forked from k-space/kube
481 lines
19 KiB
YAML
481 lines
19 KiB
YAML
---
|
|
apiVersion: v1
|
|
automountServiceAccountToken: false
|
|
kind: ServiceAccount
|
|
metadata:
|
|
name: kube-state-metrics
|
|
labels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRole
|
|
metadata:
|
|
name: kube-state-metrics
|
|
labels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
rules:
|
|
- apiGroups:
|
|
- ""
|
|
resources:
|
|
- configmaps
|
|
- secrets
|
|
- nodes
|
|
- pods
|
|
- services
|
|
- serviceaccounts
|
|
- resourcequotas
|
|
- replicationcontrollers
|
|
- limitranges
|
|
- persistentvolumeclaims
|
|
- persistentvolumes
|
|
- namespaces
|
|
- endpoints
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- apps
|
|
resources:
|
|
- statefulsets
|
|
- daemonsets
|
|
- deployments
|
|
- replicasets
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- batch
|
|
resources:
|
|
- cronjobs
|
|
- jobs
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- autoscaling
|
|
resources:
|
|
- horizontalpodautoscalers
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- authentication.k8s.io
|
|
resources:
|
|
- tokenreviews
|
|
verbs:
|
|
- create
|
|
- apiGroups:
|
|
- authorization.k8s.io
|
|
resources:
|
|
- subjectaccessreviews
|
|
verbs:
|
|
- create
|
|
- apiGroups:
|
|
- policy
|
|
resources:
|
|
- poddisruptionbudgets
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- certificates.k8s.io
|
|
resources:
|
|
- certificatesigningrequests
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- storage.k8s.io
|
|
resources:
|
|
- storageclasses
|
|
- volumeattachments
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- admissionregistration.k8s.io
|
|
resources:
|
|
- mutatingwebhookconfigurations
|
|
- validatingwebhookconfigurations
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- networking.k8s.io
|
|
resources:
|
|
- networkpolicies
|
|
- ingresses
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- coordination.k8s.io
|
|
resources:
|
|
- leases
|
|
verbs:
|
|
- list
|
|
- watch
|
|
- apiGroups:
|
|
- rbac.authorization.k8s.io
|
|
resources:
|
|
- clusterrolebindings
|
|
- clusterroles
|
|
- rolebindings
|
|
- roles
|
|
verbs:
|
|
- list
|
|
- watch
|
|
---
|
|
apiVersion: rbac.authorization.k8s.io/v1
|
|
kind: ClusterRoleBinding
|
|
metadata:
|
|
name: kube-state-metrics
|
|
labels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
roleRef:
|
|
apiGroup: rbac.authorization.k8s.io
|
|
kind: ClusterRole
|
|
name: kube-state-metrics
|
|
subjects:
|
|
- kind: ServiceAccount
|
|
name: kube-state-metrics
|
|
namespace: kube-system
|
|
---
|
|
apiVersion: apps/v1
|
|
kind: Deployment
|
|
metadata:
|
|
name: kube-state-metrics
|
|
labels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
spec:
|
|
replicas: 1
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
template:
|
|
metadata:
|
|
labels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
spec:
|
|
automountServiceAccountToken: true
|
|
containers:
|
|
- image: registry.k8s.io/kube-state-metrics/kube-state-metrics:v2.7.0
|
|
args:
|
|
- --metric-labels-allowlist=pods=[*]
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /healthz
|
|
port: 8080
|
|
initialDelaySeconds: 5
|
|
timeoutSeconds: 5
|
|
name: kube-state-metrics
|
|
ports:
|
|
- containerPort: 8080
|
|
name: http-metrics
|
|
- containerPort: 8081
|
|
name: telemetry
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /
|
|
port: 8081
|
|
initialDelaySeconds: 5
|
|
timeoutSeconds: 5
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop:
|
|
- ALL
|
|
readOnlyRootFilesystem: true
|
|
runAsUser: 65534
|
|
nodeSelector:
|
|
kubernetes.io/os: linux
|
|
serviceAccountName: kube-state-metrics
|
|
---
|
|
apiVersion: v1
|
|
kind: Service
|
|
metadata:
|
|
name: kube-state-metrics
|
|
labels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
spec:
|
|
clusterIP: None
|
|
ports:
|
|
- name: http-metrics
|
|
port: 8080
|
|
targetPort: http-metrics
|
|
- name: telemetry
|
|
port: 8081
|
|
targetPort: telemetry
|
|
selector:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: ServiceMonitor
|
|
metadata:
|
|
name: kube-state-metrics
|
|
spec:
|
|
endpoints:
|
|
- honorLabels: true
|
|
path: /metrics
|
|
port: http-metrics
|
|
selector:
|
|
matchLabels:
|
|
app.kubernetes.io/name: kube-state-metrics
|
|
---
|
|
apiVersion: monitoring.coreos.com/v1
|
|
kind: PrometheusRule
|
|
metadata:
|
|
name: kube-state-metrics
|
|
spec:
|
|
groups:
|
|
- name: kube-state-metrics
|
|
rules:
|
|
- alert: KubernetesNodeReady
|
|
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes Node ready (instance {{ $labels.instance }})
|
|
description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesMemoryPressure
|
|
expr: kube_node_status_condition{condition="MemoryPressure",status="true"} == 1
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes memory pressure (instance {{ $labels.instance }})
|
|
description: "{{ $labels.node }} has MemoryPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesDiskPressure
|
|
expr: kube_node_status_condition{condition="DiskPressure",status="true"} == 1
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes disk pressure (instance {{ $labels.instance }})
|
|
description: "{{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesOutOfDisk
|
|
expr: kube_node_status_condition{condition="OutOfDisk",status="true"} == 1
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes out of disk (instance {{ $labels.instance }})
|
|
description: "{{ $labels.node }} has OutOfDisk condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesOutOfCapacity
|
|
expr: sum by (node) ((kube_pod_status_phase{phase="Running"} == 1) + on(uid) group_left(node) (0 * kube_pod_info{pod_template_hash=""})) / sum by (node) (kube_node_status_allocatable{resource="pods"}) * 100 > 90
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes out of capacity (instance {{ $labels.instance }})
|
|
description: "{{ $labels.node }} is out of capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesContainerOomKiller
|
|
expr: (kube_pod_container_status_restarts_total - kube_pod_container_status_restarts_total offset 10m >= 1) and ignoring (reason) min_over_time(kube_pod_container_status_last_terminated_reason{reason="OOMKilled"}[10m]) == 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes container oom killer (instance {{ $labels.instance }})
|
|
description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesJobFailed
|
|
expr: kube_job_status_failed > 0
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes Job failed (instance {{ $labels.instance }})
|
|
description: "Job {{$labels.namespace}}/{{$labels.exported_job}} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesCronjobSuspended
|
|
expr: kube_cronjob_spec_suspend != 0
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes CronJob suspended (instance {{ $labels.instance }})
|
|
description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesPersistentvolumeclaimPending
|
|
expr: kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }})
|
|
description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesVolumeOutOfDiskSpace
|
|
expr: kubelet_volume_stats_available_bytes / kubelet_volume_stats_capacity_bytes * 100 < 10
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes Volume out of disk space (instance {{ $labels.instance }})
|
|
description: "Volume is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesPersistentvolumeError
|
|
expr: kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }})
|
|
description: "Persistent volume is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesStatefulsetDown
|
|
expr: (kube_statefulset_status_replicas_ready / kube_statefulset_status_replicas_current) != 1
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes StatefulSet down (instance {{ $labels.instance }})
|
|
description: "A StatefulSet went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesHpaScalingAbility
|
|
expr: kube_horizontalpodautoscaler_status_condition{status="false", condition="AbleToScale"} == 1
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes HPA scaling ability (instance {{ $labels.instance }})
|
|
description: "Pod is unable to scale\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesHpaMetricAvailability
|
|
expr: kube_horizontalpodautoscaler_status_condition{status="false", condition="ScalingActive"} == 1
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes HPA metric availability (instance {{ $labels.instance }})
|
|
description: "HPA is not able to collect metrics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesHpaScaleCapability
|
|
expr: kube_horizontalpodautoscaler_status_desired_replicas >= kube_horizontalpodautoscaler_spec_max_replicas
|
|
for: 2m
|
|
labels:
|
|
severity: info
|
|
annotations:
|
|
summary: Kubernetes HPA scale capability (instance {{ $labels.instance }})
|
|
description: "The maximum number of desired Pods has been hit\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesPodNotHealthy
|
|
expr: min_over_time(sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"})[15m:1m]) > 0
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes Pod not healthy (instance {{ $labels.instance }})
|
|
description: "Pod has been in a non-ready state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesPodCrashLooping
|
|
expr: increase(kube_pod_container_status_restarts_total[1m]) > 3
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes pod crash looping (instance {{ $labels.instance }})
|
|
description: "Pod {{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesReplicassetMismatch
|
|
expr: kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes ReplicasSet mismatch (instance {{ $labels.instance }})
|
|
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesDeploymentReplicasMismatch
|
|
expr: kube_deployment_spec_replicas != kube_deployment_status_replicas_available
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }})
|
|
description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesStatefulsetReplicasMismatch
|
|
expr: kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes StatefulSet replicas mismatch (instance {{ $labels.instance }})
|
|
description: "A StatefulSet does not match the expected number of replicas.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesDeploymentGenerationMismatch
|
|
expr: kube_deployment_status_observed_generation != kube_deployment_metadata_generation
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes Deployment generation mismatch (instance {{ $labels.instance }})
|
|
description: "A Deployment has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesStatefulsetGenerationMismatch
|
|
expr: kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation
|
|
for: 10m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes StatefulSet generation mismatch (instance {{ $labels.instance }})
|
|
description: "A StatefulSet has failed but has not been rolled back.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesStatefulsetUpdateNotRolledOut
|
|
expr: max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes StatefulSet update not rolled out (instance {{ $labels.instance }})
|
|
description: "StatefulSet update has not been rolled out.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesDaemonsetRolloutStuck
|
|
expr: kube_daemonset_status_number_ready / kube_daemonset_status_desired_number_scheduled * 100 < 100 or kube_daemonset_status_desired_number_scheduled - kube_daemonset_status_current_number_scheduled > 0
|
|
for: 10m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes DaemonSet rollout stuck (instance {{ $labels.instance }})
|
|
description: "Some Pods of DaemonSet are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesDaemonsetMisscheduled
|
|
expr: sum by (namespace, daemonset) (kube_daemonset_status_number_misscheduled) > 0
|
|
for: 1m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes DaemonSet misscheduled (instance {{ $labels.instance }})
|
|
description: "Some DaemonSet Pods are running where they are not supposed to run\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesJobSlowCompletion
|
|
expr: kube_job_spec_completions - kube_job_status_succeeded > 0
|
|
for: 12h
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes job slow completion (instance {{ $labels.instance }})
|
|
description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesApiServerErrors
|
|
expr: sum(rate(apiserver_request_total{job="apiserver",code=~"^(?:5..)$"}[1m])) / sum(rate(apiserver_request_total{job="apiserver"}[1m])) * 100 > 3
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes API server errors (instance {{ $labels.instance }})
|
|
description: "Kubernetes API server is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesApiClientErrors
|
|
expr: (sum(rate(rest_client_requests_total{code=~"(4|5).."}[1m])) by (instance, job) / sum(rate(rest_client_requests_total[1m])) by (instance, job)) * 100 > 1
|
|
for: 2m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes API client errors (instance {{ $labels.instance }})
|
|
description: "Kubernetes API client is experiencing high error rate\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesClientCertificateExpiresNextWeek
|
|
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 7*24*60*60
|
|
for: 0m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes client certificate expires next week (instance {{ $labels.instance }})
|
|
description: "A client certificate used to authenticate to the apiserver is expiring next week.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesClientCertificateExpiresSoon
|
|
expr: apiserver_client_certificate_expiration_seconds_count{job="apiserver"} > 0 and histogram_quantile(0.01, sum by (job, le) (rate(apiserver_client_certificate_expiration_seconds_bucket{job="apiserver"}[5m]))) < 24*60*60
|
|
for: 0m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: Kubernetes client certificate expires soon (instance {{ $labels.instance }})
|
|
description: "A client certificate used to authenticate to the apiserver is expiring in less than 24.0 hours.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|
|
- alert: KubernetesApiServerLatency
|
|
expr: histogram_quantile(0.99, sum(rate(apiserver_request_latencies_bucket{subresource!="log",verb!~"^(?:CONNECT|WATCHLIST|WATCH|PROXY)$"} [10m])) WITHOUT (instance, resource)) / 1e+06 > 1
|
|
for: 2m
|
|
labels:
|
|
severity: warning
|
|
annotations:
|
|
summary: Kubernetes API server latency (instance {{ $labels.instance }})
|
|
description: "Kubernetes API server has a 99th percentile latency of {{ $value }} seconds for {{ $labels.verb }} {{ $labels.resource }}.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}"
|