#!/usr/bin/env bash
# Wait until Ceph reports HEALTH_OK or HEALTH_WARN (single-node often stays WARN).
set -euo pipefail

TIMEOUT="${1:-900}"
ROOK_NS="rook-ceph"
START=$(date +%s)

echo "Waiting for rook-ceph-tools deployment..."
for _ in $(seq 1 60); do
  if kubectl -n "${ROOK_NS}" get deploy rook-ceph-tools >/dev/null 2>&1; then
    if kubectl -n "${ROOK_NS}" rollout status deploy/rook-ceph-tools --timeout=120s 2>/dev/null; then
      break
    fi
  fi
  sleep 5
done

while true; do
  NOW=$(date +%s)
  if (( NOW - START > TIMEOUT )); then
    echo "Timed out after ${TIMEOUT}s waiting for Ceph health" >&2
    kubectl -n "${ROOK_NS}" get cephcluster,pod -o wide || true
    exit 1
  fi

  if kubectl -n "${ROOK_NS}" get deploy rook-ceph-tools >/dev/null 2>&1; then
    HEALTH=$(kubectl -n "${ROOK_NS}" exec deploy/rook-ceph-tools -- ceph health 2>/dev/null || echo "unknown")
    echo "Ceph health: ${HEALTH}"
    if [[ "${HEALTH}" == "HEALTH_OK" || "${HEALTH}" == HEALTH_WARN* ]]; then
      PHASE=$(kubectl -n "${ROOK_NS}" get cephcluster rook-ceph -o jsonpath='{.status.phase}' 2>/dev/null || echo "")
      echo "CephCluster phase: ${PHASE}"
      if [[ "${PHASE}" == "Ready" ]]; then
        exit 0
      fi
    fi
  fi
  sleep 15
done