railiance-apps/tools/cnpg-backup-status.sh

#!/usr/bin/env bash
set -euo pipefail

namespace="${CNPG_NAMESPACE:-databases}"

if ! kubectl get ns "$namespace" >/dev/null 2>&1; then
  echo "ERROR: namespace $namespace is not reachable from the current kubeconfig" >&2
  exit 1
fi

echo "CNPG backup posture in namespace ${namespace}"
context="$(kubectl config current-context 2>/dev/null || echo unknown)"
server="$(kubectl config view --minify -o jsonpath='{.clusters[0].cluster.server}' 2>/dev/null || echo unknown)"
echo "kube-context: ${context}"
echo "api-server:   ${server}"
echo

mapfile -t clusters < <(
  kubectl get cluster -n "$namespace" -o jsonpath='{range .items[*]}{.metadata.name}{"\n"}{end}' 2>/dev/null \
    | sort
)
if ((${#clusters[@]} == 0)); then
  echo "ERROR: no CNPG Cluster resources in ${namespace}" >&2
  exit 1
fi

missing=0
logical_backup_note=0

for cluster in "${clusters[@]}"; do
  if ! kubectl get cluster "$cluster" -n "$namespace" >/dev/null 2>&1; then
    echo "${cluster}: MISSING (Cluster CR not found)"
    missing=$((missing + 1))
    echo
    continue
  fi

  backup_spec="$(kubectl get cluster "$cluster" -n "$namespace" \
    -o jsonpath='{.spec.backup}' 2>/dev/null || true)"
  if [[ -z "$backup_spec" || "$backup_spec" == "null" ]]; then
    echo "${cluster}: backup spec = null"
  else
    echo "${cluster}: backup spec configured"
  fi

  scheduled="$(kubectl get scheduledbackup -n "$namespace" \
    -o jsonpath="{range .items[?(@.spec.cluster.name=='${cluster}')]}{.metadata.name}{' '}{end}" 2>/dev/null || true)"
  scheduled="${scheduled%" "}"
  if [[ -z "$scheduled" ]]; then
    echo "${cluster}: ScheduledBackup = none"
    missing=$((missing + 1))
    if [[ "$cluster" == "apps-pg" || "$cluster" == "gitea-db" || "$cluster" == "forgejo-db" ]]; then
      echo "${cluster}: Phase 1 fallback = logical pg_dump (see make apps-pg-backup-dry-run or platform forgejo-backup)"
      logical_backup_note=1
    fi
  else
    echo "${cluster}: ScheduledBackup = ${scheduled}"
  fi

  if command -v kubectl >/dev/null 2>&1 && kubectl cnpg status "$cluster" -n "$namespace" >/dev/null 2>&1; then
    echo "${cluster}: kubectl cnpg status available"
    kubectl cnpg status "$cluster" -n "$namespace" | sed -n '1,8p'
  else
    phase="$(kubectl get cluster "$cluster" -n "$namespace" -o jsonpath='{.status.phase}' 2>/dev/null || true)"
    instances="$(kubectl get cluster "$cluster" -n "$namespace" -o jsonpath='{.status.instances}' 2>/dev/null || true)"
    echo "${cluster}: phase=${phase:-unknown} instances=${instances:-unknown}"
  fi

  echo
done

if (( missing > 0 )); then
  echo "RESULT: degraded — ${missing} cluster(s) lack ScheduledBackup coverage"
  echo "See docs/app-data-backup-restore-handoff.md and manifests/cnpg-backup-readiness.yaml"
  if (( logical_backup_note )); then
    echo "Phase 1: logical pg_dump lane may still run when OpenBao offsite-lane is reachable"
    echo "See docs/credential-routing-railiance-apps.md"
  fi
  exit 1
fi

echo "RESULT: ok — all tracked clusters have ScheduledBackup resources"