-
Notifications
You must be signed in to change notification settings - Fork 26
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
* adding helm chart Signed-off-by: ssundaresha2 <sandeep_sundaresha@intuit.com> * Templatize image tag image tag is templatized. Signed-off-by: ssundaresha2 <sandeep_sundaresha@intuit.com> * Updating cluster role for pod-reaper Signed-off-by: ssundaresha2 <sandeep_sundaresha@intuit.com> * Adding missing conditions for nodereaper and pdbreaper Signed-off-by: ssundaresha2 <sandeep_sundaresha@intuit.com> Co-authored-by: ssundaresha2 <sandeep_sundaresha@intuit.com>
- Loading branch information
1 parent
fc4eb61
commit 7a30831
Showing
11 changed files
with
354 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| # Patterns to ignore when building packages. | ||
| # This supports shell glob matching, relative path matching, and | ||
| # negation (prefixed with !). Only one pattern per line. | ||
| .DS_Store | ||
| # Common VCS dirs | ||
| .git/ | ||
| .gitignore | ||
| .bzr/ | ||
| .bzrignore | ||
| .hg/ | ||
| .hgignore | ||
| .svn/ | ||
| # Common backup files | ||
| *.swp | ||
| *.bak | ||
| *.tmp | ||
| *.orig | ||
| *~ | ||
| # Various IDEs | ||
| .project | ||
| .idea/ | ||
| *.tmproj | ||
| .vscode/ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,6 @@ | ||
| apiVersion: v2 | ||
| name: governor | ||
| description: A Helm chart for governor. https://github.com/keikoproj/governor | ||
| type: application | ||
| version: 0.1.0 | ||
| appVersion: "0.3.0-aplha" |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,9 @@ | ||
| {{- define "image.version" }} | ||
| {{- if .Values.reaper.imageVersion }} | ||
| {{ .Values.reaper.imageVersion }} | ||
| {{- else if (eq .Chart.AppVersion "0.3.0-aplha") }} | ||
| 0.3.0 | ||
| {{- else }} | ||
| latest | ||
| {{- end }} | ||
| {{- end }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,53 @@ | ||
| {{ if .Values.reaper.podreaper }} | ||
| kind: ClusterRole | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| metadata: | ||
| name: pod-reaper | ||
| rules: | ||
| - apiGroups: [""] | ||
| resources: ["pods"] | ||
| verbs: ["get", "delete", "list"] | ||
| - apiGroups: [""] | ||
| resources: ["namespaces"] | ||
| verbs: ["list"] | ||
| --- | ||
| {{ end }} | ||
| {{ if .Values.reaper.pdbreaper }} | ||
| kind: ClusterRole | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| metadata: | ||
| name: pdb-reaper | ||
| rules: | ||
| - apiGroups: [""] | ||
| resources: ["pods"] | ||
| verbs: ["list"] | ||
| - apiGroups: [""] | ||
| resources: ["events"] | ||
| verbs: ["create"] | ||
| - apiGroups: ["policy"] | ||
| resources: ["poddisruptionbudgets"] | ||
| verbs: ["list", "delete"] | ||
| --- | ||
| {{ end }} | ||
| {{ if .Values.reaper.nodereaper }} | ||
| kind: ClusterRole | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| metadata: | ||
| name: node-reaper | ||
| rules: | ||
| - apiGroups: [""] | ||
| resources: ["nodes", "pods"] | ||
| verbs: ["get", "list", "patch"] | ||
| - apiGroups: [""] | ||
| resources: ["events"] | ||
| verbs: ["get", "list", "create"] | ||
| - apiGroups: [""] | ||
| resources: ["pods/eviction"] | ||
| verbs: ["create"] | ||
| - apiGroups: ["batch"] | ||
| resources: ["cronjobs"] | ||
| verbs: ["get", "patch"] | ||
| - apiGroups: ["extensions", "apps"] | ||
| resources: ["daemonsets"] | ||
| verbs: ["get"] | ||
| {{ end }} |
44 changes: 44 additions & 0 deletions
44
examples/helm-chart/governor/templates/clusterrolebinding.yaml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,44 @@ | ||
| {{ if .Values.reaper.podreaper }} | ||
| kind: ClusterRoleBinding | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| metadata: | ||
| name: pod-reaper | ||
| subjects: | ||
| - kind: ServiceAccount | ||
| name: pod-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| roleRef: | ||
| kind: ClusterRole | ||
| name: pod-reaper | ||
| apiGroup: rbac.authorization.k8s.io | ||
| --- | ||
| {{ end }} | ||
| {{ if .Values.reaper.pdbreaper }} | ||
| kind: ClusterRoleBinding | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| metadata: | ||
| name: pdb-reaper | ||
| subjects: | ||
| - kind: ServiceAccount | ||
| name: pdb-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| roleRef: | ||
| kind: ClusterRole | ||
| name: pdb-reaper | ||
| apiGroup: rbac.authorization.k8s.io | ||
| --- | ||
| {{ end }} | ||
| {{ if .Values.reaper.nodereaper }} | ||
| kind: ClusterRoleBinding | ||
| apiVersion: rbac.authorization.k8s.io/v1 | ||
| metadata: | ||
| name: node-reaper | ||
| subjects: | ||
| - kind: ServiceAccount | ||
| name: node-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| roleRef: | ||
| kind: ClusterRole | ||
| name: node-reaper | ||
| apiGroup: rbac.authorization.k8s.io | ||
| {{ end }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,62 @@ | ||
| {{- if .Values.reaper.nodereaper }} | ||
| apiVersion: batch/v1 | ||
| kind: CronJob | ||
| metadata: | ||
| name: node-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| spec: | ||
| schedule: "{{ .Values.reaper.nodereaper.schedule }}" | ||
| failedJobsHistoryLimit: {{ .Values.reaper.nodereaper.failedJobsHistoryLimit }} | ||
| successfulJobsHistoryLimit: {{ .Values.reaper.nodereaper.successfulJobsHistoryLimit }} | ||
| # Disallow concurrent executions | ||
| concurrencyPolicy: {{ .Values.reaper.nodereaper.concurrencyPolicy }} | ||
| startingDeadlineSeconds: {{ .Values.reaper.nodereaper.startingDeadlineSeconds }} | ||
| jobTemplate: | ||
| spec: | ||
| # Terminate long running pods | ||
| activeDeadlineSeconds: {{ .Values.reaper.nodereaper.activeDeadlineSeconds }} | ||
| backoffLimit: 0 | ||
| template: | ||
| spec: | ||
| serviceAccountName: node-reaper | ||
| restartPolicy: Never | ||
| containers: | ||
| - name: node-reaper | ||
| env: | ||
| - name: POD_NAME | ||
| valueFrom: | ||
| fieldRef: | ||
| fieldPath: metadata.name | ||
| - name: POD_NAMESPACE | ||
| valueFrom: | ||
| fieldRef: | ||
| fieldPath: metadata.namespace | ||
| # Expose self nodeName as NODE_NAME environment variable - required for reapOld | ||
| - name: NODE_NAME | ||
| valueFrom: | ||
| fieldRef: | ||
| fieldPath: spec.nodeName | ||
| image: keikoproj/governor:{{- include "image.version" . | trim}} | ||
| args: | ||
| - governor | ||
| - reap | ||
| - node | ||
| - --dry-run={{ .Values.reaper.nodereaper.dryrun }} | ||
| - --region={{ .Values.reaper.nodereaper.region }} | ||
| - --reap-after={{ .Values.reaper.nodereaper.reapafter }} | ||
| - --soft-reap={{ .Values.reaper.nodereaper.softreap }} | ||
| - --reap-unknown={{ .Values.reaper.nodereaper.reapunknown }} | ||
| - --reap-unready={{ .Values.reaper.nodereaper.reapunready }} | ||
| - --reap-throttle={{ .Values.reaper.nodereaper.reapthreshold }} | ||
| - --reap-ghost={{ .Values.reaper.nodereaper.reapghost }} | ||
| - --reap-unjoined={{ .Values.reaper.nodereaper.reapunjoined }} | ||
| - --reap-unjoined-threshold-minutes={{ .Values.reaper.nodereaper.reapunjoinedthreshold }} | ||
| - --reap-unjoined-tag-key={{ .Values.reaper.nodereaper.reapunjoinedkey }} | ||
| - --reap-unjoined-tag-value={{ .Values.reaper.nodereaper.reapunjoinedtagvalue }} | ||
| {{- if .Values.reaper.nodereaper.reapold }} | ||
| - --reap-old | ||
| - --reap-old-threshold-minutes={{ .Values.reaper.nodereaper.reapoldthreshold }} | ||
| - --reap-old-throttle={{ .Values.reaper.nodereaper.reapoldthrottle }} | ||
| {{- end }} | ||
| - --max-kill-nodes={{ .Values.reaper.nodereaper.maxkillnodes }} | ||
| {{- end }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| {{- if .Values.reaper.pdbreaper }} | ||
| apiVersion: batch/v1 | ||
| kind: CronJob | ||
| metadata: | ||
| name: pdb-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| spec: | ||
| # Scan every 10 minutes | ||
| schedule: "{{ .Values.reaper.pdbreaper.schedule }}" | ||
| failedJobsHistoryLimit: {{ .Values.reaper.pdbreaper.failedJobsHistoryLimit }} | ||
| successfulJobsHistoryLimit: {{ .Values.reaper.pdbreaper.successfulJobsHistoryLimit }} | ||
| # Disallow concurrent executions | ||
| concurrencyPolicy: {{ .Values.reaper.pdbreaper.concurrencyPolicy }} | ||
| startingDeadlineSeconds: {{ .Values.reaper.pdbreaper.startingDeadlineSeconds }} | ||
| jobTemplate: | ||
| spec: | ||
| # Terminate long running pods | ||
| activeDeadlineSeconds: {{ .Values.reaper.pdbreaper.activeDeadlineSeconds }} | ||
| backoffLimit: 0 | ||
| template: | ||
| spec: | ||
| serviceAccountName: pdb-reaper | ||
| restartPolicy: Never | ||
| containers: | ||
| - name: pdb-reaper | ||
| image: keikoproj/governor:{{- include "image.version" . | trim}} | ||
| args: | ||
| - governor | ||
| - reap | ||
| - pdb | ||
| # Reap PDBs blocking when there are pods in crashloop backoff with N > 3 restarts | ||
| - --reap-crashloop={{ .Values.reaper.pdbreaper.reapcrashloop }} | ||
| {{- end }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,33 @@ | ||
| {{ if .Values.reaper.podreaper }} | ||
| apiVersion: batch/v1 | ||
| kind: CronJob | ||
| metadata: | ||
| name: pod-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| spec: | ||
| # Scan every 10 minutes | ||
| schedule: "{{ .Values.reaper.podreaper.schedule }}" | ||
| failedJobsHistoryLimit: {{ .Values.reaper.podreaper.failedJobsHistoryLimit }} | ||
| successfulJobsHistoryLimit: {{ .Values.reaper.podreaper.successfulJobsHistoryLimit }} | ||
| # Disallow concurrent executions | ||
| concurrencyPolicy: Forbid | ||
| startingDeadlineSeconds: {{ .Values.reaper.podreaper.startingDeadlineSeconds }} | ||
| jobTemplate: | ||
| spec: | ||
| # Terminate long running pods | ||
| activeDeadlineSeconds: {{ .Values.reaper.podreaper.activeDeadlineSeconds }} | ||
| backoffLimit: 0 | ||
| template: | ||
| spec: | ||
| serviceAccountName: pod-reaper | ||
| restartPolicy: Never | ||
| containers: | ||
| - name: pod-reaper | ||
| image: keikoproj/governor:{{- include "image.version" . | trim}} | ||
| args: | ||
| - governor | ||
| - reap | ||
| - pod | ||
| - --reap-after={{ .Values.reaper.podreaper.reapafter }} | ||
| - --soft-reap={{ .Values.reaper.podreaper.softreap }} | ||
| {{ end }} |
23 changes: 23 additions & 0 deletions
23
examples/helm-chart/governor/templates/serviceAccount.yaml
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,23 @@ | ||
| {{ if .Values.reaper.podreaper }} | ||
| apiVersion: v1 | ||
| kind: ServiceAccount | ||
| metadata: | ||
| name: pod-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| --- | ||
| {{ end }} | ||
| {{ if .Values.reaper.pdbreaper }} | ||
| apiVersion: v1 | ||
| kind: ServiceAccount | ||
| metadata: | ||
| name: pdb-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| --- | ||
| {{ end }} | ||
| {{ if .Values.reaper.nodereaper }} | ||
| apiVersion: v1 | ||
| kind: ServiceAccount | ||
| metadata: | ||
| name: node-reaper | ||
| namespace: {{ .Release.Namespace }} | ||
| {{ end }} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,64 @@ | ||
| # Default values for governor. | ||
| # This is a YAML-formatted file. | ||
| # Declare variables to be passed into your templates. | ||
| reaper: | ||
| # The image version is derived from the app version. However, if you wish to have a different one, it can be overridden here | ||
| imageVersion: | ||
| podreaper: | ||
| schedule: "*/10 * * * *" | ||
| failedJobsHistoryLimit: 3 | ||
| successfulJobsHistoryLimit: 3 | ||
| startingDeadlineSeconds: 900 | ||
| activeDeadlineSeconds: 1800 | ||
| #Duration (in minutes) in Termination after which a pod is considered reapable | ||
| reapafter: 10 | ||
| #Only reap pods without containers running | ||
| softreap: true | ||
| pdbreaper: | ||
| schedule: "*/10 * * * *" | ||
| failedJobsHistoryLimit: 3 | ||
| successfulJobsHistoryLimit: 3 | ||
| concurrencyPolicy: Forbid | ||
| startingDeadlineSeconds: 900 | ||
| # terminate long running pods | ||
| activeDeadlineSeconds: 1800 | ||
| # Reap PDBs blocking when there are pods in crashloop backoff with N > 3 restarts | ||
| reapcrashloop: true | ||
| nodereaper: | ||
| schedule: "*/10 * * * *" | ||
| failedJobsHistoryLimit: 3 | ||
| successfulJobsHistoryLimit: 3 | ||
| concurrencyPolicy: Forbid | ||
| startingDeadlineSeconds: 900 | ||
| activeDeadlineSeconds: 1800 | ||
| dryrun: true | ||
| # Only operate in us-west-2 | ||
| region: west-2 | ||
| # Consider nodes reapable after 10 mintues in a bad state | ||
| reapafter: 10 | ||
| # Only reap nodes without active pods | ||
| softreap: true | ||
| # Unknown nodes are reapable | ||
| reapunknown: true | ||
| # NotReady nodes are reapable | ||
| reapunready: true | ||
| # Wait 180 seconds after each unhealthy node termination | ||
| reapthreshold: 180 | ||
| # Nodes with an invalid/incorrect instance-id are reapable | ||
| reapghost: true | ||
| # Nodes which fail to join the cluster are reapable | ||
| reapunjoined: true | ||
| # Nodes should join the cluster within 15 mintues | ||
| reapunjoinedthreshold: 15 | ||
| # Tag key and value used to identify an unjoined node, this is an EC2 tag that should | ||
| # exist on the instances as they are launched (part of ASG), be careful not to get this | ||
| # wrong as it can cause termination of other instances if they are not detected as nodes | ||
| # in the cluster | ||
| reapunjoinedkey: KubernetesCluster | ||
| reapunjoinedtagvalue: my-cluster-name | ||
| # Old nodes are reapable | ||
| reapold: true | ||
| reapoldthreshold: 43200 | ||
| reapoldthrottle: 3600 | ||
| # Kill a maximum of 1 nodes per run considering throttle wait times | ||
| maxkillnodes: 1 |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters