kubernetes

Overview

A set of Grafana dashboards and Prometheus alerts for Kubernetes.

Jsonnet source code is available at github.com/kubernetes-monitoring/kubernetes-mixin

Alerts

Complete list of pregenerated alerts is available here.

kubernetes-apps

KubePodCrashLooping

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping


alert: KubePodCrashLooping
annotations:
  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
  summary: Pod is crash looping.
expr: |
  rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[5m]) * 60 * 5 > 0
for: 15m
labels:
  severity: warning

KubePodNotReady

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready


alert: KubePodNotReady
annotations:
  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
  summary: Pod has been in a non-ready state for more than 15 minutes.
expr: |
  sum by (namespace, pod) (
    max by(namespace, pod) (
      kube_pod_status_phase{job="kube-state-metrics", phase=~"Pending|Unknown"}
    ) * on(namespace, pod) group_left(owner_kind) topk by(namespace, pod) (
      1, max by(namespace, pod, owner_kind) (kube_pod_owner{owner_kind!="Job"})
    )
  ) > 0
for: 15m
labels:
  severity: warning

KubeDeploymentGenerationMismatch

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch


alert: KubeDeploymentGenerationMismatch
annotations:
  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
  summary: Deployment generation mismatch due to possible roll-back
expr: |
  kube_deployment_status_observed_generation{job="kube-state-metrics"}
    !=
  kube_deployment_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
  severity: warning

KubeDeploymentReplicasMismatch

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch


alert: KubeDeploymentReplicasMismatch
annotations:
  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
  summary: Deployment has not matched the expected number of replicas.
expr: |
  (
    kube_deployment_spec_replicas{job="kube-state-metrics"}
      !=
    kube_deployment_status_replicas_available{job="kube-state-metrics"}
  ) and (
    changes(kube_deployment_status_replicas_updated{job="kube-state-metrics"}[5m])
      ==
    0
  )
for: 15m
labels:
  severity: warning

KubeStatefulSetReplicasMismatch

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch


alert: KubeStatefulSetReplicasMismatch
annotations:
  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
  summary: Deployment has not matched the expected number of replicas.
expr: |
  (
    kube_statefulset_status_replicas_ready{job="kube-state-metrics"}
      !=
    kube_statefulset_status_replicas{job="kube-state-metrics"}
  ) and (
    changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m])
      ==
    0
  )
for: 15m
labels:
  severity: warning

KubeStatefulSetGenerationMismatch

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch


alert: KubeStatefulSetGenerationMismatch
annotations:
  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
  summary: StatefulSet generation mismatch due to possible roll-back
expr: |
  kube_statefulset_status_observed_generation{job="kube-state-metrics"}
    !=
  kube_statefulset_metadata_generation{job="kube-state-metrics"}
for: 15m
labels:
  severity: warning

KubeStatefulSetUpdateNotRolledOut

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout


alert: KubeStatefulSetUpdateNotRolledOut
annotations:
  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
  summary: StatefulSet update has not been rolled out.
expr: |
  (
    max without (revision) (
      kube_statefulset_status_current_revision{job="kube-state-metrics"}
        unless
      kube_statefulset_status_update_revision{job="kube-state-metrics"}
    )
      *
    (
      kube_statefulset_replicas{job="kube-state-metrics"}
        !=
      kube_statefulset_status_replicas_updated{job="kube-state-metrics"}
    )
  )  and (
    changes(kube_statefulset_status_replicas_updated{job="kube-state-metrics"}[5m])
      ==
    0
  )
for: 15m
labels:
  severity: warning

KubeDaemonSetRolloutStuck

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck


alert: KubeDaemonSetRolloutStuck
annotations:
  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
  summary: DaemonSet rollout is stuck.
expr: |
  (
    (
      kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"}
       !=
      kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
    ) or (
      kube_daemonset_status_number_misscheduled{job="kube-state-metrics"}
       !=
      0
    ) or (
      kube_daemonset_updated_number_scheduled{job="kube-state-metrics"}
       !=
      kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
    ) or (
      kube_daemonset_status_number_available{job="kube-state-metrics"}
       !=
      kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
    )
  ) and (
    changes(kube_daemonset_updated_number_scheduled{job="kube-state-metrics"}[5m])
      ==
    0
  )
for: 15m
labels:
  severity: warning

KubeContainerWaiting

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontainerwaiting


alert: KubeContainerWaiting
annotations:
  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
  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
for: 1h
labels:
  severity: warning

KubeDaemonSetNotScheduled

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled


alert: KubeDaemonSetNotScheduled
annotations:
  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
  summary: DaemonSet pods are not scheduled.
expr: |
  kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"}
    -
  kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0
for: 10m
labels:
  severity: warning

KubeDaemonSetMisScheduled

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled


alert: KubeDaemonSetMisScheduled
annotations:
  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
  summary: DaemonSet pods are misscheduled.
expr: |
  kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
for: 15m
labels:
  severity: warning

KubeJobCompletion

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion


alert: KubeJobCompletion
annotations:
  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
  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
for: 12h
labels:
  severity: warning

KubeJobFailed

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed


alert: KubeJobFailed
annotations:
  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
  summary: Job failed to complete.
expr: |
  kube_job_failed{job="kube-state-metrics"}  > 0
for: 15m
labels:
  severity: warning

KubeHpaReplicasMismatch

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpareplicasmismatch


alert: KubeHpaReplicasMismatch
annotations:
  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
  summary: HPA has not matched descired number of replicas.
expr: |
  (kube_hpa_status_desired_replicas{job="kube-state-metrics"}
    !=
  kube_hpa_status_current_replicas{job="kube-state-metrics"})
    and
  changes(kube_hpa_status_current_replicas[15m]) == 0
for: 15m
labels:
  severity: warning

KubeHpaMaxedOut

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubehpamaxedout


alert: KubeHpaMaxedOut
annotations:
  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
  summary: HPA is running at max replicas
expr: |
  kube_hpa_status_current_replicas{job="kube-state-metrics"}
    ==
  kube_hpa_spec_max_replicas{job="kube-state-metrics"}
for: 15m
labels:
  severity: warning

kubernetes-resources

KubeCPUOvercommit

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuovercommit


alert: KubeCPUOvercommit
annotations:
  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
  summary: Cluster has overcommitted CPU resource requests.
expr: |
  sum(namespace:kube_pod_container_resource_requests_cpu_cores:sum{})
    /
  sum(kube_node_status_allocatable_cpu_cores)
    >
  (count(kube_node_status_allocatable_cpu_cores)-1) / count(kube_node_status_allocatable_cpu_cores)
for: 5m
labels:
  severity: warning

KubeMemoryOvercommit

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryovercommit


alert: KubeMemoryOvercommit
annotations:
  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-kubememoryovercommit
  summary: Cluster has overcommitted memory resource requests.
expr: |
  sum(namespace:kube_pod_container_resource_requests_memory_bytes:sum{})
    /
  sum(kube_node_status_allocatable_memory_bytes)
    >
  (count(kube_node_status_allocatable_memory_bytes)-1)
    /
  count(kube_node_status_allocatable_memory_bytes)
for: 5m
labels:
  severity: warning

KubeCPUQuotaOvercommit

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecpuquotaovercommit


alert: KubeCPUQuotaOvercommit
annotations:
  description: Cluster has overcommitted CPU resource requests for Namespaces.
  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"})
    /
  sum(kube_node_status_allocatable_cpu_cores)
    > 1.5
for: 5m
labels:
  severity: warning

KubeMemoryQuotaOvercommit

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubememoryquotaovercommit


alert: KubeMemoryQuotaOvercommit
annotations:
  description: Cluster has overcommitted memory resource requests for Namespaces.
  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"})
    /
  sum(kube_node_status_allocatable_memory_bytes{job="node-exporter"})
    > 1.5
for: 5m
labels:
  severity: warning

KubeQuotaAlmostFull

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaalmostfull


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"}
    / ignoring(instance, job, type)
  (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
    > 0.9 < 1
for: 15m
labels:
  severity: info

KubeQuotaFullyUsed

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotafullyused


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"}
    / ignoring(instance, job, type)
  (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
    == 1
for: 15m
labels:
  severity: info

KubeQuotaExceeded

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubequotaexceeded


alert: KubeQuotaExceeded
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-kubequotaexceeded
  summary: Namespace quota has exceeded the limits.
expr: |
  kube_resourcequota{job="kube-state-metrics", type="used"}
    / ignoring(instance, job, type)
  (kube_resourcequota{job="kube-state-metrics", type="hard"} > 0)
    > 1
for: 15m
labels:
  severity: warning

CPUThrottlingHigh

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-cputhrottlinghigh


alert: CPUThrottlingHigh
annotations:
  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
  summary: Processes experience elevated CPU throttling.
expr: |
  sum(increase(container_cpu_cfs_throttled_periods_total{container!="", }[5m])) by (container, pod, namespace)
    /
  sum(increase(container_cpu_cfs_periods_total{}[5m])) by (container, pod, namespace)
    > ( 25 / 100 )
for: 15m
labels:
  severity: info

kubernetes-storage

KubePersistentVolumeFillingUp

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup


alert: KubePersistentVolumeFillingUp
annotations:
  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-kubepersistentvolumefillingup
  summary: PersistentVolume is filling up.
expr: |
  kubelet_volume_stats_available_bytes{job="kubelet"}
    /
  kubelet_volume_stats_capacity_bytes{job="kubelet"}
    < 0.03
for: 1m
labels:
  severity: critical

KubePersistentVolumeFillingUp

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumefillingup


alert: KubePersistentVolumeFillingUp
annotations:
  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-kubepersistentvolumefillingup
  summary: PersistentVolume is filling up.
expr: |
  (
    kubelet_volume_stats_available_bytes{job="kubelet"}
      /
    kubelet_volume_stats_capacity_bytes{job="kubelet"}
  ) < 0.15
  and
  predict_linear(kubelet_volume_stats_available_bytes{job="kubelet"}[6h], 4 * 24 * 3600) < 0
for: 1h
labels:
  severity: warning

KubePersistentVolumeErrors

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepersistentvolumeerrors


alert: KubePersistentVolumeErrors
annotations:
  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
  summary: PersistentVolume is having issues with provisioning.
expr: |
  kube_persistentvolume_status_phase{phase=~"Failed|Pending",job="kube-state-metrics"} > 0
for: 5m
labels:
  severity: critical

kubernetes-system

KubeVersionMismatch

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeversionmismatch


alert: KubeVersionMismatch
annotations:
  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
  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]*).*"))) > 1
for: 15m
labels:
  severity: warning

KubeClientErrors

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclienterrors


alert: KubeClientErrors
annotations:
  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
  summary: Kubernetes API server client is experiencing errors.
expr: |
  (sum(rate(rest_client_requests_total{code=~"5.."}[5m])) by (instance, job)
    /
  sum(rate(rest_client_requests_total[5m])) by (instance, job))
  > 0.01
for: 15m
labels:
  severity: warning

kube-apiserver-slos

KubeAPIErrorBudgetBurn

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn


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)
  and
  sum(apiserver_request:burnrate5m) > (14.40 * 0.01000)
for: 2m
labels:
  long: 1h
  severity: critical
  short: 5m

KubeAPIErrorBudgetBurn

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn


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)
  and
  sum(apiserver_request:burnrate30m) > (6.00 * 0.01000)
for: 15m
labels:
  long: 6h
  severity: critical
  short: 30m

KubeAPIErrorBudgetBurn

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn


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)
  and
  sum(apiserver_request:burnrate2h) > (3.00 * 0.01000)
for: 1h
labels:
  long: 1d
  severity: warning
  short: 2h

KubeAPIErrorBudgetBurn

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapierrorbudgetburn


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)
  and
  sum(apiserver_request:burnrate6h) > (1.00 * 0.01000)
for: 3h
labels:
  long: 3d
  severity: warning
  short: 6h

kubernetes-system-apiserver

KubeClientCertificateExpiration

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration


alert: KubeClientCertificateExpiration
annotations:
  description: A client certificate used to authenticate to the apiserver is expiring
    in less than 7.0 days.
  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="kube-apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 604800
labels:
  severity: warning

KubeClientCertificateExpiration

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeclientcertificateexpiration


alert: KubeClientCertificateExpiration
annotations:
  description: A client certificate used to authenticate to the apiserver is expiring
    in less than 24.0 hours.
  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="kube-apiserver"} > 0 and on(job) histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="kube-apiserver"}[5m]))) < 86400
labels:
  severity: critical

AggregatedAPIErrors

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapierrors


alert: AggregatedAPIErrors
annotations:
  description: An aggregated API {{ $labels.name }}/{{ $labels.namespace }} has reported
    errors. The number of errors have increased for it in the past five minutes. High
    values indicate that the availability of the service changes too often.
  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[5m])) > 2
labels:
  severity: warning

AggregatedAPIDown

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-aggregatedapidown


alert: AggregatedAPIDown
annotations:
  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-aggregatedapidown
  summary: An aggregated API is down.
expr: |
  (1 - max by(name, namespace)(avg_over_time(aggregator_unavailable_apiservice[10m]))) * 100 < 85
for: 5m
labels:
  severity: warning

KubeAPIDown

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeapidown


alert: KubeAPIDown
annotations:
  description: KubeAPI has disappeared from Prometheus target discovery.
  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="kube-apiserver"} == 1)
for: 15m
labels:
  severity: critical

kubernetes-system-kubelet

KubeNodeNotReady

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodenotready


alert: KubeNodeNotReady
annotations:
  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
  summary: Node is not ready.
expr: |
  kube_node_status_condition{job="kube-state-metrics",condition="Ready",status="true"} == 0
for: 15m
labels:
  severity: warning

KubeNodeUnreachable

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodeunreachable


alert: KubeNodeUnreachable
annotations:
  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
  summary: Node is unreachable.
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
for: 15m
labels:
  severity: warning

KubeletTooManyPods

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubelettoomanypods


alert: KubeletTooManyPods
annotations:
  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
  summary: Kubelet is running at capacity.
expr: |
  count by(node) (
    (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"})
  )
  /
  max by(node) (
    kube_node_status_capacity_pods{job="kube-state-metrics"} != 1
  ) > 0.95
for: 15m
labels:
  severity: warning

KubeNodeReadinessFlapping

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubenodereadinessflapping


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
for: 15m
labels:
  severity: warning

KubeletPlegDurationHigh

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletplegdurationhigh


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
for: 5m
labels:
  severity: warning

KubeletPodStartUpLatencyHigh

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletpodstartuplatencyhigh


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
for: 15m
labels:
  severity: warning

KubeletClientCertificateExpiration

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration


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 < 604800
labels:
  severity: warning

KubeletClientCertificateExpiration

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificateexpiration


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 < 86400
labels:
  severity: critical

KubeletServerCertificateExpiration

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration


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 < 604800
labels:
  severity: warning

KubeletServerCertificateExpiration

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificateexpiration


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 < 86400
labels:
  severity: critical

KubeletClientCertificateRenewalErrors

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletclientcertificaterenewalerrors


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
for: 15m
labels:
  severity: warning

KubeletServerCertificateRenewalErrors

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletservercertificaterenewalerrors


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
for: 15m
labels:
  severity: warning

KubeletDown

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeletdown


alert: KubeletDown
annotations:
  description: Kubelet has disappeared from Prometheus target discovery.
  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)
for: 15m
labels:
  severity: critical

kubernetes-system-scheduler

KubeSchedulerDown

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubeschedulerdown


alert: KubeSchedulerDown
annotations:
  description: KubeScheduler has disappeared from Prometheus target discovery.
  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)
for: 15m
labels:
  severity: critical

kubernetes-system-controller-manager

KubeControllerManagerDown

https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecontrollermanagerdown


alert: KubeControllerManagerDown
annotations:
  description: KubeControllerManager has disappeared from Prometheus target discovery.
  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)
for: 15m
labels:
  severity: critical

Recording rules

Complete list of pregenerated recording rules is available here.

kube-apiserver.rules

apiserver_request:burnrate1d

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[1d]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1d]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1d]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1d]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[1d]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[1d]))
labels:
  verb: read
record: apiserver_request:burnrate1d

apiserver_request:burnrate1h

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[1h]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[1h]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[1h]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[1h]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[1h]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[1h]))
labels:
  verb: read
record: apiserver_request:burnrate1h

apiserver_request:burnrate2h

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[2h]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[2h]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[2h]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[2h]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[2h]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[2h]))
labels:
  verb: read
record: apiserver_request:burnrate2h

apiserver_request:burnrate30m

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[30m]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30m]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30m]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30m]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[30m]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[30m]))
labels:
  verb: read
record: apiserver_request:burnrate30m

apiserver_request:burnrate3d

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[3d]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[3d]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[3d]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[3d]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[3d]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[3d]))
labels:
  verb: read
record: apiserver_request:burnrate3d

apiserver_request:burnrate5m

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[5m]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[5m]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[5m]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[5m]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[5m]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[5m]))
labels:
  verb: read
record: apiserver_request:burnrate5m

apiserver_request:burnrate6h

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[6h]))
      -
      (
        (
          sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[6h]))
          or
          vector(0)
        )
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[6h]))
        +
        sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[6h]))
      )
    )
    +
    # errors
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET",code=~"5.."}[6h]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[6h]))
labels:
  verb: read
record: apiserver_request:burnrate6h

apiserver_request:burnrate1d

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1d]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1d]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1d]))
labels:
  verb: write
record: apiserver_request:burnrate1d

apiserver_request:burnrate1h

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[1h]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[1h]))
labels:
  verb: write
record: apiserver_request:burnrate1h

apiserver_request:burnrate2h

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[2h]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[2h]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[2h]))
labels:
  verb: write
record: apiserver_request:burnrate2h

apiserver_request:burnrate30m

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[30m]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[30m]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[30m]))
labels:
  verb: write
record: apiserver_request:burnrate30m

apiserver_request:burnrate3d

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[3d]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[3d]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[3d]))
labels:
  verb: write
record: apiserver_request:burnrate3d

apiserver_request:burnrate5m

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[5m]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[5m]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
  verb: write
record: apiserver_request:burnrate5m

apiserver_request:burnrate6h

expr: |
  (
    (
      # too slow
      sum(rate(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
      -
      sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",le="1"}[6h]))
    )
    +
    sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE",code=~"5.."}[6h]))
  )
  /
  sum(rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[6h]))
labels:
  verb: write
record: apiserver_request:burnrate6h

code_resource:apiserver_request_total:rate5m

expr: |
  sum by (code,resource) (rate(apiserver_request_total{job="kube-apiserver",verb=~"LIST|GET"}[5m]))
labels:
  verb: read
record: code_resource:apiserver_request_total:rate5m

code_resource:apiserver_request_total:rate5m

expr: |
  sum by (code,resource) (rate(apiserver_request_total{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
labels:
  verb: write
record: code_resource:apiserver_request_total:rate5m

cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET"}[5m]))) > 0
labels:
  quantile: "0.99"
  verb: read
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.99, sum by (le, resource) (rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))) > 0
labels:
  quantile: "0.99"
  verb: write
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

cluster:apiserver_request_duration_seconds:mean5m

expr: |
  sum(rate(apiserver_request_duration_seconds_sum{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)
  /
  sum(rate(apiserver_request_duration_seconds_count{subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod)
record: cluster:apiserver_request_duration_seconds:mean5m

cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.99, sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
  quantile: "0.99"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.9, sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
  quantile: "0.9"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.5, sum(rate(apiserver_request_duration_seconds_bucket{job="kube-apiserver",subresource!="log",verb!~"LIST|WATCH|WATCHLIST|DELETECOLLECTION|PROXY|CONNECT"}[5m])) without(instance, pod))
labels:
  quantile: "0.5"
record: cluster_quantile:apiserver_request_duration_seconds:histogram_quantile

kube-apiserver-availability.rules

apiserver_request:availability30d

expr: |
  1 - (
    (
      # write too slow
      sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
      -
      sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
    ) +
    (
      # read too slow
      sum(increase(apiserver_request_duration_seconds_count{verb=~"LIST|GET"}[30d]))
      -
      (
        (
          sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
          or
          vector(0)
        )
        +
        sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
        +
        sum(increase(apiserver_request_duration_seconds_bucket{verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
      )
    ) +
    # errors
    sum(code:apiserver_request_total:increase30d{code=~"5.."} or vector(0))
  )
  /
  sum(code:apiserver_request_total:increase30d)
labels:
  verb: all
record: apiserver_request:availability30d

apiserver_request:availability30d

expr: |
  1 - (
    sum(increase(apiserver_request_duration_seconds_count{job="kube-apiserver",verb=~"LIST|GET"}[30d]))
    -
    (
      # too slow
      (
        sum(increase(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope=~"resource|",le="0.1"}[30d]))
        or
        vector(0)
      )
      +
      sum(increase(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="namespace",le="0.5"}[30d]))
      +
      sum(increase(apiserver_request_duration_seconds_bucket{job="kube-apiserver",verb=~"LIST|GET",scope="cluster",le="5"}[30d]))
    )
    +
    # errors
    sum(code:apiserver_request_total:increase30d{verb="read",code=~"5.."} or vector(0))
  )
  /
  sum(code:apiserver_request_total:increase30d{verb="read"})
labels:
  verb: read
record: apiserver_request:availability30d

apiserver_request:availability30d

expr: |
  1 - (
    (
      # too slow
      sum(increase(apiserver_request_duration_seconds_count{verb=~"POST|PUT|PATCH|DELETE"}[30d]))
      -
      sum(increase(apiserver_request_duration_seconds_bucket{verb=~"POST|PUT|PATCH|DELETE",le="1"}[30d]))
    )
    +
    # errors
    sum(code:apiserver_request_total:increase30d{verb="write",code=~"5.."} or vector(0))
  )
  /
  sum(code:apiserver_request_total:increase30d{verb="write"})
labels:
  verb: write
record: apiserver_request:availability30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="LIST",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="GET",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="POST",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PUT",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PATCH",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="DELETE",code=~"2.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="LIST",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="GET",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="POST",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PUT",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PATCH",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="DELETE",code=~"3.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="LIST",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="GET",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="POST",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PUT",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PATCH",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="DELETE",code=~"4.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="LIST",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="GET",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="POST",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PUT",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="PATCH",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code_verb:apiserver_request_total:increase30d

expr: |
  sum by (code, verb) (increase(apiserver_request_total{job="kube-apiserver",verb="DELETE",code=~"5.."}[30d]))
record: code_verb:apiserver_request_total:increase30d

code:apiserver_request_total:increase30d

expr: |
  sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
labels:
  verb: read
record: code:apiserver_request_total:increase30d

code:apiserver_request_total:increase30d

expr: |
  sum by (code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
labels:
  verb: write
record: code:apiserver_request_total:increase30d

k8s.rules

namespace:container_cpu_usage_seconds_total:sum_rate

expr: |
  sum(rate(container_cpu_usage_seconds_total{job="cadvisor", image!="", container!="POD"}[5m])) by (namespace)
record: namespace:container_cpu_usage_seconds_total:sum_rate

node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate

expr: |
  sum by (cluster, namespace, pod, container) (
    rate(container_cpu_usage_seconds_total{job="cadvisor", image!="", container!="POD"}[5m])
  ) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (
    1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=""})
  )
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_rate

node_namespace_pod_container:container_memory_working_set_bytes

expr: |
  container_memory_working_set_bytes{job="cadvisor", image!=""}
  * on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
    max by(namespace, pod, node) (kube_pod_info{node!=""})
  )
record: node_namespace_pod_container:container_memory_working_set_bytes

node_namespace_pod_container:container_memory_rss

expr: |
  container_memory_rss{job="cadvisor", image!=""}
  * on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
    max by(namespace, pod, node) (kube_pod_info{node!=""})
  )
record: node_namespace_pod_container:container_memory_rss

node_namespace_pod_container:container_memory_cache

expr: |
  container_memory_cache{job="cadvisor", image!=""}
  * on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
    max by(namespace, pod, node) (kube_pod_info{node!=""})
  )
record: node_namespace_pod_container:container_memory_cache

node_namespace_pod_container:container_memory_swap

expr: |
  container_memory_swap{job="cadvisor", image!=""}
  * on (namespace, pod) group_left(node) topk by(namespace, pod) (1,
    max by(namespace, pod, node) (kube_pod_info{node!=""})
  )
record: node_namespace_pod_container:container_memory_swap

namespace:container_memory_usage_bytes:sum

expr: |
  sum(container_memory_usage_bytes{job="cadvisor", image!="", container!="POD"}) by (namespace)
record: namespace:container_memory_usage_bytes:sum

namespace:kube_pod_container_resource_requests_memory_bytes:sum

expr: |
  sum by (namespace) (
      sum by (namespace, pod) (
          max by (namespace, pod, container) (
              kube_pod_container_resource_requests_memory_bytes{job="kube-state-metrics"}
          ) * on(namespace, pod) group_left() max by (namespace, pod) (
              kube_pod_status_phase{phase=~"Pending|Running"} == 1
          )
      )
  )
record: namespace:kube_pod_container_resource_requests_memory_bytes:sum

namespace:kube_pod_container_resource_requests_cpu_cores:sum

expr: |
  sum by (namespace) (
      sum by (namespace, pod) (
          max by (namespace, pod, container) (
              kube_pod_container_resource_requests_cpu_cores{job="kube-state-metrics"}
          ) * on(namespace, pod) group_left() max by (namespace, pod) (
            kube_pod_status_phase{phase=~"Pending|Running"} == 1
          )
      )
  )
record: namespace:kube_pod_container_resource_requests_cpu_cores:sum

namespace_workload_pod:kube_pod_owner:relabel

expr: |
  max by (cluster, namespace, workload, pod) (
    label_replace(
      label_replace(
        kube_pod_owner{job="kube-state-metrics", owner_kind="ReplicaSet"},
        "replicaset", "$1", "owner_name", "(.*)"
      ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (
        1, max by (replicaset, namespace, owner_name) (
          kube_replicaset_owner{job="kube-state-metrics"}
        )
      ),
      "workload", "$1", "owner_name", "(.*)"
    )
  )
labels:
  workload_type: deployment
record: namespace_workload_pod:kube_pod_owner:relabel

namespace_workload_pod:kube_pod_owner:relabel

expr: |
  max by (cluster, namespace, workload, pod) (
    label_replace(
      kube_pod_owner{job="kube-state-metrics", owner_kind="DaemonSet"},
      "workload", "$1", "owner_name", "(.*)"
    )
  )
labels:
  workload_type: daemonset
record: namespace_workload_pod:kube_pod_owner:relabel

namespace_workload_pod:kube_pod_owner:relabel

expr: |
  max by (cluster, namespace, workload, pod) (
    label_replace(
      kube_pod_owner{job="kube-state-metrics", owner_kind="StatefulSet"},
      "workload", "$1", "owner_name", "(.*)"
    )
  )
labels:
  workload_type: statefulset
record: namespace_workload_pod:kube_pod_owner:relabel

kube-scheduler.rules

cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.99, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.99"
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile

cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.99, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.99"
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile

cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.99, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.99"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile

cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.9, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.9"
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile

cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.9, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.9"
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile

cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.9, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.9"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile

cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.5, sum(rate(scheduler_e2e_scheduling_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.5"
record: cluster_quantile:scheduler_e2e_scheduling_duration_seconds:histogram_quantile

cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.5, sum(rate(scheduler_scheduling_algorithm_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.5"
record: cluster_quantile:scheduler_scheduling_algorithm_duration_seconds:histogram_quantile

cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile

expr: |
  histogram_quantile(0.5, sum(rate(scheduler_binding_duration_seconds_bucket{job="kube-scheduler"}[5m])) without(instance, pod))
labels:
  quantile: "0.5"
record: cluster_quantile:scheduler_binding_duration_seconds:histogram_quantile

node.rules

‘:kube_pod_info_node_count:’

expr: |
  sum(min(kube_pod_info{node!=""}) by (cluster, node))
record: ':kube_pod_info_node_count:'

‘node_namespace_pod:kube_pod_info:’

expr: |
  topk by(namespace, pod) (1,
    max by (node, namespace, pod) (
      label_replace(kube_pod_info{job="kube-state-metrics",node!=""}, "pod", "$1", "pod", "(.*)")
  ))
record: 'node_namespace_pod:kube_pod_info:'

node:node_num_cpu:sum

expr: |
  count by (cluster, node) (sum by (node, cpu) (
    node_cpu_seconds_total{job="node-exporter"}
  * on (namespace, pod) group_left(node)
    node_namespace_pod:kube_pod_info:
  ))
record: node:node_num_cpu:sum

:node_memory_MemAvailable_bytes:sum

expr: |
  sum(
    node_memory_MemAvailable_bytes{job="node-exporter"} or
    (
      node_memory_Buffers_bytes{job="node-exporter"} +
      node_memory_Cached_bytes{job="node-exporter"} +
      node_memory_MemFree_bytes{job="node-exporter"} +
      node_memory_Slab_bytes{job="node-exporter"}
    )
  ) by (cluster)
record: :node_memory_MemAvailable_bytes:sum

kubelet.rules

node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile

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"})
labels:
  quantile: "0.99"
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile

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"})
labels:
  quantile: "0.9"
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile

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"})
labels:
  quantile: "0.5"
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile

Dashboards

Following dashboards are generated from mixins and hosted on github: