ALERT K8SControllerManagerDown IF absent(up{job="kube-controller-manager"}) or (count by(cluster) (up{job="kube-controller-manager"} == 1) == 0) FOR 5m LABELS { severity = "critical", } ANNOTATIONS { summary = "Controller manager is down", description = "There is no running K8S controller manager. Deployments and replication controllers are not making progress.", }