Add Harbor/Ceph runbooks and align single-node Ceph docs with abr deployment.

Document registry ingress split, image mirroring, loop OSD setup, and platform integration paths.
2026-07-01 00:22:06 +03:30
parent 8d1855b89c
commit ee5bd0a291
21 changed files with 2124 additions and 2 deletions
@@ -0,0 +1,52 @@
+#!/usr/bin/env bash
+# Install Rook-Ceph operator + cluster + CloudHost bucket extras.
+# Usage: ./scripts/install.sh [single-node|multi-node]
+set -euo pipefail
+
+PROFILE="${1:-single-node}"
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+CHART_DIR="$(cd "${SCRIPT_DIR}/.." && pwd)"
+ROOK_NS="rook-ceph"
+EXTRAS_NS="cloudhost-builds"
+CLUSTER_VALUES="${CHART_DIR}/values-rook-cluster-${PROFILE}.yaml"
+
+if [[ ! -f "${CLUSTER_VALUES}" ]]; then
+  echo "Unknown profile: ${PROFILE} (missing ${CLUSTER_VALUES})" >&2
+  exit 1
+fi
+
+echo "==> Profile: ${PROFILE}"
+echo "==> Adding rook-release helm repo"
+helm repo add rook-release https://charts.rook.io/release 2>/dev/null || true
+helm repo update rook-release
+
+echo "==> [1/4] Installing Rook operator in ${ROOK_NS}"
+helm upgrade --install rook-ceph rook-release/rook-ceph \
+  --namespace "${ROOK_NS}" \
+  --create-namespace \
+  --wait \
+  --timeout 10m
+
+echo "==> [2/4] Waiting for Rook operator deployment"
+kubectl -n "${ROOK_NS}" rollout status deploy/rook-ceph-operator --timeout=300s
+
+echo "==> [3/4] Installing Ceph cluster (${CLUSTER_VALUES})"
+helm upgrade --install rook-ceph-cluster rook-release/rook-ceph-cluster \
+  --namespace "${ROOK_NS}" \
+  -f "${CLUSTER_VALUES}" \
+  --wait \
+  --timeout 25m
+
+echo "==> Waiting for CephCluster phase = Ready (up to 20 min)"
+"${SCRIPT_DIR}/wait-ceph-ready.sh" 1200
+
+echo "==> [4/4] Installing CloudHost Ceph extras (ObjectBucketClaim) in ${EXTRAS_NS}"
+kubectl create namespace "${EXTRAS_NS}" 2>/dev/null || true
+helm upgrade --install cloudhost-ceph "${CHART_DIR}" \
+  --namespace "${EXTRAS_NS}" \
+  -f "${CHART_DIR}/values.yaml" \
+  --wait \
+  --timeout 15m
+
+echo ""
+echo "==> Done. Run ./scripts/verify.sh to confirm health and print integration hints."
@@ -0,0 +1,26 @@
+#!/usr/bin/env bash
+# Remove CloudHost extras + Rook cluster + operator (DATA LOSS).
+set -euo pipefail
+
+read -r -p "This deletes ALL Ceph data. Type 'delete-ceph' to continue: " CONFIRM
+if [[ "${CONFIRM}" != "delete-ceph" ]]; then
+  echo "Aborted."
+  exit 1
+fi
+
+helm uninstall cloudhost-ceph -n cloudhost-builds 2>/dev/null || true
+helm uninstall rook-ceph-cluster -n rook-ceph 2>/dev/null || true
+helm uninstall rook-ceph -n rook-ceph 2>/dev/null || true
+
+echo "Waiting for Rook resources to terminate..."
+sleep 15
+kubectl -n rook-ceph get pods 2>/dev/null || true
+
+cat <<'EOF'
+
+IMPORTANT: On each node, wipe Rook state before reinstalling:
+  sudo rm -rf /var/lib/rook
+  sudo rm -rf /var/lib/rook/osd
+
+For raw-disk OSDs also zap disks (see RUNBOOK-CEPH.fa.md).
+EOF
@@ -0,0 +1,35 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+ROOK_NS="rook-ceph"
+EXTRAS_NS="cloudhost-builds"
+
+echo "=== StorageClasses ==="
+kubectl get storageclass | grep -E 'NAME|rook-ceph' || true
+
+echo ""
+echo "=== Ceph status ==="
+kubectl -n "${ROOK_NS}" exec deploy/rook-ceph-tools -- ceph status 2>/dev/null || echo "(tools pod not ready yet)"
+
+echo ""
+echo "=== OSD / MON pods ==="
+kubectl -n "${ROOK_NS}" get pods -l app=rook-ceph-osd 2>/dev/null || kubectl -n "${ROOK_NS}" get pods | grep -E 'osd|mon|mgr|rgw' || true
+
+echo ""
+echo "=== Object bucket claim ==="
+kubectl -n "${EXTRAS_NS}" get obc,app-sources 2>/dev/null || kubectl -n "${EXTRAS_NS}" get obc 2>/dev/null || true
+
+echo ""
+echo "=== Platform credentials secret ==="
+if kubectl -n "${EXTRAS_NS}" get secret ceph-app-sources-credentials >/dev/null 2>&1; then
+  echo "Secret ceph-app-sources-credentials exists"
+  kubectl -n "${EXTRAS_NS}" get secret ceph-app-sources-credentials -o jsonpath='{.data.SOURCE_STORAGE_BUCKET}' | base64 -d
+  echo ""
+else
+  echo "Secret ceph-app-sources-credentials not ready — check bucket sync job:"
+  kubectl -n "${EXTRAS_NS}" get jobs,pods | grep bucket-sync || true
+fi
+
+echo ""
+echo "=== Suggested backend env ==="
+kubectl -n "${EXTRAS_NS}" get configmap cloudhost-ceph-integration -o yaml 2>/dev/null | sed -n '/PLATFORM_/p;/SOURCE_STORAGE_ENDPOINT/p' || true
@@ -0,0 +1,39 @@
+#!/usr/bin/env bash
+# Wait until Ceph reports HEALTH_OK or HEALTH_WARN (single-node often stays WARN).
+set -euo pipefail
+
+TIMEOUT="${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