From 7fa11bf6cc2f1f5204d3fbab8a3a3939cd0a0dbd Mon Sep 17 00:00:00 2001 From: michaelact <86778470+michaelact@users.noreply.github.com> Date: Sat, 2 Dec 2023 00:25:11 +0700 Subject: [PATCH] Add simple and meaningful `kube-state-metrics` alert summary (#394) * feat: add 'summary' to be overriden from rules.yml * chore: add simple and meaningful summary for kubernetes alerts --- _data/rules.yml | 20 ++++++++++++++++++++ dist/template.yml | 2 +- 2 files changed, 21 insertions(+), 1 deletion(-) diff --git a/_data/rules.yml b/_data/rules.yml index ed73ece..2403b71 100644 --- a/_data/rules.yml +++ b/_data/rules.yml @@ -1776,16 +1776,19 @@ groups: doc_url: https://github.com/kubernetes/kube-state-metrics/tree/master/docs rules: - name: Kubernetes Node not ready + summary: Kubernetes Node ready (node {{ $labels.node }}) description: Node {{ $labels.node }} has been unready for a long time query: 'kube_node_status_condition{condition="Ready",status="true"} == 0' severity: critical for: 10m - name: Kubernetes Node memory pressure + summary: Kubernetes memory pressure (node {{ $labels.node }}) description: "Node {{ $labels.node }} has MemoryPressure condition" query: 'kube_node_status_condition{condition="MemoryPressure",status="true"} == 1' severity: critical for: 2m - name: Kubernetes Node disk pressure + summary: Kubernetes disk pressure (node {{ $labels.node }}) description: "Node {{ $labels.node }} has DiskPressure condition" query: 'kube_node_status_condition{condition="DiskPressure",status="true"} == 1' severity: critical @@ -1801,18 +1804,22 @@ groups: severity: warning for: 2m - name: Kubernetes Container oom killer + summary: Kubernetes container oom killer ({{ $labels.namespace }}/{{ $labels.pod }}:{{ $labels.container }}) description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} has been OOMKilled {{ $value }} times in the last 10 minutes." query: '(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' severity: warning - name: Kubernetes Job failed + summary: Kubernetes Job failed ({{ $labels.namespace }}/{{ $labels.job_name }}) description: "Job {{ $labels.namespace }}/{{ $labels.job_name }} failed to complete" query: 'kube_job_status_failed > 0' severity: warning - name: Kubernetes CronJob suspended + summary: Kubernetes CronJob suspended ({{ $labels.namespace }}/{{ $labels.cronjob }}) description: "CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is suspended" query: 'kube_cronjob_spec_suspend != 0' severity: warning - name: Kubernetes PersistentVolumeClaim pending + summary: Kubernetes PersistentVolumeClaim pending ({{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }}) description: "PersistentVolumeClaim {{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }} is pending" query: 'kube_persistentvolumeclaim_status_phase{phase="Pending"} == 1' severity: warning @@ -1827,10 +1834,12 @@ groups: query: 'predict_linear(kubelet_volume_stats_available_bytes[6h:5m], 4 * 24 * 3600) < 0' severity: critical - name: Kubernetes PersistentVolume error + summary: Kubernetes PersistentVolumeClaim pending ({{ $labels.namespace }}/{{ $labels.persistentvolumeclaim }}) description: "Persistent volume {{ $labels.persistentvolume }} is in bad state" query: 'kube_persistentvolume_status_phase{phase=~"Failed|Pending", job="kube-state-metrics"} > 0' severity: critical - name: Kubernetes StatefulSet down + summary: Kubernetes StatefulSet down ({{ $labels.namespace }}/{{ $labels.statefulset }}) description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} went down query: 'kube_statefulset_replicas != kube_statefulset_status_replicas_ready > 0' severity: critical @@ -1854,21 +1863,25 @@ groups: query: 'max(quantile_over_time(0.5, kube_horizontalpodautoscaler_status_desired_replicas[1d]) == kube_horizontalpodautoscaler_spec_min_replicas) by (horizontalpodautoscaler) > 3' # allow minimum 3 replicas running severity: info - name: Kubernetes Pod not healthy + summary: Kubernetes Pod not healthy ({{ $labels.namespace }}/{{ $labels.pod }}) description: Pod {{ $labels.namespace }}/{{ $labels.pod }} has been in a non-running state for longer than 15 minutes. query: 'sum by (namespace, pod) (kube_pod_status_phase{phase=~"Pending|Unknown|Failed"}) > 0' severity: critical for: 15m - name: Kubernetes pod crash looping + summary: Kubernetes pod crash looping ({{ $labels.namespace }}/{{ $labels.pod }}) description: Pod {{ $labels.namespace }}/{{ $labels.pod }} is crash looping query: 'increase(kube_pod_container_status_restarts_total[1m]) > 3' severity: warning for: 2m - name: Kubernetes ReplicaSet replicas mismatch + summary: Kubernetes ReplicasSet mismatch ({{ $labels.namespace }}/{{ $labels.replicaset }}) description: ReplicaSet {{ $labels.namespace }}/{{ $labels.replicaset }} replicas mismatch query: 'kube_replicaset_spec_replicas != kube_replicaset_status_ready_replicas' severity: warning for: 10m - name: Kubernetes Deployment replicas mismatch + summary: Kubernetes Deployment replicas mismatch ({{ $labels.namespace }}/{{ $labels.deployment }}) description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} replicas mismatch query: 'kube_deployment_spec_replicas != kube_deployment_status_replicas_available' severity: warning @@ -1879,37 +1892,44 @@ groups: severity: warning for: 10m - name: Kubernetes Deployment generation mismatch + summary: Kubernetes Deployment generation mismatch ({{ $labels.namespace }}/{{ $labels.deployment }}) description: Deployment {{ $labels.namespace }}/{{ $labels.deployment }} has failed but has not been rolled back. query: 'kube_deployment_status_observed_generation != kube_deployment_metadata_generation' severity: critical for: 10m - name: Kubernetes StatefulSet generation mismatch + summary: Kubernetes StatefulSet generation mismatch ({{ $labels.namespace }}/{{ $labels.statefulset }}) description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} has failed but has not been rolled back. query: 'kube_statefulset_status_observed_generation != kube_statefulset_metadata_generation' severity: critical for: 10m - name: Kubernetes StatefulSet update not rolled out + summary: Kubernetes StatefulSet update not rolled out ({{ $labels.namespace }}/{{ $labels.statefulset }}) description: StatefulSet {{ $labels.namespace }}/{{ $labels.statefulset }} update has not been rolled out. query: 'max without (revision) (kube_statefulset_status_current_revision unless kube_statefulset_status_update_revision) * (kube_statefulset_replicas != kube_statefulset_status_replicas_updated)' severity: warning for: 10m - name: Kubernetes DaemonSet rollout stuck + summary: Kubernetes DaemonSet rollout stuck ({{ $labels.namespace }}/{{ $labels.daemonset }}) description: Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are not scheduled or not ready query: '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' severity: warning for: 10m - name: Kubernetes DaemonSet misscheduled + summary: Kubernetes DaemonSet misscheduled ({{ $labels.namespace }}/{{ $labels.daemonset }}) description: Some Pods of DaemonSet {{ $labels.namespace }}/{{ $labels.daemonset }} are running where they are not supposed to run query: 'kube_daemonset_status_number_misscheduled > 0' severity: critical for: 1m - name: Kubernetes CronJob too long + summary: Kubernetes CronJob too long ({{ $labels.namespace }}/{{ $labels.cronjob }}) description: CronJob {{ $labels.namespace }}/{{ $labels.cronjob }} is taking more than 1h to complete. query: 'time() - kube_cronjob_next_schedule_time > 3600' severity: warning comments: | Threshold should be customized for each cronjob name. - name: Kubernetes Job slow completion + summary: Kubernetes job slow completion ({{ $labels.namespace }}/{{ $labels.job_name }}) description: Kubernetes Job {{ $labels.namespace }}/{{ $labels.job_name }} did not complete in time. query: 'kube_job_spec_completions - kube_job_status_succeeded - kube_job_status_failed > 0' severity: critical diff --git a/dist/template.yml b/dist/template.yml index 0dd9684..cdde4ea 100644 --- a/dist/template.yml +++ b/dist/template.yml @@ -11,6 +11,6 @@ groups: labels: severity: {{ rule.severity }} annotations: - summary: {{ rule.name }} (instance {% raw %}{{ $labels.instance }}{% endraw %}) + summary: {% if rule.summary %}{{ rule.summary }}{% else %}{{ rule.name }} (instance {% raw %}{{ $labels.instance }}{% endraw %}){% endif %} description: "{{ rule.description | replace: '"', '\"' }}\n VALUE = {% raw %}{{ $value }}{% endraw %}\n LABELS = {% raw %}{{ $labels }}{% endraw %}" {% endfor %} \ No newline at end of file