fix: ignore stale Rancher helm operation pods
Deploy Cluster / Terraform (push) Successful in 28s
Deploy Cluster / Ansible (push) Has been cancelled

This commit is contained in:
2026-04-25 02:23:30 +00:00
parent bfcf57bcc5
commit 045880bdd6
+5 -2
View File
@@ -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 kustomization/addon-observability-content --timeout=60s
kubectl -n flux-system wait --for=condition=Ready helmrelease --all --timeout=60s kubectl -n flux-system wait --for=condition=Ready helmrelease --all --timeout=60s
kubectl get storageclass | grep -E "^flash-nfs.*\\(default\\)" 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 kubectl get pods -A --no-headers \
test ! -s /tmp/nonrunning-pods | 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 kube-system get pods -o wide
kubectl -n tailscale-system get pods -o wide kubectl -n tailscale-system get pods -o wide
kubectl -n external-secrets get pods -o wide kubectl -n external-secrets get pods -o wide