bstein/titan-iac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

recovery(ananke): leave flux root stopped on final hold

Browse Source
This commit is contained in:
jenkins 2026-06-18 20:54:16 -03:00
parent ea333f6648
commit 62d9791b76
1 changed files with 8 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
scripts/cluster_power_recovery.sh
View File

@ -146,6 +146,7 @@ RECOVERY_FLUX_APPLY_BOOTSTRAP_KUSTOMIZATION="${RECOVERY_FLUX_APPLY_BOOTSTRAP_KUS
RECOVERY_FLUX_ROOT_APPLY_TIMEOUT="${RECOVERY_FLUX_ROOT_APPLY_TIMEOUT:-15m}" RECOVERY_FLUX_ROOT_APPLY_TIMEOUT="${RECOVERY_FLUX_ROOT_APPLY_TIMEOUT:-15m}"
RECOVERY_FLUX_SUSPEND_VERIFY_ATTEMPTS="${RECOVERY_FLUX_SUSPEND_VERIFY_ATTEMPTS:-6}" RECOVERY_FLUX_SUSPEND_VERIFY_ATTEMPTS="${RECOVERY_FLUX_SUSPEND_VERIFY_ATTEMPTS:-6}"
RECOVERY_FLUX_SUSPEND_VERIFY_SLEEP_SECONDS="${RECOVERY_FLUX_SUSPEND_VERIFY_SLEEP_SECONDS:-10}" RECOVERY_FLUX_SUSPEND_VERIFY_SLEEP_SECONDS="${RECOVERY_FLUX_SUSPEND_VERIFY_SLEEP_SECONDS:-10}"
RECOVERY_FLUX_FINAL_RESTART_KUSTOMIZE_CONTROLLER="${RECOVERY_FLUX_FINAL_RESTART_KUSTOMIZE_CONTROLLER:-0}"
STARTUP_SERVICE_CHECK_TIMEOUT_SECONDS="${STARTUP_SERVICE_CHECK_TIMEOUT_SECONDS:-10}" STARTUP_SERVICE_CHECK_TIMEOUT_SECONDS="${STARTUP_SERVICE_CHECK_TIMEOUT_SECONDS:-10}"
STARTUP_SERVICE_CHECKLIST="${STARTUP_SERVICE_CHECKLIST:-}" STARTUP_SERVICE_CHECKLIST="${STARTUP_SERVICE_CHECKLIST:-}"
STARTUP_INCLUDE_INGRESS_CHECKS="${STARTUP_INCLUDE_INGRESS_CHECKS:-1}" STARTUP_INCLUDE_INGRESS_CHECKS="${STARTUP_INCLUDE_INGRESS_CHECKS:-1}"
@ -1095,9 +1096,13 @@ force_recovery_flux_suspend_with_controller_stop() {
fi fi
patch_recovery_optional_flux_suspend_without_snapshot true patch_recovery_optional_flux_suspend_without_snapshot true
if [[ "${RECOVERY_FLUX_FINAL_RESTART_KUSTOMIZE_CONTROLLER}" == "1" || "${RECOVERY_FLUX_FINAL_RESTART_KUSTOMIZE_CONTROLLER}" == "true" ]]; then
run kubectl -n flux-system scale deployment kustomize-controller --replicas=1 run kubectl -n flux-system scale deployment kustomize-controller --replicas=1
kubectl -n flux-system rollout status deployment/kustomize-controller --timeout=2m || warn "kustomize-controller did not become Ready after final Flux suspend reassertion." kubectl -n flux-system rollout status deployment/kustomize-controller --timeout=2m || warn "kustomize-controller did not become Ready after final Flux suspend reassertion."
sleep "${RECOVERY_FLUX_SUSPEND_VERIFY_SLEEP_SECONDS}" sleep "${RECOVERY_FLUX_SUSPEND_VERIFY_SLEEP_SECONDS}"
else
warn "Leaving kustomize-controller stopped to preserve the recovery Flux hold."
fi
local unsuspended local unsuspended
unsuspended="$(recovery_flux_unsuspended_list | paste -sd, -)" unsuspended="$(recovery_flux_unsuspended_list | paste -sd, -)"