Script to fix rancher managed RKE2 clusters stuck in "Waiting for probes: kube-controller-manager, kube-scheduler"

rancher-fix-waiting-for-probes-controller-manager-cert.sh

export CRI_CONFIG_FILE=/var/lib/rancher/rke2/agent/etc/crictl.yaml
export CONTAINERD_ADDRESS=unix:///run/k3s/containerd/containerd.sock
export PATH=$PATH:/var/lib/rancher/rke2/bin

echo "=== CHECK BEFORE ==="
(
curl  --cacert /var/lib/rancher/rke2/server/tls/kube-controller-manager/kube-controller-manager.crt \
  https://127.0.0.1:10257/healthz >/dev/null 2>&1 \
  && echo "[OK] Kube Controller probe" \
  || echo "[FAIL] Kube Controller probe";

curl --cacert /var/lib/rancher/rke2/server/tls/kube-scheduler/kube-scheduler.crt \
  https://127.0.0.1:10259/healthz >/dev/null 2>&1  \
  && echo "[OK] Scheduler probe" \
  || echo "[FAIL] Scheduler probe";
)
echo "=== ROTATIONS ==="
echo "Rotating kube-controller-manager certificate"
rm /var/lib/rancher/rke2/server/tls/kube-controller-manager/kube-controller-manager.{crt,key}
crictl rm -f $(crictl ps -q --name kube-controller-manager)

echo "Rotating kube-scheduler certificate"
rm /var/lib/rancher/rke2/server/tls/kube-scheduler/kube-scheduler.{crt,key}
crictl rm -f $(crictl ps -q --name kube-scheduler)

echo "Waiting for pods to restart"
sleep 5

echo "=== CHECK AFTER ==="

(
curl  --cacert /var/lib/rancher/rke2/server/tls/kube-controller-manager/kube-controller-manager.crt \
  https://127.0.0.1:10257/healthz >/dev/null 2>&1 \
  && echo "[OK] Kube Controller probe" \
  || echo "[FAIL] Kube Controller probe";

curl --cacert /var/lib/rancher/rke2/server/tls/kube-scheduler/kube-scheduler.crt \
  https://127.0.0.1:10259/healthz >/dev/null 2>&1  \
  && echo "[OK] Scheduler probe" \
  || echo "[FAIL] Scheduler probe";
)