fix: ignore stale Rancher helm operation pods

2026-04-25 02:23:30 +00:00
parent bfcf57bcc5
commit 045880bdd6
1 changed files with 5 additions and 2 deletions
@@ -616,8 +616,11 @@ jobs:
            kubectl -n flux-system wait --for=condition=Ready kustomization/addon-observability-content --timeout=60s
            kubectl -n flux-system wait --for=condition=Ready helmrelease --all --timeout=60s
            kubectl get storageclass | grep -E "^flash-nfs.*\\(default\\)"
-            kubectl get pods -A --field-selector=status.phase!=Running,status.phase!=Succeeded --no-headers | tee /tmp/nonrunning-pods
-            test ! -s /tmp/nonrunning-pods
+            kubectl get pods -A --no-headers \
+              | grep -Ev "[[:space:]](Running|Completed)[[:space:]]" \
+              | grep -Ev "^cattle-system[[:space:]]+helm-operation-" \
+              | tee /tmp/unhealthy-pods || true
+            test ! -s /tmp/unhealthy-pods
            kubectl -n kube-system get pods -o wide
            kubectl -n tailscale-system get pods -o wide
            kubectl -n external-secrets get pods -o wide