问题:本地完整栈起齐后 nginx 容器报 unhealthy,但宿主 curl http://localhost:6688/nginx-health 返回 200 —— 探针与实际服务不一致。 根因(实证,非推断): - nginx 的 `listen 80` 只绑 IPv4:容器内 netstat 显示 0.0.0.0:80,无 [::]:80; - /etc/hosts 中存在 `::1 localhost`,busybox wget 解析 localhost 时优先取 ::1; - 容器内实测:wget http://127.0.0.1/nginx-health → ok wget http://localhost/nginx-health → Connection refused。 即探针地址与服务的实际绑定族不一致,属「探针与被探对象脱钩」的假告警, 并会连带拖垮 depends_on: service_healthy 的下游等待。 (backend 之所以此前一直 healthy,是因为 Java 恰好双栈监听 :::8080 —— 属偶然,不应被依赖。) 修复: - infrastructure/docker-compose.yml:nginx 与 backend 探针改用 127.0.0.1,并各加注释写明理由; - infrastructure/docker-compose.staging.yml:backend 探针的同类写法一并改(staging 栈未起, 未经运行验证,仅保持写法同构)。 验证: - docker compose config 通过;nginx 重建后 State.Health = healthy(FailingStreak=0,探针 ExitCode=0); - 链路回归:/admin/ 200(877B)、/admin/assets/index-CDxMNwaf.js 200(1,267,697B)、 /nginx-health 200、/api/v1/health/live 200;/admin 与根路径均 301 → /admin/; - 活栈 E2E 49 passed;UI 契约门禁 14/14 PASS。
104 lines
3.3 KiB
YAML
104 lines
3.3 KiB
YAML
# Staging Docker Compose(预发环境,仅开发/测试)
|
||
version: '3.8'
|
||
|
||
services:
|
||
postgres:
|
||
image: postgres:16-alpine
|
||
environment:
|
||
POSTGRES_DB: danyang_match_staging
|
||
POSTGRES_USER: staging
|
||
POSTGRES_PASSWORD: staging_dev_password_change_me
|
||
ports:
|
||
- "5433:5432"
|
||
volumes:
|
||
- postgres_staging_data:/var/lib/postgresql/data
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "pg_isready -U staging -d danyang_match_staging"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
redis:
|
||
image: redis:7-alpine
|
||
ports:
|
||
- "6380:6379"
|
||
command: redis-server --appendonly yes --requirepass staging-redis-pass-change-me
|
||
volumes:
|
||
- redis_staging_data:/data
|
||
healthcheck:
|
||
test: ["CMD", "redis-cli", "-a", "staging-redis-pass-change-me", "ping"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
minio:
|
||
image: minio/minio:latest
|
||
command: server /data --console-address ":9001"
|
||
environment:
|
||
MINIO_ROOT_USER: staging
|
||
MINIO_ROOT_PASSWORD: staging_dev_password
|
||
ports:
|
||
- "9010:9000"
|
||
- "9011:9001"
|
||
volumes:
|
||
- minio_staging_data:/data
|
||
|
||
backend:
|
||
build:
|
||
context: ../backend
|
||
dockerfile: Dockerfile
|
||
container_name: danyang-match-staging-backend
|
||
depends_on:
|
||
postgres:
|
||
condition: service_healthy
|
||
redis:
|
||
condition: service_healthy
|
||
environment:
|
||
SPRING_PROFILES_ACTIVE: staging
|
||
DB_HOST: postgres
|
||
DB_PORT: 5432
|
||
DB_NAME: danyang_match_staging
|
||
DB_USER: staging
|
||
DB_PASSWORD: staging_dev_password_change_me
|
||
REDIS_HOST: redis
|
||
REDIS_PORT: 6379
|
||
REDIS_PASSWORD: staging-redis-pass-change-me
|
||
MINIO_ENDPOINT: http://minio:9000
|
||
MINIO_ACCESS_KEY: staging
|
||
MINIO_SECRET_KEY: staging_dev_password
|
||
JWT_ACCESS_SECRET: staging-access-secret-dev-only
|
||
JWT_REFRESH_SECRET: staging-refresh-secret-dev-only
|
||
CHECKIN_TOKEN_SECRET: staging-checkin-secret-dev-only
|
||
ENCRYPTION_KEY: 32539f3d2fa8123dcec899cc3dbee7347034123a126ac22fcb4702e10c454d50
|
||
FEATURES_APPEAL_ENABLED: "true"
|
||
ports:
|
||
- "8081:8080"
|
||
healthcheck:
|
||
# 探针用 127.0.0.1 而非 localhost:busybox wget 解析 localhost 时可能优先取 ::1,
|
||
# 而服务若只绑 IPv4 会导致探针假失败(本地栈的 nginx 已实测踩到)。
|
||
test: ["CMD-SHELL", "curl -f http://127.0.0.1:8080/api/v1/health/ready || exit 1"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
|
||
admin-web:
|
||
build:
|
||
context: ../admin-web
|
||
dockerfile: Dockerfile
|
||
container_name: danyang-match-staging-admin
|
||
depends_on:
|
||
- backend
|
||
ports:
|
||
# staging 与生产同机共存,全部端口按「生产 + 1」错开(5433/6380/8081/13521)。
|
||
# 生产管理端为 13520(admin-web/vite.config.ts + docker-compose.prod.yml),
|
||
# 故此处为 13521 —— 与 tests/uat/run-uat.sh 的 UAT_ADMIN_URL 默认值一致,
|
||
# 两处均由 ui-tests/ui-document-baseline-contracts.mjs 钉住。
|
||
# 管理端构建产物部署在 /admin/ 子路径下(见 admin-web/vite.config.ts 的 base),
|
||
# 故直连访问地址为 http://localhost:13521/admin/ 。
|
||
- "13521:80"
|
||
|
||
volumes:
|
||
postgres_staging_data:
|
||
redis_staging_data:
|
||
minio_staging_data:
|