diff --git a/CHANGELOG.md b/CHANGELOG.md index ca39d181c..47981f5c2 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Changed - reduced sensitivity for lokiringunhealthy +- added check if KSM was up 2 minutes ago in `WorkloadClusterCriticalPodNotRunningAWS` alert ## [2.144.0] - 2023-11-27 diff --git a/helm/prometheus-rules/templates/alerting-rules/aws.workload-cluster.rules.yml b/helm/prometheus-rules/templates/alerting-rules/aws.workload-cluster.rules.yml index 0720535e6..f77d22f92 100644 --- a/helm/prometheus-rules/templates/alerting-rules/aws.workload-cluster.rules.yml +++ b/helm/prometheus-rules/templates/alerting-rules/aws.workload-cluster.rules.yml @@ -32,7 +32,7 @@ spec: annotations: description: '{{`Critical pod {{ $labels.namespace }}/{{ $labels.pod }} is not running.`}}' opsrecipe: critical-pod-is-not-running/ - expr: kube_pod_container_status_running{namespace="kube-system",container=~"(k8s-api-server|k8s-controller-manager|k8s-scheduler)"} != 1 or label_replace(absent(kube_pod_container_status_running{namespace="kube-system",container="k8s-api-server"}), "pod", "$1", "container", "(.+)") == 1 or label_replace(absent(kube_pod_container_status_running{namespace="kube-system",container="k8s-controller-manager"}), "pod", "$1", "container", "(.+)") == 1 or label_replace(absent(kube_pod_container_status_running{namespace="kube-system",container="k8s-scheduler"}), "pod", "$1", "container", "(.+)") == 1 + expr: kube_pod_container_status_running{namespace="kube-system",container=~"(k8s-api-server|k8s-controller-manager|k8s-scheduler)"} != 1 or (label_replace(absent(kube_pod_container_status_running{namespace="kube-system",container="k8s-api-server"}), "pod", "$1", "container", "(.+)") == 1 or label_replace(absent(kube_pod_container_status_running{namespace="kube-system",container="k8s-controller-manager"}), "pod", "$1", "container", "(.+)") == 1 or label_replace(absent(kube_pod_container_status_running{namespace="kube-system",container="k8s-scheduler"}), "pod", "$1", "container", "(.+)") == 1) and (up{app="kube-state-metrics"} offset 2m) for: 20m labels: area: kaas