ci: staging deploy改为Registry方式,去掉tar/scp/docker load
CI/CD Pipeline / Staging E2E Tests (push) Has been skipped
CI/CD Pipeline / Build Production Runtime Images (push) Has been skipped
CI/CD Pipeline / Deploy Production (push) Has been skipped
CI/CD Pipeline / Production Browser E2E (push) Has been skipped
CI/CD Pipeline / Deploy Staging (push) Failing after 40h1m36s
CI/CD Pipeline / Frontend Lint (push) Failing after 40h2m31s
CI/CD Pipeline / Validate Code Quality And Tests (push) Failing after 40h2m31s

This commit is contained in:
CI Test
2026-07-07 20:52:01 +08:00
parent bfb11c3526
commit d99ee6fc84
2 changed files with 215 additions and 78 deletions
+42 -78
View File
@@ -328,125 +328,89 @@ jobs:
apt-get update -qq && apt-get install -y -qq openssh-client >/dev/null 2>&1
echo "openssh-client installed"
- name: Build staging web artifact
shell: sh
run: |
set -eu
docker run --rm \
-v "$PWD:/workspace" \
-w /workspace/apps/web \
docker.m.daocloud.io/library/node:20 \
sh -lc 'npm ci && npm run build'
docker build --pull=false \
-f infra/docker/web-artifact.Dockerfile \
--build-arg NGINX_CONF=infra/docker/nginx-staging.conf \
-t "xiaoxia-saas-web:staging-${GITHUB_SHA}" \
.
test -f apps/web/dist/index.html
- name: Build and push staging API/Worker images
- name: Build and push all images to Gitea Registry
shell: bash
env:
REGISTRY_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
run: |
set -eu
REGISTRY="172.30.18.198:5000"
CACHE_REGISTRY="git.xiaoxiajianji.com/xiaoxia/xiaoxia-saas"
REGISTRY="git.xiaoxiajianji.com/xiaoxia/xiaoxia-saas"
TAG="${GITHUB_SHA}"
CACHE_BRANCH="${GITHUB_REF_NAME//\//-}"
# 登录 Gitea Registry(用于构建缓存,PAT 带 packages 权限)
printf '%s' "${REGISTRY_TOKEN}" | docker login git.xiaoxiajianji.com -u xiaoxia --password-stdin
docker buildx use default 2>/dev/null || true
# 登录内网 Registry(运行时镜像推送目标)
printf '%s' "Xiaoxia2026" | docker login 172.30.18.198:5000 -u admin --password-stdin 2>/dev/null || true
# 用默认 docker driver builder(共享 docker daemon 凭证,解决 buildx 认证问题)
docker buildx use default 2>/dev/null || {
echo "Warning: default builder not available, buildx cache may not work"
}
# 验证 builder 状态
docker buildx ls
# 构建 API(带分布式缓存,缓存存 Gitea Registry,镜像推内网 Registry
echo "=== Building API image ==="
docker buildx build \
--cache-from "type=registry,ref=${CACHE_REGISTRY}/api-cache:${CACHE_BRANCH},ignore-error=true" \
--cache-to "type=registry,ref=${CACHE_REGISTRY}/api-cache:${CACHE_BRANCH},mode=max" \
--cache-from "type=registry,ref=${REGISTRY}/api-cache:${CACHE_BRANCH},ignore-error=true" \
--cache-to "type=registry,ref=${REGISTRY}/api-cache:${CACHE_BRANCH},mode=max" \
-f infra/docker/api.Dockerfile \
-t "${REGISTRY}/xiaoxia-saas-api:dev" \
-t "${REGISTRY}/xiaoxia-saas-api:${TAG}" \
--push \
.
# 构建 Worker(带分布式缓存)
echo "=== Building Worker image ==="
docker buildx build \
--cache-from "type=registry,ref=${CACHE_REGISTRY}/worker-cache:${CACHE_BRANCH},ignore-error=true" \
--cache-to "type=registry,ref=${CACHE_REGISTRY}/worker-cache:${CACHE_BRANCH},mode=max" \
--cache-from "type=registry,ref=${REGISTRY}/worker-cache:${CACHE_BRANCH},ignore-error=true" \
--cache-to "type=registry,ref=${REGISTRY}/worker-cache:${CACHE_BRANCH},mode=max" \
-f infra/docker/worker.Dockerfile \
-t "${REGISTRY}/xiaoxia-saas-worker:dev" \
-t "${REGISTRY}/xiaoxia-saas-worker:${TAG}" \
--push \
.
- name: Package staging release artifact
shell: sh
run: |
set -eu
rm -rf dist/staging-artifacts
mkdir -p dist/staging-artifacts
tar --exclude=.git --exclude=apps/web/node_modules --exclude=./dist \
-czf dist/staging-artifacts/xiaoxia-staging-${GITHUB_SHA}.tar.gz .
docker save -o "dist/staging-artifacts/xiaoxia-web-staging-${GITHUB_SHA}.tar" "xiaoxia-saas-web:staging-${GITHUB_SHA}"
echo "=== Building web frontend ==="
docker run --rm \
-v "$PWD:/workspace" \
-w /workspace/apps/web \
docker.m.daocloud.io/library/node:20 \
sh -lc 'npm ci && npm run build'
test -f apps/web/dist/index.html
- name: Upload staging artifact to business host
echo "=== Building Web image ==="
docker buildx build \
--cache-from "type=registry,ref=${REGISTRY}/web-cache:${CACHE_BRANCH},ignore-error=true" \
--cache-to "type=registry,ref=${REGISTRY}/web-cache:${CACHE_BRANCH},mode=max" \
-f infra/docker/web-artifact.Dockerfile \
--build-arg NGINX_CONF=infra/docker/nginx-production.conf \
-t "${REGISTRY}/xiaoxia-saas-web:${TAG}" \
--push \
.
echo "=== All images pushed ==="
docker images | grep "${GITHUB_SHA}" || true
- name: Deploy staging via Registry pull
shell: sh
env:
STAGING_SSH_HOST: ${{ secrets.STAGING_SSH_HOST }}
STAGING_SSH_USER: ${{ secrets.STAGING_SSH_USER }}
STAGING_SSH_KEY: ${{ secrets.STAGING_SSH_KEY }}
REGISTRY_TOKEN: ${{ secrets.REGISTRY_TOKEN }}
run: |
set -eu
staging_host="${STAGING_SSH_HOST:-47.98.113.167}"
staging_user="${STAGING_SSH_USER:-root}"
mkdir -p ~/.ssh
# Prefer host key if available (more reliable), fallback to secrets
if [ -f /root/.ssh/xiaoxia_runtime_builder ]; then
key_path="/root/.ssh/xiaoxia_runtime_builder"
echo "Using host SSH key: $key_path"
elif [ -n "${STAGING_SSH_KEY:-}" ]; then
key_path="$HOME/.ssh/id_ed25519"
printf '%s\n' "$STAGING_SSH_KEY" > "$key_path"
chmod 600 "$key_path"
echo "Using secret SSH key: $key_path"
else
echo "ERROR: No SSH key available"
exit 1
fi
ssh-keyscan -H "$staging_host" >> ~/.ssh/known_hosts
ssh -i "$key_path" "$staging_user@$staging_host" "mkdir -p /var/lib/xiaoxia-saas-staging/artifacts"
scp -i "$key_path" "dist/staging-artifacts/xiaoxia-staging-${GITHUB_SHA}.tar.gz" \
"$staging_user@$staging_host:/var/lib/xiaoxia-saas-staging/artifacts/xiaoxia-staging-${GITHUB_SHA}.tar.gz"
scp -i "$key_path" "dist/staging-artifacts/xiaoxia-web-staging-${GITHUB_SHA}.tar" \
"$staging_user@$staging_host:/var/lib/xiaoxia-saas-staging/artifacts/xiaoxia-web-staging-${GITHUB_SHA}.tar"
ssh-keyscan -H "$staging_host" >> ~/.ssh/known_hosts 2>/dev/null || true
- name: Deploy staging stack on business host
shell: sh
env:
STAGING_SSH_HOST: ${{ secrets.STAGING_SSH_HOST }}
STAGING_SSH_USER: ${{ secrets.STAGING_SSH_USER }}
STAGING_SSH_KEY: ${{ secrets.STAGING_SSH_KEY }}
run: |
set -eu
staging_host="${STAGING_SSH_HOST:-47.98.113.167}"
staging_user="${STAGING_SSH_USER:-root}"
if [ -f /root/.ssh/xiaoxia_runtime_builder ]; then
key_path="/root/.ssh/xiaoxia_runtime_builder"
elif [ -n "${STAGING_SSH_KEY:-}" ]; then
key_path="$HOME/.ssh/id_ed25519"
else
echo "ERROR: No SSH key available"
exit 1
fi
echo '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' | base64 -d | ssh -i "$key_path" "$staging_user@$staging_host" "GITHUB_SHA='${GITHUB_SHA}' sh"
# 上传部署脚本(小文件,非源码包)
scp -i "$key_path" infra/docker/deploy-staging-registry.sh \
"$staging_user@$staging_host:/tmp/deploy-staging-registry.sh"
# SSH 执行部署
ssh -i "$key_path" "$staging_user@$staging_host" \
"IMAGE_TAG='${GITHUB_SHA}' REGISTRY_TOKEN='${REGISTRY_TOKEN}' sh /tmp/deploy-staging-registry.sh"
- name: Post-deploy smoke test
shell: sh
+173
View File
@@ -0,0 +1,173 @@
#!/bin/sh
set -eu
# ============================================
# Staging 部署脚本 - Registry 方式
# 用法:IMAGE_TAG=<sha|version> REGISTRY_TOKEN=<token> sh deploy-staging.sh
# ============================================
IMAGE_TAG="${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-staging/.env}"
COMPOSE_DIR="${COMPOSE_DIR:-/var/lib/xiaoxia-saas-staging/repo/infra/docker}"
GENERATED_DIR="${GENERATED_DIR:-/var/lib/xiaoxia-saas-staging/generated}"
if [ -z "$IMAGE_TAG" ]; then
echo "ERROR: IMAGE_TAG is required"
exit 1
fi
test -f "$ENV_FILE"
mkdir -p "$GENERATED_DIR"
# ---- 登录 Registry ----
if [ -n "$REGISTRY_TOKEN" ]; then
echo "Logging in to registry: $REGISTRY"
printf %s "$REGISTRY_TOKEN" | docker login "$(echo $REGISTRY | cut -d/ -f1)" -u "$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:staging-${IMAGE_TAG}"
LOCAL_WORKER="xiaoxia-saas-worker:staging-${IMAGE_TAG}"
LOCAL_WEB="xiaoxia-saas-web:staging-${IMAGE_TAG}"
echo "Pulling API image..."
docker pull "$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."
# ---- 确保基础设施容器在运行 ----
for c in xiaoxia-postgres-staging xiaoxia-redis-staging; 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 staging 网络存在 ----
docker network create xiaoxia-net-staging 2>/dev/null || true
# ---- 执行数据库 Migration ----
echo "Running database migrations..."
docker run --rm --env-file "$ENV_FILE" --network xiaoxia-net-staging "$LOCAL_API" sh -c "cd /app && alembic upgrade head"
echo "Migrations completed."
# ---- 停止旧容器 ----
docker rm -f xiaoxia-api-staging 2>/dev/null || true
docker rm -f xiaoxia-worker-staging 2>/dev/null || true
docker rm -f xiaoxia-web-staging 2>/dev/null || true
# ---- 启动 API ----
echo "Starting API container..."
docker run -d \
--name xiaoxia-api-staging \
--env-file "$ENV_FILE" \
--network xiaoxia-net-staging \
-p 127.0.0.1:8000:8000 \
-e APP_ENV=staging \
-e APP_VERSION="$IMAGE_TAG" \
-e GENERATED_FILES_DIR=/app/generated \
-e GENERATED_FILES_URL_PREFIX=/generated-files \
-v "$GENERATED_DIR:/app/generated" \
--restart unless-stopped \
--health-cmd "python -c \"import urllib.request; urllib.request.urlopen(http://localhost:8000/health, timeout=5)\"" \
--health-interval 30s \
--health-timeout 10s \
--health-retries 3 \
--health-start-period 40s \
"$LOCAL_API"
# ---- 启动 Worker ----
echo "Starting Worker container..."
docker run -d \
--name xiaoxia-worker-staging \
--env-file "$ENV_FILE" \
--network xiaoxia-net-staging \
-e APP_ENV=staging \
-e APP_VERSION="$IMAGE_TAG" \
-e WORKER_CONCURRENCY=1 \
-e WORKER_MAX_TASKS_PER_CHILD=100 \
-e GENERATED_FILES_DIR=/app/generated \
-e GENERATED_FILES_URL_PREFIX=/generated-files \
-v "$GENERATED_DIR:/app/generated" \
--restart unless-stopped \
--health-cmd "sh -c \"grep -q celery /proc/1/cmdline || exit 1\"" \
--health-interval 30s \
--health-timeout 10s \
--health-retries 3 \
--health-start-period 30s \
"$LOCAL_WORKER"
# ---- 启动 Web ----
# Web 镜像默认打包 production nginx.confstaging 需要挂载 staging 配置
NGINX_CONF="${NGINX_CONF:-${COMPOSE_DIR}/nginx-staging.conf}"
if [ ! -f "$NGINX_CONF" ]; then
echo "WARN: nginx config not found at $NGINX_CONF, using image default"
NGINX_VOLUME=""
else
NGINX_VOLUME="-v ${NGINX_CONF}:/etc/nginx/conf.d/default.conf:ro"
fi
echo "Starting Web container..."
docker run -d \
--name xiaoxia-web-staging \
--network xiaoxia-net-staging \
-p 127.0.0.1:3001:80 \
--restart unless-stopped \
$NGINX_VOLUME \
--health-cmd "wget --spider -q http://127.0.0.1:80" \
--health-interval 30s \
--health-timeout 5s \
--health-retries 3 \
"$LOCAL_WEB"
# ---- 等待 API 健康 ----
echo "Waiting for API to become healthy..."
i=0
while [ "$i" -lt 30 ]; do
if curl -sf --max-time 5 http://127.0.0.1:8000/health >/dev/null 2>&1; then
echo "API is healthy!"
break
fi
i=$((i + 1))
echo " Waiting... ($i/30)"
sleep 2
done
if [ "$i" -ge 30 ]; then
echo "ERROR: API did not become healthy within 60s"
docker logs --tail 30 xiaoxia-api-staging
exit 1
fi
# ---- 清理旧镜像 ----
docker image prune -af --filter "until=72h" 2>/dev/null || true
echo ""
echo "=== Staging deployment complete ==="
echo "API: http://127.0.0.1:8000"
echo "Web: http://127.0.0.1:3001"
echo "Version: $IMAGE_TAG"
docker ps --format "table {{.Names}}\t{{.Status}}" | grep staging