KubeZero/charts/kubezero-metrics/templates/rules/kubernetes.yaml

950 lines
71 KiB
YAML

apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
name: {{ printf "%s-%s" (include "kubezero-lib.fullname" $) "kubernetes" | trunc 63 | trimSuffix "-" }}
namespace: {{ .Release.Namespace }}
labels:
{{- include "kubezero-lib.labels" . | nindent 4 }}
spec:
groups:
- name: kubernetes-apps
rules:
- alert: KubePodCrashLooping
annotations:
description: 'Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} ({{`{{`}} $labels.container {{`}}`}}) is in waiting state (reason: "CrashLoopBackOff").'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodcrashlooping
summary: Pod is crash looping.
expr: 'max_over_time(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff", job="kube-state-metrics"}[5m]) >= 1
'
for: 15m
labels:
severity: warning
- alert: KubePodNotReady
annotations:
description: Pod {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.pod {{`}}`}} has been in a non-ready state for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepodnotready
summary: Pod has been in a non-ready state for more than 15 minutes.
expr: "sum by (namespace, pod, cluster) (\n max by(namespace, pod, cluster) (\n kube_pod_status_phase{job=\"kube-state-metrics\", phase=~\"Pending|Unknown|Failed\"}\n ) * on(namespace, pod, cluster) group_left(owner_kind) topk by(namespace, pod, cluster) (\n 1, max by(namespace, pod, owner_kind, cluster) (kube_pod_owner{owner_kind!=\"Job\"})\n )\n) > 0\n"
for: 15m
labels:
severity: warning
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentgenerationmismatch
summary: Deployment generation mismatch due to possible roll-back
expr: "kube_deployment_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_deployment_metadata_generation{job=\"kube-state-metrics\"}\n"
for: 15m
labels:
severity: warning
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentreplicasmismatch
summary: Deployment has not matched the expected number of replicas.
expr: "(\n kube_deployment_spec_replicas{job=\"kube-state-metrics\"}\n >\n kube_deployment_status_replicas_available{job=\"kube-state-metrics\"}\n) and (\n changes(kube_deployment_status_replicas_updated{job=\"kube-state-metrics\"}[10m])\n ==\n 0\n)\n"
for: 15m
labels:
severity: warning
- alert: KubeDeploymentRolloutStuck
annotations:
description: Rollout of deployment {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.deployment {{`}}`}} is not progressing for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedeploymentrolloutstuck
summary: Deployment rollout is not progressing.
expr: 'kube_deployment_status_condition{condition="Progressing", status="false",job="kube-state-metrics"}
!= 0
'
for: 15m
labels:
severity: warning
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetreplicasmismatch
summary: StatefulSet has not matched the expected number of replicas.
expr: "(\n kube_statefulset_status_replicas_ready{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas{job=\"kube-state-metrics\"}\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[10m])\n ==\n 0\n)\n"
for: 15m
labels:
severity: warning
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetgenerationmismatch
summary: StatefulSet generation mismatch due to possible roll-back
expr: "kube_statefulset_status_observed_generation{job=\"kube-state-metrics\"}\n !=\nkube_statefulset_metadata_generation{job=\"kube-state-metrics\"}\n"
for: 15m
labels:
severity: warning
- alert: KubeStatefulSetUpdateNotRolledOut
annotations:
description: StatefulSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.statefulset {{`}}`}} update has not been rolled out.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubestatefulsetupdatenotrolledout
summary: StatefulSet update has not been rolled out.
expr: "(\n max by(namespace, statefulset, job, cluster) (\n kube_statefulset_status_current_revision{job=\"kube-state-metrics\"}\n unless\n kube_statefulset_status_update_revision{job=\"kube-state-metrics\"}\n )\n *\n (\n kube_statefulset_replicas{job=\"kube-state-metrics\"}\n !=\n kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_statefulset_status_replicas_updated{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n"
for: 15m
labels:
severity: warning
- alert: KubeDaemonSetRolloutStuck
annotations:
description: DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} has not finished or progressed for at least 15m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetrolloutstuck
summary: DaemonSet rollout is stuck.
expr: "(\n (\n kube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_misscheduled{job=\"kube-state-metrics\"}\n !=\n 0\n ) or (\n kube_daemonset_status_updated_number_scheduled{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n ) or (\n kube_daemonset_status_number_available{job=\"kube-state-metrics\"}\n !=\n kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n )\n) and (\n changes(kube_daemonset_status_updated_number_scheduled{job=\"kube-state-metrics\"}[5m])\n ==\n 0\n)\n"
for: 15m
labels:
severity: warning
- alert: KubeContainerWaiting
annotations:
description: 'pod/{{`{{`}} $labels.pod {{`}}`}} in namespace {{`{{`}} $labels.namespace {{`}}`}} on container {{`{{`}} $labels.container{{`}}`}} has been in waiting state for longer than 1 hour. (reason: "{{`{{`}} $labels.reason {{`}}`}}").'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontainerwaiting
summary: Pod container waiting longer than 1 hour
expr: 'kube_pod_container_status_waiting_reason{reason!="CrashLoopBackOff", job="kube-state-metrics"} > 0
'
for: 1h
labels:
severity: warning
- alert: KubeDaemonSetNotScheduled
annotations:
description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are not scheduled.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetnotscheduled
summary: DaemonSet pods are not scheduled.
expr: "kube_daemonset_status_desired_number_scheduled{job=\"kube-state-metrics\"}\n -\nkube_daemonset_status_current_number_scheduled{job=\"kube-state-metrics\"} > 0\n"
for: 10m
labels:
severity: warning
- alert: KubeDaemonSetMisScheduled
annotations:
description: '{{`{{`}} $value {{`}}`}} Pods of DaemonSet {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.daemonset {{`}}`}} are running where they are not supposed to run.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubedaemonsetmisscheduled
summary: DaemonSet pods are misscheduled.
expr: 'kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0
'
for: 15m
labels:
severity: warning
- alert: KubeJobNotCompleted
annotations:
description: Job {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.job_name {{`}}`}} is taking more than {{`{{`}} "43200" | humanizeDuration {{`}}`}} to complete.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobnotcompleted
summary: Job did not complete in time
expr: "time() - max by(namespace, job_name, cluster) (kube_job_status_start_time{job=\"kube-state-metrics\"}\n and\nkube_job_status_active{job=\"kube-state-metrics\"} > 0) > 43200\n"
labels:
severity: warning
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubejobfailed
summary: Job failed to complete.
expr: 'kube_job_failed{job="kube-state-metrics"} > 0
'
for: 15m
labels:
severity: warning
- alert: KubeHpaReplicasMismatch
annotations:
description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has not matched the desired number of replicas for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpareplicasmismatch
summary: HPA has not matched desired number of replicas.
expr: "(kube_horizontalpodautoscaler_status_desired_replicas{job=\"kube-state-metrics\"}\n !=\nkube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"})\n and\n(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n >\nkube_horizontalpodautoscaler_spec_min_replicas{job=\"kube-state-metrics\"})\n and\n(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n <\nkube_horizontalpodautoscaler_spec_max_replicas{job=\"kube-state-metrics\"})\n and\nchanges(kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}[15m]) == 0\n"
for: 15m
labels:
severity: warning
- alert: KubeHpaMaxedOut
annotations:
description: HPA {{`{{`}} $labels.namespace {{`}}`}}/{{`{{`}} $labels.horizontalpodautoscaler {{`}}`}} has been running at max replicas for longer than 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubehpamaxedout
summary: HPA is running at max replicas
expr: "kube_horizontalpodautoscaler_status_current_replicas{job=\"kube-state-metrics\"}\n ==\nkube_horizontalpodautoscaler_spec_max_replicas{job=\"kube-state-metrics\"}\n"
for: 15m
labels:
severity: warning
- name: kubernetes-resources
rules:
- alert: ClusterAutoscalerNodeGroupsEnabled
annotations:
description: Inhibitor rule if the Cluster Autoscaler found at least one node group
summary: Cluster Autoscaler found at least one node group.
expr: cluster_autoscaler_node_groups_count{job="addons-aws-cluster-autoscaler",node_group_type="autoscaled"} > 0
for: 5m
labels:
severity: none
- alert: KubeCPUOvercommit
annotations:
description: Cluster {{`{{`}} $labels.cluster {{`}}`}} has overcommitted CPU resource requests for Pods by {{`{{`}} $value {{`}}`}} CPU shares and cannot tolerate node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: 'sum(namespace_cpu:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
and
(sum(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster) - max(kube_node_status_allocatable{job="kube-state-metrics",resource="cpu"}) by (cluster)) > 0
'
for: 10m
labels:
severity: warning
- alert: KubeMemoryOvercommit
annotations:
description: Cluster {{`{{`}} $labels.cluster {{`}}`}} has overcommitted memory resource requests for Pods by {{`{{`}} $value | humanize {{`}}`}} bytes and cannot tolerate node failure.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryovercommit
summary: Cluster has overcommitted memory resource requests.
expr: 'sum(namespace_memory:kube_pod_container_resource_requests:sum{}) by (cluster) - (sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
and
(sum(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster) - max(kube_node_status_allocatable{resource="memory", job="kube-state-metrics"}) by (cluster)) > 0
'
for: 10m
labels:
severity: warning
- alert: KubeCPUQuotaOvercommit
annotations:
description: Cluster {{`{{`}} $labels.cluster {{`}}`}} has overcommitted CPU resource requests for Namespaces.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecpuquotaovercommit
summary: Cluster has overcommitted CPU resource requests.
expr: "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(cpu|requests.cpu)\"})) by (cluster)\n /\nsum(kube_node_status_allocatable{resource=\"cpu\", job=\"kube-state-metrics\"}) by (cluster)\n > 1.5\n"
for: 5m
labels:
severity: warning
- alert: KubeMemoryQuotaOvercommit
annotations:
description: Cluster {{`{{`}} $labels.cluster {{`}}`}} has overcommitted memory resource requests for Namespaces.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubememoryquotaovercommit
summary: Cluster has overcommitted memory resource requests.
expr: "sum(min without(resource) (kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\", resource=~\"(memory|requests.memory)\"})) by (cluster)\n /\nsum(kube_node_status_allocatable{resource=\"memory\", job=\"kube-state-metrics\"}) by (cluster)\n > 1.5\n"
for: 5m
labels:
severity: warning
- alert: KubeQuotaAlmostFull
annotations:
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaalmostfull
summary: Namespace quota is going to be full.
expr: "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 0.9 < 1\n"
for: 15m
labels:
severity: info
- alert: KubeQuotaFullyUsed
annotations:
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotafullyused
summary: Namespace quota is fully used.
expr: "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n == 1\n"
for: 15m
labels:
severity: info
- alert: KubeQuotaExceeded
annotations:
description: Namespace {{`{{`}} $labels.namespace {{`}}`}} is using {{`{{`}} $value | humanizePercentage {{`}}`}} of its {{`{{`}} $labels.resource {{`}}`}} quota.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubequotaexceeded
summary: Namespace quota has exceeded the limits.
expr: "kube_resourcequota{job=\"kube-state-metrics\", type=\"used\"}\n / ignoring(instance, job, type)\n(kube_resourcequota{job=\"kube-state-metrics\", type=\"hard\"} > 0)\n > 1\n"
for: 15m
labels:
severity: warning
- alert: CPUThrottlingHigh
annotations:
description: '{{`{{`}} $value | humanizePercentage {{`}}`}} throttling of CPU in namespace {{`{{`}} $labels.namespace {{`}}`}} for container {{`{{`}} $labels.container {{`}}`}} in pod {{`{{`}} $labels.pod {{`}}`}}.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/cputhrottlinghigh
summary: Processes experience elevated CPU throttling.
expr: "sum(increase(container_cpu_cfs_throttled_periods_total{container!=\"\", job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)\n /\nsum(increase(container_cpu_cfs_periods_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", }[5m])) without (id, metrics_path, name, image, endpoint, job, node)\n > ( 25 / 100 )\n"
for: 15m
labels:
severity: info
- name: kubernetes-storage
rules:
- alert: KubePersistentVolumeFillingUp
annotations:
description: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} {{`{{`}} with $labels.cluster -{{`}}`}} on Cluster {{`{{`}} . {{`}}`}} {{`{{`}}- end {{`}}`}} is only {{`{{`}} $value | humanizePercentage {{`}}`}} free.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
summary: PersistentVolume is filling up.
expr: "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.03\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n"
for: 1m
labels:
severity: critical
- alert: KubePersistentVolumeFillingUp
annotations:
description: Based on recent sampling, the PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} {{`{{`}} with $labels.cluster -{{`}}`}} on Cluster {{`{{`}} . {{`}}`}} {{`{{`}}- end {{`}}`}} is expected to fill up within four days. Currently {{`{{`}} $value | humanizePercentage {{`}}`}} is available.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumefillingup
summary: PersistentVolume is filling up.
expr: "(\n kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n /\n kubelet_volume_stats_capacity_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.15\nand\nkubelet_volume_stats_used_bytes{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nand\npredict_linear(kubelet_volume_stats_available_bytes{job=\"kubelet\", metrics_path=\"/metrics\"}[6h], 4 * 24 * 3600) < 0\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n"
for: 1h
labels:
severity: warning
- alert: KubePersistentVolumeInodesFillingUp
annotations:
description: The PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} {{`{{`}} with $labels.cluster -{{`}}`}} on Cluster {{`{{`}} . {{`}}`}} {{`{{`}}- end {{`}}`}} only has {{`{{`}} $value | humanizePercentage {{`}}`}} free inodes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup
summary: PersistentVolumeInodes are filling up.
expr: "(\n kubelet_volume_stats_inodes_free{job=\"kubelet\", metrics_path=\"/metrics\"}\n /\n kubelet_volume_stats_inodes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.03\nand\nkubelet_volume_stats_inodes_used{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n"
for: 1m
labels:
severity: critical
- alert: KubePersistentVolumeInodesFillingUp
annotations:
description: Based on recent sampling, the PersistentVolume claimed by {{`{{`}} $labels.persistentvolumeclaim {{`}}`}} in Namespace {{`{{`}} $labels.namespace {{`}}`}} {{`{{`}} with $labels.cluster -{{`}}`}} on Cluster {{`{{`}} . {{`}}`}} {{`{{`}}- end {{`}}`}} is expected to run out of inodes within four days. Currently {{`{{`}} $value | humanizePercentage {{`}}`}} of its inodes are free.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubepersistentvolumeinodesfillingup
summary: PersistentVolumeInodes are filling up.
expr: "(\n kubelet_volume_stats_inodes_free{job=\"kubelet\", metrics_path=\"/metrics\"}\n /\n kubelet_volume_stats_inodes{job=\"kubelet\", metrics_path=\"/metrics\"}\n) < 0.15\nand\nkubelet_volume_stats_inodes_used{job=\"kubelet\", metrics_path=\"/metrics\"} > 0\nand\npredict_linear(kubelet_volume_stats_inodes_free{job=\"kubelet\", metrics_path=\"/metrics\"}[6h], 4 * 24 * 3600) < 0\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_access_mode{ access_mode=\"ReadOnlyMany\"} == 1\nunless on(cluster, namespace, persistentvolumeclaim)\nkube_persistentvolumeclaim_labels{label_excluded_from_alerts=\"true\"} == 1\n"
for: 1h
labels:
severity: warning
- alert: KubePersistentVolumeErrors
annotations:
description: The persistent volume {{`{{`}} $labels.persistentvolume {{`}}`}} {{`{{`}} with $labels.cluster -{{`}}`}} on Cluster {{`{{`}} . {{`}}`}} {{`{{`}}- end {{`}}`}} has status {{`{{`}} $labels.phase {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/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
- name: kubernetes-system
rules:
- alert: KubeVersionMismatch
annotations:
description: There are {{`{{`}} $value {{`}}`}} different semantic versions of Kubernetes components running.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeversionmismatch
summary: Different semantic versions of Kubernetes components running.
expr: 'count by (cluster) (count by (git_version, cluster) (label_replace(kubernetes_build_info{job!~"kube-dns|coredns"},"git_version","$1","git_version","(v[0-9]*.[0-9]*).*"))) > 1
'
for: 15m
labels:
severity: warning
- alert: KubeClientErrors
annotations:
description: Kubernetes API server client '{{`{{`}} $labels.job {{`}}`}}/{{`{{`}} $labels.instance {{`}}`}}' is experiencing {{`{{`}} $value | humanizePercentage {{`}}`}} errors.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclienterrors
summary: Kubernetes API server client is experiencing errors.
expr: "(sum(rate(rest_client_requests_total{job=\"apiserver\",code=~\"5..\"}[5m])) by (cluster, instance, job, namespace)\n /\nsum(rate(rest_client_requests_total{job=\"apiserver\"}[5m])) by (cluster, instance, job, namespace))\n> 0.01\n"
for: 15m
labels:
severity: warning
- name: kube-apiserver-slos
rules:
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: 'sum by(cluster) (apiserver_request:burnrate1h) > (14.40 * 0.01000)
and on(cluster)
sum by(cluster) (apiserver_request:burnrate5m) > (14.40 * 0.01000)
'
for: 2m
labels:
long: 1h
severity: critical
short: 5m
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: 'sum by(cluster) (apiserver_request:burnrate6h) > (6.00 * 0.01000)
and on(cluster)
sum by(cluster) (apiserver_request:burnrate30m) > (6.00 * 0.01000)
'
for: 15m
labels:
long: 6h
severity: critical
short: 30m
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: 'sum by(cluster) (apiserver_request:burnrate1d) > (3.00 * 0.01000)
and on(cluster)
sum by(cluster) (apiserver_request:burnrate2h) > (3.00 * 0.01000)
'
for: 1h
labels:
long: 1d
severity: warning
short: 2h
- alert: KubeAPIErrorBudgetBurn
annotations:
description: The API server is burning too much error budget.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapierrorbudgetburn
summary: The API server is burning too much error budget.
expr: 'sum by(cluster) (apiserver_request:burnrate3d) > (1.00 * 0.01000)
and on(cluster)
sum by(cluster) (apiserver_request:burnrate6h) > (1.00 * 0.01000)
'
for: 3h
labels:
long: 3d
severity: warning
short: 6h
- name: kubernetes-system-apiserver
rules:
- alert: KubeClientCertificateExpiration
annotations:
description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 7.0 days on cluster {{`{{`}} $labels.cluster {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
summary: Client certificate is about to expire.
expr: 'histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 604800
and
on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0
'
for: 5m
labels:
severity: warning
- alert: KubeClientCertificateExpiration
annotations:
description: A client certificate used to authenticate to kubernetes apiserver is expiring in less than 24.0 hours on cluster {{`{{`}} $labels.cluster {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeclientcertificateexpiration
summary: Client certificate is about to expire.
expr: 'histogram_quantile(0.01, sum without (namespace, service, endpoint) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 86400
and
on(job, cluster, instance) apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0
'
for: 5m
labels:
severity: critical
- alert: KubeAggregatedAPIErrors
annotations:
description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has reported errors. It has appeared unavailable {{`{{`}} $value | humanize {{`}}`}} times averaged over the past 10m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapierrors
summary: Kubernetes aggregated API has reported errors.
expr: 'sum by(name, namespace, cluster)(increase(aggregator_unavailable_apiservice_total{job="apiserver"}[10m])) > 4
'
labels:
severity: warning
- alert: KubeAggregatedAPIDown
annotations:
description: Kubernetes aggregated API {{`{{`}} $labels.name {{`}}`}}/{{`{{`}} $labels.namespace {{`}}`}} has been only {{`{{`}} $value | humanize {{`}}`}}% available over the last 10m.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeaggregatedapidown
summary: Kubernetes aggregated API is down.
expr: '(1 - max by(name, namespace, cluster)(avg_over_time(aggregator_unavailable_apiservice{job="apiserver"}[10m]))) * 100 < 85
'
for: 5m
labels:
severity: warning
- alert: KubeAPIDown
annotations:
description: KubeAPI has disappeared from Prometheus target discovery.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapidown
summary: Target disappeared from Prometheus target discovery.
expr: 'absent(up{job="apiserver"} == 1)
'
for: 15m
labels:
severity: critical
- alert: KubeAPITerminatedRequests
annotations:
description: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeapiterminatedrequests
summary: The kubernetes apiserver has terminated {{`{{`}} $value | humanizePercentage {{`}}`}} of its incoming requests.
expr: 'sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) / ( sum by(cluster) (rate(apiserver_request_total{job="apiserver"}[10m])) + sum by(cluster) (rate(apiserver_request_terminations_total{job="apiserver"}[10m])) ) > 0.20
'
for: 5m
labels:
severity: warning
- name: kubernetes-system-kubelet
rules:
- alert: KubeNodeNotReady
annotations:
description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/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
- alert: KubeNodeUnreachable
annotations:
description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled.'
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/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
- alert: KubeletTooManyPods
annotations:
description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubelettoomanypods
summary: Kubelet is running at capacity.
expr: "count by(cluster, node) (\n (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\"})\n)\n/\nmax by(cluster, node) (\n kube_node_status_capacity{job=\"kube-state-metrics\",resource=\"pods\"} != 1\n) > 0.95\n"
for: 15m
labels:
severity: info
- alert: KubeNodeReadinessFlapping
annotations:
description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubenodereadinessflapping
summary: Node readiness status is flapping.
expr: 'sum(changes(kube_node_status_condition{job="kube-state-metrics",status="true",condition="Ready"}[15m])) by (cluster, node) > 2
'
for: 15m
labels:
severity: warning
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/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
- alert: KubeletPodStartUpLatencyHigh
annotations:
description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletpodstartuplatencyhigh
summary: Kubelet Pod startup latency is too high.
expr: 'histogram_quantile(0.99, sum(rate(kubelet_pod_worker_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le)) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
'
for: 15m
labels:
severity: warning
- alert: KubeletClientCertificateExpiration
annotations:
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
expr: 'kubelet_certificate_manager_client_ttl_seconds < 604800
'
labels:
severity: warning
- alert: KubeletClientCertificateExpiration
annotations:
description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletclientcertificateexpiration
summary: Kubelet client certificate is about to expire.
expr: 'kubelet_certificate_manager_client_ttl_seconds < 86400
'
labels:
severity: critical
- alert: KubeletServerCertificateExpiration
annotations:
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
expr: 'kubelet_certificate_manager_server_ttl_seconds < 604800
'
labels:
severity: warning
- alert: KubeletServerCertificateExpiration
annotations:
description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}}.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificateexpiration
summary: Kubelet server certificate is about to expire.
expr: 'kubelet_certificate_manager_server_ttl_seconds < 86400
'
labels:
severity: critical
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/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
- 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://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletservercertificaterenewalerrors
summary: Kubelet has failed to renew its server certificate.
expr: 'increase(kubelet_server_expiration_renew_errors[5m]) > 0
'
for: 15m
labels:
severity: warning
- alert: KubeletDown
annotations:
description: Kubelet has disappeared from Prometheus target discovery.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeletdown
summary: Target disappeared from Prometheus target discovery.
expr: 'absent(up{job="kubelet", metrics_path="/metrics"} == 1)
'
for: 15m
labels:
severity: critical
- name: kubernetes-system-scheduler
rules:
- alert: KubeSchedulerDown
annotations:
description: KubeScheduler has disappeared from Prometheus target discovery.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubeschedulerdown
summary: Target disappeared from Prometheus target discovery.
expr: 'absent(up{job="kube-scheduler"} == 1)
'
for: 15m
labels:
severity: critical
- name: kubernetes-system-controller-manager
rules:
- alert: KubeControllerManagerDown
annotations:
description: KubeControllerManager has disappeared from Prometheus target discovery.
runbook_url: https://runbooks.prometheus-operator.dev/runbooks/kubernetes/kubecontrollermanagerdown
summary: Target disappeared from Prometheus target discovery.
expr: 'absent(up{job="kube-controller-manager"} == 1)
'
for: 15m
labels:
severity: critical
- interval: 3m
name: kube-apiserver-availability.rules
rules:
- expr: 'avg_over_time(code_verb:apiserver_request_total:increase1h[30d]) * 24 * 30
'
record: code_verb:apiserver_request_total:increase30d
- expr: 'sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"LIST|GET"})
'
labels:
verb: read
record: code:apiserver_request_total:increase30d
- expr: 'sum by (cluster, code) (code_verb:apiserver_request_total:increase30d{verb=~"POST|PUT|PATCH|DELETE"})
'
labels:
verb: write
record: code:apiserver_request_total:increase30d
- expr: 'sum by (cluster, verb, scope, le) (increase(apiserver_request_sli_duration_seconds_bucket[1h]))
'
record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h
- expr: 'sum by (cluster, verb, scope, le) (avg_over_time(cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h[30d]) * 24 * 30)
'
record: cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d
- expr: 'sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase1h{le="+Inf"})
'
record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase1h
- expr: 'sum by (cluster, verb, scope) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{le="+Inf"} * 24 * 30)
'
record: cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d
- expr: "1 - (\n (\n # write too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n ) +\n (\n # read too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"\
cluster\",le=\"30\"})\n )\n ) +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d)\n"
labels:
verb: all
record: apiserver_request:availability30d
- expr: "1 - (\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"LIST|GET\"})\n -\n (\n # too slow\n (\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=~\"resource|\",le=\"1\"})\n or\n vector(0)\n )\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"namespace\",le=\"5\"})\n +\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"LIST|GET\",scope=\"cluster\",le=\"30\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"read\"})\n"
labels:
verb: read
record: apiserver_request:availability30d
- expr: "1 - (\n (\n # too slow\n sum by (cluster) (cluster_verb_scope:apiserver_request_sli_duration_seconds_count:increase30d{verb=~\"POST|PUT|PATCH|DELETE\"})\n -\n sum by (cluster) (cluster_verb_scope_le:apiserver_request_sli_duration_seconds_bucket:increase30d{verb=~\"POST|PUT|PATCH|DELETE\",le=\"1\"})\n )\n +\n # errors\n sum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\",code=~\"5..\"} or vector(0))\n)\n/\nsum by (cluster) (code:apiserver_request_total:increase30d{verb=\"write\"})\n"
labels:
verb: write
record: apiserver_request:availability30d
- expr: 'sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"LIST|GET"}[5m]))
'
labels:
verb: read
record: code_resource:apiserver_request_total:rate5m
- expr: 'sum by (cluster,code,resource) (rate(apiserver_request_total{job="apiserver",verb=~"POST|PUT|PATCH|DELETE"}[5m]))
'
labels:
verb: write
record: code_resource:apiserver_request_total:rate5m
- expr: 'sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"2.."}[1h]))
'
record: code_verb:apiserver_request_total:increase1h
- expr: 'sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"3.."}[1h]))
'
record: code_verb:apiserver_request_total:increase1h
- expr: 'sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"4.."}[1h]))
'
record: code_verb:apiserver_request_total:increase1h
- expr: 'sum by (cluster, code, verb) (increase(apiserver_request_total{job="apiserver",verb=~"LIST|GET|POST|PUT|PATCH|DELETE",code=~"5.."}[1h]))
'
record: code_verb:apiserver_request_total:increase1h
- name: kube-apiserver-burnrate.rules
rules:
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1d]))\n"
labels:
verb: read
record: apiserver_request:burnrate1d
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[1h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[1h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[1h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[1h]))\n"
labels:
verb: read
record: apiserver_request:burnrate1h
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[2h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[2h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[2h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[2h]))\n"
labels:
verb: read
record: apiserver_request:burnrate2h
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[30m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[30m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[30m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"\
,code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[30m]))\n"
labels:
verb: read
record: apiserver_request:burnrate30m
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[3d]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[3d]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[3d]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[3d]))\n"
labels:
verb: read
record: apiserver_request:burnrate3d
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[5m]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[5m]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[5m]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[5m]))\n"
labels:
verb: read
record: apiserver_request:burnrate5m
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n (\n (\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=~\"resource|\",le=\"1\"}[6h]))\n or\n vector(0)\n )\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"namespace\",le=\"5\"}[6h]))\n +\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"LIST|GET\",subresource!~\"proxy|attach|log|exec|portforward\",scope=\"cluster\",le=\"30\"}[6h]))\n )\n )\n +\n # errors\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\",code=~\"\
5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"LIST|GET\"}[6h]))\n"
labels:
verb: read
record: apiserver_request:burnrate6h
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1d]))\n"
labels:
verb: write
record: apiserver_request:burnrate1d
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[1h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[1h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[1h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[1h]))\n"
labels:
verb: write
record: apiserver_request:burnrate1h
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[2h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[2h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[2h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[2h]))\n"
labels:
verb: write
record: apiserver_request:burnrate2h
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[30m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[30m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[30m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[30m]))\n"
labels:
verb: write
record: apiserver_request:burnrate30m
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[3d]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[3d]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[3d]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[3d]))\n"
labels:
verb: write
record: apiserver_request:burnrate3d
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[5m]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[5m]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[5m]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[5m]))\n"
labels:
verb: write
record: apiserver_request:burnrate5m
- expr: "(\n (\n # too slow\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_count{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\"}[6h]))\n -\n sum by (cluster) (rate(apiserver_request_sli_duration_seconds_bucket{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",subresource!~\"proxy|attach|log|exec|portforward\",le=\"1\"}[6h]))\n )\n +\n sum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\",code=~\"5..\"}[6h]))\n)\n/\nsum by (cluster) (rate(apiserver_request_total{job=\"apiserver\",verb=~\"POST|PUT|PATCH|DELETE\"}[6h]))\n"
labels:
verb: write
record: apiserver_request:burnrate6h
- name: kube-apiserver-histogram.rules
rules:
- expr: 'histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"LIST|GET",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0
'
labels:
quantile: '0.99'
verb: read
record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile
- expr: 'histogram_quantile(0.99, sum by (cluster, le, resource) (rate(apiserver_request_sli_duration_seconds_bucket{job="apiserver",verb=~"POST|PUT|PATCH|DELETE",subresource!~"proxy|attach|log|exec|portforward"}[5m]))) > 0
'
labels:
quantile: '0.99'
verb: write
record: cluster_quantile:apiserver_request_sli_duration_seconds:histogram_quantile
- name: k8s.rules.container_cpu_usage_seconds_total
rules:
- expr: "sum by (cluster, namespace, pod, container) (\n irate(container_cpu_usage_seconds_total{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", image!=\"\"}[5m])\n) * on (cluster, namespace, pod) group_left(node) topk by (cluster, namespace, pod) (\n 1, max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n"
record: node_namespace_pod_container:container_cpu_usage_seconds_total:sum_irate
- name: k8s.rules.container_memory_working_set_bytes
rules:
- expr: "container_memory_working_set_bytes{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", image!=\"\"}\n* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,\n max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n"
record: node_namespace_pod_container:container_memory_working_set_bytes
- name: k8s.rules.container_memory_rss
rules:
- expr: "container_memory_rss{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", image!=\"\"}\n* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,\n max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n"
record: node_namespace_pod_container:container_memory_rss
- name: k8s.rules.container_memory_cache
rules:
- expr: "container_memory_cache{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", image!=\"\"}\n* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,\n max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n"
record: node_namespace_pod_container:container_memory_cache
- name: k8s.rules.container_memory_swap
rules:
- expr: "container_memory_swap{job=\"kubelet\", metrics_path=\"/metrics/cadvisor\", image!=\"\"}\n* on (cluster, namespace, pod) group_left(node) topk by(cluster, namespace, pod) (1,\n max by(cluster, namespace, pod, node) (kube_pod_info{node!=\"\"})\n)\n"
record: node_namespace_pod_container:container_memory_swap
- name: k8s.rules.container_memory_requests
rules:
- expr: "kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
record: cluster:namespace:pod_memory:active:kube_pod_container_resource_requests
- expr: "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_requests{resource=\"memory\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n"
record: namespace_memory:kube_pod_container_resource_requests:sum
- name: k8s.rules.container_cpu_requests
rules:
- expr: "kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_requests
- expr: "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_requests{resource=\"cpu\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n"
record: namespace_cpu:kube_pod_container_resource_requests:sum
- name: k8s.rules.container_memory_limits
rules:
- expr: "kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n)\n"
record: cluster:namespace:pod_memory:active:kube_pod_container_resource_limits
- expr: "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_limits{resource=\"memory\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n"
record: namespace_memory:kube_pod_container_resource_limits:sum
- name: k8s.rules.container_cpu_limits
rules:
- expr: "kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"} * on (namespace, pod, cluster)\ngroup_left() max by (namespace, pod, cluster) (\n (kube_pod_status_phase{phase=~\"Pending|Running\"} == 1)\n )\n"
record: cluster:namespace:pod_cpu:active:kube_pod_container_resource_limits
- expr: "sum by (namespace, cluster) (\n sum by (namespace, pod, cluster) (\n max by (namespace, pod, container, cluster) (\n kube_pod_container_resource_limits{resource=\"cpu\",job=\"kube-state-metrics\"}\n ) * on(namespace, pod, cluster) group_left() max by (namespace, pod, cluster) (\n kube_pod_status_phase{phase=~\"Pending|Running\"} == 1\n )\n )\n)\n"
record: namespace_cpu:kube_pod_container_resource_limits:sum
- name: k8s.rules.pod_owner
rules:
- expr: "max by (cluster, namespace, workload, pod) (\n label_replace(\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"ReplicaSet\"},\n \"replicaset\", \"$1\", \"owner_name\", \"(.*)\"\n ) * on(replicaset, namespace) group_left(owner_name) topk by(replicaset, namespace) (\n 1, max by (replicaset, namespace, owner_name) (\n kube_replicaset_owner{job=\"kube-state-metrics\"}\n )\n ),\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n"
labels:
workload_type: deployment
record: namespace_workload_pod:kube_pod_owner:relabel
- expr: "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"DaemonSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n"
labels:
workload_type: daemonset
record: namespace_workload_pod:kube_pod_owner:relabel
- expr: "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"StatefulSet\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n"
labels:
workload_type: statefulset
record: namespace_workload_pod:kube_pod_owner:relabel
- expr: "max by (cluster, namespace, workload, pod) (\n label_replace(\n kube_pod_owner{job=\"kube-state-metrics\", owner_kind=\"Job\"},\n \"workload\", \"$1\", \"owner_name\", \"(.*)\"\n )\n)\n"
labels:
workload_type: job
record: namespace_workload_pod:kube_pod_owner:relabel
- name: kube-scheduler.rules
rules:
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- name: node.rules
rules:
- expr: "topk by(cluster, namespace, pod) (1,\n max by (cluster, node, namespace, pod) (\n label_replace(kube_pod_info{job=\"kube-state-metrics\",node!=\"\"}, \"pod\", \"$1\", \"pod\", \"(.*)\")\n))\n"
record: 'node_namespace_pod:kube_pod_info:'
- expr: "count by (cluster, node) (\n node_cpu_seconds_total{mode=\"idle\",job=\"node-exporter\"}\n * on (cluster, namespace, pod) group_left(node)\n topk by(cluster, namespace, pod) (1, node_namespace_pod:kube_pod_info:)\n)\n"
record: node:node_num_cpu:sum
- expr: "sum(\n node_memory_MemAvailable_bytes{job=\"node-exporter\"} or\n (\n node_memory_Buffers_bytes{job=\"node-exporter\"} +\n node_memory_Cached_bytes{job=\"node-exporter\"} +\n node_memory_MemFree_bytes{job=\"node-exporter\"} +\n node_memory_Slab_bytes{job=\"node-exporter\"}\n )\n) by (cluster)\n"
record: :node_memory_MemAvailable_bytes:sum
- expr: "avg by (cluster, node) (\n sum without (mode) (\n rate(node_cpu_seconds_total{mode!=\"idle\",mode!=\"iowait\",mode!=\"steal\",job=\"node-exporter\"}[5m])\n )\n)\n"
record: node:node_cpu_utilization:ratio_rate5m
- expr: "avg by (cluster) (\n node:node_cpu_utilization:ratio_rate5m\n)\n"
record: cluster:node_cpu:ratio_rate5m
- name: kubelet.rules
rules:
- expr: 'histogram_quantile(0.99, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
'
labels:
quantile: '0.99'
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
- expr: 'histogram_quantile(0.9, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
'
labels:
quantile: '0.9'
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile
- expr: 'histogram_quantile(0.5, sum(rate(kubelet_pleg_relist_duration_seconds_bucket{job="kubelet", metrics_path="/metrics"}[5m])) by (cluster, instance, le) * on(cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"})
'
labels:
quantile: '0.5'
record: node_quantile:kubelet_pleg_relist_duration_seconds:histogram_quantile