- 5 NestJS services add /metrics endpoint via app.getHttpAdapter() - prometheus.yml scales to 8 services with rule_files and alertmanager - monitoring compose replaces blackbox with Loki+Promtail - Grafana datasource adds Loki - docker-compose.deploy.yml scales to 11 services - deploy.env.example completes Neo4j/ES/ClickHouse/LLM vars - teacher-bff adds health.controller - CI removes continue-on-error on lint step - teacher-portal lint script changed to eslint src
141 lines
4.1 KiB
YAML
141 lines
4.1 KiB
YAML
# 监控栈 docker-compose(独立 profile)
|
||
# 使用方式: docker compose -f docker-compose.monitoring.yml --profile monitoring up -d
|
||
version: "3.9"
|
||
|
||
networks:
|
||
edu-network:
|
||
name: edu-network
|
||
external: true
|
||
|
||
volumes:
|
||
prometheus-data:
|
||
name: edu-prometheus-data
|
||
alertmanager-data:
|
||
name: edu-alertmanager-data
|
||
grafana-data:
|
||
name: edu-grafana-data
|
||
loki-data:
|
||
name: edu-loki-data
|
||
|
||
services:
|
||
# ============================================================
|
||
# Prometheus - 指标采集与存储
|
||
# ============================================================
|
||
prometheus:
|
||
image: prom/prometheus:v2.54.1
|
||
container_name: edu-prometheus
|
||
profiles: ["monitoring"]
|
||
restart: unless-stopped
|
||
command:
|
||
- "--config.file=/etc/prometheus/prometheus.yml"
|
||
- "--storage.tsdb.path=/prometheus"
|
||
- "--storage.tsdb.retention.time=15d"
|
||
- "--web.enable-lifecycle"
|
||
- "--web.enable-admin-api"
|
||
ports:
|
||
- "9090:9090"
|
||
volumes:
|
||
- ./prometheus.yml:/etc/prometheus/prometheus.yml:ro
|
||
- ./prometheus/rules.yml:/etc/prometheus/rules.yml:ro
|
||
- prometheus-data:/prometheus
|
||
networks:
|
||
- edu-network
|
||
|
||
# ============================================================
|
||
# Alertmanager - 告警路由与抑制
|
||
# ============================================================
|
||
alertmanager:
|
||
image: prom/alertmanager:v0.27.0
|
||
container_name: edu-alertmanager
|
||
profiles: ["monitoring"]
|
||
restart: unless-stopped
|
||
command:
|
||
- "--config.file=/etc/alertmanager/alertmanager.yml"
|
||
- "--storage.path=/alertmanager"
|
||
ports:
|
||
- "9093:9093"
|
||
volumes:
|
||
- ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
|
||
- alertmanager-data:/alertmanager
|
||
networks:
|
||
- edu-network
|
||
depends_on:
|
||
- prometheus
|
||
|
||
# ============================================================
|
||
# Grafana - 可视化
|
||
# ============================================================
|
||
grafana:
|
||
image: grafana/grafana:11.2.2
|
||
container_name: edu-grafana
|
||
profiles: ["monitoring"]
|
||
restart: unless-stopped
|
||
environment:
|
||
- GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
|
||
- GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
|
||
- GF_USERS_ALLOW_SIGN_UP=false
|
||
- GF_AUTH_ANONYMOUS_ENABLED=false
|
||
ports:
|
||
- "3000:3000"
|
||
volumes:
|
||
- ./grafana/provisioning:/etc/grafana/provisioning:ro
|
||
- ./grafana/dashboards:/var/lib/grafana/dashboards:ro
|
||
- grafana-data:/var/lib/grafana
|
||
networks:
|
||
- edu-network
|
||
depends_on:
|
||
- prometheus
|
||
|
||
# ============================================================
|
||
# node-exporter - 主机指标采集
|
||
# ============================================================
|
||
node-exporter:
|
||
image: prom/node-exporter:v1.8.2
|
||
container_name: edu-node-exporter
|
||
profiles: ["monitoring"]
|
||
restart: unless-stopped
|
||
command:
|
||
- "--path.rootfs=/host"
|
||
ports:
|
||
- "9100:9100"
|
||
volumes:
|
||
- /proc:/host/proc:ro
|
||
- /sys:/host/sys:ro
|
||
- /:/host:ro
|
||
networks:
|
||
- edu-network
|
||
|
||
# ============================================================
|
||
# Loki - 日志聚合(P6 硬化新增)
|
||
# ============================================================
|
||
loki:
|
||
image: grafana/loki:3.2.1
|
||
container_name: edu-loki
|
||
profiles: ["monitoring"]
|
||
restart: unless-stopped
|
||
command: -config.file=/etc/loki/local-config.yaml
|
||
ports:
|
||
- "3100:3100"
|
||
volumes:
|
||
- loki-data:/loki
|
||
networks:
|
||
- edu-network
|
||
|
||
# ============================================================
|
||
# Promtail - 日志采集(收集 Docker 容器日志发送到 Loki)
|
||
# ============================================================
|
||
promtail:
|
||
image: grafana/promtail:3.2.1
|
||
container_name: edu-promtail
|
||
profiles: ["monitoring"]
|
||
restart: unless-stopped
|
||
command: -config.file=/etc/promtail/config.yml
|
||
volumes:
|
||
- ./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
|
||
networks:
|
||
- edu-network
|
||
depends_on:
|
||
- loki
|