mirror of
https://github.com/samber/awesome-prometheus-alerts.git
synced 2026-06-21 00:47:18 +08:00
Publish
This commit is contained in:
samber
parent
7fa11bf6cc
commit
6ee065c636
1 changed files with 20 additions and 20 deletions
40
dist/rules/kubernetes/kubestate-exporter.yml
vendored
40
dist/rules/kubernetes/kubestate-exporter.yml
vendored
|
|
@ -10,7 +10,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Node not ready (instance {{ $labels.instance }})
|
||||
summary: Kubernetes Node ready (node {{ $labels.node }})
|
||||
description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesNodeMemoryPressure
|
||||
|
|
@ -19,7 +19,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Node memory pressure (instance {{ $labels.instance }})
|
||||
summary: Kubernetes memory pressure (node {{ $labels.node }})
|
||||
description: "Node {{ $labels.node }} has MemoryPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesNodeDiskPressure
|
||||
|
|
@ -28,7 +28,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Node disk pressure (instance {{ $labels.instance }})
|
||||
summary: Kubernetes disk pressure (node {{ $labels.node }})
|
||||
description: "Node {{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesNodeNetworkUnavailable
|
||||
|
|
@ -55,7 +55,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes Container oom killer (instance {{ $labels.instance }})
|
||||
summary: Kubernetes container oom killer ({{ $labels.namespace }}/{{ $labels.pod }}:{{ $labels.container }})
|
||||
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesJobFailed
|
||||
|
|
@ -64,7 +64,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes Job failed (instance {{ $labels.instance }})
|
||||
summary: Kubernetes Job failed ({{ $labels.namespace }}/{{ $labels.job_name }})
|
||||
description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesCronjobSuspended
|
||||
|
|
@ -73,7 +73,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes CronJob suspended (instance {{ $labels.instance }})
|
||||
summary: Kubernetes CronJob suspended ({{ $labels.namespace }}/{{ $labels.cronjob }})
|
||||
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesPersistentvolumeclaimPending
|
||||
|
|
@ -82,7 +82,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})
|
||||
summary: Kubernetes PersistentVolumeClaim pending ({{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }})
|
||||
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesVolumeOutOfDiskSpace
|
||||
|
|
@ -109,7 +109,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
|
||||
summary: Kubernetes PersistentVolumeClaim pending ({{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }})
|
||||
description: "Persistent volume {{ $labels.persistentvolume }} is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetDown
|
||||
|
|
@ -118,7 +118,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet down (instance {{ $labels.instance }})
|
||||
summary: Kubernetes StatefulSet down ({{ $labels.namespace }}/{{ $labels.statefulset }})
|
||||
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesHpaScaleInability
|
||||
|
|
@ -163,7 +163,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
|
||||
summary: Kubernetes Pod not healthy ({{ $labels.namespace }}/{{ $labels.pod }})
|
||||
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-running state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesPodCrashLooping
|
||||
|
|
@ -172,7 +172,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
|
||||
summary: Kubernetes pod crash looping ({{ $labels.namespace }}/{{ $labels.pod }})
|
||||
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesReplicasetReplicasMismatch
|
||||
|
|
@ -181,7 +181,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes ReplicaSet replicas mismatch (instance {{ $labels.instance }})
|
||||
summary: Kubernetes ReplicasSet mismatch ({{ $labels.namespace }}/{{ $labels.replicaset }})
|
||||
description: "ReplicaSet {{ $labels.namespace }}/{{ $labels.replicaset }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDeploymentReplicasMismatch
|
||||
|
|
@ -190,7 +190,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})
|
||||
summary: Kubernetes Deployment replicas mismatch ({{ $labels.namespace }}/{{ $labels.deployment }})
|
||||
description: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetReplicasMismatch
|
||||
|
|
@ -208,7 +208,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})
|
||||
summary: Kubernetes Deployment generation mismatch ({{ $labels.namespace }}/{{ $labels.deployment }})
|
||||
description: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetGenerationMismatch
|
||||
|
|
@ -217,7 +217,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})
|
||||
summary: Kubernetes StatefulSet generation mismatch ({{ $labels.namespace }}/{{ $labels.statefulset }})
|
||||
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesStatefulsetUpdateNotRolledOut
|
||||
|
|
@ -226,7 +226,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})
|
||||
summary: Kubernetes StatefulSet update not rolled out ({{ $labels.namespace }}/{{ $labels.statefulset }})
|
||||
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDaemonsetRolloutStuck
|
||||
|
|
@ -235,7 +235,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})
|
||||
summary: Kubernetes DaemonSet rollout stuck ({{ $labels.namespace }}/{{ $labels.daemonset }})
|
||||
description: "Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesDaemonsetMisscheduled
|
||||
|
|
@ -244,7 +244,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})
|
||||
summary: Kubernetes DaemonSet misscheduled ({{ $labels.namespace }}/{{ $labels.daemonset }})
|
||||
description: "Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesCronjobTooLong
|
||||
|
|
@ -253,7 +253,7 @@ groups:
|
|||
labels:
|
||||
severity: warning
|
||||
annotations:
|
||||
summary: Kubernetes CronJob too long (instance {{ $labels.instance }})
|
||||
summary: Kubernetes CronJob too long ({{ $labels.namespace }}/{{ $labels.cronjob }})
|
||||
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesJobSlowCompletion
|
||||
|
|
@ -262,7 +262,7 @@ groups:
|
|||
labels:
|
||||
severity: critical
|
||||
annotations:
|
||||
summary: Kubernetes Job slow completion (instance {{ $labels.instance }})
|
||||
summary: Kubernetes job slow completion ({{ $labels.namespace }}/{{ $labels.job_name }})
|
||||
description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
||||
|
||||
- alert: KubernetesApiServerErrors
|
||||
|
|
|
|||
Loading…
Reference in a new issue