diff --git a/servers/gcp/k8s/argocd-apps/vault-helm-gke.yaml b/servers/gcp/k8s/argocd-apps/vault-helm-gke.yaml index 10d3f07..6631196 100644 --- a/servers/gcp/k8s/argocd-apps/vault-helm-gke.yaml +++ b/servers/gcp/k8s/argocd-apps/vault-helm-gke.yaml @@ -103,15 +103,26 @@ spec: storageClass: standard-rwo accessMode: ReadWriteOnce + # Annotations on the pod template — bumping rollme triggers a + # StatefulSet rolling restart (pods 2→1→0) to pick up the + # corrected raft retry_join addresses. + podAnnotations: + rollme: "2026-05-05-raft-join-fix" + readinessProbe: enabled: true - path: "/v1/sys/health?standbyok=true&sealedok=true&uninitcode=200" + # standbyok=true: standby pods pass (they serve reads). + # sealedok removed: sealed/uninit pods fail readiness so they + # leave the service endpoints and stop receiving external traffic. + path: "/v1/sys/health?standbyok=true" initialDelaySeconds: 5 periodSeconds: 5 failureThreshold: 3 livenessProbe: enabled: true + # Liveness keeps sealedok=true so sealed pods aren't killed — + # they need time to join raft and auto-unseal. path: "/v1/sys/health?standbyok=true&sealedok=true&uninitcode=200" initialDelaySeconds: 60 periodSeconds: 10