diff options
Diffstat (limited to 'vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-apps.yaml')
| -rw-r--r-- | vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-apps.yaml | 154 |
1 files changed, 154 insertions, 0 deletions
diff --git a/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-apps.yaml b/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-apps.yaml new file mode 100644 index 00000000..21549c23 --- /dev/null +++ b/vnfs/DAaaS/prometheus-operator/templates/alertmanager/rules/kubernetes-apps.yaml @@ -0,0 +1,154 @@ +# Generated from 'kubernetes-apps' group from https://raw.githubusercontent.com/coreos/prometheus-operator/master/contrib/kube-prometheus/manifests/prometheus-rules.yaml +{{- if and .Values.defaultRules.create .Values.kubeStateMetrics.enabled }} +apiVersion: {{ printf "%s/v1" (.Values.prometheusOperator.crdApiGroup | default "monitoring.coreos.com") }} +kind: PrometheusRule +metadata: + name: {{ printf "%s-%s" (include "prometheus-operator.fullname" .) "kubernetes-apps" | trunc 63 | trimSuffix "-" }} + labels: + app: {{ template "prometheus-operator.name" . }} +{{ include "prometheus-operator.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-apps + rules: + - alert: KubePodCrashLooping + annotations: + message: Pod {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} ({{`{{ $labels.container }}`}}) is restarting {{`{{ printf "%.2f" $value }}`}} times / 5 minutes. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodcrashlooping + expr: rate(kube_pod_container_status_restarts_total{job="kube-state-metrics"}[15m]) * 60 * 5 > 0 + for: 1h + labels: + severity: critical + - alert: KubePodNotReady + annotations: + message: Pod {{`{{ $labels.namespace }}`}}/{{`{{ $labels.pod }}`}} has been in a non-ready state for longer than an hour. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubepodnotready + expr: sum by (namespace, pod) (kube_pod_status_phase{job="kube-state-metrics", phase=~"Pending|Unknown"}) > 0 + for: 1h + labels: + severity: critical + - alert: KubeDeploymentGenerationMismatch + annotations: + message: Deployment generation for {{`{{ $labels.namespace }}`}}/{{`{{ $labels.deployment }}`}} does not match, this indicates that the Deployment has failed but has not been rolled back. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentgenerationmismatch + expr: |- + kube_deployment_status_observed_generation{job="kube-state-metrics"} + != + kube_deployment_metadata_generation{job="kube-state-metrics"} + for: 15m + labels: + severity: critical + - alert: KubeDeploymentReplicasMismatch + annotations: + message: Deployment {{`{{ $labels.namespace }}`}}/{{`{{ $labels.deployment }}`}} has not matched the expected number of replicas for longer than an hour. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedeploymentreplicasmismatch + expr: |- + kube_deployment_spec_replicas{job="kube-state-metrics"} + != + kube_deployment_status_replicas_available{job="kube-state-metrics"} + for: 1h + labels: + severity: critical + - alert: KubeStatefulSetReplicasMismatch + annotations: + message: StatefulSet {{`{{ $labels.namespace }}`}}/{{`{{ $labels.statefulset }}`}} has not matched the expected number of replicas for longer than 15 minutes. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetreplicasmismatch + expr: |- + kube_statefulset_status_replicas_ready{job="kube-state-metrics"} + != + kube_statefulset_status_replicas{job="kube-state-metrics"} + for: 15m + labels: + severity: critical + - alert: KubeStatefulSetGenerationMismatch + annotations: + message: StatefulSet generation for {{`{{ $labels.namespace }}`}}/{{`{{ $labels.statefulset }}`}} does not match, this indicates that the StatefulSet has failed but has not been rolled back. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetgenerationmismatch + expr: |- + kube_statefulset_status_observed_generation{job="kube-state-metrics"} + != + kube_statefulset_metadata_generation{job="kube-state-metrics"} + for: 15m + labels: + severity: critical + - alert: KubeStatefulSetUpdateNotRolledOut + annotations: + message: StatefulSet {{`{{ $labels.namespace }}`}}/{{`{{ $labels.statefulset }}`}} update has not been rolled out. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubestatefulsetupdatenotrolledout + expr: |- + max without (revision) ( + kube_statefulset_status_current_revision{job="kube-state-metrics"} + unless + kube_statefulset_status_update_revision{job="kube-state-metrics"} + ) + * + ( + kube_statefulset_replicas{job="kube-state-metrics"} + != + kube_statefulset_status_replicas_updated{job="kube-state-metrics"} + ) + for: 15m + labels: + severity: critical + - alert: KubeDaemonSetRolloutStuck + annotations: + message: Only {{`{{ $value }}`}}% of the desired Pods of DaemonSet {{`{{ $labels.namespace }}`}}/{{`{{ $labels.daemonset }}`}} are scheduled and ready. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetrolloutstuck + expr: |- + kube_daemonset_status_number_ready{job="kube-state-metrics"} + / + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} * 100 < 100 + for: 15m + labels: + severity: critical + - alert: KubeDaemonSetNotScheduled + annotations: + message: '{{`{{ $value }}`}} Pods of DaemonSet {{`{{ $labels.namespace }}`}}/{{`{{ $labels.daemonset }}`}} are not scheduled.' + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetnotscheduled + expr: |- + kube_daemonset_status_desired_number_scheduled{job="kube-state-metrics"} + - + kube_daemonset_status_current_number_scheduled{job="kube-state-metrics"} > 0 + for: 10m + labels: + severity: warning + - alert: KubeDaemonSetMisScheduled + annotations: + message: '{{`{{ $value }}`}} Pods of DaemonSet {{`{{ $labels.namespace }}`}}/{{`{{ $labels.daemonset }}`}} are running where they are not supposed to run.' + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubedaemonsetmisscheduled + expr: kube_daemonset_status_number_misscheduled{job="kube-state-metrics"} > 0 + for: 10m + labels: + severity: warning + - alert: KubeCronJobRunning + annotations: + message: CronJob {{`{{ $labels.namespace }}`}}/{{`{{ $labels.cronjob }}`}} is taking more than 1h to complete. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubecronjobrunning + expr: time() - kube_cronjob_next_schedule_time{job="kube-state-metrics"} > 3600 + for: 1h + labels: + severity: warning + - alert: KubeJobCompletion + annotations: + message: Job {{`{{ $labels.namespace }}`}}/{{`{{ $labels.job_name }}`}} is taking more than one hour to complete. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobcompletion + expr: kube_job_spec_completions{job="kube-state-metrics"} - kube_job_status_succeeded{job="kube-state-metrics"} > 0 + for: 1h + labels: + severity: warning + - alert: KubeJobFailed + annotations: + message: Job {{`{{ $labels.namespace }}`}}/{{`{{ $labels.job_name }}`}} failed to complete. + runbook_url: https://github.com/kubernetes-monitoring/kubernetes-mixin/tree/master/runbook.md#alert-name-kubejobfailed + expr: kube_job_status_failed{job="kube-state-metrics"} > 0 + for: 1h + labels: + severity: warning +{{- end }}
\ No newline at end of file |