From e3c615b5c1ff63c0026bb22962a1b93343545078 Mon Sep 17 00:00:00 2001 From: Mayne0213 Date: Fri, 9 Jan 2026 15:09:43 +0900 Subject: [PATCH] FEAT(alertmanager): add OOMKilled alert rule - Add PrometheusRule to alert when containers are OOMKilled - Severity: warning, fires immediately --- alertmanager/kustomization.yaml | 1 + alertmanager/manifests/oom-alert-rule.yaml | 21 +++++++++++++++++++++ 2 files changed, 22 insertions(+) create mode 100644 alertmanager/manifests/oom-alert-rule.yaml diff --git a/alertmanager/kustomization.yaml b/alertmanager/kustomization.yaml index 584d185..e02835a 100644 --- a/alertmanager/kustomization.yaml +++ b/alertmanager/kustomization.yaml @@ -3,3 +3,4 @@ kind: Kustomization resources: - manifests/servicemonitor.yaml - manifests/secret.yaml +- manifests/oom-alert-rule.yaml diff --git a/alertmanager/manifests/oom-alert-rule.yaml b/alertmanager/manifests/oom-alert-rule.yaml new file mode 100644 index 0000000..04e840e --- /dev/null +++ b/alertmanager/manifests/oom-alert-rule.yaml @@ -0,0 +1,21 @@ +apiVersion: monitoring.coreos.com/v1 +kind: PrometheusRule +metadata: + name: oom-alerts + namespace: prometheus + labels: + app: kube-prometheus-stack + release: prometheus +spec: + groups: + - name: oom.rules + rules: + - alert: KubeContainerOOMKilled + annotations: + description: "Container {{ $labels.container }} in pod {{ $labels.namespace }}/{{ $labels.pod }} was OOMKilled." + summary: "Container was OOMKilled" + expr: | + kube_pod_container_status_last_terminated_reason{reason="OOMKilled"} == 1 + for: 0m + labels: + severity: warning