{{- /*
Generated from 'kubernetes-system-kubelet' group from https://github.com/prometheus-operator/kube-prometheus.git
Do not change in-place! In order to change this file first read following link:
https://github.com/prometheus-community/helm-charts/tree/main/charts/kube-prometheus-stack/hack
*/ -}}
{{- $kubeTargetVersion := default .Capabilities.KubeVersion.GitVersion .Values.kubeTargetVersionOverride }}
{{- if and (semverCompare ">=1.14.0-0" $kubeTargetVersion) (semverCompare "<9.9.9-9" $kubeTargetVersion) .Values.defaultRules.create .Values.defaultRules.rules.kubernetesSystem }}
{{- $kubeStateMetricsJob := include "kube-prometheus-stack-kube-state-metrics.name" . }}
apiVersion: monitoring.coreos.com/v1
kind: PrometheusRule
metadata:
  name: {{ printf "%s-%s" (include "kube-prometheus-stack.fullname" .) "kubernetes-system-kubelet" | trunc 63 | trimSuffix "-" }}
  namespace: {{ template "kube-prometheus-stack.namespace" . }}
  labels:
    app: {{ template "kube-prometheus-stack.name" . }}
{{ include "kube-prometheus-stack.labels" . | indent 4 }}
{{- if .Values.defaultRules.labels }}
{{ toYaml .Values.defaultRules.labels | indent 4 }}
{{- end }}
{{- if .Values.defaultRules.annotations }}
  annotations:
{{ toYaml .Values.defaultRules.annotations | indent 4 }}
{{- end }}
spec:
  groups:
  - name: kubernetes-system-kubelet
    rules:
{{- if not (.Values.defaultRules.disabled.KubeNodeNotReady | default false) }}
    - alert: KubeNodeNotReady
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: '{{`{{`}} $labels.node {{`}}`}} has been unready for more than 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubenodenotready
        summary: Node is not ready.
      expr: |-
        kube_node_status_condition{job="{{ $kubeStateMetricsJob }}",condition="Ready",status="true"} == 0
        and on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, node)
        kube_node_spec_unschedulable{job="{{ $kubeStateMetricsJob }}"} == 0
      for: {{ dig "KubeNodeNotReady" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeNodeNotReady" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeNodePressure | default false) }}
    - alert: KubeNodePressure
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: '{{`{{`}} $labels.node {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}} has active Condition {{`{{`}} $labels.condition {{`}}`}}. This is caused by resource usage exceeding eviction thresholds.'
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubenodepressure
        summary: Node has as active Condition.
      expr: |-
        kube_node_status_condition{job="{{ $kubeStateMetricsJob }}",condition=~"(MemoryPressure|DiskPressure|PIDPressure)",status="true"} == 1
        and on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, node)
        kube_node_spec_unschedulable{job="{{ $kubeStateMetricsJob }}"} == 0
      for: {{ dig "KubeNodePressure" "for" "10m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeNodePressure" "severity" "info" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeNodeUnreachable | default false) }}
    - alert: KubeNodeUnreachable
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: '{{`{{`}} $labels.node {{`}}`}} is unreachable and some workloads may be rescheduled on cluster {{`{{`}} $labels.cluster {{`}}`}}.'
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubenodeunreachable
        summary: Node is unreachable.
      expr: (kube_node_spec_taint{job="{{ $kubeStateMetricsJob }}",key="node.kubernetes.io/unreachable",effect="NoSchedule"} unless ignoring(key,value) kube_node_spec_taint{job="{{ $kubeStateMetricsJob }}",key=~"ToBeDeletedByClusterAutoscaler|cloud.google.com/impending-node-termination|aws-node-termination-handler/spot-itn"}) == 1
      for: {{ dig "KubeNodeUnreachable" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeNodeUnreachable" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletTooManyPods | default false) }}
    - alert: KubeletTooManyPods
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Kubelet '{{`{{`}} $labels.node {{`}}`}}' is running at {{`{{`}} $value | humanizePercentage {{`}}`}} of its Pod capacity on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubelettoomanypods
        summary: Kubelet is running at capacity.
      expr: |-
        (
          max by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance) (
            kubelet_running_pods{job="kubelet", metrics_path="/metrics"} > 1
          )
          * on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance) group_left(node)
          max by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance, node) (
            kubelet_node_name{job="kubelet", metrics_path="/metrics"}
          )
        )
        / on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, node) group_left()
        max by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, node) (
          kube_node_status_capacity{job="{{ $kubeStateMetricsJob }}", resource="pods"} != 1
        ) > 0.95
      for: {{ dig "KubeletTooManyPods" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeletTooManyPods" "severity" "info" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeNodeReadinessFlapping | default false) }}
    - alert: KubeNodeReadinessFlapping
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: The readiness status of node {{`{{`}} $labels.node {{`}}`}} has changed {{`{{`}} $value {{`}}`}} times in the last 15 minutes on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubenodereadinessflapping
        summary: Node readiness status is flapping.
      expr: |-
        sum(changes(kube_node_status_condition{job="{{ $kubeStateMetricsJob }}",status="true",condition="Ready"}[15m])) by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, node) > 2
        and on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, node)
        kube_node_spec_unschedulable{job="{{ $kubeStateMetricsJob }}"} == 0
      for: {{ dig "KubeNodeReadinessFlapping" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeNodeReadinessFlapping" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeNodeEviction | default false) }}
    - alert: KubeNodeEviction
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Node {{`{{`}} $labels.node {{`}}`}} on {{`{{`}} $labels.cluster {{`}}`}} is evicting Pods due to {{`{{`}} $labels.eviction_signal {{`}}`}}.  Eviction occurs when eviction thresholds are crossed, typically caused by Pods exceeding RAM/ephemeral-storage limits.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubenodeeviction
        summary: Node is evicting pods.
      expr: |-
        sum(rate(kubelet_evictions{job="kubelet", metrics_path="/metrics"}[15m])) by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, eviction_signal, instance)
        * on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance) group_left(node)
        max by ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance, node) (
          kubelet_node_name{job="kubelet", metrics_path="/metrics"}
        )
        > 0
      for: {{ dig "KubeNodeEviction" "for" "0s" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeNodeEviction" "severity" "info" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletPlegDurationHigh | default false) }}
    - alert: KubeletPlegDurationHigh
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: The Kubelet Pod Lifecycle Event Generator has a 99th percentile duration of {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/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: {{ dig "KubeletPlegDurationHigh" "for" "5m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeletPlegDurationHigh" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletPodStartUpLatencyHigh | default false) }}
    - alert: KubeletPodStartUpLatencyHigh
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Kubelet Pod startup 99th percentile latency is {{`{{`}} $value {{`}}`}} seconds on node {{`{{`}} $labels.node {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/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 ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance, le)) * on ({{ range $.Values.defaultRules.additionalAggregationLabels }}{{ . }},{{ end }}cluster, instance) group_left(node) kubelet_node_name{job="kubelet", metrics_path="/metrics"} > 60
      for: {{ dig "KubeletPodStartUpLatencyHigh" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeletPodStartUpLatencyHigh" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletClientCertificateExpiration | default false) }}
    - alert: KubeletClientCertificateExpiration
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletclientcertificateexpiration
        summary: Kubelet client certificate is about to expire.
      expr: kubelet_certificate_manager_client_ttl_seconds < 604800
      labels:
        severity: {{ dig "KubeletClientCertificateExpiration" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletClientCertificateExpiration | default false) }}
    - alert: KubeletClientCertificateExpiration
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Client certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletclientcertificateexpiration
        summary: Kubelet client certificate is about to expire.
      expr: kubelet_certificate_manager_client_ttl_seconds < 86400
      labels:
        severity: {{ dig "KubeletClientCertificateExpiration" "severity" "critical" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletServerCertificateExpiration | default false) }}
    - alert: KubeletServerCertificateExpiration
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletservercertificateexpiration
        summary: Kubelet server certificate is about to expire.
      expr: kubelet_certificate_manager_server_ttl_seconds < 604800
      labels:
        severity: {{ dig "KubeletServerCertificateExpiration" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletServerCertificateExpiration | default false) }}
    - alert: KubeletServerCertificateExpiration
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Server certificate for Kubelet on node {{`{{`}} $labels.node {{`}}`}} expires in {{`{{`}} $value | humanizeDuration {{`}}`}} on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletservercertificateexpiration
        summary: Kubelet server certificate is about to expire.
      expr: kubelet_certificate_manager_server_ttl_seconds < 86400
      labels:
        severity: {{ dig "KubeletServerCertificateExpiration" "severity" "critical" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletClientCertificateRenewalErrors | default false) }}
    - alert: KubeletClientCertificateRenewalErrors
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its client certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes) on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletclientcertificaterenewalerrors
        summary: Kubelet has failed to renew its client certificate.
      expr: increase(kubelet_certificate_manager_client_expiration_renew_errors[5m]) > 0
      for: {{ dig "KubeletClientCertificateRenewalErrors" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeletClientCertificateRenewalErrors" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if not (.Values.defaultRules.disabled.KubeletServerCertificateRenewalErrors | default false) }}
    - alert: KubeletServerCertificateRenewalErrors
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Kubelet on node {{`{{`}} $labels.node {{`}}`}} has failed to renew its server certificate ({{`{{`}} $value | humanize {{`}}`}} errors in the last 5 minutes) on cluster {{`{{`}} $labels.cluster {{`}}`}}.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletservercertificaterenewalerrors
        summary: Kubelet has failed to renew its server certificate.
      expr: increase(kubelet_server_expiration_renew_errors[5m]) > 0
      for: {{ dig "KubeletServerCertificateRenewalErrors" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeletServerCertificateRenewalErrors" "severity" "warning" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- if .Values.prometheusOperator.kubeletService.enabled }}
{{- if not (.Values.defaultRules.disabled.KubeletDown | default false) }}
    - alert: KubeletDown
      annotations:
{{- if .Values.defaultRules.additionalRuleAnnotations }}
{{ toYaml .Values.defaultRules.additionalRuleAnnotations | indent 8 }}
{{- end }}
{{- if .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem }}
{{ toYaml .Values.defaultRules.additionalRuleGroupAnnotations.kubernetesSystem | indent 8 }}
{{- end }}
        description: Kubelet has disappeared from Prometheus target discovery.
        runbook_url: {{ .Values.defaultRules.runbookUrl }}/kubernetes/kubeletdown
        summary: Target disappeared from Prometheus target discovery.
      expr: absent(up{job="kubelet", metrics_path="/metrics"} == 1)
      for: {{ dig "KubeletDown" "for" "15m" .Values.customRules }}
      {{- with .Values.defaultRules.keepFiringFor }}
      keep_firing_for: "{{ . }}"
      {{- end }}
      labels:
        severity: {{ dig "KubeletDown" "severity" "critical" .Values.customRules }}
      {{- if or .Values.defaultRules.additionalRuleLabels .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
        {{- with .Values.defaultRules.additionalRuleLabels }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
        {{- with .Values.defaultRules.additionalRuleGroupLabels.kubernetesSystem }}
          {{- toYaml . | nindent 8 }}
        {{- end }}
      {{- end }}
{{- end }}
{{- end }}
{{- end }}