BIZ-28: deploy monitoring dashboard + alert config

Co-authored-by: multica-agent <github@multica.ai>
2026-06-23 15:56:49 +08:00
parent 80ef3c2796
commit f4191f82f5
7 changed files with 843 additions and 0 deletions
@@ -0,0 +1,92 @@
+version: '3.8'
+
+services:
+  prometheus:
+    image: m.daocloud.io/docker.io/prom/prometheus:v2.52.0
+    container_name: prometheus
+    ports:
+      - "9090:9090"
+    volumes:
+      - ./config/prometheus.yml:/etc/prometheus/prometheus.yml
+      - ./config/agent_alerts.yml:/etc/prometheus/agent_alerts.yml
+      - ./data/prometheus:/prometheus
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--web.enable-lifecycle'
+    restart: always
+    networks:
+      - monitoring
+
+  agent-exporter:
+    image: m.daocloud.io/docker.io/python:3.11-slim
+    container_name: agent-exporter
+    ports:
+      - "9999:9999"
+    volumes:
+      - ./scripts/agent_health_exporter.py:/app/exporter.py:ro
+    command: python3 /app/exporter.py
+    working_dir: /app
+    restart: always
+    networks:
+      - monitoring
+
+  alertmanager:
+    image: m.daocloud.io/docker.io/prom/alertmanager:v0.27.0
+    container_name: alertmanager
+    ports:
+      - "9093:9093"
+    volumes:
+      - ./config/alertmanager.yml:/etc/alertmanager/alertmanager.yml
+      - ./data/alertmanager:/alertmanager
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    command:
+      - '--config.file=/etc/alertmanager/alertmanager.yml'
+      - '--storage.path=/alertmanager'
+      - '--web.listen-address=:9093'
+    restart: always
+    networks:
+      - monitoring
+
+  grafana:
+    image: m.daocloud.io/docker.io/grafana/grafana:11.0.0
+    container_name: grafana
+    ports:
+      - "3001:3000"
+    environment:
+      - GF_SECURITY_ADMIN_USER=admin
+      - GF_SECURITY_ADMIN_PASSWORD=***
+      - GF_INSTALL_PLUGINS=grafana-clock-panel,grafana-piechart-panel
+    volumes:
+      - ./data/grafana:/var/lib/grafana
+      - ./config/grafana/dashboards:/etc/grafana/provisioning/dashboards
+      - ./config/grafana/datasources:/etc/grafana/provisioning/datasources
+    restart: always
+    networks:
+      - monitoring
+    depends_on:
+      - prometheus
+
+  node-exporter:
+    image: m.daocloud.io/docker.io/prom/node-exporter:v1.8.2
+    container_name: node-exporter
+    ports:
+      - "9100:9100"
+    volumes:
+      - /proc:/host/proc:ro
+      - /sys:/host/sys:ro
+      - /:/rootfs:ro
+    command:
+      - '--path.procfs=/host/proc'
+      - '--path.sysfs=/host/sys'
+      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($|/)'
+    restart: always
+    networks:
+      - monitoring
+
+networks:
+  monitoring:
+    driver: bridge