MachineLearningKubernetesNonCriticalPodCrashLooping

Reference information for MachineLearningKubernetesNonCriticalPodCrashLooping used as part of Pulse in CDP Private Cloud Data Services.

Summary

Machine Learning Pod is crash looping

PromQL Expression

increase(kube_pod_container_status_restarts_total{pod!~"{{ .Values.alerts.mlCriticalPodsRegexp }}", appType="ml"} [15m]) > 2

Time Period

0s

Severity

warning

Source

environments/ml