fix(minio): freeze the community image by digest and alert on pull failure (#57)

Co-authored-by: rock <[email protected]>
2026-10-06 03:43:12 +00:00
parent b6e317b34c
commit 64cd1f2c4e
4 changed files with 25 additions and 4 deletions
@@ -27,6 +27,24 @@ spec:
          annotations:
            summary: "{{ $value }} pod(s) stuck in Pending state for >10m"

+        # ImagePullBackOff on a vendor-deleted image produced no alert for 13 days
+        - alert: PodImagePullFailure
+          expr: sum(kube_pod_container_status_waiting_reason{reason=~"ImagePullBackOff|ErrImagePull"}) by (namespace, pod) > 0
+          for: 10m
+          labels:
+            severity: critical
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.pod }} cannot pull its image"
+
+        # Pod not ready
+        - alert: PodNotReady
+          expr: sum(kube_pod_status_ready{condition="false"}) by (namespace, pod) > 0
+          for: 15m
+          labels:
+            severity: warning
+          annotations:
+            summary: "{{ $labels.namespace }}/{{ $labels.pod }} is not ready"
+
        # CrashLoopBackOff
        - alert: PodCrashLooping
          expr: sum(kube_pod_container_status_waiting_reason{reason="CrashLoopBackOff"}) by (namespace, pod) > 0