-
Notifications
You must be signed in to change notification settings - Fork 1
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
feat: detect frequently restarting pods (#71)
* feat: detect frequently restarting pods * chore: add test case for high restarts but a long time ago * fix: time limit of restarts
- Loading branch information
1 parent
921c352
commit 9680abe
Showing
4 changed files
with
356 additions
and
12 deletions.
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
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
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 +1,170 @@ | ||
| apiVersion: v1 | ||
| kind: Pod | ||
| metadata: | ||
| uid: ba54f218-3435-464c-9f37-75ac7d76104a | ||
| name: config-db-5867b6596f-gs79g | ||
| labels: | ||
| control-plane: config-db | ||
| pod-template-hash: 5867b6596f | ||
| app.kubernetes.io/name: config-db | ||
| app.kubernetes.io/instance: mission-control | ||
| namespace: mission-control | ||
| generateName: config-db-5867b6596f- | ||
| ownerReferences: | ||
| - uid: 00427427-8dee-4003-bd4e-496b0cc275d1 | ||
| kind: ReplicaSet | ||
| name: config-db-5867b6596f | ||
| apiVersion: apps/v1 | ||
| controller: true | ||
| blockOwnerDeletion: true | ||
| creationTimestamp: 2024-07-16T13:31:23Z | ||
| spec: | ||
| volumes: | ||
| - name: aws-iam-token | ||
| projected: | ||
| sources: | ||
| - serviceAccountToken: | ||
| path: token | ||
| audience: sts.amazonaws.com | ||
| expirationSeconds: 86400 | ||
| defaultMode: 420 | ||
| - name: kube-api-access-7jmn6 | ||
| projected: | ||
| sources: | ||
| - serviceAccountToken: | ||
| path: token | ||
| expirationSeconds: 3607 | ||
| - configMap: | ||
| name: kube-root-ca.crt | ||
| items: | ||
| - key: ca.crt | ||
| path: ca.crt | ||
| - downwardAPI: | ||
| items: | ||
| - path: namespace | ||
| fieldRef: | ||
| fieldPath: metadata.namespace | ||
| apiVersion: v1 | ||
| defaultMode: 420 | ||
| nodeName: ip-10-0-6-40.eu-west-1.compute.internal | ||
| priority: 0 | ||
| dnsPolicy: ClusterFirst | ||
| containers: | ||
| - env: | ||
| - name: DB_URL | ||
| valueFrom: | ||
| secretKeyRef: | ||
| key: DB_URL | ||
| name: incident-commander-postgres | ||
| - name: NAMESPACE | ||
| value: mission-control | ||
| - name: AWS_STS_REGIONAL_ENDPOINTS | ||
| value: regional | ||
| - name: AWS_DEFAULT_REGION | ||
| value: eu-west-1 | ||
| - name: AWS_REGION | ||
| value: eu-west-1 | ||
| - name: AWS_ROLE_ARN | ||
| value: arn:aws:iam::765618022540:role/eksctl-config-db-sa | ||
| - name: AWS_WEB_IDENTITY_TOKEN_FILE | ||
| value: /var/run/secrets/eks.amazonaws.com/serviceaccount/token | ||
| args: | ||
| - operator | ||
| - --disable-postgrest=true | ||
| - --change-retention-days=60 | ||
| - --analysis-retention-days=60 | ||
| - --json-logs | ||
| - --otel-collector-url=grafana-alloy.monitoring:4317 | ||
| - --otel-service-name=config-db | ||
| name: config-db | ||
| image: public.ecr.aws/k4y9r6y5/config-db:v0.0.400 | ||
| command: | ||
| - /app/config-db | ||
| resources: | ||
| limits: | ||
| cpu: 500m | ||
| memory: 4Gi | ||
| requests: | ||
| cpu: 200m | ||
| memory: 1Gi | ||
| volumeMounts: | ||
| - name: kube-api-access-7jmn6 | ||
| readOnly: true | ||
| mountPath: /var/run/secrets/kubernetes.io/serviceaccount | ||
| - name: aws-iam-token | ||
| readOnly: true | ||
| mountPath: /var/run/secrets/eks.amazonaws.com/serviceaccount | ||
| livenessProbe: | ||
| httpGet: | ||
| path: /live | ||
| port: 8080 | ||
| scheme: HTTP | ||
| periodSeconds: 10 | ||
| timeoutSeconds: 1 | ||
| failureThreshold: 3 | ||
| successThreshold: 1 | ||
| readinessProbe: | ||
| httpGet: | ||
| path: /ready | ||
| port: 8080 | ||
| scheme: HTTP | ||
| periodSeconds: 10 | ||
| timeoutSeconds: 1 | ||
| failureThreshold: 3 | ||
| successThreshold: 1 | ||
| imagePullPolicy: IfNotPresent | ||
| terminationMessagePath: /dev/termination-log | ||
| terminationMessagePolicy: File | ||
| tolerations: | ||
| - key: node.kubernetes.io/not-ready | ||
| effect: NoExecute | ||
| operator: Exists | ||
| tolerationSeconds: 300 | ||
| - key: node.kubernetes.io/unreachable | ||
| effect: NoExecute | ||
| operator: Exists | ||
| tolerationSeconds: 300 | ||
| restartPolicy: Always | ||
| schedulerName: default-scheduler | ||
| serviceAccount: config-db-sa | ||
| securityContext: | ||
| fsGroup: 1000 | ||
| preemptionPolicy: PreemptLowerPriority | ||
| enableServiceLinks: true | ||
| serviceAccountName: config-db-sa | ||
| terminationGracePeriodSeconds: 30 | ||
| status: | ||
| phase: Running | ||
| podIP: 10.0.6.38 | ||
| hostIP: 10.0.6.40 | ||
| podIPs: | ||
| - ip: 10.0.6.38 | ||
| qosClass: Burstable | ||
| startTime: 2024-07-16T13:31:23Z | ||
| conditions: | ||
| - type: Initialized | ||
| status: "True" | ||
| - type: Ready | ||
| status: "True" | ||
| - type: ContainersReady | ||
| status: "True" | ||
| - type: PodScheduled | ||
| status: "True" | ||
| containerStatuses: | ||
| - name: config-db | ||
| image: public.ecr.aws/k4y9r6y5/config-db:v0.0.400 | ||
| ready: true | ||
| state: | ||
| running: | ||
| startedAt: 2024-07-17T14:29:52Z | ||
| imageID: public.ecr.aws/k4y9r6y5/config-db@sha256:b8803113097931662bda448b53c6ca256957957d74d5e8fd1fc442cec197b025 | ||
| started: true | ||
| lastState: | ||
| terminated: | ||
| reason: OOMKilled | ||
| exitCode: 137 | ||
| startedAt: 2024-07-17T14:13:28Z | ||
| finishedAt: 2024-07-17T14:29:51Z | ||
| containerID: containerd://ee5467962528e4a836dfb48cf9f23d7d547eb7e17cb0e96b9ebf698b05d04420 | ||
| containerID: containerd://68dab40e5ad9d6a66477dd2d388e2d7bf37607743b48c0aa454a623d4fa7f7a7 | ||
| restartCount: 101 |
Oops, something went wrong.