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。
132 lines
4.5 KiB
YAML
132 lines
4.5 KiB
YAML
# 丹阳公益婚恋服务平台 - 本地完整环境
|
||
|
||
services:
|
||
postgres:
|
||
image: postgres:16-alpine
|
||
container_name: danyang-match-postgres
|
||
environment:
|
||
POSTGRES_DB: danyang_match
|
||
POSTGRES_USER: postgres
|
||
POSTGRES_PASSWORD: ${DB_PASSWORD:?请在本地 .env 设置 DB_PASSWORD}
|
||
ports:
|
||
- "5434:5432"
|
||
volumes:
|
||
- postgres_data:/var/lib/postgresql/data
|
||
healthcheck:
|
||
test: ["CMD-SHELL", "pg_isready -U postgres -d danyang_match"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
redis:
|
||
image: redis:7-alpine
|
||
container_name: danyang-match-redis
|
||
ports:
|
||
- "6381:6379"
|
||
command: redis-server --appendonly yes --requirepass ${REDIS_PASSWORD:?请在本地 .env 设置 REDIS_PASSWORD}
|
||
volumes:
|
||
- redis_data:/data
|
||
healthcheck:
|
||
test: ["CMD", "redis-cli", "-a", "${REDIS_PASSWORD:?请在本地 .env 设置 REDIS_PASSWORD}", "ping"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
minio:
|
||
# pin 到确定版本:`latest` 是滚动 tag,MinIO 已多次改动镜像内容(如移除内嵌 console),
|
||
# 用 `latest` 会让 CI 的 E2E 拉到一个与本地验证时不同的镜像 → 不可复现的偶发失败。
|
||
image: minio/minio:RELEASE.2025-09-07T16-13-09Z
|
||
container_name: danyang-match-minio
|
||
command: server /data --console-address ":9001"
|
||
environment:
|
||
MINIO_ROOT_USER: ${MINIO_ACCESS_KEY:?请在本地 .env 设置 MINIO_ACCESS_KEY}
|
||
MINIO_ROOT_PASSWORD: ${MINIO_SECRET_KEY:?请在本地 .env 设置 MINIO_SECRET_KEY}
|
||
ports:
|
||
- "9003:9000"
|
||
- "9004:9001"
|
||
volumes:
|
||
- minio_data:/data
|
||
healthcheck:
|
||
test: ["CMD", "mc", "ready", "local"]
|
||
interval: 10s
|
||
timeout: 5s
|
||
retries: 5
|
||
|
||
backend:
|
||
build:
|
||
context: ../backend
|
||
dockerfile: Dockerfile
|
||
container_name: danyang-match-backend
|
||
depends_on:
|
||
postgres:
|
||
condition: service_healthy
|
||
redis:
|
||
condition: service_healthy
|
||
minio:
|
||
condition: service_healthy
|
||
environment:
|
||
SPRING_PROFILES_ACTIVE: docker
|
||
DB_HOST: postgres
|
||
DB_PORT: 5432
|
||
DB_NAME: danyang_match
|
||
DB_USER: postgres
|
||
DB_PASSWORD: ${DB_PASSWORD:?请在本地 .env 设置 DB_PASSWORD}
|
||
REDIS_HOST: redis
|
||
REDIS_PORT: 6379
|
||
REDIS_PASSWORD: ${REDIS_PASSWORD:?请在本地 .env 设置 REDIS_PASSWORD}
|
||
MINIO_ENDPOINT: http://minio:9000
|
||
MINIO_ACCESS_KEY: ${MINIO_ACCESS_KEY:?请在本地 .env 设置 MINIO_ACCESS_KEY}
|
||
MINIO_SECRET_KEY: ${MINIO_SECRET_KEY:?请在本地 .env 设置 MINIO_SECRET_KEY}
|
||
JWT_ACCESS_SECRET: ${JWT_ACCESS_SECRET:?请在本地 .env 设置 JWT_ACCESS_SECRET}
|
||
JWT_REFRESH_SECRET: ${JWT_REFRESH_SECRET:?请在本地 .env 设置 JWT_REFRESH_SECRET}
|
||
ENCRYPTION_KEY: ${ENCRYPTION_KEY:?请在本地 .env 设置 ENCRYPTION_KEY}
|
||
WECHAT_APP_ID: dev-wechat-app-id
|
||
WECHAT_APP_SECRET: ${WECHAT_APP_SECRET:-}
|
||
ports:
|
||
- "8085:8080"
|
||
healthcheck:
|
||
# 与 nginx 同理,用 127.0.0.1 而非 localhost:backend 当前恰好双栈监听(:::8080),
|
||
# 故 localhost 解析成 ::1 也能通;但探针不应依赖「服务恰好绑了 IPv6」这一偶然事实。
|
||
test: ["CMD-SHELL", "wget -qO /dev/null http://127.0.0.1:8080/api/v1/health/live || exit 1"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
|
||
admin-web:
|
||
build:
|
||
context: ../admin-web
|
||
dockerfile: Dockerfile
|
||
container_name: danyang-match-admin
|
||
depends_on:
|
||
backend:
|
||
condition: service_healthy
|
||
|
||
nginx:
|
||
image: nginx:alpine
|
||
container_name: danyang-match-nginx
|
||
depends_on:
|
||
backend:
|
||
condition: service_healthy
|
||
admin-web:
|
||
condition: service_started
|
||
ports:
|
||
- "6688:80"
|
||
volumes:
|
||
- ./nginx.conf:/etc/nginx/nginx.conf:ro
|
||
healthcheck:
|
||
# 探针地址必须写 127.0.0.1,不能写 localhost。
|
||
# 实测:nginx 的 `listen 80` 只绑 IPv4(容器内 netstat = 0.0.0.0:80),
|
||
# 而 /etc/hosts 中 `::1 localhost` 同样存在,busybox wget 解析 localhost 时优先取 ::1
|
||
# → 探针连 IPv6 回环被拒(Connection refused)→ 容器被标 unhealthy,
|
||
# 但服务其实完全正常(宿主 curl http://localhost:6688/nginx-health = 200)。
|
||
# 这是一类「探针与被探对象脱钩」的假告警,还会连带拖垮 depends_on: service_healthy。
|
||
test: ["CMD-SHELL", "wget -qO /dev/null http://127.0.0.1/nginx-health || exit 1"]
|
||
interval: 30s
|
||
timeout: 10s
|
||
retries: 3
|
||
|
||
volumes:
|
||
postgres_data:
|
||
redis_data:
|
||
minio_data:
|