diff --git a/dist/rules/kubernetes/kubestate-exporter.yml b/dist/rules/kubernetes/kubestate-exporter.yml index 783682e..719948e 100644 --- a/dist/rules/kubernetes/kubestate-exporter.yml +++ b/dist/rules/kubernetes/kubestate-exporter.yml @@ -10,52 +10,52 @@ groups: labels: severity: critical annotations: - summary: Kubernetes node not ready (instance {{ $labels.instance }}) + summary: Kubernetes Node not ready (node {{ $labels.node }}) description: "Node {{ $labels.node }} has been unready for a long time\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesMemoryPressure + - alert: KubernetesNodeMemoryPressure 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 }}" + summary: Kubernetes Node memory pressure (node {{ $labels.node }}) + description: "Node {{ $labels.node }} has MemoryPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesDiskPressure + - alert: KubernetesNodeDiskPressure 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 }}" + summary: Kubernetes Node disk pressure (node {{ $labels.node }}) + description: "Node {{ $labels.node }} has DiskPressure condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesNetworkUnavailable + - alert: KubernetesNodeNetworkUnavailable expr: 'kube_node_status_condition{condition="NetworkUnavailable",status="true"} == 1' for: 2m labels: severity: critical annotations: - summary: Kubernetes network unavailable (instance {{ $labels.instance }}) - description: "{{ $labels.node }} has NetworkUnavailable condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Kubernetes Node network unavailable (node {{ $labels.node }}) + description: "Node {{ $labels.node }} has NetworkUnavailable condition\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesOutOfCapacity + - alert: KubernetesNodeOutOfPodCapacity 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 }}" + summary: Kubernetes Node out of pod capacity (node {{ $labels.node }}) + description: "Node {{ $labels.node }} is out of pod capacity\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesContainerOomKiller + - alert: KubernetesContainerOomKilled 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 }}) + summary: Kubernetes Container oom killed (pod {{ $labels.pod }}) 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 @@ -64,7 +64,7 @@ groups: labels: severity: warning annotations: - summary: Kubernetes Job failed (instance {{ $labels.instance }}) + summary: Kubernetes Job failed (job_name {{ $labels.job_name }}) description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesCronjobSuspended @@ -73,7 +73,7 @@ groups: labels: severity: warning annotations: - summary: Kubernetes CronJob suspended (instance {{ $labels.instance }}) + summary: Kubernetes CronJob suspended (cronjob {{ $labels.cronjob }}) description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesPersistentvolumeclaimPending @@ -82,7 +82,7 @@ groups: labels: severity: warning annotations: - summary: Kubernetes PersistentVolumeClaim pending (instance {{ $labels.instance }}) + summary: Kubernetes PersistentVolumeClaim pending (pvc {{ $labels.persistentvolumeclaim }}) description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesVolumeOutOfDiskSpace @@ -91,8 +91,8 @@ groups: 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 }}" + summary: Kubernetes Volume out of disk space (pvc {{ $labels.persistentvolumeclaim }}) + description: "Volume under {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is almost full (< 10% left)\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesVolumeFullInFourDays expr: 'predict_linear(kubelet_volume_stats_available_bytes[6h], 4 * 24 * 3600) < 0' @@ -100,8 +100,8 @@ groups: labels: severity: critical annotations: - summary: Kubernetes Volume full in four days (instance {{ $labels.instance }}) - description: "{{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Kubernetes Volume full in four days (pvc {{ $labels.persistentvolumeclaim }}) + description: "Volume under {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is expected to fill up within four days. Currently {{ $value | humanize }}% is available.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesPersistentvolumeError expr: 'kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0' @@ -109,8 +109,8 @@ groups: labels: severity: critical annotations: - summary: Kubernetes PersistentVolume error (instance {{ $labels.instance }}) - description: "Persistent volume is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Kubernetes PersistentVolume error (pv {{ $labels.persistentvolume }}) + description: "Persistent volume {{ $labels.persistentvolume }} is in bad state\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesStatefulsetDown expr: 'kube_statefulset_replicas != kube_statefulset_status_replicas_ready > 0' @@ -118,35 +118,36 @@ groups: labels: severity: critical annotations: - summary: Kubernetes StatefulSet down (instance {{ $labels.instance }}) - description: "A StatefulSet went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Kubernetes StatefulSet down (statefulset {{ $labels.statefulset }}) + description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} went down\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesHpaScalingAbility + - alert: KubernetesHpaScaleInability 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 }}" + summary: Kubernetes HPA scale inability (hpa {{ $labels.horizontalpodautoscaler }}) + description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to scale\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesHpaMetricAvailability + - alert: KubernetesHpaMetricsUnavailability 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 }}" + summary: Kubernetes HPA metrics unavailability (hpa {{ $labels.horizontalpodautoscaler }}) + description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is unable to collect metrics\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesHpaScaleCapability + + - alert: KubernetesHpaScaleMaximum 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 }}" + summary: Kubernetes HPA scale maximum (hpa {{ $labels.horizontalpodautoscaler }}) + description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} has hit maximum number of desired pods\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesHpaUnderutilized expr: 'max(quantile_over_time(0.5, kube_horizontalpodautoscaler_status_desired_replicas[1d]) == kube_horizontalpodautoscaler_spec_min_replicas) by (horizontalpodautoscaler) > 3' @@ -154,8 +155,8 @@ groups: labels: severity: info annotations: - summary: Kubernetes HPA underutilized (instance {{ $labels.instance }}) - description: "HPA is constantly at minimum replicas for 50% of the time. Potential cost saving here.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Kubernetes HPA underutilized (hpa {{ $labels.horizontalpodautoscaler }}) + description: "HPA {{ $labels.namespace }}/{{ $labels.horizontalpodautoscaler }} is constantly at minimum replicas for 50% of the time. Potential cost saving here.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesPodNotHealthy expr: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0' @@ -163,8 +164,8 @@ groups: 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 }}" + summary: Kubernetes Pod not healthy (pod {{ $labels.pod }}) + description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-running state for longer than 15 minutes.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesPodCrashLooping expr: 'increase(kube_pod_container_status_restarts_total[1m]) > 3' @@ -172,17 +173,17 @@ groups: 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 }}" + summary: Kubernetes pod crash looping (pod {{ $labels.pod }}) + description: "Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - - alert: KubernetesReplicassetMismatch + - alert: KubernetesReplicasetReplicasMismatch 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 }}" + summary: Kubernetes ReplicaSet replicas mismatch (replicaset {{ $labels.replicaset }}) + description: "ReplicaSet {{ $labels.namespace }}/{{ $labels.replicaset }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesDeploymentReplicasMismatch expr: 'kube_deployment_spec_replicas != kube_deployment_status_replicas_available' @@ -190,8 +191,8 @@ groups: labels: severity: warning annotations: - summary: Kubernetes Deployment replicas mismatch (instance {{ $labels.instance }}) - description: "Deployment Replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" + summary: Kubernetes Deployment replicas mismatch (deployment {{ $labels.deployment }}) + description: "Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesStatefulsetReplicasMismatch expr: 'kube_statefulset_status_replicas_ready != kube_statefulset_status_replicas' @@ -199,8 +200,8 @@ groups: 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 }}" + summary: Kubernetes StatefulSet replicas mismatch (statefulset {{ $labels.statefulset }}) + description: "StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} replicas mismatch\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesDeploymentGenerationMismatch expr: 'kube_deployment_status_observed_generation != kube_deployment_metadata_generation' @@ -208,8 +209,8 @@ groups: 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 }}" + summary: Kubernetes Deployment generation mismatch (deployment {{ $labels.deployment }}) + description: "Deployment {{ $labels.namespace }}/{{ $labels.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' @@ -217,8 +218,8 @@ groups: 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 }}" + summary: Kubernetes StatefulSet generation mismatch (statefulset {{ $labels.statefulset }}) + description: "StatefulSet {{ $labels.namespace }}/{{ $labels.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)' @@ -226,8 +227,8 @@ groups: 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 }}" + summary: Kubernetes StatefulSet update not rolled out (statefulset {{ $labels.statefulset }}) + description: "StatefulSet {{ $labels.namespace }}/{{ $labels.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' @@ -235,8 +236,8 @@ groups: 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 }}" + summary: Kubernetes DaemonSet rollout stuck (daemonset {{ $labels.daemonset }}) + description: "Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled or not ready\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesDaemonsetMisscheduled expr: 'kube_daemonset_status_number_misscheduled > 0' @@ -244,8 +245,8 @@ groups: 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 }}" + summary: Kubernetes DaemonSet misscheduled (daemonset {{ $labels.daemonset }}) + description: "Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesCronjobTooLong expr: 'time() - kube_cronjob_next_schedule_time > 3600' @@ -253,7 +254,7 @@ groups: labels: severity: warning annotations: - summary: Kubernetes CronJob too long (instance {{ $labels.instance }}) + summary: Kubernetes CronJob too long (cronjob {{ $labels.cronjob }}) description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesJobSlowCompletion @@ -262,7 +263,7 @@ groups: labels: severity: critical annotations: - summary: Kubernetes job slow completion (instance {{ $labels.instance }}) + summary: Kubernetes Job slow completion (job_name {{ $labels.job_name }}) description: "Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time.\n VALUE = {{ $value }}\n LABELS = {{ $labels }}" - alert: KubernetesApiServerErrors