xiaoxia-saas/infra/docker/deploy-production-registry.sh

#!/bin/sh
set -eu

# ============================================
# Production 部署脚本 - Registry 方式
# 用法：IMAGE_TAG=<version> REGISTRY_TOKEN=<token> sh deploy-production-registry.sh
# ============================================

IMAGE_TAG="${IMAGE_TAG:-}"
REGISTRY="${REGISTRY:-git.xiaoxiajianji.com/xiaoxia/xiaoxia-saas}"
REGISTRY_USER="${REGISTRY_USER:-xiaoxia}"
REGISTRY_TOKEN="${REGISTRY_TOKEN:-}"

ENV_FILE="${ENV_FILE:-/var/lib/xiaoxia-saas-production/.env}"
GENERATED_DIR="${GENERATED_DIR:-/var/lib/xiaoxia-saas-production/generated}"
LEGACY_ASSETS_DIR="${LEGACY_ASSETS_DIR:-/var/lib/xiaoxia-saas-production/legacy-assets}"

if [ -z "$IMAGE_TAG" ]; then
  echo "ERROR: IMAGE_TAG is required"
  exit 1
fi

test -f "$ENV_FILE"
mkdir -p "$GENERATED_DIR"
mkdir -p "$LEGACY_ASSETS_DIR"

# ---- 登录 Registry ----
if [ -n "$REGISTRY_TOKEN" ]; then
  echo "Logging in to registry: $REGISTRY"
  REGISTRY_HOST=$(echo "$REGISTRY" | cut -d/ -f1)
  printf %s "$REGISTRY_TOKEN" | docker login "$REGISTRY_HOST" -u "$REGISTRY_USER" --password-stdin 2>/dev/null || {
    echo "WARN: docker login failed, will try to pull anyway"
  }
fi

# ---- Pull 三镜像 ----
REGISTRY_API="${REGISTRY}/xiaoxia-saas-api:${IMAGE_TAG}"
REGISTRY_WORKER="${REGISTRY}/xiaoxia-saas-worker:${IMAGE_TAG}"
REGISTRY_WEB="${REGISTRY}/xiaoxia-saas-web:${IMAGE_TAG}"

LOCAL_API="xiaoxia-saas-api:${IMAGE_TAG}"
LOCAL_WORKER="xiaoxia-saas-worker:${IMAGE_TAG}"
LOCAL_WEB="xiaoxia-saas-web:${IMAGE_TAG}"

echo "Pulling API image..."
docker pull "$REGISTRY_API"
echo "Pulling Worker image..."
docker pull "$REGISTRY_WORKER"
echo "Pulling Web image..."
docker pull "$REGISTRY_WEB"

# ---- Re-tag 成本地名 ----
docker tag "$REGISTRY_API" "$LOCAL_API"
docker tag "$REGISTRY_WORKER" "$LOCAL_WORKER"
docker tag "$REGISTRY_WEB" "$LOCAL_WEB"
echo "All images pulled and tagged."

# ---- 备份旧版 assets（部署期间缓存用户不 404） ----
echo "Backing up legacy assets from current web container..."
if docker inspect xiaoxia-web-production >/dev/null 2>&1; then
  _tmpdir="/tmp/legacy-assets-$$"
  rm -rf "$_tmpdir"
  mkdir -p "$_tmpdir"
  docker cp xiaoxia-web-production:/usr/share/nginx/html/assets/. "$_tmpdir/" 2>/dev/null || true
  # 合并到 LEGACY_ASSETS_DIR（保留所有历史版本的 assets）
  if [ -d "$_tmpdir" ] && [ "$(ls -A "$_tmpdir" 2>/dev/null)" ]; then
    cp -an "$_tmpdir"/. "$LEGACY_ASSETS_DIR"/ 2>/dev/null || true
    echo "Legacy assets backed up: $(ls "$_tmpdir" | wc -l) files"
  fi
  rm -rf "$_tmpdir"
else
  echo "No existing web container, skipping legacy assets backup"
fi

# 清理超过 7 天的旧 assets 文件（避免无限增长）
if [ -d "$LEGACY_ASSETS_DIR" ]; then
  find "$LEGACY_ASSETS_DIR" -type f -mtime +7 -delete 2>/dev/null || true
  echo "Legacy assets cleanup done (retain 7 days)"
fi

# ---- 确保基础设施容器在运行 ----
echo "Checking infrastructure containers..."
for c in xiaoxia-postgres-production xiaoxia-redis-production; do
  if ! docker inspect "$c" >/dev/null 2>&1; then
    echo "ERROR: Required container not found: $c"
    exit 1
  fi
  state=$(docker inspect -f '{{.State.Status}}' "$c")
  if [ "$state" != "running" ]; then
    echo "ERROR: Container not running: $c ($state)"
    exit 1
  fi
done

# ---- 确保生产网络存在 ----
docker network create xiaoxia-net-production 2>/dev/null || true

# ---- 执行数据库 Migration ----
echo "Running database migrations..."
docker run --rm \
  --env-file "$ENV_FILE" \
  --network xiaoxia-net-production \
  -e APP_ENV=production \
  "$LOCAL_API" sh -c "cd /app && alembic upgrade head"
echo "Migrations completed."

# ---- 停止旧容器 ----
echo "Stopping old containers..."
docker rm -f xiaoxia-api-production 2>/dev/null || true
docker rm -f xiaoxia-worker-production 2>/dev/null || true
docker rm -f xiaoxia-web-production 2>/dev/null || true

# ---- 日志配置（所有容器共用） ----
LOG_OPTS="--log-driver json-file --log-opt max-size=50m --log-opt max-file=3"

# ---- 启动 API ----
echo "Starting API container..."
docker run -d \
  --name xiaoxia-api-production \
  --env-file "$ENV_FILE" \
  --network xiaoxia-net-production \
  -p 127.0.0.1:8001:8000 \
  -e APP_ENV=production \
  -e APP_VERSION="$IMAGE_TAG" \
  -e GENERATED_FILES_DIR=/app/generated \
  -e GENERATED_FILES_URL_PREFIX=/generated-files \
  -e PUBLIC_API_BASE_URL=https://api.xiaoxiajianji.com \
  -v "$GENERATED_DIR:/app/generated" \
  --restart unless-stopped \
  --cpus 2 \
  --memory 2g \
  --health-cmd "python -c \"import urllib.request; urllib.request.urlopen('http://localhost:8000/health', timeout=5)\"" \
  --health-interval 30s \
  --health-timeout 10s \
  --health-retries 3 \
  --health-start-period 40s \
  $LOG_OPTS \
  "$LOCAL_API"

# ---- 启动 Worker ----
echo "Starting Worker container..."
docker run -d \
  --name xiaoxia-worker-production \
  --env-file "$ENV_FILE" \
  --network xiaoxia-net-production \
  -e APP_ENV=production \
  -e APP_VERSION="$IMAGE_TAG" \
  -e WORKER_CONCURRENCY="${WORKER_CONCURRENCY:-4}" \
  -e GENERATION_CONCURRENCY="${GENERATION_CONCURRENCY:-2}" \
  -e WORKER_MAX_TASKS_PER_CHILD=100 \
  -e GENERATED_FILES_DIR=/app/generated \
  -e GENERATED_FILES_URL_PREFIX=/generated-files \
  -e PUBLIC_API_BASE_URL=https://api.xiaoxiajianji.com \
  -v "$GENERATED_DIR:/app/generated" \
  --restart unless-stopped \
  --cpus 2 \
  --memory 2g \
  --health-cmd "sh -c \"pgrep -f 'celery.*worker' >/dev/null 2>&1 || grep -q celery /proc/1/cmdline || exit 1\"" \
  --health-interval 30s \
  --health-timeout 10s \
  --health-retries 3 \
  --health-start-period 30s \
  $LOG_OPTS \
  "$LOCAL_WORKER"

# ---- 启动 Web ----
# Legacy assets 挂载到 /usr/share/nginx/html/assets-legacy/assets/
# nginx 配置中 assets location 有 fallback 逻辑
LEGACY_VOLUME=""
if [ -d "$LEGACY_ASSETS_DIR" ] && [ "$(ls -A "$LEGACY_ASSETS_DIR" 2>/dev/null)" ]; then
  LEGACY_VOLUME="-v ${LEGACY_ASSETS_DIR}:/usr/share/nginx/html/assets-legacy/assets:ro"
  echo "Web container: legacy assets mounted (fallback)"
else
  echo "Web container: no legacy assets to mount"
fi

echo "Starting Web container..."
docker run -d \
  --name xiaoxia-web-production \
  --network xiaoxia-net-production \
  -p 127.0.0.1:3002:80 \
  --restart unless-stopped \
  --cpus 0.5 \
  --memory 512m \
  $LEGACY_VOLUME \
  --health-cmd "wget --spider -q http://127.0.0.1:80" \
  --health-interval 30s \
  --health-timeout 5s \
  --health-retries 3 \
  $LOG_OPTS \
  "$LOCAL_WEB"

# ---- 等待 API 健康 ----
echo "Waiting for API to become healthy..."
i=0
while [ "$i" -lt 40 ]; do
  if curl -sf --max-time 5 http://127.0.0.1:8001/health >/dev/null 2>&1; then
    echo "API is healthy!"
    break
  fi
  i=$((i + 1))
  echo "  Waiting... ($i/40)"
  sleep 3
done

if [ "$i" -ge 40 ]; then
  echo "ERROR: API did not become healthy within 120s"
  docker logs --tail 50 xiaoxia-api-production
  exit 1
fi

# ---- 等待 Web 健康 ----
echo "Waiting for Web to become healthy..."
i=0
while [ "$i" -lt 15 ]; do
  if curl -sf --max-time 5 http://127.0.0.1:3002/ >/dev/null 2>&1; then
    echo "Web is healthy!"
    break
  fi
  i=$((i + 1))
  echo "  Waiting... ($i/15)"
  sleep 2
done

if [ "$i" -ge 15 ]; then
  echo "ERROR: Web did not become healthy within 30s"
  docker logs --tail 30 xiaoxia-web-production
  exit 1
fi

# ---- 清理旧镜像 ----
echo "Cleaning up old images..."
docker image prune -af --filter "until=168h" 2>/dev/null || true
docker builder prune -af --filter "until=168h" 2>/dev/null || true

echo ""
echo "=== Production deployment complete ==="
echo "API:      http://127.0.0.1:8001"
echo "Web:      http://127.0.0.1:3002"
echo "Version:  $IMAGE_TAG"
docker ps --format "table {{.Names}}\t{{.Status}}\t{{.Image}}" | grep production