- 新增 Prometheus/Grafana/Loki/Promtail 监控 profile\n- 覆盖 DB、磁盘、慢 API、慢 Prisma、任务失败和小宝摘要 stale 告警\n- 补充 postgres-exporter 自定义查询、Dashboard、部署文档和校验\n\nCo-Authored-By: GPT-5 Codex <codex@openai.com>
240 lines
7.0 KiB
YAML
240 lines
7.0 KiB
YAML
name: ftb-project-management
|
|
|
|
services:
|
|
postgres:
|
|
image: postgres:16-alpine
|
|
restart: unless-stopped
|
|
environment:
|
|
POSTGRES_USER: ${POSTGRES_USER:-postgres}
|
|
POSTGRES_PASSWORD: ${POSTGRES_PASSWORD:?Set POSTGRES_PASSWORD in .env.production}
|
|
POSTGRES_DB: ${POSTGRES_DB:-ftb_pm}
|
|
volumes:
|
|
- postgres_data:/var/lib/postgresql/data
|
|
healthcheck:
|
|
test: ['CMD-SHELL', 'pg_isready -U "$${POSTGRES_USER}" -d "$${POSTGRES_DB}"']
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 10
|
|
|
|
redis:
|
|
image: redis:7-alpine
|
|
restart: unless-stopped
|
|
command: ['redis-server', '--appendonly', 'yes']
|
|
volumes:
|
|
- redis_data:/data
|
|
healthcheck:
|
|
test: ['CMD', 'redis-cli', 'ping']
|
|
interval: 10s
|
|
timeout: 5s
|
|
retries: 10
|
|
|
|
server:
|
|
image: ${SERVER_IMAGE:?Set SERVER_IMAGE in .env.production}
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile.server
|
|
args:
|
|
APP_VERSION: ${APP_VERSION:-unknown}
|
|
APP_BUILD_TIME: ${APP_BUILD_TIME:-}
|
|
APP_IMAGE_TAG: ${SERVER_IMAGE:-}
|
|
restart: unless-stopped
|
|
environment:
|
|
NODE_ENV: production
|
|
APP_VERSION: ${APP_VERSION:-unknown}
|
|
APP_BUILD_TIME: ${APP_BUILD_TIME:-}
|
|
APP_IMAGE_TAG: ${SERVER_IMAGE:-}
|
|
DATABASE_URL: ${DATABASE_URL:-postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-ftb_pm}}
|
|
REDIS_URL: ${REDIS_URL:-redis://redis:6379}
|
|
ANTHROPIC_API_KEY: ${ANTHROPIC_API_KEY:-}
|
|
SMTP_HOST: ${SMTP_HOST:-}
|
|
SMTP_PORT: ${SMTP_PORT:-}
|
|
SMTP_USER: ${SMTP_USER:-}
|
|
SMTP_PASS: ${SMTP_PASS:-}
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
redis:
|
|
condition: service_healthy
|
|
volumes:
|
|
- server_data:/app/apps/server/data
|
|
expose:
|
|
- '3001'
|
|
healthcheck:
|
|
test:
|
|
[
|
|
'CMD-SHELL',
|
|
'node -e "fetch(''http://127.0.0.1:3001/api/v1/health/version'').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))"',
|
|
]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 20
|
|
start_period: 20s
|
|
|
|
web:
|
|
image: ${WEB_IMAGE:?Set WEB_IMAGE in .env.production}
|
|
build:
|
|
context: .
|
|
dockerfile: Dockerfile.web
|
|
args:
|
|
NEXT_PUBLIC_API_URL: ${NEXT_PUBLIC_API_URL:-/api/v1}
|
|
NEXT_API_PROXY_TARGET: ${NEXT_API_PROXY_TARGET:-http://server:3001}
|
|
APP_VERSION: ${APP_VERSION:-unknown}
|
|
APP_BUILD_TIME: ${APP_BUILD_TIME:-}
|
|
APP_IMAGE_TAG: ${WEB_IMAGE:-}
|
|
restart: unless-stopped
|
|
environment:
|
|
NODE_ENV: production
|
|
NEXT_PUBLIC_API_URL: ${NEXT_PUBLIC_API_URL:-/api/v1}
|
|
NEXT_API_PROXY_TARGET: ${NEXT_API_PROXY_TARGET:-http://server:3001}
|
|
NEXT_PUBLIC_APP_VERSION: ${APP_VERSION:-unknown}
|
|
NEXT_PUBLIC_APP_BUILD_TIME: ${APP_BUILD_TIME:-}
|
|
NEXT_PUBLIC_APP_IMAGE_TAG: ${WEB_IMAGE:-}
|
|
NEXTAUTH_URL: ${NEXTAUTH_URL:-}
|
|
NEXTAUTH_SECRET: ${NEXTAUTH_SECRET:-}
|
|
depends_on:
|
|
server:
|
|
condition: service_healthy
|
|
expose:
|
|
- '3000'
|
|
healthcheck:
|
|
test:
|
|
[
|
|
'CMD-SHELL',
|
|
'node -e "fetch(''http://127.0.0.1:3000'').then(r=>process.exit(r.ok?0:1)).catch(()=>process.exit(1))"',
|
|
]
|
|
interval: 15s
|
|
timeout: 5s
|
|
retries: 20
|
|
start_period: 20s
|
|
|
|
nginx:
|
|
image: nginx:1.27-alpine
|
|
restart: unless-stopped
|
|
ports:
|
|
- '${HTTP_PORT:-80}:80'
|
|
environment:
|
|
SERVER_NAME: ${SERVER_NAME:-_}
|
|
CLIENT_MAX_BODY_SIZE: ${CLIENT_MAX_BODY_SIZE:-20m}
|
|
volumes:
|
|
- ./deploy/nginx/default.conf.template:/etc/nginx/templates/default.conf.template:ro
|
|
depends_on:
|
|
web:
|
|
condition: service_healthy
|
|
server:
|
|
condition: service_healthy
|
|
|
|
prometheus:
|
|
image: prom/prometheus:v2.53.1
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
command:
|
|
- '--config.file=/etc/prometheus/prometheus.yml'
|
|
- '--storage.tsdb.path=/prometheus'
|
|
- '--storage.tsdb.retention.time=${PROMETHEUS_RETENTION:-15d}'
|
|
- '--web.enable-lifecycle'
|
|
ports:
|
|
- '${PROMETHEUS_PORT:-9090}:9090'
|
|
volumes:
|
|
- ./deploy/monitoring/prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
|
- ./deploy/monitoring/prometheus/alert-rules.yml:/etc/prometheus/alert-rules.yml:ro
|
|
- prometheus_data:/prometheus
|
|
depends_on:
|
|
- postgres-exporter
|
|
- node-exporter
|
|
- cadvisor
|
|
- promtail
|
|
- blackbox-exporter
|
|
|
|
grafana:
|
|
image: grafana/grafana:11.1.0
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
ports:
|
|
- '${GRAFANA_PORT:-3002}:3000'
|
|
environment:
|
|
GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
|
|
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:-change-me-monitoring-password}
|
|
GF_USERS_ALLOW_SIGN_UP: 'false'
|
|
volumes:
|
|
- grafana_data:/var/lib/grafana
|
|
- ./deploy/monitoring/grafana/provisioning:/etc/grafana/provisioning:ro
|
|
- ./deploy/monitoring/grafana/dashboards:/var/lib/grafana/dashboards:ro
|
|
depends_on:
|
|
- prometheus
|
|
- loki
|
|
|
|
loki:
|
|
image: grafana/loki:2.9.8
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
command: ['-config.file=/etc/loki/config.yml']
|
|
volumes:
|
|
- ./deploy/monitoring/loki/config.yml:/etc/loki/config.yml:ro
|
|
- loki_data:/loki
|
|
|
|
promtail:
|
|
image: grafana/promtail:2.9.8
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
command: ['-config.file=/etc/promtail/config.yml']
|
|
volumes:
|
|
- ./deploy/monitoring/promtail/config.yml:/etc/promtail/config.yml:ro
|
|
- /var/lib/docker/containers:/var/lib/docker/containers:ro
|
|
- /var/run/docker.sock:/var/run/docker.sock:ro
|
|
depends_on:
|
|
- loki
|
|
|
|
postgres-exporter:
|
|
image: quay.io/prometheuscommunity/postgres-exporter:v0.15.0
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
command:
|
|
- '--extend.query-path=/etc/postgres-exporter/postgres-queries.yml'
|
|
environment:
|
|
DATA_SOURCE_NAME: postgresql://${POSTGRES_USER:-postgres}:${POSTGRES_PASSWORD}@postgres:5432/${POSTGRES_DB:-ftb_pm}?sslmode=disable
|
|
volumes:
|
|
- ./deploy/monitoring/postgres/postgres-queries.yml:/etc/postgres-exporter/postgres-queries.yml:ro
|
|
depends_on:
|
|
postgres:
|
|
condition: service_healthy
|
|
|
|
node-exporter:
|
|
image: prom/node-exporter:v1.8.2
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
command:
|
|
- '--path.rootfs=/host'
|
|
volumes:
|
|
- /:/host:ro,rslave
|
|
|
|
cadvisor:
|
|
image: gcr.io/cadvisor/cadvisor:v0.49.1
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
privileged: true
|
|
devices:
|
|
- /dev/kmsg:/dev/kmsg
|
|
volumes:
|
|
- /:/rootfs:ro
|
|
- /var/run:/var/run:ro
|
|
- /sys:/sys:ro
|
|
- /var/lib/docker/:/var/lib/docker:ro
|
|
- /dev/disk/:/dev/disk:ro
|
|
|
|
blackbox-exporter:
|
|
image: prom/blackbox-exporter:v0.25.0
|
|
profiles: ['monitoring']
|
|
restart: unless-stopped
|
|
command:
|
|
- '--config.file=/etc/blackbox/config.yml'
|
|
volumes:
|
|
- ./deploy/monitoring/blackbox/config.yml:/etc/blackbox/config.yml:ro
|
|
|
|
volumes:
|
|
postgres_data:
|
|
redis_data:
|
|
server_data:
|
|
prometheus_data:
|
|
grafana_data:
|
|
loki_data:
|