debug: print detailed Flannel pod diagnostics on rollout timeout
All checks were successful
Terraform Plan / Terraform Plan (push) Successful in 18s

When kube-flannel daemonset rollout stalls, print pod descriptions and per-container logs for the init containers and main flannel container so the next failure shows the actual cause instead of only Init:0/2.
This commit is contained in:
2026-03-07 12:18:52 +00:00
parent e740d47011
commit 065567210e

View File

@@ -331,6 +331,18 @@ class Controller:
check=False,
)
print(proc.stdout)
proc = self.remote(
self.primary_ip,
"for p in $(sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel get pods -o name 2>/dev/null); do echo \"--- describe $p ---\"; sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel describe $p || true; done",
check=False,
)
print(proc.stdout)
proc = self.remote(
self.primary_ip,
"for p in $(sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel get pods -o name 2>/dev/null); do echo \"--- logs $p kube-flannel ---\"; sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel logs $p -c kube-flannel --tail=120 || true; echo \"--- logs $p install-cni-plugin ---\"; sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel logs $p -c install-cni-plugin --tail=120 || true; echo \"--- logs $p install-cni ---\"; sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel logs $p -c install-cni --tail=120 || true; done",
check=False,
)
print(proc.stdout)
proc = self.remote(
self.primary_ip,
"for p in $(sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel get pods -o name 2>/dev/null); do sudo kubectl --kubeconfig /etc/kubernetes/admin.conf -n kube-flannel logs --tail=120 $p || true; done",