XeLabs/awesome-prometheus-alerts
2
0
Fork 0
mirror of https://github.com/samber/awesome-prometheus-alerts.git synced 2026-06-21 00:47:18 +08:00
Code Issues Projects Releases Packages Wiki Activity

Publish

Browse source
This commit is contained in:
samber 2023-08-19 22:41:12 +00:00
parent 6b1685261d
commit 4279dedb52
1 changed files with 32 additions and 33 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

65
dist/rules/kubernetes/kubestate-exporter.yml vendored
View file

@ -10,7 +10,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes Node not ready (node {{ $labels.node }})
summary: Kubernetes Node not ready (instance {{ $labels.instance }})
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 (node {{ $labels.node }})
summary: Kubernetes Node memory pressure (instance {{ $labels.instance }})
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 (node {{ $labels.node }})
summary: Kubernetes Node disk pressure (instance {{ $labels.instance }})
description: "Node {{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesNodeNetworkUnavailable
@ -37,7 +37,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes Node network unavailable (node {{ $labels.node }})
summary: Kubernetes Node network unavailable (instance {{ $labels.instance }})
description: "Node {{ $labels.node }} has NetworkUnavailable condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesNodeOutOfPodCapacity
@ -46,16 +46,16 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes Node out of pod capacity (node {{ $labels.node }})
summary: Kubernetes Node out of pod capacity (instance {{ $labels.instance }})
description: "Node {{ $labels.node }} is out of pod capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesContainerOomKilled
- alert: KubernetesContainerOomKiller
expr: '(kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1'
for: 0m
labels:
severity: warning
annotations:
summary: Kubernetes Container oom killed (pod {{ $labels.pod }})
summary: Kubernetes Container oom killer (instance {{ $labels.instance }})
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 (job_name {{ $labels.job_name }})
summary: Kubernetes Job failed (instance {{ $labels.instance }})
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 (cronjob {{ $labels.cronjob }})
summary: Kubernetes CronJob suspended (instance {{ $labels.instance }})
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 (pvc {{ $labels.persistentvolumeclaim }})
summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesVolumeOutOfDiskSpace
@ -91,8 +91,8 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes Volume out of disk space (pvc {{ $labels.persistentvolumeclaim }})
description: "Volume under {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
summary: Kubernetes Volume out of disk space (instance {{ $labels.instance }})
description: "Volume is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesVolumeFullInFourDays
expr: 'predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0'
@ -100,7 +100,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes Volume full in four days (pvc {{ $labels.persistentvolumeclaim }})
summary: Kubernetes Volume full in four days (instance {{ $labels.instance }})
description: "Volume under {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPersistentvolumeError
@ -109,7 +109,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes PersistentVolume error (pv {{ $labels.persistentvolume }})
summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
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 (statefulset {{ $labels.statefulset }})
summary: Kubernetes StatefulSet down (instance {{ $labels.instance }})
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaScaleInability
@ -127,7 +127,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes HPA scale inability (hpa {{ $labels.horizontalpodautoscaler }})
summary: Kubernetes HPA scale inability (instance {{ $labels.instance }})
description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to scale\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaMetricsUnavailability
@ -136,17 +136,16 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes HPA metrics unavailability (hpa {{ $labels.horizontalpodautoscaler }})
summary: Kubernetes HPA metrics unavailability (instance {{ $labels.instance }})
description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to collect metrics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaScaleMaximum
expr: 'kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas'
for: 2m
labels:
severity: info
annotations:
summary: Kubernetes HPA scale maximum (hpa {{ $labels.horizontalpodautoscaler }})
summary: Kubernetes HPA scale maximum (instance {{ $labels.instance }})
description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesHpaUnderutilized
@ -155,7 +154,7 @@ groups:
labels:
severity: info
annotations:
summary: Kubernetes HPA underutilized (hpa {{ $labels.horizontalpodautoscaler }})
summary: Kubernetes HPA underutilized (instance {{ $labels.instance }})
description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is constantly at minimum replicas for 50% of the time. Potential cost saving here.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesPodNotHealthy
@ -164,7 +163,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes Pod not healthy (pod {{ $labels.pod }})
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
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
@ -173,7 +172,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes pod crash looping (pod {{ $labels.pod }})
summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesReplicasetReplicasMismatch
@ -182,7 +181,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes ReplicaSet replicas mismatch (replicaset {{ $labels.replicaset }})
summary: Kubernetes ReplicaSet replicas mismatch (instance {{ $labels.instance }})
description: "ReplicaSet {{ $labels.namespace }}/{{ $labels.replicaset }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDeploymentReplicasMismatch
@ -191,7 +190,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes Deployment replicas mismatch (deployment {{ $labels.deployment }})
summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})
description: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetReplicasMismatch
@ -200,8 +199,8 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes StatefulSet replicas mismatch (statefulset {{ $labels.statefulset }})
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
summary: Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})
description: "StatefulSet does not match the expected number of replicas.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDeploymentGenerationMismatch
expr: 'kube_deployment_status_observed_generation != kube_deployment_metadata_generation'
@ -209,7 +208,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes Deployment generation mismatch (deployment {{ $labels.deployment }})
summary: Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})
description: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetGenerationMismatch
@ -218,7 +217,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes StatefulSet generation mismatch (statefulset {{ $labels.statefulset }})
summary: Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesStatefulsetUpdateNotRolledOut
@ -227,7 +226,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes StatefulSet update not rolled out (statefulset {{ $labels.statefulset }})
summary: Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})
description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDaemonsetRolloutStuck
@ -236,7 +235,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes DaemonSet rollout stuck (daemonset {{ $labels.daemonset }})
summary: Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})
description: "Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesDaemonsetMisscheduled
@ -245,7 +244,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes DaemonSet misscheduled (daemonset {{ $labels.daemonset }})
summary: Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})
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
@ -254,7 +253,7 @@ groups:
labels:
severity: warning
annotations:
summary: Kubernetes CronJob too long (cronjob {{ $labels.cronjob }})
summary: Kubernetes CronJob too long (instance {{ $labels.instance }})
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesJobSlowCompletion
@ -263,7 +262,7 @@ groups:
labels:
severity: critical
annotations:
summary: Kubernetes Job slow completion (job_name {{ $labels.job_name }})
summary: Kubernetes Job slow completion (instance {{ $labels.instance }})
description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
- alert: KubernetesApiServerErrors