!=\"\", container!=\"POD\"}) by (namespace)\n",
+              "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: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",
               "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"
+              "record": "namespace_workload_pod:kube_pod_owner:relabel"
             },
             {
-              "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"
+              "record": "namespace_workload_pod:kube_pod_owner:relabel"
             },
             {
-              "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"
               },
-              "record": "mixin_pod_workload"
+              "record": "namespace_workload_pod:kube_pod_owner:relabel"
             }
           ]
         },
@@ -305,127 +607,158 @@ data:
           "name": "node.rules",
           "rules": [
             {
-              "expr": "sum(min(kube_pod_info) by (node))",
+              "expr": "topk by(namespace, pod) (1,\n  max by (node, namespace, pod) (\n    label_replace(kube_pod_info{job=\"kube-state-metrics\",node!=\"\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n",
-              "record": ":kube_pod_info_node_count:"
-            },
-            {
-              "expr": "max(label_replace(kube_pod_info{job=\"kube-state-metrics\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")) by (node, namespace, pod)\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": [
             {
               "alert": "KubePodCrashLooping",
               "annotations": {
-                "message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf \"%.2f\" $value }} times / 5 minutes.",
+                "description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} ({{ $labels.container }}) is restarting {{ printf \"%.2f\" $value }} times / 5 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping",
+                "summary": "Pod is crash looping."
               },
-              "expr": "rate(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\"}[15m]) * 60 * 5 > 0\n",
+              "expr": "rate(kube_pod_container_status_restarts_total{job=\"kube-state-metrics\"}[5m]) * 60 * 5 > 0\n",
               "for": "15m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubePodNotReady",
               "annotations": {
-                "message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
+                "description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-ready state for longer than 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready",
+                "summary": "Pod has been in a non-ready state for more than 15 minutes."
               },
-              "expr": "sum by (namespace, pod) (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) (\n  max by(namespace, pod) (\n    kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown\"}\n  ) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) (\n    1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!=\"Job\"})\n  )\n) > 0\n",
               "for": "15m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeDeploymentGenerationMismatch",
               "annotations": {
-                "message": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
+                "description": "Deployment generation for {{ $labels.namespace }}/{{ $labels.deployment }} does not match, this indicates that the Deployment has failed but has not been rolled back.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch",
+                "summary": "Deployment generation mismatch due to possible roll-back"
               },
               "expr": "kube_deployment_status_observed_generation{job=\"kube-state-metrics\"}\n  !=\nkube_deployment_metadata_generation{job=\"kube-state-metrics\"}\n",
               "for": "15m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeDeploymentReplicasMismatch",
               "annotations": {
-                "message": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
+                "description": "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has not matched the expected number of replicas for longer than 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch",
+                "summary": "Deployment has not matched the expected number of replicas."
               },
-              "expr": "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"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeStatefulSetReplicasMismatch",
               "annotations": {
-                "message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
+                "description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has not matched the expected number of replicas for longer than 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch",
+                "summary": "Deployment has not matched the expected number of replicas."
               },
-              "expr": "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"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeStatefulSetGenerationMismatch",
               "annotations": {
-                "message": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
+                "description": "StatefulSet generation for {{ $labels.namespace }}/{{ $labels.statefulset }} does not match, this indicates that the StatefulSet has failed but has not been rolled back.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch",
+                "summary": "StatefulSet generation mismatch due to possible roll-back"
               },
               "expr": "kube_statefulset_status_observed_generation{job=\"kube-state-metrics\"}\n  !=\nkube_statefulset_metadata_generation{job=\"kube-state-metrics\"}\n",
               "for": "15m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeStatefulSetUpdateNotRolledOut",
               "annotations": {
-                "message": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.",
+                "description": "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout",
+                "summary": "StatefulSet update has not been rolled out."
               },
-              "expr": "max without (revision) (\n  kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n    unless\n  kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n)\n  *\n(\n  kube_statefulset_replicas{job=\"kube-state-metrics\"}\n    !=\n  kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n)\n",
+              "expr": "(\n  max without (revision) (\n    kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n      unless\n    kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n  )\n    *\n  (\n    kube_statefulset_replicas{job=\"kube-state-metrics\"}\n      !=\n    kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n  )\n)  and (\n  changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n    ==\n  0\n)\n",
               "for": "15m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeDaemonSetRolloutStuck",
               "annotations": {
-                "message": "Only {{ $value | humanizePercentage }} of the desired Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are scheduled and ready.",
+                "description": "DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} has not finished or progressed for at least 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck",
+                "summary": "DaemonSet rollout is stuck."
               },
-              "expr": "kube_daemonset_status_number_ready{job=\"kube-state-metrics\"}\n  /\nkube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"} < 1.00\n",
+              "expr": "(\n  (\n    kube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"}\n     !=\n    kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n  ) or (\n    kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"}\n     !=\n    0\n  ) or (\n    kube_daemonset_updated_number_scheduled{job=\"kube-state-metrics\"}\n     !=\n    kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n  ) or (\n    kube_daemonset_status_number_available{job=\"kube-state-metrics\"}\n     !=\n    kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n  )\n) and (\n  changes(kube_daemonset_updated_number_scheduled{job=\"kube-state-metrics\"}[5m])\n    ==\n  0\n)\n",
               "for": "15m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeContainerWaiting",
               "annotations": {
-                "message": "Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
+                "description": "Pod {{ $labels.namespace }}/{{ $labels.pod }} container {{ $labels.container}} has been in waiting state for longer than 1 hour.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting",
+                "summary": "Pod container waiting longer than 1 hour"
               },
               "expr": "sum by (namespace, pod, container) (kube_pod_container_status_waiting_reason{job=\"kube-state-metrics\"}) > 0\n",
               "for": "1h",
@@ -436,8 +769,9 @@ data:
             {
               "alert": "KubeDaemonSetNotScheduled",
               "annotations": {
-                "message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
+                "description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled",
+                "summary": "DaemonSet pods are not scheduled."
               },
               "expr": "kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n  -\nkube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"} > 0\n",
               "for": "10m",
@@ -448,23 +782,12 @@ data:
             {
               "alert": "KubeDaemonSetMisScheduled",
               "annotations": {
-                "message": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
+                "description": "{{ $value }} Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled",
+                "summary": "DaemonSet pods are misscheduled."
               },
               "expr": "kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"} > 0\n",
-              "for": "10m",
+              "for": "15m",
-              "labels": {
-                "severity": "warning"
-              }
-            },
-            {
-              "alert": "KubeCronJobRunning",
-              "annotations": {
-                "message": "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning"
-              },
-              "expr": "time() - kube_cronjob_next_schedule_time{job=\"kube-state-metrics\"} > 3600\n",
-              "for": "1h",
               "labels": {
                 "severity": "warning"
               }
@@ -472,11 +795,12 @@ data:
             {
               "alert": "KubeJobCompletion",
               "annotations": {
-                "message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than one hour to complete.",
+                "description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} is taking more than 12 hours to complete.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion",
+                "summary": "Job did not complete in time"
               },
               "expr": "kube_job_spec_completions{job=\"kube-state-metrics\"} - kube_job_status_succeeded{job=\"kube-state-metrics\"}  > 0\n",
-              "for": "1h",
+              "for": "12h",
               "labels": {
                 "severity": "warning"
               }
@@ -484,8 +808,9 @@ data:
             {
               "alert": "KubeJobFailed",
               "annotations": {
-                "message": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete.",
+                "description": "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete. Removing failed job after investigation should clear this alert.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed",
+                "summary": "Job failed to complete."
               },
               "expr": "kube_job_failed{job=\"kube-state-metrics\"}  > 0\n",
               "for": "15m",
@@ -496,10 +821,11 @@ data:
             {
               "alert": "KubeHpaReplicasMismatch",
               "annotations": {
-                "message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.",
+                "description": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has not matched the desired number of replicas for longer than 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch",
+                "summary": "HPA has not matched descired number of replicas."
               },
-              "expr": "(kube_hpa_status_desired_replicas{job=\"kube-state-metrics\"}\n  !=\nkube_hpa_status_current_replicas{job=\"kube-state-metrics\"})\n  and\nchanges(kube_hpa_status_current_replicas[15m]) == 0\n",
+              "expr": "(kube_hpa_status_desired_replicas{job=\"kube-state-metrics\"}\n  !=\nkube_hpa_status_current_replicas{job=\"kube-state-metrics\"})\n  and\n(kube_hpa_status_current_replicas{job=\"kube-state-metrics\"}\n  >\nkube_hpa_spec_min_replicas{job=\"kube-state-metrics\"})\n  and\n(kube_hpa_status_current_replicas{job=\"kube-state-metrics\"}\n  <\nkube_hpa_spec_max_replicas{job=\"kube-state-metrics\"})\n  and\nchanges(kube_hpa_status_current_replicas[15m]) == 0\n",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -508,8 +834,9 @@ data:
             {
               "alert": "KubeHpaMaxedOut",
               "annotations": {
-                "message": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.",
+                "description": "HPA {{ $labels.namespace }}/{{ $labels.hpa }} has been running at max replicas for longer than 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout",
+                "summary": "HPA is running at max replicas"
               },
               "expr": "kube_hpa_status_current_replicas{job=\"kube-state-metrics\"}\n  ==\nkube_hpa_spec_max_replicas{job=\"kube-state-metrics\"}\n",
               "for": "15m",
@@ -525,32 +852,35 @@ data:
             {
               "alert": "KubeCPUOvercommit",
               "annotations": {
-                "message": "Cluster has overcommitted CPU resource requests for Pods and cannot tolerate node failure.",
+                "description": "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"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit",
+                "summary": "Cluster has overcommitted CPU resource requests."
               },
-              "expr": "sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum)\n  /\nsum(kube_node_status_allocatable_cpu_cores)\n  >\n(count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)\n",
+              "expr": "sum(namespace: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"
               }
             },
             {
-              "alert": "KubeMemOvercommit",
+              "alert": "KubeMemoryOvercommit",
               "annotations": {
-                "message": "Cluster has overcommitted memory resource requests for Pods and cannot tolerate node failure.",
+                "description": "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"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit",
+                "summary": "Cluster has overcommitted memory resource requests."
               },
-              "expr": "sum(namespace: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"
               }
             },
             {
-              "alert": "KubeCPUOvercommit",
+              "alert": "KubeCPUQuotaOvercommit",
               "annotations": {
-                "message": "Cluster has overcommitted CPU resource requests for Namespaces.",
+                "description": "Cluster has overcommitted CPU resource requests for Namespaces.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit",
+                "summary": "Cluster has overcommitted CPU resource requests."
               },
               "expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"cpu\"})\n  /\nsum(kube_node_status_allocatable_cpu_cores)\n  > 1.5\n",
               "for": "5m",
@@ -559,24 +889,52 @@ data:
               }
             },
             {
-              "alert": "KubeMemOvercommit",
+              "alert": "KubeMemoryQuotaOvercommit",
               "annotations": {
-                "message": "Cluster has overcommitted memory resource requests for Namespaces.",
+                "description": "Cluster has overcommitted memory resource requests for Namespaces.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememovercommit"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit",
+                "summary": "Cluster has overcommitted memory resource requests."
               },
-              "expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n  /\nsum(kube_node_status_allocatable_memory_bytes{job=\"node-exporter\"})\n  > 1.5\n",
+              "expr": "sum(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=\"memory\"})\n  /\nsum(kube_node_status_allocatable_memory_bytes{job=\"kube-state-metrics\"})\n  > 1.5\n",
               "for": "5m",
               "labels": {
                 "severity": "warning"
               }
             },
+            {
+              "alert": "KubeQuotaAlmostFull",
+              "annotations": {
+                "description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaalmostfull",
+                "summary": "Namespace quota is going to be full."
+              },
+              "expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n  / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n  > 0.9 < 1\n",
+              "for": "15m",
+              "labels": {
+                "severity": "info"
+              }
+            },
+            {
+              "alert": "KubeQuotaFullyUsed",
+              "annotations": {
+                "description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotafullyused",
+                "summary": "Namespace quota is fully used."
+              },
+              "expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n  / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n  == 1\n",
+              "for": "15m",
+              "labels": {
+                "severity": "info"
+              }
+            },
             {
               "alert": "KubeQuotaExceeded",
               "annotations": {
-                "message": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
+                "description": "Namespace {{ $labels.namespace }} is using {{ $value | humanizePercentage }} of its {{ $labels.resource }} quota.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded",
+                "summary": "Namespace quota has exceeded the limits."
               },
-              "expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n  / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n  > 0.90\n",
+              "expr": "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n  / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n  > 1\n",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -585,13 +943,14 @@ data:
             {
               "alert": "CPUThrottlingHigh",
               "annotations": {
-                "message": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.",
+                "description": "{{ $value | humanizePercentage }} throttling of CPU in namespace {{ $labels.namespace }} for container {{ $labels.container }} in pod {{ $labels.pod }}.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh",
+                "summary": "Processes experience elevated CPU throttling."
               },
-              "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n  /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n  > ( 100 / 100 )\n",
+              "expr": "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", }[5m])) by (container, pod, namespace)\n  /\nsum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)\n  > ( 80 / 100 )\n",
               "for": "15m",
               "labels": {
-                "severity": "warning"
+                "severity": "info"
               }
             }
           ]
@@ -600,10 +959,11 @@ data:
           "name": "kubernetes-storage",
           "rules": [
             {
-              "alert": "KubePersistentVolumeUsageCritical",
+              "alert": "KubePersistentVolumeFillingUp",
               "annotations": {
-                "message": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.",
+                "description": "The PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is only {{ $value | humanizePercentage }} free.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeusagecritical"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup",
+                "summary": "PersistentVolume is filling up."
               },
               "expr": "kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n  /\nkubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n  < 0.03\n",
               "for": "1m",
@@ -612,22 +972,24 @@ data:
               }
             },
             {
-              "alert": "KubePersistentVolumeFullInFourDays",
+              "alert": "KubePersistentVolumeFillingUp",
               "annotations": {
-                "message": "Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available.",
+                "description": "Based on recent sampling, the PersistentVolume claimed by {{ $labels.persistentvolumeclaim }} in Namespace {{ $labels.namespace }} is expected to fill up within four days. Currently {{ $value | humanizePercentage }} is available.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefullinfourdays"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup",
+                "summary": "PersistentVolume is filling up."
               },
               "expr": "(\n  kubelet_volume_stats_available_bytes{job=\"kubelet\"}\n    /\n  kubelet_volume_stats_capacity_bytes{job=\"kubelet\"}\n) < 0.15\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\"}[6h], 4 * 24 * 3600) < 0\n",
-              "for": "5m",
+              "for": "1h",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubePersistentVolumeErrors",
               "annotations": {
-                "message": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.",
+                "description": "The persistent volume {{ $labels.persistentvolume }} has status {{ $labels.phase }}.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors",
+                "summary": "PersistentVolume is having issues with provisioning."
               },
               "expr": "kube_persistentvolume_status_phase{phase=~\"Failed|Pending\",job=\"kube-state-metrics\"} > 0\n",
               "for": "5m",
@@ -643,10 +1005,11 @@ data:
             {
               "alert": "KubeVersionMismatch",
               "annotations": {
-                "message": "There are {{ $value }} different semantic versions of Kubernetes components running.",
+                "description": "There are {{ $value }} different semantic versions of Kubernetes components running.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch",
+                "summary": "Different semantic versions of Kubernetes components running."
               },
-              "expr": "count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~\"kube-dns|coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*.[0-9]*).*\"))) > 1\n",
+              "expr": "count(count by (gitVersion) (label_replace(kubernetes_build_info{job!~\"kube-dns|coredns\"},\"gitVersion\",\"$1\",\"gitVersion\",\"(v[0-9]*.[0-9]*).*\"))) > 1\n",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -655,8 +1018,9 @@ data:
             {
               "alert": "KubeClientErrors",
               "annotations": {
-                "message": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
+                "description": "Kubernetes API server client '{{ $labels.job }}/{{ $labels.instance }}' is experiencing {{ $value | humanizePercentage }} errors.'",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors",
+                "summary": "Kubernetes API server client is experiencing errors."
               },
               "expr": "(sum(rate(rest_client_requests_total{code=~\"5..\"}[5m])) by (instance, job)\n  /\nsum(rate(rest_client_requests_total[5m])) by (instance, job))\n> 0.01\n",
               "for": "15m",
@@ -666,77 +1030,82 @@ data:
             }
           ]
         },
+        {
+          "name": "kube-apiserver-slos",
+          "rules": [
+            {
+              "alert": "KubeAPIErrorBudgetBurn",
+              "annotations": {
+                "description": "The API server is burning too much error budget.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
+                "summary": "The API server is burning too much error budget."
+              },
+              "expr": "sum(apiserver_request:burnrate1h) > (14.40 * 0.01000)\nand\nsum(apiserver_request:burnrate5m) > (14.40 * 0.01000)\n",
+              "for": "2m",
+              "labels": {
+                "long": "1h",
+                "severity": "critical",
+                "short": "5m"
+              }
+            },
+            {
+              "alert": "KubeAPIErrorBudgetBurn",
+              "annotations": {
+                "description": "The API server is burning too much error budget.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
+                "summary": "The API server is burning too much error budget."
+              },
+              "expr": "sum(apiserver_request:burnrate6h) > (6.00 * 0.01000)\nand\nsum(apiserver_request:burnrate30m) > (6.00 * 0.01000)\n",
+              "for": "15m",
+              "labels": {
+                "long": "6h",
+                "severity": "critical",
+                "short": "30m"
+              }
+            },
+            {
+              "alert": "KubeAPIErrorBudgetBurn",
+              "annotations": {
+                "description": "The API server is burning too much error budget.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
+                "summary": "The API server is burning too much error budget."
+              },
+              "expr": "sum(apiserver_request:burnrate1d) > (3.00 * 0.01000)\nand\nsum(apiserver_request:burnrate2h) > (3.00 * 0.01000)\n",
+              "for": "1h",
+              "labels": {
+                "long": "1d",
+                "severity": "warning",
+                "short": "2h"
+              }
+            },
+            {
+              "alert": "KubeAPIErrorBudgetBurn",
+              "annotations": {
+                "description": "The API server is burning too much error budget.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn",
+                "summary": "The API server is burning too much error budget."
+              },
+              "expr": "sum(apiserver_request:burnrate3d) > (1.00 * 0.01000)\nand\nsum(apiserver_request:burnrate6h) > (1.00 * 0.01000)\n",
+              "for": "3h",
+              "labels": {
+                "long": "3d",
+                "severity": "warning",
+                "short": "6h"
+              }
+            }
+          ]
+        },
         {
           "name": "kubernetes-system-apiserver",
           "rules": [
             {
-              "alert": "KubeAPILatencyHigh",
+              "alert": "KubeClientCertificateExpiration",
               "annotations": {
-                "message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
+                "description": "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-kubeapilatencyhigh"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration",
+                "summary": "Client certificate is about to expire."
               },
-              "expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 1\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",
-              "for": "10m",
-              "labels": {
-                "severity": "warning"
-              }
-            },
-            {
-              "alert": "KubeAPILatencyHigh",
-              "annotations": {
-                "message": "The API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapilatencyhigh"
-              },
-              "expr": "cluster_quantile:apiserver_request_duration_seconds:histogram_quantile{job=\"apiserver\",quantile=\"0.99\",subresource!=\"log\",verb!~\"LIST|WATCH|WATCHLIST|PROXY|CONNECT\"} > 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": {
-                "message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
-              },
-              "expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (resource,subresource,verb)\n  /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.10\n",
-              "for": "10m",
-              "labels": {
-                "severity": "critical"
-              }
-            },
-            {
-              "alert": "KubeAPIErrorsHigh",
-              "annotations": {
-                "message": "API server is returning errors for {{ $value | humanizePercentage }} of requests for {{ $labels.verb }} {{ $labels.resource }} {{ $labels.subresource }}.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorshigh"
-              },
-              "expr": "sum(rate(apiserver_request_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (resource,subresource,verb)\n  /\nsum(rate(apiserver_request_total{job=\"apiserver\"}[5m])) by (resource,subresource,verb) > 0.05\n",
-              "for": "10m",
               "labels": {
                 "severity": "warning"
               }
@@ -744,30 +1113,46 @@ data:
             {
               "alert": "KubeClientCertificateExpiration",
               "annotations": {
-                "message": "A client certificate used to authenticate to the apiserver is expiring in less than 7.0 days.",
+                "description": "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"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration",
+                "summary": "Client certificate is about to expire."
               },
-              "expr": "apiserver_client_certificate_expiration_seconds_count{job=\"apiserver\"} > 0 and 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]))) < 300\n",
+              "labels": {
+                "severity": "critical"
+              }
+            },
+            {
+              "alert": "AggregatedAPIErrors",
+              "annotations": {
+                "description": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported errors. It has appeared unavailable {{ $value | humanize }} times averaged over the past 10m.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors",
+                "summary": "An aggregated API has reported errors."
+              },
+              "expr": "sum by(name, namespace)(increase(aggregator_unavailable_apiservice_count[10m])) > 4\n",
               "labels": {
                 "severity": "warning"
               }
             },
             {
-              "alert": "KubeClientCertificateExpiration",
+              "alert": "AggregatedAPIDown",
               "annotations": {
-                "message": "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.",
+                "description": "An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has been only {{ $value | humanize }}% available over the last 10m.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown",
+                "summary": "An aggregated API is down."
               },
-              "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": "(1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85\n",
+              "for": "5m",
               "labels": {
-                "severity": "critical"
+                "severity": "warning"
               }
             },
             {
               "alert": "KubeAPIDown",
               "annotations": {
-                "message": "KubeAPI has disappeared from Prometheus target discovery.",
+                "description": "KubeAPI has disappeared from Prometheus target discovery.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown",
+                "summary": "Target disappeared from Prometheus target discovery."
               },
               "expr": "absent(up{job=\"apiserver\"} == 1)\n",
               "for": "15m",
@@ -783,8 +1168,9 @@ data:
             {
               "alert": "KubeNodeNotReady",
               "annotations": {
-                "message": "{{ $labels.node }} has been unready for more than 15 minutes.",
+                "description": "{{ $labels.node }} has been unready for more than 15 minutes.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready",
+                "summary": "Node is not ready."
               },
               "expr": "kube_node_status_condition{job=\"kube-state-metrics\",condition=\"Ready\",status=\"true\"} == 0\n",
               "for": "15m",
@@ -795,10 +1181,12 @@ data:
             {
               "alert": "KubeNodeUnreachable",
               "annotations": {
-                "message": "{{ $labels.node }} is unreachable and some workloads may be rescheduled.",
+                "description": "{{ $labels.node }} is unreachable and some workloads may be rescheduled.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable",
+                "summary": "Node is unreachable."
               },
-              "expr": "kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} == 1\n",
+              "expr": "(kube_node_spec_taint{job=\"kube-state-metrics\",key=\"node.kubernetes.io/unreachable\",effect=\"NoSchedule\"} unless ignoring(key,value) kube_node_spec_taint{job=\"kube-state-metrics\",key=~\"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn\"}) == 1\n",
+              "for": "15m",
               "labels": {
                 "severity": "warning"
               }
@@ -806,10 +1194,124 @@ data:
             {
               "alert": "KubeletTooManyPods",
               "annotations": {
-                "message": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
+                "description": "Kubelet '{{ $labels.node }}' is running at {{ $value | humanizePercentage }} of its Pod capacity.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods",
+                "summary": "Kubelet is running at capacity."
               },
-              "expr": "max(max(kubelet_running_pod_count{job=\"kubelet\"}) by(instance) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"}) by(node) / max(kube_node_status_capacity_pods{job=\"kube-state-metrics\"}) by(node) > 0.95\n",
+              "expr": "count by(node) (\n  (kube_pod_status_phase{job=\"kube-state-metrics\",phase=\"Running\"} == 1) * on(instance,pod,namespace,cluster) group_left(node) topk by(instance,pod,namespace,cluster) (1, kube_pod_info{job=\"kube-state-metrics\"})\n)\n/\nmax by(node) (\n  kube_node_status_capacity_pods{job=\"kube-state-metrics\"} != 1\n) > 0.95\n",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeNodeReadinessFlapping",
+              "annotations": {
+                "description": "The readiness status of node {{ $labels.node }} has changed {{ $value }} times in the last 15 minutes.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping",
+                "summary": "Node readiness status is flapping."
+              },
+              "expr": "sum(changes(kube_node_status_condition{status=\"true\",condition=\"Ready\"}[15m])) by (node) > 2\n",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeletPlegDurationHigh",
+              "annotations": {
+                "description": "The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{ $value }} seconds on node {{ $labels.node }}.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh",
+                "summary": "Kubelet Pod Lifecycle Event Generator is taking too long to relist."
+              },
+              "expr": "node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile{quantile=\"0.99\"} >= 10\n",
+              "for": "5m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeletPodStartUpLatencyHigh",
+              "annotations": {
+                "description": "Kubelet Pod startup 99th percentile latency is {{ $value }} seconds on node {{ $labels.node }}.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh",
+                "summary": "Kubelet Pod startup latency is too high."
+              },
+              "expr": "histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job=\"kubelet\"}[5m])) by (instance, le)) * on(instance) group_left(node) kubelet_node_name{job=\"kubelet\"} > 60\n",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeletClientCertificateExpiration",
+              "annotations": {
+                "description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration",
+                "summary": "Kubelet client certificate is about to expire."
+              },
+              "expr": "kubelet_certificate_manager_client_ttl_seconds < 3600\n",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeletClientCertificateExpiration",
+              "annotations": {
+                "description": "Client certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration",
+                "summary": "Kubelet client certificate is about to expire."
+              },
+              "expr": "kubelet_certificate_manager_client_ttl_seconds < 300\n",
+              "labels": {
+                "severity": "critical"
+              }
+            },
+            {
+              "alert": "KubeletServerCertificateExpiration",
+              "annotations": {
+                "description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration",
+                "summary": "Kubelet server certificate is about to expire."
+              },
+              "expr": "kubelet_certificate_manager_server_ttl_seconds < 3600\n",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeletServerCertificateExpiration",
+              "annotations": {
+                "description": "Server certificate for Kubelet on node {{ $labels.node }} expires in {{ $value | humanizeDuration }}.",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration",
+                "summary": "Kubelet server certificate is about to expire."
+              },
+              "expr": "kubelet_certificate_manager_server_ttl_seconds < 300\n",
+              "labels": {
+                "severity": "critical"
+              }
+            },
+            {
+              "alert": "KubeletClientCertificateRenewalErrors",
+              "annotations": {
+                "description": "Kubelet on node {{ $labels.node }} has failed to renew its client certificate ({{ $value | humanize }} errors in the last 5 minutes).",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificaterenewalerrors",
+                "summary": "Kubelet has failed to renew its client certificate."
+              },
+              "expr": "increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0\n",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "KubeletServerCertificateRenewalErrors",
+              "annotations": {
+                "description": "Kubelet on node {{ $labels.node }} has failed to renew its server certificate ({{ $value | humanize }} errors in the last 5 minutes).",
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificaterenewalerrors",
+                "summary": "Kubelet has failed to renew its server certificate."
+              },
+              "expr": "increase(kubelet_server_expiration_renew_errors[5m]) > 0\n",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -818,8 +1320,9 @@ data:
             {
               "alert": "KubeletDown",
               "annotations": {
-                "message": "Kubelet has disappeared from Prometheus target discovery.",
+                "description": "Kubelet has disappeared from Prometheus target discovery.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown",
+                "summary": "Target disappeared from Prometheus target discovery."
               },
               "expr": "absent(up{job=\"kubelet\"} == 1)\n",
               "for": "15m",
@@ -835,8 +1338,9 @@ data:
             {
               "alert": "KubeSchedulerDown",
               "annotations": {
-                "message": "KubeScheduler has disappeared from Prometheus target discovery.",
+                "description": "KubeScheduler has disappeared from Prometheus target discovery.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown",
+                "summary": "Target disappeared from Prometheus target discovery."
               },
               "expr": "absent(up{job=\"kube-scheduler\"} == 1)\n",
               "for": "15m",
@@ -852,8 +1356,9 @@ data:
             {
               "alert": "KubeControllerManagerDown",
               "annotations": {
-                "message": "KubeControllerManager has disappeared from Prometheus target discovery.",
+                "description": "KubeControllerManager has disappeared from Prometheus target discovery.",
-                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown"
+                "runbook_url": "https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown",
+                "summary": "Target disappeared from Prometheus target discovery."
               },
               "expr": "absent(up{job=\"kube-controller-manager\"} == 1)\n",
               "for": "15m",
@@ -868,6 +1373,55 @@ data:
   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": [
@@ -973,7 +1527,7 @@ data:
                 "description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} receive errors in the last two minutes.",
                 "summary": "Network interface is reporting many receive errors."
               },
-              "expr": "increase(node_network_receive_errs_total[2m]) > 10\n",
+              "expr": "rate(node_network_receive_errs_total[2m]) / rate(node_network_receive_packets_total[2m]) > 0.01\n",
               "for": "1h",
               "labels": {
                 "severity": "warning"
@@ -985,11 +1539,80 @@ data:
                 "description": "{{ $labels.instance }} interface {{ $labels.device }} has encountered {{ printf \"%.0f\" $value }} transmit errors in the last two minutes.",
                 "summary": "Network interface is reporting many transmit errors."
               },
-              "expr": "increase(node_network_transmit_errs_total[2m]) > 10\n",
+              "expr": "rate(node_network_transmit_errs_total[2m]) / rate(node_network_transmit_packets_total[2m]) > 0.01\n",
               "for": "1h",
               "labels": {
                 "severity": "warning"
               }
+            },
+            {
+              "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": "NodeTextFileCollectorScrapeError",
+              "annotations": {
+                "description": "Node Exporter text file collector failed to scrape.",
+                "summary": "Node Exporter text file collector failed to scrape."
+              },
+              "expr": "node_textfile_scrape_error{job=\"node-exporter\"} == 1\n",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "NodeClockSkewDetected",
+              "annotations": {
+                "message": "Clock on {{ $labels.instance }} is out of sync by more than 300s. Ensure NTP is configured correctly on this host.",
+                "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\nand\nnode_timex_maxerror_seconds >= 16\n",
+              "for": "10m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "NodeRAIDDegraded",
+              "annotations": {
+                "description": "RAID array '{{ $labels.device }}' on {{ $labels.instance }} is in degraded state due to one or more disks failures. Number of spare drives is insufficient to fix issue automatically.",
+                "summary": "RAID Array is degraded"
+              },
+              "expr": "node_md_disks_required - ignoring (state) (node_md_disks{state=\"active\"}) > 0\n",
+              "for": "15m",
+              "labels": {
+                "severity": "critical"
+              }
+            },
+            {
+              "alert": "NodeRAIDDiskFailure",
+              "annotations": {
+                "description": "At least one device in RAID array on {{ $labels.instance }} failed. Array '{{ $labels.device }}' needs attention and possibly a disk swap.",
+                "summary": "Failed device in RAID array"
+              },
+              "expr": "node_md_disks{state=\"fail\"} > 0\n",
+              "labels": {
+                "severity": "warning"
+              }
             }
           ]
         }
@@ -1037,18 +1660,6 @@ data:
                 "severity": "warning"
               }
             },
-            {
-              "alert": "PrometheusErrorSendingAlertsToAnyAlertmanager",
-              "annotations": {
-                "description": "{{ printf \"%.1f\" $value }}% minimum errors while sending alerts from Prometheus {{$labels.instance}} to any Alertmanager.",
-                "summary": "Prometheus encounters more than 3% errors sending alerts to any Alertmanager."
-              },
-              "expr": "min without(alertmanager) (\n  rate(prometheus_notifications_errors_total{job=\"prometheus\"}[5m])\n/\n  rate(prometheus_notifications_sent_total{job=\"prometheus\"}[5m])\n)\n* 100\n> 3\n",
-              "for": "15m",
-              "labels": {
-                "severity": "critical"
-              }
-            },
             {
               "alert": "PrometheusNotConnectedToAlertmanagers",
               "annotations": {
@@ -1091,7 +1702,7 @@ data:
                 "description": "Prometheus {{$labels.instance}} is not ingesting samples.",
                 "summary": "Prometheus is not ingesting samples."
               },
-              "expr": "rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus\"}[5m]) <= 0\n",
+              "expr": "(\n  rate(prometheus_tsdb_head_samples_appended_total{job=\"prometheus\"}[5m]) <= 0\nand\n  (\n    sum without(scrape_job) (prometheus_target_metadata_cache_entries{job=\"prometheus\"}) > 0\n  or\n    sum without(rule_group) (prometheus_rule_group_rules{job=\"prometheus\"}) > 0\n  )\n)\n",
               "for": "10m",
               "labels": {
                 "severity": "warning"
@@ -1124,7 +1735,7 @@ data:
             {
               "alert": "PrometheusRemoteStorageFailures",
               "annotations": {
-                "description": "Prometheus {{$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 {{ $labels.remote_name}}:{{ $labels.url }}",
                 "summary": "Prometheus fails to send samples to remote storage."
               },
               "expr": "(\n  rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n/\n  (\n    rate(prometheus_remote_storage_failed_samples_total{job=\"prometheus\"}[5m])\n  +\n    rate(prometheus_remote_storage_succeeded_samples_total{job=\"prometheus\"}[5m])\n  )\n)\n* 100\n> 1\n",
@@ -1136,10 +1747,10 @@ data:
             {
               "alert": "PrometheusRemoteWriteBehind",
               "annotations": {
-                "description": "Prometheus {{$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 {{ $labels.remote_name}}:{{ $labels.url }}.",
                 "summary": "Prometheus remote write is behind."
               },
-              "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- on(job, instance) group_right\n  max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
+              "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_highest_timestamp_in_seconds{job=\"prometheus\"}[5m])\n- ignoring(remote_name, url) group_right\n  max_over_time(prometheus_remote_storage_queue_highest_sent_timestamp_seconds{job=\"prometheus\"}[5m])\n)\n> 120\n",
               "for": "15m",
               "labels": {
                 "severity": "critical"
@@ -1148,10 +1759,10 @@ data:
             {
               "alert": "PrometheusRemoteWriteDesiredShards",
               "annotations": {
-                "description": "Prometheus {{$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 for queue {{ $labels.remote_name}}:{{ $labels.url }}, which is more than the max of {{ printf `prometheus_remote_storage_shards_max{instance=\"%s\",job=\"prometheus\"}` $labels.instance | query | first | value }}.",
                 "summary": "Prometheus remote write desired shards calculation wants to run more than configured max shards."
               },
-              "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n> on(job, instance) group_right\n  max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
+              "expr": "# Without max_over_time, failed scrapes could create false negatives, see\n# https://www.robustperception.io/alerting-on-gauges-in-prometheus-2-0 for details.\n(\n  max_over_time(prometheus_remote_storage_shards_desired{job=\"prometheus\"}[5m])\n>\n  max_over_time(prometheus_remote_storage_shards_max{job=\"prometheus\"}[5m])\n)\n",
               "for": "15m",
               "labels": {
                 "severity": "warning"
@@ -1180,6 +1791,30 @@ data:
               "labels": {
                 "severity": "warning"
               }
+            },
+            {
+              "alert": "PrometheusTargetLimitHit",
+              "annotations": {
+                "description": "Prometheus {{$labels.instance}} has dropped {{ printf \"%.0f\" $value }} targets because the number of targets exceeded the configured target_limit.",
+                "summary": "Prometheus has dropped targets because some scrape configs have exceeded the targets limit."
+              },
+              "expr": "increase(prometheus_target_scrape_pool_exceeded_target_limit_total{job=\"prometheus\"}[5m]) > 0\n",
+              "for": "15m",
+              "labels": {
+                "severity": "warning"
+              }
+            },
+            {
+              "alert": "PrometheusErrorSendingAlertsToAnyAlertmanager",
+              "annotations": {
+                "description": "{{ printf \"%.1f\" $value }}% minimum errors while sending alerts from Prometheus {{$labels.instance}} to any Alertmanager.",
+                "summary": "Prometheus encounters more than 3% errors sending alerts to any Alertmanager."
+              },
+              "expr": "min without (alertmanager) (\n  rate(prometheus_notifications_errors_total{job=\"prometheus\",alertmanager!~``}[5m])\n/\n  rate(prometheus_notifications_sent_total{job=\"prometheus\",alertmanager!~``}[5m])\n)\n* 100\n> 3\n",
+              "for": "15m",
+              "labels": {
+                "severity": "critical"
+              }
             }
           ]
         }
@@ -1201,6 +1836,17 @@ data:
               "labels": {
                 "severity": "warning"
               }
+            },
+            {
+              "alert": "BlackboxProbeFailure",
+              "annotations": {
+                "message": "Blackbox probe {{$labels.instance}} failed"
+              },
+              "expr": "probe_success == 0",
+              "for": "2m",
+              "labels": {
+                "severity": "critical"
+              }
             }
           ]
         },
@@ -1212,7 +1858,7 @@ 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/ami.tf

@@ -1,50 +0,0 @@
-locals {
-  # Pick a CoreOS Container Linux derivative
-  # coreos-stable -> Container Linux AMI
-  # flatcar-stable -> Flatcar Linux AMI
-  ami_id = local.flavor == "flatcar" ? data.aws_ami.flatcar.image_id : data.aws_ami.coreos.image_id
-
-  flavor  = split("-", var.os_image)[0]
-  channel = split("-", var.os_image)[1]
-}
-
-data "aws_ami" "coreos" {
-  most_recent = true
-  owners      = ["595879546273"]
-
-  filter {
-    name   = "architecture"
-    values = ["x86_64"]
-  }
-
-  filter {
-    name   = "virtualization-type"
-    values = ["hvm"]
-  }
-
-  filter {
-    name   = "name"
-    values = ["CoreOS-${local.flavor == "coreos" ? local.channel : "stable"}-*"]
-  }
-}
-
-data "aws_ami" "flatcar" {
-  most_recent = true
-  owners      = ["075585003325"]
-
-  filter {
-    name   = "architecture"
-    values = ["x86_64"]
-  }
-
-  filter {
-    name   = "virtualization-type"
-    values = ["hvm"]
-  }
-
-  filter {
-    name   = "name"
-    values = ["Flatcar-${local.flavor == "flatcar" ? local.channel : "stable"}-*"]
-  }
-}
-

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

@@ -1,198 +0,0 @@
----
-systemd:
-  units:
-    - name: etcd-member.service
-      enable: true
-      dropins:
-        - name: 40-etcd-cluster.conf
-          contents: |
-            [Service]
-            Environment="ETCD_IMAGE_TAG=v3.4.3"
-            Environment="ETCD_NAME=${etcd_name}"
-            Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379"
-            Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380"
-            Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
-            Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
-            Environment="ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381"
-            Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
-            Environment="ETCD_STRICT_RECONFIG_CHECK=true"
-            Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
-            Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
-            Environment="ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt"
-            Environment="ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key"
-            Environment="ETCD_CLIENT_CERT_AUTH=true"
-            Environment="ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt"
-            Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
-            Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
-            Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
-    - name: docker.service
-      enable: true
-    - name: locksmithd.service
-      mask: true
-    - name: wait-for-dns.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Wait for DNS entries
-        Wants=systemd-resolved.service
-        Before=kubelet.service
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
-        [Install]
-        RequiredBy=kubelet.service
-        RequiredBy=etcd-member.service
-    - name: kubelet.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Kubelet via Hyperkube
-        Wants=rpc-statd.service
-        [Service]
-        Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
-        ExecStartPre=/bin/mkdir -p /opt/cni/bin
-        ExecStartPre=/bin/mkdir -p /var/lib/calico
-        ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
-        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
-        ExecStart=/usr/bin/rkt run \
-          --uuid-file-save=/var/cache/kubelet-pod.uuid \
-          --stage1-from-dir=stage1-fly.aci \
-          --hosts-entry host \
-          --insecure-options=image \
-          --volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
-          --mount volume=etc-kubernetes,target=/etc/kubernetes \
-          --volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
-          --mount volume=etc-machine-id,target=/etc/machine-id \
-          --volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
-          --mount volume=etc-os-release,target=/etc/os-release \
-          --volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
-          --mount volume=etc-resolv,target=/etc/resolv.conf \
-          --volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
-          --mount volume=etc-ssl-certs,target=/etc/ssl/certs \
-          --volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
-          --mount volume=lib-modules,target=/lib/modules \
-          --volume run,kind=host,source=/run \
-          --mount volume=run,target=/run \
-          --volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
-          --mount volume=usr-share-certs,target=/usr/share/ca-certificates \
-          --volume var-lib-calico,kind=host,source=/var/lib/calico \
-          --mount volume=var-lib-calico,target=/var/lib/calico \
-          --volume var-lib-docker,kind=host,source=/var/lib/docker \
-          --mount volume=var-lib-docker,target=/var/lib/docker \
-          --volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
-          --mount volume=var-lib-kubelet,target=/var/lib/kubelet \
-          --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log \
-          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
-          --mount volume=opt-cni-bin,target=/opt/cni/bin \
-          docker://k8s.gcr.io/hyperkube:v1.17.1 \
-          --exec=/usr/local/bin/kubelet -- \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
-          --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 \
-          --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 \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
-        Restart=always
-        RestartSec=10
-        [Install]
-        WantedBy=multi-user.target
-    - name: bootstrap.service
-      contents: |
-        [Unit]
-        Description=Kubernetes control plane
-        ConditionPathExists=!/opt/bootstrap/bootstrap.done
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        WorkingDirectory=/opt/bootstrap
-        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 \
-            --mount volume=config,target=/etc/kubernetes/secrets \
-            --volume assets,kind=host,source=/opt/bootstrap/assets \
-            --mount volume=assets,target=/assets \
-            --volume script,kind=host,source=/opt/bootstrap/apply \
-            --mount volume=script,target=/apply \
-            --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.1 \
-            --net=host \
-            --dns=host \
-            --exec=/apply
-        ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
-        [Install]
-        WantedBy=multi-user.target
-storage:
-  files:
-    - path: /etc/kubernetes/kubeconfig
-      filesystem: root
-      mode: 0644
-      contents:
-        inline: |
-          ${kubeconfig}
-    - path: /opt/bootstrap/layout
-      filesystem: root
-      mode: 0544
-      contents:
-        inline: |
-          #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
-          awk '/#####/ {filename=$2; next} {print > filename}' assets
-          mkdir -p /etc/ssl/etcd/etcd
-          mkdir -p /etc/kubernetes/bootstrap-secrets
-          mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
-          mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
-          chown -R etcd:etcd /etc/ssl/etcd
-          chmod -R 500 /etc/ssl/etcd
-          mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
-          mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
-          sudo mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
-          rm -rf assets auth static-manifests tls
-    - path: /opt/bootstrap/apply
-      filesystem: root
-      mode: 0544
-      contents:
-        inline: |
-          #!/bin/bash -e
-          export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
-          until kubectl version; do
-            echo "Waiting for static pod control plane"
-            sleep 5
-          done
-          until kubectl apply -f /assets/manifests -R; do
-             echo "Retry applying manifests"
-             sleep 5
-          done
-    - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
-      contents:
-        inline: |
-          fs.inotify.max_user_watches=16184
-passwd:
-  users:
-    - name: core
-      ssh_authorized_keys:
-        - "${ssh_authorized_key}"

aws/container-linux/kubernetes/versions.tf

@@ -1,11 +0,0 @@
-# Terraform version and plugin versions
-
-terraform {
-  required_version = "~> 0.12.6"
-  required_providers {
-    aws      = "~> 2.23"
-    ct       = "~> 0.3"
-    template = "~> 2.1"
-    null     = "~> 2.1"
-  }
-}

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

@@ -1,50 +0,0 @@
-locals {
-  # Pick a CoreOS Container Linux derivative
-  # coreos-stable -> Container Linux AMI
-  # flatcar-stable -> Flatcar Linux AMI
-  ami_id = local.flavor == "flatcar" ? data.aws_ami.flatcar.image_id : data.aws_ami.coreos.image_id
-
-  flavor  = split("-", var.os_image)[0]
-  channel = split("-", var.os_image)[1]
-}
-
-data "aws_ami" "coreos" {
-  most_recent = true
-  owners      = ["595879546273"]
-
-  filter {
-    name   = "architecture"
-    values = ["x86_64"]
-  }
-
-  filter {
-    name   = "virtualization-type"
-    values = ["hvm"]
-  }
-
-  filter {
-    name   = "name"
-    values = ["CoreOS-${local.flavor == "coreos" ? local.channel : "stable"}-*"]
-  }
-}
-
-data "aws_ami" "flatcar" {
-  most_recent = true
-  owners      = ["075585003325"]
-
-  filter {
-    name   = "architecture"
-    values = ["x86_64"]
-  }
-
-  filter {
-    name   = "virtualization-type"
-    values = ["hvm"]
-  }
-
-  filter {
-    name   = "name"
-    values = ["Flatcar-${local.flavor == "flatcar" ? local.channel : "stable"}-*"]
-  }
-}
-

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

@@ -1,140 +0,0 @@
----
-systemd:
-  units:
-    - name: docker.service
-      enable: true
-    - name: locksmithd.service
-      mask: true
-    - name: wait-for-dns.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Wait for DNS entries
-        Wants=systemd-resolved.service
-        Before=kubelet.service
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
-        [Install]
-        RequiredBy=kubelet.service
-    - name: kubelet.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Kubelet via Hyperkube
-        Wants=rpc-statd.service
-        [Service]
-        Environment=KUBELET_CGROUP_DRIVER=${cgroup_driver}
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
-        ExecStartPre=/bin/mkdir -p /opt/cni/bin
-        ExecStartPre=/bin/mkdir -p /var/lib/calico
-        ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
-        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
-        ExecStart=/usr/bin/rkt run \
-          --uuid-file-save=/var/cache/kubelet-pod.uuid \
-          --stage1-from-dir=stage1-fly.aci \
-          --hosts-entry host \
-          --insecure-options=image \
-          --volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
-          --mount volume=etc-kubernetes,target=/etc/kubernetes \
-          --volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
-          --mount volume=etc-machine-id,target=/etc/machine-id \
-          --volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
-          --mount volume=etc-os-release,target=/etc/os-release \
-          --volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
-          --mount volume=etc-resolv,target=/etc/resolv.conf \
-          --volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
-          --mount volume=etc-ssl-certs,target=/etc/ssl/certs \
-          --volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
-          --mount volume=lib-modules,target=/lib/modules \
-          --volume run,kind=host,source=/run \
-          --mount volume=run,target=/run \
-          --volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
-          --mount volume=usr-share-certs,target=/usr/share/ca-certificates \
-          --volume var-lib-calico,kind=host,source=/var/lib/calico \
-          --mount volume=var-lib-calico,target=/var/lib/calico \
-          --volume var-lib-docker,kind=host,source=/var/lib/docker \
-          --mount volume=var-lib-docker,target=/var/lib/docker \
-          --volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
-          --mount volume=var-lib-kubelet,target=/var/lib/kubelet \
-          --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log \
-          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
-          --mount volume=opt-cni-bin,target=/opt/cni/bin \
-          docker://k8s.gcr.io/hyperkube:v1.17.1 \
-          --exec=/usr/local/bin/kubelet -- \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
-          --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 \
-          --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 \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
-        Restart=always
-        RestartSec=5
-        [Install]
-        WantedBy=multi-user.target
-    - name: delete-node.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Waiting to delete Kubernetes node on shutdown
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/true
-        ExecStop=/etc/kubernetes/delete-node
-        [Install]
-        WantedBy=multi-user.target
-storage:
-  files:
-    - path: /etc/kubernetes/kubeconfig
-      filesystem: root
-      mode: 0644
-      contents:
-        inline: |
-          ${kubeconfig}
-    - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
-      contents:
-        inline: |
-          fs.inotify.max_user_watches=16184
-    - path: /etc/kubernetes/delete-node
-      filesystem: root
-      mode: 0744
-      contents:
-        inline: |
-          #!/bin/bash
-          set -e
-          exec /usr/bin/rkt run \
-            --trust-keys-from-https \
-            --volume config,kind=host,source=/etc/kubernetes \
-            --mount volume=config,target=/etc/kubernetes \
-            --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.1 \
-            --net=host \
-            --dns=host \
-            -- \
-            kubectl --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname)
-passwd:
-  users:
-    - name: core
-      ssh_authorized_keys:
-        - "${ssh_authorized_key}"

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

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

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 v1.17.1 (upstream)
+* Kubernetes v1.21.1 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* 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/)
+* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
-* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/cl/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
+* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/fedora-coreos/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
-* Ready for Ingress, Prometheus, Grafana, 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 +14,33 @@ data "aws_ami" "fedora-coreos" {
   }
 
   filter {
-    name   = "name"
+    name   = "description"
-    values = ["fedora-coreos-31.*.*.*-hvm"]
+    values = ["Fedora CoreOS ${var.os_stream} *"]
+  }
+}
+
+# Experimental Fedora CoreOS arm64 / aarch64 AMIs from Poseidon
+# WARNING: These AMIs will be removed when Fedora CoreOS publishes arm64 AMIs
+# and may be removed for any reason before then as well. Do not use.
+data "aws_ami" "fedora-coreos-arm" {
+  count = var.arch == "arm64" ? 1 : 0
+
+  most_recent = true
+  owners      = ["099663496933"]
+
+  filter {
+    name   = "architecture"
+    values = ["arm64"]
   }
 
-  # try to filter out dev images (AWS filters can't)
+  filter {
-  name_regex = "^fedora-coreos-31.[0-9]*.[0-9]*.[0-9]*-hvm*"
+    name   = "virtualization-type"
+    values = ["hvm"]
+  }
+
+  filter {
+    name   = "name"
+    values = ["fedora-coreos-*"]
+  }
 }
+

aws/fedora-coreos/kubernetes/bootstrap.tf

@@ -1,11 +1,10 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=de85f1da7df0b13dfb7488350c20a510f3090cdf"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=ebe3d5526a59b34c8f119a206358b0c0a6f6f67d"
 
   cluster_name          = var.cluster_name
   api_servers           = [format("%s.%s", var.cluster_name, var.dns_zone)]
   etcd_servers          = aws_route53_record.etcds.*.fqdn
-  asset_dir             = var.asset_dir
   networking            = var.networking
   network_mtu           = var.network_mtu
   pod_cidr              = var.pod_cidr
@@ -13,6 +12,7 @@ module "bootstrap" {
   cluster_domain_suffix = var.cluster_domain_suffix
   enable_reporting      = var.enable_reporting
   enable_aggregation    = var.enable_aggregation
+  daemonset_tolerations = var.daemonset_tolerations
 
   trusted_certs_dir = "/etc/pki/tls/certs"
 }

aws/fedora-coreos/kubernetes/controllers.tf

@@ -22,9 +22,8 @@ resource "aws_instance" "controllers" {
   }
 
   instance_type = var.controller_type
-
+  ami           = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
-  ami       = data.aws_ami.fedora-coreos.image_id
+  user_data     = data.ct_config.controller-ignitions.*.rendered[count.index]
-  user_data = data.ct_config.controller-ignitions.*.rendered[count.index]
 
   # storage
   root_block_device {
@@ -36,7 +35,7 @@ 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 {
@@ -63,6 +62,7 @@ data "template_file" "controller-configs" {
 
   vars = {
     # Cannot use cyclic dependencies on controllers or their DNS records
+    etcd_arch   = var.arch == "arm64" ? "-arm64" : ""
     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,...

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

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.0.0
+version: 1.2.0
 systemd:
   units:
     - name: etcd-member.service
@@ -8,28 +8,25 @@ systemd:
       contents: |
         [Unit]
         Description=etcd (System Container)
-        Documentation=https://github.com/coreos/etcd
+        Documentation=https://github.com/etcd-io/etcd
         Wants=network-online.target network.target
         After=network-online.target
         [Service]
-        # https://github.com/opencontainers/runc/pull/1807
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.4.16${etcd_arch}
-        # 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 $${NOTIFY_SOCKET}:/run/systemd/notify \
         ExecStart=/usr/bin/podman run --name etcd \
           --env-file /etc/etcd/etcd.env \
           --network host \
           --volume /var/lib/etcd:/var/lib/etcd:rw,Z \
           --volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
-          quay.io/coreos/etcd:v3.4.3
+          $${ETCD_IMAGE}
         ExecStop=/usr/bin/podman stop etcd
+        Restart=on-failure
+        RestartSec=10s
+        TimeoutStartSec=0
+        LimitNOFILE=40000
         [Install]
         WantedBy=multi-user.target
     - name: docker.service
@@ -38,11 +35,12 @@ 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
@@ -51,10 +49,14 @@ systemd:
       enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube (System Container)
+        Description=Kubelet (System Container)
+        Requires=afterburn.service
+        After=afterburn.service
         Wants=rpc-statd.service
         [Service]
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        EnvironmentFile=/run/metadata/afterburn
+        ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /var/lib/calico
@@ -65,41 +67,38 @@ systemd:
           --privileged \
           --pid host \
           --network host \
+          --volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
           --volume /etc/kubernetes:/etc/kubernetes:ro,z \
           --volume /usr/lib/os-release:/etc/os-release:ro \
-          --volume /etc/ssl/certs:/etc/ssl/certs:ro \
           --volume /lib/modules:/lib/modules:ro \
           --volume /run:/run \
-          --volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
+          --volume /sys/fs/cgroup:/sys/fs/cgroup \
-          --volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
+          --volume /var/lib/calico:/var/lib/calico:ro \
-          --volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
-          --volume /var/lib/calico:/var/lib/calico \
           --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:v1.17.1 kubelet \
+          $${KUBELET_IMAGE} \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
           --cgroup-driver=systemd \
           --cgroups-per-qos=true \
           --enforce-node-allocatable=pods \
           --client-ca-file=/etc/kubernetes/ca.crt \
           --cluster_dns=${cluster_dns_service_ip} \
           --cluster_domain=${cluster_domain_suffix} \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
           --network-plugin=cni \
-          --node-labels=node.kubernetes.io/master \
           --node-labels=node.kubernetes.io/controller="true" \
           --pod-manifest-path=/etc/kubernetes/manifests \
+          --provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID} \
           --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 +115,20 @@ 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/pki:/etc/kubernetes/pki:ro,z \
             --volume /opt/bootstrap/assets:/assets:ro,Z \
             --volume /opt/bootstrap/apply:/apply:ro,Z \
             --entrypoint=/apply \
-            k8s.gcr.io/hyperkube:v1.17.1
+            quay.io/poseidon/kubelet:v1.21.1
         ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
         ExecStartPost=-/usr/bin/podman stop bootstrap
 storage:
   directories:
+    - path: /var/lib/etcd
+      mode: 0700
     - path: /etc/kubernetes
     - path: /opt/bootstrap
   files:
@@ -144,25 +145,26 @@ storage:
           mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
           awk '/#####/ {filename=$2; next} {print > filename}' assets
           mkdir -p /etc/ssl/etcd/etcd
-          mkdir -p /etc/kubernetes/bootstrap-secrets
+          mkdir -p /etc/kubernetes/pki
           mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
-          mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
+          mv tls/etcd/etcd-client* /etc/kubernetes/pki/
           chown -R etcd:etcd /etc/ssl/etcd
           chmod -R 500 /etc/ssl/etcd
-          mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
+          mv auth/* /etc/kubernetes/pki/
-          mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
+          mv tls/k8s/* /etc/kubernetes/pki/
-          sudo mkdir -p /etc/kubernetes/manifests
+          mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
+          mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
+          mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
+          mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
+          mv manifests-networking/* /opt/bootstrap/assets/manifests/
-          rm -rf assets auth static-manifests tls
+          rm -rf assets auth static-manifests tls manifests-networking
+          chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
     - path: /opt/bootstrap/apply
       mode: 0544
       contents:
         inline: |
           #!/bin/bash -e
-          export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
+          export KUBECONFIG=/etc/kubernetes/pki/admin.conf
           until kubectl version; do
             echo "Waiting for static pod control plane"
             sleep 5
@@ -171,14 +173,22 @@ storage:
              echo "Retry applying manifests"
              sleep 5
           done
-    - path: /etc/sysctl.d/reverse-path-filter.conf
-      contents:
-        inline: |
-          net.ipv4.conf.all.rp_filter=1
     - 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: |
@@ -190,8 +200,6 @@ storage:
       mode: 0644
       contents:
         inline: |
-          # TODO: Use a systemd dropin once podman v1.4.5 is avail.
-          NOTIFY_SOCKET=/run/systemd/notify
           ETCD_NAME=${etcd_name}
           ETCD_DATA_DIR=/var/lib/etcd
           ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379
@@ -209,6 +217,7 @@ storage:
           ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
           ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
           ETCD_PEER_CLIENT_CERT_AUTH=true
+          ETCD_UNSUPPORTED_ARCH=arm64
 passwd:
   users:
     - name: core

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/nlb.tf

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

aws/fedora-coreos/kubernetes/outputs.tf

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

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" "controller-cilium-health" {
-resource "aws_security_group_rule" "kube-proxy-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
   type                     = "ingress"
   protocol                 = "tcp"
-  from_port                = 10249
+  from_port                = 4240
-  to_port                  = 10249
+  to_port                  = 4240
   source_security_group_id = aws_security_group.worker.id
 }
 
-# Allow Prometheus to scrape kube-scheduler
+resource "aws_security_group_rule" "controller-cilium-health-self" {
-resource "aws_security_group_rule" "controller-scheduler-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
-  type                     = "ingress"
+  type      = "ingress"
-  protocol                 = "tcp"
+  protocol  = "tcp"
-  from_port                = 10251
+  from_port = 4240
-  to_port                  = 10251
+  to_port   = 4240
-  source_security_group_id = aws_security_group.worker.id
+  self      = true
-}
-
-# 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
 }
 
+# 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

@@ -41,16 +41,21 @@ variable "worker_type" {
   default     = "t3.small"
 }
 
-variable "os_image" {
+variable "os_stream" {
   type        = string
-  description = "AMI channel for Fedora CoreOS (not yet used)"
+  description = "Fedora CoreOS image stream for instances (e.g. stable, testing, next)"
-  default     = "coreos-stable"
+  default     = "stable"
+
+  validation {
+    condition     = contains(["stable", "testing", "next"], var.os_stream)
+    error_message = "The os_stream must be stable, testing, or next."
+  }
 }
 
 variable "disk_size" {
   type        = number
   description = "Size of the EBS volume in GB"
-  default     = 40
+  default     = 30
 }
 
 variable "disk_type" {
@@ -96,12 +101,6 @@ 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)"
@@ -161,3 +160,19 @@ variable "cluster_domain_suffix" {
   default     = "cluster.local"
 }
 
+variable "arch" {
+  type        = string
+  description = "Container architecture (amd64 or arm64)"
+  default     = "amd64"
+
+  validation {
+    condition     = var.arch == "amd64" || var.arch == "arm64"
+    error_message = "The arch must be amd64 or arm64."
+  }
+}
+
+variable "daemonset_tolerations" {
+  type        = list(string)
+  description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
+  default     = []
+}

aws/fedora-coreos/kubernetes/versions.tf

@@ -1,11 +1,15 @@
 # Terraform version and plugin versions
 
 terraform {
-  required_version = "~> 0.12.6"
+  required_version = ">= 0.13.0, < 0.16.0"
   required_providers {
-    aws      = "~> 2.23"
+    aws      = ">= 2.23, <= 4.0"
-    ct       = "~> 0.4"
     template = "~> 2.1"
     null     = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.8"
+    }
   }
 }

aws/fedora-coreos/kubernetes/workers.tf

@@ -8,7 +8,8 @@ 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
+  arch            = var.arch
   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 +14,33 @@ data "aws_ami" "fedora-coreos" {
   }
 
   filter {
-    name   = "name"
+    name   = "description"
-    values = ["fedora-coreos-31.*.*.*-hvm"]
+    values = ["Fedora CoreOS ${var.os_stream} *"]
+  }
+}
+
+# Experimental Fedora CoreOS arm64 / aarch64 AMIs from Poseidon
+# WARNING: These AMIs will be removed when Fedora CoreOS publishes arm64 AMIs
+# and may be removed for any reason before then as well. Do not use.
+data "aws_ami" "fedora-coreos-arm" {
+  count = var.arch == "arm64" ? 1 : 0
+
+  most_recent = true
+  owners      = ["099663496933"]
+
+  filter {
+    name   = "architecture"
+    values = ["arm64"]
   }
 
-  # try to filter out dev images (AWS filters can't)
+  filter {
-  name_regex = "^fedora-coreos-31.[0-9]*.[0-9]*.[0-9]*-hvm*"
+    name   = "virtualization-type"
+    values = ["hvm"]
+  }
+
+  filter {
+    name   = "name"
+    values = ["fedora-coreos-*"]
+  }
 }
+

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

@@ -1,6 +1,6 @@
 ---
 variant: fcos
-version: 1.0.0
+version: 1.2.0
 systemd:
   units:
     - name: docker.service
@@ -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
@@ -21,10 +22,14 @@ systemd:
       enabled: true
       contents: |
         [Unit]
-        Description=Kubelet via Hyperkube (System Container)
+        Description=Kubelet (System Container)
+        Requires=afterburn.service
+        After=afterburn.service
         Wants=rpc-statd.service
         [Service]
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        EnvironmentFile=/run/metadata/afterburn
+        ExecStartPre=/bin/mkdir -p /etc/cni/net.d
         ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
         ExecStartPre=/bin/mkdir -p /opt/cni/bin
         ExecStartPre=/bin/mkdir -p /var/lib/calico
@@ -35,42 +40,43 @@ systemd:
           --privileged \
           --pid host \
           --network host \
+          --volume /etc/cni/net.d:/etc/cni/net.d:ro,z \
           --volume /etc/kubernetes:/etc/kubernetes:ro,z \
           --volume /usr/lib/os-release:/etc/os-release:ro \
-          --volume /etc/ssl/certs:/etc/ssl/certs:ro \
           --volume /lib/modules:/lib/modules:ro \
           --volume /run:/run \
-          --volume /sys/fs/cgroup:/sys/fs/cgroup:ro \
+          --volume /sys/fs/cgroup:/sys/fs/cgroup \
-          --volume /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
+          --volume /var/lib/calico:/var/lib/calico:ro \
-          --volume /etc/pki/tls/certs:/usr/share/ca-certificates:ro \
-          --volume /var/lib/calico:/var/lib/calico \
           --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:v1.17.1 kubelet \
+          $${KUBELET_IMAGE} \
           --anonymous-auth=false \
           --authentication-token-webhook \
           --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
           --cgroup-driver=systemd \
           --cgroups-per-qos=true \
           --enforce-node-allocatable=pods \
           --client-ca-file=/etc/kubernetes/ca.crt \
           --cluster_dns=${cluster_dns_service_ip} \
           --cluster_domain=${cluster_domain_suffix} \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --exit-on-lock-contention \
           --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
           --network-plugin=cni \
           --node-labels=node.kubernetes.io/node \
-          %{ for label in split(",", node_labels) }
+          %{~ for label in split(",", node_labels) ~}
           --node-labels=${label} \
-          %{ endfor ~}
+          %{~ endfor ~}
+          %{~ for taint in split(",", node_taints) ~}
+          --register-with-taints=${taint} \
+          %{~ endfor ~}
           --pod-manifest-path=/etc/kubernetes/manifests \
+          --provider-id=aws:///$${AFTERBURN_AWS_AVAILABILITY_ZONE}/$${AFTERBURN_AWS_INSTANCE_ID} \
           --read-only-port=0 \
+          --rotate-certificates \
           --volume-plugin-dir=/var/lib/kubelet/volumeplugins
         ExecStop=-/usr/bin/podman stop kubelet
         Delegate=yes
@@ -78,6 +84,19 @@ systemd:
         RestartSec=10
         [Install]
         WantedBy=multi-user.target
+    - name: delete-node.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Delete Kubernetes node on shutdown
+        [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        Type=oneshot
+        RemainAfterExit=true
+        ExecStart=/bin/true
+        ExecStop=/bin/bash -c '/usr/bin/podman run --volume /var/lib/kubelet:/var/lib/kubelet:ro,z --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
+        [Install]
+        WantedBy=multi-user.target
 storage:
   directories:
     - path: /etc/kubernetes
@@ -87,14 +106,22 @@ storage:
       contents:
         inline: |
           ${kubeconfig}
-    - path: /etc/sysctl.d/reverse-path-filter.conf
-      contents:
-        inline: |
-          net.ipv4.conf.all.rp_filter=1
     - 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: |

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

@@ -34,16 +34,21 @@ variable "instance_type" {
   default     = "t3.small"
 }
 
-variable "os_image" {
+variable "os_stream" {
   type        = string
-  description = "AMI channel for Fedora CoreOS (not yet used)"
+  description = "Fedora CoreOS image stream for instances (e.g. stable, testing, next)"
-  default     = "coreos-stable"
+  default     = "stable"
+
+  validation {
+    condition     = contains(["stable", "testing", "next"], var.os_stream)
+    error_message = "The os_stream must be stable, testing, or next."
+  }
 }
 
 variable "disk_size" {
   type        = number
   description = "Size of the EBS volume in GB"
-  default     = 40
+  default     = 30
 }
 
 variable "disk_type" {
@@ -108,3 +113,22 @@ variable "node_labels" {
   description = "List of initial node labels"
   default     = []
 }
+
+variable "node_taints" {
+  type        = list(string)
+  description = "List of initial node taints"
+  default     = []
+}
+
+# unofficial, undocumented, unsupported
+
+variable "arch" {
+  type        = string
+  description = "Container architecture (amd64 or arm64)"
+  default     = "amd64"
+
+  validation {
+    condition     = var.arch == "amd64" || var.arch == "arm64"
+    error_message = "The arch must be amd64 or arm64."
+  }
+}

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

@@ -1,4 +1,14 @@
+# Terraform version and plugin versions
 
 terraform {
-  required_version = ">= 0.12"
+  required_version = ">= 0.13.0, < 0.16.0"
+  required_providers {
+    aws      = ">= 2.23, <= 4.0"
+    template = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.8"
+    }
+  }
 }

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

@@ -44,7 +44,7 @@ resource "aws_autoscaling_group" "workers" {
 
 # Worker template
 resource "aws_launch_configuration" "worker" {
-  image_id          = data.aws_ami.fedora-coreos.image_id
+  image_id          = var.arch == "arm64" ? data.aws_ami.fedora-coreos-arm[0].image_id : data.aws_ami.fedora-coreos.image_id
   instance_type     = var.instance_type
   spot_price        = var.spot_price > 0 ? var.spot_price : null
   enable_monitoring = false
@@ -86,6 +86,7 @@ data "template_file" "worker-config" {
     cluster_dns_service_ip = cidrhost(var.service_cidr, 10)
     cluster_domain_suffix  = var.cluster_domain_suffix
     node_labels            = join(",", var.node_labels)
+    node_taints            = join(",", var.node_taints)
   }
 }
 

aws/flatcar-linux/kubernetes/README.md

@@ -11,13 +11,13 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.17.1 (upstream)
+* Kubernetes v1.21.1 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* 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/), [preemptible](https://typhoon.psdn.io/cl/google-cloud/#preemption) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
+* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/flatcar-linux/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
-* Ready for Ingress, Prometheus, Grafana, 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
 
-Please see the [official docs](https://typhoon.psdn.io) and the Google Cloud [tutorial](https://typhoon.psdn.io/cl/google-cloud/).
+Please see the [official docs](https://typhoon.psdn.io) and the AWS [tutorial](https://typhoon.psdn.io/flatcar-linux/aws/).
 

aws/flatcar-linux/kubernetes/ami.tf

@@ -0,0 +1,27 @@
+locals {
+  # Pick a Flatcar Linux AMI
+  # flatcar-stable -> Flatcar Linux AMI
+  ami_id  = data.aws_ami.flatcar.image_id
+  channel = split("-", var.os_image)[1]
+}
+
+data "aws_ami" "flatcar" {
+  most_recent = true
+  owners      = ["075585003325"]
+
+  filter {
+    name   = "architecture"
+    values = ["x86_64"]
+  }
+
+  filter {
+    name   = "virtualization-type"
+    values = ["hvm"]
+  }
+
+  filter {
+    name   = "name"
+    values = ["Flatcar-${local.channel}-*"]
+  }
+}
+

aws/flatcar-linux/kubernetes/bootstrap.tf

@@ -1,11 +1,10 @@
 # Kubernetes assets (kubeconfig, manifests)
 module "bootstrap" {
-  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=de85f1da7df0b13dfb7488350c20a510f3090cdf"
+  source = "git::https://github.com/poseidon/terraform-render-bootstrap.git?ref=ebe3d5526a59b34c8f119a206358b0c0a6f6f67d"
 
   cluster_name          = var.cluster_name
   api_servers           = [format("%s.%s", var.cluster_name, var.dns_zone)]
   etcd_servers          = aws_route53_record.etcds.*.fqdn
-  asset_dir             = var.asset_dir
   networking            = var.networking
   network_mtu           = var.network_mtu
   pod_cidr              = var.pod_cidr
@@ -13,5 +12,6 @@ module "bootstrap" {
   cluster_domain_suffix = var.cluster_domain_suffix
   enable_reporting      = var.enable_reporting
   enable_aggregation    = var.enable_aggregation
+  daemonset_tolerations = var.daemonset_tolerations
 }
 

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

@@ -0,0 +1,215 @@
+---
+systemd:
+  units:
+    - name: etcd-member.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=etcd (System Container)
+        Documentation=https://github.com/etcd-io/etcd
+        Requires=docker.service
+        After=docker.service
+        [Service]
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.4.16
+        ExecStartPre=/usr/bin/docker run -d \
+          --name etcd \
+          --network host \
+          --env-file /etc/etcd/etcd.env \
+          --user 232:232 \
+          --volume /etc/ssl/etcd:/etc/ssl/certs:ro \
+          --volume /var/lib/etcd:/var/lib/etcd:rw \
+          $${ETCD_IMAGE}
+        ExecStart=docker logs -f etcd
+        ExecStop=docker stop etcd
+        ExecStopPost=docker rm etcd
+        Restart=always
+        RestartSec=10s
+        TimeoutStartSec=0
+        LimitNOFILE=40000
+        [Install]
+        WantedBy=multi-user.target
+    - name: docker.service
+      enabled: true
+    - name: locksmithd.service
+      mask: true
+    - name: wait-for-dns.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Wait for DNS entries
+        Wants=systemd-resolved.service
+        Before=kubelet.service
+        [Service]
+        Type=oneshot
+        RemainAfterExit=true
+        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
+        [Install]
+        RequiredBy=kubelet.service
+        RequiredBy=etcd-member.service
+    - name: kubelet.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Kubelet (System Container)
+        Requires=docker.service
+        After=docker.service
+        Requires=coreos-metadata.service
+        After=coreos-metadata.service
+        Wants=rpc-statd.service
+        [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        EnvironmentFile=/run/metadata/coreos
+        ExecStartPre=/bin/mkdir -p /etc/cni/net.d
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
+        ExecStartPre=/bin/mkdir -p /var/lib/calico
+        ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
+        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
+        ExecStartPre=/usr/bin/docker run -d \
+          --name kubelet \
+          --privileged \
+          --pid host \
+          --network host \
+          -v /etc/cni/net.d:/etc/cni/net.d:ro \
+          -v /etc/kubernetes:/etc/kubernetes:ro \
+          -v /etc/machine-id:/etc/machine-id:ro \
+          -v /usr/lib/os-release:/etc/os-release:ro \
+          -v /lib/modules:/lib/modules:ro \
+          -v /run:/run \
+          -v /sys/fs/cgroup:/sys/fs/cgroup:ro \
+          -v /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
+          -v /var/lib/calico:/var/lib/calico:ro \
+          -v /var/lib/docker:/var/lib/docker \
+          -v /var/lib/kubelet:/var/lib/kubelet:rshared \
+          -v /var/log:/var/log \
+          -v /opt/cni/bin:/opt/cni/bin \
+          $${KUBELET_IMAGE} \
+          --anonymous-auth=false \
+          --authentication-token-webhook \
+          --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${cluster_dns_service_ip} \
+          --cluster_domain=${cluster_domain_suffix} \
+          --healthz-port=0 \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
+          --network-plugin=cni \
+          --node-labels=node.kubernetes.io/controller="true" \
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID} \
+          --read-only-port=0 \
+          --register-with-taints=node-role.kubernetes.io/controller=:NoSchedule \
+          --rotate-certificates \
+          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+        ExecStart=docker logs -f kubelet
+        ExecStop=docker stop kubelet
+        ExecStopPost=docker rm kubelet
+        Restart=always
+        RestartSec=10
+        [Install]
+        WantedBy=multi-user.target
+    - name: bootstrap.service
+      contents: |
+        [Unit]
+        Description=Kubernetes control plane
+        Wants=docker.service
+        After=docker.service
+        ConditionPathExists=!/opt/bootstrap/bootstrap.done
+        [Service]
+        Type=oneshot
+        RemainAfterExit=true
+        WorkingDirectory=/opt/bootstrap
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        ExecStart=/usr/bin/docker run \
+            -v /etc/kubernetes/pki:/etc/kubernetes/pki:ro \
+            -v /opt/bootstrap/assets:/assets:ro \
+            -v /opt/bootstrap/apply:/apply:ro \
+            --entrypoint=/apply \
+            $${KUBELET_IMAGE}
+        ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
+        [Install]
+        WantedBy=multi-user.target
+storage:
+  directories:
+    - path: /var/lib/etcd
+      filesystem: root
+      mode: 0700
+      overwrite: true
+  files:
+    - path: /etc/kubernetes/kubeconfig
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          ${kubeconfig}
+    - path: /opt/bootstrap/layout
+      filesystem: root
+      mode: 0544
+      contents:
+        inline: |
+          #!/bin/bash -e
+          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
+          awk '/#####/ {filename=$2; next} {print > filename}' assets
+          mkdir -p /etc/ssl/etcd/etcd
+          mkdir -p /etc/kubernetes/pki
+          mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
+          mv tls/etcd/etcd-client* /etc/kubernetes/pki/
+          chown -R etcd:etcd /etc/ssl/etcd
+          chmod -R 500 /etc/ssl/etcd
+          chmod -R 700 /var/lib/etcd
+          mv auth/* /etc/kubernetes/pki/
+          mv tls/k8s/* /etc/kubernetes/pki/
+          mkdir -p /etc/kubernetes/manifests
+          mv static-manifests/* /etc/kubernetes/manifests/
+          mkdir -p /opt/bootstrap/assets
+          mv manifests /opt/bootstrap/assets/manifests
+          mv manifests-networking/* /opt/bootstrap/assets/manifests/
+          rm -rf assets auth static-manifests tls manifests-networking
+    - path: /opt/bootstrap/apply
+      filesystem: root
+      mode: 0544
+      contents:
+        inline: |
+          #!/bin/bash -e
+          export KUBECONFIG=/etc/kubernetes/pki/admin.conf
+          until kubectl version; do
+            echo "Waiting for static pod control plane"
+            sleep 5
+          done
+          until kubectl apply -f /assets/manifests -R; do
+             echo "Retry applying manifests"
+             sleep 5
+          done
+    - path: /etc/sysctl.d/max-user-watches.conf
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          fs.inotify.max_user_watches=16184
+    - path: /etc/etcd/etcd.env
+      filesystem: root
+      mode: 0644
+      contents:
+          inline: |
+            ETCD_NAME=${etcd_name}
+            ETCD_DATA_DIR=/var/lib/etcd
+            ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379
+            ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380
+            ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379
+            ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380
+            ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381
+            ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}
+            ETCD_STRICT_RECONFIG_CHECK=true
+            ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt
+            ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt
+            ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key
+            ETCD_CLIENT_CERT_AUTH=true
+            ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt
+            ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt
+            ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key
+            ETCD_PEER_CLIENT_CERT_AUTH=true
+passwd:
+  users:
+    - name: core
+      ssh_authorized_keys:
+        - "${ssh_authorized_key}"

aws/flatcar-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
+  count    = var.controller_count
-  content      = data.template_file.controller-configs.*.rendered[count.index]
+  content  = data.template_file.controller-configs.*.rendered[count.index]
-  pretty_print = false
+  strict   = true
-  snippets     = var.controller_clc_snippets
+  snippets = var.controller_snippets
 }
 
 # Controller Container Linux configs
@@ -67,7 +67,6 @@ 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)

aws/flatcar-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/flatcar-linux/kubernetes/nlb.tf

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

aws/flatcar-linux/kubernetes/outputs.tf

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

aws/flatcar-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" "controller-cilium-health" {
-resource "aws_security_group_rule" "kube-proxy-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
   type                     = "ingress"
   protocol                 = "tcp"
-  from_port                = 10249
+  from_port                = 4240
-  to_port                  = 10249
+  to_port                  = 4240
   source_security_group_id = aws_security_group.worker.id
 }
 
-# Allow Prometheus to scrape kube-scheduler
+resource "aws_security_group_rule" "controller-cilium-health-self" {
-resource "aws_security_group_rule" "controller-scheduler-metrics" {
+  count = var.networking == "cilium" ? 1 : 0
+
   security_group_id = aws_security_group.controller.id
 
-  type                     = "ingress"
+  type      = "ingress"
-  protocol                 = "tcp"
+  protocol  = "tcp"
-  from_port                = 10251
+  from_port = 4240
-  to_port                  = 10251
+  to_port   = 4240
-  source_security_group_id = aws_security_group.worker.id
+  self      = true
-}
-
-# 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
 }
 
+# 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/flatcar-linux/kubernetes/variables.tf

@@ -43,14 +43,19 @@ variable "worker_type" {
 
 variable "os_image" {
   type        = string
-  description = "AMI channel for a Container Linux derivative (coreos-stable, coreos-beta, coreos-alpha, flatcar-stable, flatcar-beta, flatcar-alpha, flatcar-edge)"
+  description = "AMI channel for a Container Linux derivative (flatcar-stable, flatcar-beta, flatcar-alpha)"
-  default     = "coreos-stable"
+  default     = "flatcar-stable"
+
+  validation {
+    condition     = contains(["flatcar-stable", "flatcar-beta", "flatcar-alpha"], var.os_image)
+    error_message = "The os_image must be flatcar-stable, flatcar-beta, or flatcar-alpha."
+  }
 }
 
 variable "disk_size" {
   type        = number
   description = "Size of the EBS volume in GB"
-  default     = 40
+  default     = 30
 }
 
 variable "disk_type" {
@@ -77,13 +82,13 @@ 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 +101,6 @@ 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)"
@@ -161,3 +160,8 @@ variable "cluster_domain_suffix" {
   default     = "cluster.local"
 }
 
+variable "daemonset_tolerations" {
+  type        = list(string)
+  description = "List of additional taint keys kube-system DaemonSets should tolerate (e.g. ['custom-role', 'gpu-role'])"
+  default     = []
+}

aws/flatcar-linux/kubernetes/versions.tf

@@ -0,0 +1,15 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.13.0, < 0.16.0"
+  required_providers {
+    aws      = ">= 2.23, <= 4.0"
+    template = "~> 2.1"
+    null     = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.8"
+    }
+  }
+}

aws/flatcar-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/flatcar-linux/kubernetes/workers/ami.tf

@@ -0,0 +1,27 @@
+locals {
+  # Pick a Flatcar Linux AMI
+  # flatcar-stable -> Flatcar Linux AMI
+  ami_id  = data.aws_ami.flatcar.image_id
+  channel = split("-", var.os_image)[1]
+}
+
+data "aws_ami" "flatcar" {
+  most_recent = true
+  owners      = ["075585003325"]
+
+  filter {
+    name   = "architecture"
+    values = ["x86_64"]
+  }
+
+  filter {
+    name   = "virtualization-type"
+    values = ["hvm"]
+  }
+
+  filter {
+    name   = "name"
+    values = ["Flatcar-${local.channel}-*"]
+  }
+}
+

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

@@ -0,0 +1,122 @@
+---
+systemd:
+  units:
+    - name: docker.service
+      enabled: true
+    - name: locksmithd.service
+      mask: true
+    - name: wait-for-dns.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Wait for DNS entries
+        Wants=systemd-resolved.service
+        Before=kubelet.service
+        [Service]
+        Type=oneshot
+        RemainAfterExit=true
+        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
+        [Install]
+        RequiredBy=kubelet.service
+    - name: kubelet.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Kubelet
+        Requires=docker.service
+        After=docker.service
+        Requires=coreos-metadata.service
+        After=coreos-metadata.service
+        Wants=rpc-statd.service
+        [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        EnvironmentFile=/run/metadata/coreos
+        ExecStartPre=/bin/mkdir -p /etc/cni/net.d
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
+        ExecStartPre=/bin/mkdir -p /var/lib/calico
+        ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
+        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
+        # Podman, rkt, or runc run container processes, whereas docker run
+        # is a client to a daemon and requires workarounds to use within a
+        # systemd unit. https://github.com/moby/moby/issues/6791
+        ExecStartPre=/usr/bin/docker run -d \
+          --name kubelet \
+          --privileged \
+          --pid host \
+          --network host \
+          -v /etc/cni/net.d:/etc/cni/net.d:ro \
+          -v /etc/kubernetes:/etc/kubernetes:ro \
+          -v /etc/machine-id:/etc/machine-id:ro \
+          -v /usr/lib/os-release:/etc/os-release:ro \
+          -v /lib/modules:/lib/modules:ro \
+          -v /run:/run \
+          -v /sys/fs/cgroup:/sys/fs/cgroup:ro \
+          -v /sys/fs/cgroup/systemd:/sys/fs/cgroup/systemd \
+          -v /var/lib/calico:/var/lib/calico:ro \
+          -v /var/lib/docker:/var/lib/docker \
+          -v /var/lib/kubelet:/var/lib/kubelet:rshared \
+          -v /var/log:/var/log \
+          -v /opt/cni/bin:/opt/cni/bin \
+          $${KUBELET_IMAGE} \
+          --anonymous-auth=false \
+          --authentication-token-webhook \
+          --authorization-mode=Webhook \
+          --bootstrap-kubeconfig=/etc/kubernetes/kubeconfig \
+          --client-ca-file=/etc/kubernetes/ca.crt \
+          --cluster_dns=${cluster_dns_service_ip} \
+          --cluster_domain=${cluster_domain_suffix} \
+          --healthz-port=0 \
+          --kubeconfig=/var/lib/kubelet/kubeconfig \
+          --network-plugin=cni \
+          --node-labels=node.kubernetes.io/node \
+          %{~ for label in split(",", node_labels) ~}
+          --node-labels=${label} \
+          %{~ endfor ~}
+          %{~ for taint in split(",", node_taints) ~}
+          --register-with-taints=${taint} \
+          %{~ endfor ~}
+          --pod-manifest-path=/etc/kubernetes/manifests \
+          --provider-id=aws:///$${COREOS_EC2_AVAILABILITY_ZONE}/$${COREOS_EC2_INSTANCE_ID} \
+          --read-only-port=0 \
+          --rotate-certificates \
+          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
+        ExecStart=docker logs -f kubelet
+        ExecStop=docker stop kubelet
+        ExecStopPost=docker rm kubelet
+        Restart=always
+        RestartSec=5
+        [Install]
+        WantedBy=multi-user.target
+    - name: delete-node.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=Delete Kubernetes node on shutdown
+        [Service]
+        Environment=KUBELET_IMAGE=quay.io/poseidon/kubelet:v1.21.1
+        Type=oneshot
+        RemainAfterExit=true
+        ExecStart=/bin/true
+        ExecStop=/bin/bash -c '/usr/bin/docker run -v /var/lib/kubelet:/var/lib/kubelet:ro --entrypoint /usr/local/bin/kubectl $${KUBELET_IMAGE} --kubeconfig=/var/lib/kubelet/kubeconfig delete node $HOSTNAME'
+        [Install]
+        WantedBy=multi-user.target
+storage:
+  files:
+    - path: /etc/kubernetes/kubeconfig
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          ${kubeconfig}
+    - path: /etc/sysctl.d/max-user-watches.conf
+      filesystem: root
+      mode: 0644
+      contents:
+        inline: |
+          fs.inotify.max_user_watches=16184
+passwd:
+  users:
+    - name: core
+      ssh_authorized_keys:
+        - "${ssh_authorized_key}"

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

@@ -36,14 +36,19 @@ variable "instance_type" {
 
 variable "os_image" {
   type        = string
-  description = "AMI channel for a Container Linux derivative (coreos-stable, coreos-beta, coreos-alpha, flatcar-stable, flatcar-beta, flatcar-alpha, flatcar-edge)"
+  description = "AMI channel for a Container Linux derivative (flatcar-stable, flatcar-beta, flatcar-alpha)"
-  default     = "coreos-stable"
+  default     = "flatcar-stable"
+
+  validation {
+    condition     = contains(["flatcar-stable", "flatcar-beta", "flatcar-alpha"], var.os_image)
+    error_message = "The os_image must be flatcar-stable, flatcar-beta, or flatcar-alpha."
+  }
 }
 
 variable "disk_size" {
   type        = number
   description = "Size of the EBS volume in GB"
-  default     = 40
+  default     = 30
 }
 
 variable "disk_type" {
@@ -70,7 +75,7 @@ variable "target_groups" {
   default     = []
 }
 
-variable "clc_snippets" {
+variable "snippets" {
   type        = list(string)
   description = "Container Linux Config snippets"
   default     = []
@@ -108,3 +113,9 @@ variable "node_labels" {
   description = "List of initial node labels"
   default     = []
 }
+
+variable "node_taints" {
+  type        = list(string)
+  description = "List of initial node taints"
+  default     = []
+}

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

@@ -0,0 +1,14 @@
+# Terraform version and plugin versions
+
+terraform {
+  required_version = ">= 0.13.0, < 0.16.0"
+  required_providers {
+    aws      = ">= 2.23, <= 4.0"
+    template = "~> 2.1"
+
+    ct = {
+      source  = "poseidon/ct"
+      version = "~> 0.8"
+    }
+  }
+}

aws/flatcar-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
+  content  = data.template_file.worker-config.rendered
-  pretty_print = false
+  strict   = true
-  snippets     = var.clc_snippets
+  snippets = var.snippets
 }
 
 # Worker Container Linux config
@@ -85,8 +85,8 @@ 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)
+    node_taints            = join(",", var.node_taints)
   }
 }
 

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

@@ -1,196 +0,0 @@
----
-systemd:
-  units:
-    - name: etcd-member.service
-      enable: true
-      dropins:
-        - name: 40-etcd-cluster.conf
-          contents: |
-            [Service]
-            Environment="ETCD_IMAGE_TAG=v3.4.3"
-            Environment="ETCD_NAME=${etcd_name}"
-            Environment="ETCD_ADVERTISE_CLIENT_URLS=https://${etcd_domain}:2379"
-            Environment="ETCD_INITIAL_ADVERTISE_PEER_URLS=https://${etcd_domain}:2380"
-            Environment="ETCD_LISTEN_CLIENT_URLS=https://0.0.0.0:2379"
-            Environment="ETCD_LISTEN_PEER_URLS=https://0.0.0.0:2380"
-            Environment="ETCD_LISTEN_METRICS_URLS=http://0.0.0.0:2381"
-            Environment="ETCD_INITIAL_CLUSTER=${etcd_initial_cluster}"
-            Environment="ETCD_STRICT_RECONFIG_CHECK=true"
-            Environment="ETCD_SSL_DIR=/etc/ssl/etcd"
-            Environment="ETCD_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/server-ca.crt"
-            Environment="ETCD_CERT_FILE=/etc/ssl/certs/etcd/server.crt"
-            Environment="ETCD_KEY_FILE=/etc/ssl/certs/etcd/server.key"
-            Environment="ETCD_CLIENT_CERT_AUTH=true"
-            Environment="ETCD_PEER_TRUSTED_CA_FILE=/etc/ssl/certs/etcd/peer-ca.crt"
-            Environment="ETCD_PEER_CERT_FILE=/etc/ssl/certs/etcd/peer.crt"
-            Environment="ETCD_PEER_KEY_FILE=/etc/ssl/certs/etcd/peer.key"
-            Environment="ETCD_PEER_CLIENT_CERT_AUTH=true"
-    - name: docker.service
-      enable: true
-    - name: locksmithd.service
-      mask: true
-    - name: wait-for-dns.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Wait for DNS entries
-        Wants=systemd-resolved.service
-        Before=kubelet.service
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
-        [Install]
-        RequiredBy=kubelet.service
-        RequiredBy=etcd-member.service
-    - name: kubelet.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Kubelet via Hyperkube
-        Wants=rpc-statd.service
-        [Service]
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
-        ExecStartPre=/bin/mkdir -p /opt/cni/bin
-        ExecStartPre=/bin/mkdir -p /var/lib/calico
-        ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
-        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
-        ExecStart=/usr/bin/rkt run \
-          --uuid-file-save=/var/cache/kubelet-pod.uuid \
-          --stage1-from-dir=stage1-fly.aci \
-          --hosts-entry host \
-          --insecure-options=image \
-          --volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
-          --mount volume=etc-kubernetes,target=/etc/kubernetes \
-          --volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
-          --mount volume=etc-machine-id,target=/etc/machine-id \
-          --volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
-          --mount volume=etc-os-release,target=/etc/os-release \
-          --volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
-          --mount volume=etc-resolv,target=/etc/resolv.conf \
-          --volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
-          --mount volume=etc-ssl-certs,target=/etc/ssl/certs \
-          --volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
-          --mount volume=lib-modules,target=/lib/modules \
-          --volume run,kind=host,source=/run \
-          --mount volume=run,target=/run \
-          --volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
-          --mount volume=usr-share-certs,target=/usr/share/ca-certificates \
-          --volume var-lib-calico,kind=host,source=/var/lib/calico \
-          --mount volume=var-lib-calico,target=/var/lib/calico \
-          --volume var-lib-docker,kind=host,source=/var/lib/docker \
-          --mount volume=var-lib-docker,target=/var/lib/docker \
-          --volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
-          --mount volume=var-lib-kubelet,target=/var/lib/kubelet \
-          --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log \
-          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
-          --mount volume=opt-cni-bin,target=/opt/cni/bin \
-          docker://k8s.gcr.io/hyperkube:v1.17.1 \
-          --exec=/usr/local/bin/kubelet -- \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --exit-on-lock-contention \
-          --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
-          --network-plugin=cni \
-          --node-labels=node.kubernetes.io/master \
-          --node-labels=node.kubernetes.io/controller="true" \
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --read-only-port=0 \
-          --register-with-taints=node-role.kubernetes.io/master=:NoSchedule \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
-        Restart=always
-        RestartSec=10
-        [Install]
-        WantedBy=multi-user.target
-    - name: bootstrap.service
-      contents: |
-        [Unit]
-        Description=Kubernetes control plane
-        ConditionPathExists=!/opt/bootstrap/bootstrap.done
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        WorkingDirectory=/opt/bootstrap
-        ExecStartPre=-/usr/bin/bash -c 'set -x && [ -n "$(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 \
-            --mount volume=config,target=/etc/kubernetes/secrets \
-            --volume assets,kind=host,source=/opt/bootstrap/assets \
-            --mount volume=assets,target=/assets \
-            --volume script,kind=host,source=/opt/bootstrap/apply \
-            --mount volume=script,target=/apply \
-            --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.1 \
-            --net=host \
-            --dns=host \
-            --exec=/apply
-        ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
-        [Install]
-        WantedBy=multi-user.target
-storage:
-  files:
-    - path: /etc/kubernetes/kubeconfig
-      filesystem: root
-      mode: 0644
-      contents:
-        inline: |
-          ${kubeconfig}
-    - path: /opt/bootstrap/layout
-      filesystem: root
-      mode: 0544
-      contents:
-        inline: |
-          #!/bin/bash -e
-          mkdir -p -- auth tls/etcd tls/k8s static-manifests manifests/coredns manifests-networking
-          awk '/#####/ {filename=$2; next} {print > filename}' assets
-          mkdir -p /etc/ssl/etcd/etcd
-          mkdir -p /etc/kubernetes/bootstrap-secrets
-          mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
-          mv tls/etcd/etcd-client* /etc/kubernetes/bootstrap-secrets/
-          chown -R etcd:etcd /etc/ssl/etcd
-          chmod -R 500 /etc/ssl/etcd
-          mv auth/kubeconfig /etc/kubernetes/bootstrap-secrets/
-          mv tls/k8s/* /etc/kubernetes/bootstrap-secrets/
-          sudo mkdir -p /etc/kubernetes/manifests
-          sudo mv static-manifests/* /etc/kubernetes/manifests/
-          sudo mkdir -p /opt/bootstrap/assets
-          sudo mv manifests /opt/bootstrap/assets/manifests
-          sudo mv manifests-networking /opt/bootstrap/assets/manifests-networking
-          rm -rf assets auth static-manifests tls
-    - path: /opt/bootstrap/apply
-      filesystem: root
-      mode: 0544
-      contents:
-        inline: |
-          #!/bin/bash -e
-          export KUBECONFIG=/etc/kubernetes/secrets/kubeconfig
-          until kubectl version; do
-            echo "Waiting for static pod control plane"
-            sleep 5
-          done
-          until kubectl apply -f /assets/manifests -R; do
-             echo "Retry applying manifests"
-             sleep 5
-          done
-    - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
-      contents:
-        inline: |
-          fs.inotify.max_user_watches=16184
-passwd:
-  users:
-    - name: core
-      ssh_authorized_keys:
-        - "${ssh_authorized_key}"

azure/container-linux/kubernetes/versions.tf

@@ -1,12 +0,0 @@
-# Terraform version and plugin versions
-
-terraform {
-  required_version = "~> 0.12.6"
-  required_providers {
-    azurerm  = "~> 1.27"
-    ct       = "~> 0.3"
-    template = "~> 2.1"
-    null     = "~> 2.1"
-  }
-}
-

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

@@ -1,138 +0,0 @@
----
-systemd:
-  units:
-    - name: docker.service
-      enable: true
-    - name: locksmithd.service
-      mask: true
-    - name: wait-for-dns.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Wait for DNS entries
-        Wants=systemd-resolved.service
-        Before=kubelet.service
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/sh -c 'while ! /usr/bin/grep '^[^#[:space:]]' /etc/resolv.conf > /dev/null; do sleep 1; done'
-        [Install]
-        RequiredBy=kubelet.service
-    - name: kubelet.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Kubelet via Hyperkube
-        Wants=rpc-statd.service
-        [Service]
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/cni/net.d
-        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
-        ExecStartPre=/bin/mkdir -p /opt/cni/bin
-        ExecStartPre=/bin/mkdir -p /var/lib/calico
-        ExecStartPre=/bin/mkdir -p /var/lib/kubelet/volumeplugins
-        ExecStartPre=/usr/bin/bash -c "grep 'certificate-authority-data' /etc/kubernetes/kubeconfig | awk '{print $2}' | base64 -d > /etc/kubernetes/ca.crt"
-        ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/cache/kubelet-pod.uuid
-        ExecStart=/usr/bin/rkt run \
-          --uuid-file-save=/var/cache/kubelet-pod.uuid \
-          --stage1-from-dir=stage1-fly.aci \
-          --hosts-entry host \
-          --insecure-options=image \
-          --volume etc-kubernetes,kind=host,source=/etc/kubernetes,readOnly=true \
-          --mount volume=etc-kubernetes,target=/etc/kubernetes \
-          --volume etc-machine-id,kind=host,source=/etc/machine-id,readOnly=true \
-          --mount volume=etc-machine-id,target=/etc/machine-id \
-          --volume etc-os-release,kind=host,source=/usr/lib/os-release,readOnly=true \
-          --mount volume=etc-os-release,target=/etc/os-release \
-          --volume=etc-resolv,kind=host,source=/etc/resolv.conf,readOnly=true \
-          --mount volume=etc-resolv,target=/etc/resolv.conf \
-          --volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
-          --mount volume=etc-ssl-certs,target=/etc/ssl/certs \
-          --volume lib-modules,kind=host,source=/lib/modules,readOnly=true \
-          --mount volume=lib-modules,target=/lib/modules \
-          --volume run,kind=host,source=/run \
-          --mount volume=run,target=/run \
-          --volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
-          --mount volume=usr-share-certs,target=/usr/share/ca-certificates \
-          --volume var-lib-calico,kind=host,source=/var/lib/calico \
-          --mount volume=var-lib-calico,target=/var/lib/calico \
-          --volume var-lib-docker,kind=host,source=/var/lib/docker \
-          --mount volume=var-lib-docker,target=/var/lib/docker \
-          --volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,recursive=true \
-          --mount volume=var-lib-kubelet,target=/var/lib/kubelet \
-          --volume var-log,kind=host,source=/var/log \
-          --mount volume=var-log,target=/var/log \
-          --volume opt-cni-bin,kind=host,source=/opt/cni/bin \
-          --mount volume=opt-cni-bin,target=/opt/cni/bin \
-          docker://k8s.gcr.io/hyperkube:v1.17.1 \
-          --exec=/usr/local/bin/kubelet -- \
-          --anonymous-auth=false \
-          --authentication-token-webhook \
-          --authorization-mode=Webhook \
-          --client-ca-file=/etc/kubernetes/ca.crt \
-          --cluster_dns=${cluster_dns_service_ip} \
-          --cluster_domain=${cluster_domain_suffix} \
-          --cni-conf-dir=/etc/kubernetes/cni/net.d \
-          --exit-on-lock-contention \
-          --healthz-port=0 \
-          --kubeconfig=/etc/kubernetes/kubeconfig \
-          --lock-file=/var/run/lock/kubelet.lock \
-          --network-plugin=cni \
-          --node-labels=node.kubernetes.io/node \
-          %{ for label in split(",", node_labels) }
-          --node-labels=${label} \
-          %{ endfor ~}
-          --pod-manifest-path=/etc/kubernetes/manifests \
-          --read-only-port=0 \
-          --volume-plugin-dir=/var/lib/kubelet/volumeplugins
-        ExecStop=-/usr/bin/rkt stop --uuid-file=/var/cache/kubelet-pod.uuid
-        Restart=always
-        RestartSec=5
-        [Install]
-        WantedBy=multi-user.target
-    - name: delete-node.service
-      enable: true
-      contents: |
-        [Unit]
-        Description=Waiting to delete Kubernetes node on shutdown
-        [Service]
-        Type=oneshot
-        RemainAfterExit=true
-        ExecStart=/bin/true
-        ExecStop=/etc/kubernetes/delete-node
-        [Install]
-        WantedBy=multi-user.target
-storage:
-  files:
-    - path: /etc/kubernetes/kubeconfig
-      filesystem: root
-      mode: 0644
-      contents:
-        inline: |
-          ${kubeconfig}
-    - path: /etc/sysctl.d/max-user-watches.conf
-      filesystem: root
-      contents:
-        inline: |
-          fs.inotify.max_user_watches=16184
-    - path: /etc/kubernetes/delete-node
-      filesystem: root
-      mode: 0744
-      contents:
-        inline: |
-          #!/bin/bash
-          set -e
-          exec /usr/bin/rkt run \
-            --trust-keys-from-https \
-            --volume config,kind=host,source=/etc/kubernetes \
-            --mount volume=config,target=/etc/kubernetes \
-            --insecure-options=image \
-            docker://k8s.gcr.io/hyperkube:v1.17.1 \
-            --net=host \
-            --dns=host \
-            -- \
-            kubectl -- --kubeconfig=/etc/kubernetes/kubeconfig delete node $(hostname | tr '[:upper:]' '[:lower:]')
-passwd:
-  users:
-    - name: core
-      ssh_authorized_keys:
-        - "${ssh_authorized_key}"

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

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

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

@@ -11,13 +11,13 @@ Typhoon distributes upstream Kubernetes, architectural conventions, and cluster
 
 ## Features <a href="https://www.cncf.io/certification/software-conformance/"><img align="right" src="https://storage.googleapis.com/poseidon/certified-kubernetes.png"></a>
 
-* Kubernetes v1.17.1 (upstream)
+* Kubernetes v1.21.1 (upstream)
-* Single or multi-master, [Calico](https://www.projectcalico.org/) or [flannel](https://github.com/coreos/flannel) networking
+* 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/)
+* On-cluster etcd with TLS, [RBAC](https://kubernetes.io/docs/admin/authorization/rbac/)-enabled, [network policy](https://kubernetes.io/docs/concepts/services-networking/network-policies/), SELinux enforcing
-* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot](https://typhoon.psdn.io/cl/aws/#spot) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#container-linux) customization
+* Advanced features like [worker pools](https://typhoon.psdn.io/advanced/worker-pools/), [spot priority](https://typhoon.psdn.io/fedora-coreos/azure/#low-priority) workers, and [snippets](https://typhoon.psdn.io/advanced/customization/#hosts) customization
 * Ready for Ingress, Prometheus, Grafana, and other optional [addons](https://typhoon.psdn.io/addons/overview/)
 
 ## Docs
 
-Please see the [official docs](https://typhoon.psdn.io) and the AWS [tutorial](https://typhoon.psdn.io/cl/aws/).
+Please see the [official docs](https://typhoon.psdn.io) and the 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=ebe3d5526a59b34c8f119a206358b0c0a6f6f67d"
+
+  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)
+
+  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
+  daemonset_tolerations = var.daemonset_tolerations
+
+  # 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 +1,220 @@
+---
+variant: fcos
+version: 1.2.0
+systemd:
+  units:
+    - name: etcd-member.service
+      enabled: true
+      contents: |
+        [Unit]
+        Description=etcd (System Container)
+        Documentation=https://github.com/etcd-io/etcd
+        Wants=network-online.target network.target
+        After=network-online.target
+        [Service]
+        Environment=ETCD_IMAGE=quay.io/coreos/etcd:v3.4.16
+        Type=exec
+        ExecStartPre=/bin/mkdir -p /var/lib/etcd
+        ExecStartPre=-/usr/bin/podman rm etcd
+        ExecStart=/usr/bin/podman run --name etcd \
+          --env-file /etc/etcd/etcd.env \
+          --network host \
+          --volume /var/lib/etcd:/var/lib/etcd:rw,Z \
+          --volume /etc/ssl/etcd:/etc/ssl/certs:ro,Z \
+          $${ETCD_IMAGE}
+        ExecStop=/usr/bin/podman stop etcd
+        Restart=on-failure
+        RestartSec=10s
+        TimeoutStartSec=0
+        LimitNOFILE=40000
+        [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:v1.21.1
+        ExecStartPre=/bin/mkdir -p /etc/cni/net.d
+        ExecStartPre=/bin/mkdir -p /etc/kubernetes/manifests
+        ExecStartPre=/bin/mkdir -p /opt/cni/bin
+        ExecStartPre=/bin/mkdir -p /var/lib/calico
+        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/cni/net.d:/etc/cni/net.d:ro,z \
+          --volume /etc/kubernetes:/etc/kubernetes:ro,z \
+          --volume /usr/lib/os-release:/etc/os-release:ro \
+          --volume /lib/modules:/lib/modules:ro \
+          --volume /run:/run \
+          --volume /sys/fs/cgroup:/sys/fs/cgroup \
+          --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} \
+          --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/pki:/etc/kubernetes/pki:ro,z \
+            --volume /opt/bootstrap/assets:/assets:ro,Z \
+            --volume /opt/bootstrap/apply:/apply:ro,Z \
+            --entrypoint=/apply \
+            quay.io/poseidon/kubelet:v1.21.1
+        ExecStartPost=/bin/touch /opt/bootstrap/bootstrap.done
+        ExecStartPost=-/usr/bin/podman stop bootstrap
+storage:
+  directories:
+    - path: /var/lib/etcd
+      mode: 0700
+    - path: /etc/kubernetes
+    - path: /opt/bootstrap
+  files:
+    - 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/pki
+          mv tls/etcd/{peer*,server*} /etc/ssl/etcd/etcd/
+          mv tls/etcd/etcd-client* /etc/kubernetes/pki/
+          chown -R etcd:etcd /etc/ssl/etcd
+          chmod -R 500 /etc/ssl/etcd
+          mv auth/* /etc/kubernetes/pki/
+          mv tls/k8s/* /etc/kubernetes/pki/
+          mkdir -p /etc/kubernetes/manifests
+          mv static-manifests/* /etc/kubernetes/manifests/
+          mkdir -p /opt/bootstrap/assets
+          mv manifests /opt/bootstrap/assets/manifests
+          mv manifests-networking/* /opt/bootstrap/assets/manifests/
+          rm -rf assets auth static-manifests tls manifests-networking
+          chcon -R -u system_u -t container_file_t /etc/kubernetes/pki
+    - path: /opt/bootstrap/apply
+      mode: 0544
+      contents:
+        inline: |
+          #!/bin/bash -e
+          export KUBECONFIG=/etc/kubernetes/pki/admin.conf
+          until kubectl version; do
+            echo "Waiting for static pod control plane"
+            sleep 5
+          done
+          until kubectl apply -f /assets/manifests -R; do
+             echo "Retry applying manifests"
+             sleep 5
+          done
+    - path: /etc/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: |
+          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

@@ -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
@@ -94,18 +96,28 @@ resource "azurerm_lb_rule" "ingress-https" {
   probe_id                = azurerm_lb_probe.ingress.id
 }
 
-# Address pool of controllers
+# Worker outbound TCP/UDP SNAT
-resource "azurerm_lb_backend_address_pool" "controller" {
+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" {
   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
 }

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

@@ -1,5 +1,6 @@
 output "kubeconfig-admin" {
-  value = module.bootstrap.kubeconfig-admin
+  value     = module.bootstrap.kubeconfig-admin
+  sensitive = true
 }
 
 # Outputs for Kubernetes Ingress
@@ -32,7 +33,8 @@ output "security_group_id" {
 }
 
 output "kubeconfig" {
-  value = module.bootstrap.kubeconfig-kubelet
+  value     = module.bootstrap.kubeconfig-kubelet
+  sensitive = true
 }
 
 # Outputs for custom firewalling
@@ -57,3 +59,11 @@ output "backend_address_pool_id" {
   description = "ID of the worker backend address pool"
   value       = azurerm_lb_backend_address_pool.worker.id
 }
+
+# Outputs for debug
+
+output "assets_dist" {
+  value     = module.bootstrap.assets_dist
+  sensitive = true
+}
+