services: grafana: image: grafana/grafana:latest container_name: grafana healthcheck: test: ["CMD", "wget", "-q", "--spider", "http://localhost:3000"] interval: 30s timeout: 10s retries: 3 ports: - "3003:3000" environment: - GF_SECURITY_ADMIN_USER=admin - GF_SECURITY_ADMIN_PASSWORD=password # Change this in production - GF_USERS_ALLOW_SIGN_UP=false - GF_UNIFIED_ALERTING_ENABLED=true - GF_ALERTING_ENABLED=false - GF_UNIFIED_ALERTING_PROMETHEUS_ALERTS_ENABLED=true volumes: - grafana-data:/var/lib/grafana - ./config/provisioning/dashboards:/etc/grafana/provisioning/dashboards - ./config/provisioning/datasources:/etc/grafana/provisioning/datasources - ./config/provisioning/alerting:/etc/grafana/provisioning/alerting - ./config/dashboards:/var/lib/grafana/dashboards depends_on: - prometheus restart: unless-stopped networks: - monitoring loki: image: grafana/loki:latest container_name: loki ports: - "9020:3100" command: -config.file=/etc/loki/local-config.yaml restart: unless-stopped networks: - monitoring # AlertManager for handling alerts alertmanager: image: quay.io/prometheus/alertmanager:latest container_name: alertmanager ports: - "9093:9093" volumes: - ./config/alertmanager.yml:/etc/alertmanager/config.yml restart: unless-stopped networks: - monitoring # Prometheus for metrics collection prometheus: image: prom/prometheus:latest container_name: prometheus ports: - "3004:9090" volumes: - ./config/prometheus.yml:/etc/prometheus/prometheus.yml - ./config/prometheus-alerts.yml:/etc/prometheus/alerts.yml - prometheus-data:/prometheus command: - '--config.file=/etc/prometheus/prometheus.yml' - '--storage.tsdb.path=/prometheus' - '--storage.tsdb.retention.time=15d' - '--storage.tsdb.retention.size=10GB' - '--web.console.libraries=/etc/prometheus/console_libraries' - '--web.console.templates=/etc/prometheus/consoles' - '--web.enable-lifecycle' - "--web.enable-remote-write-receiver" restart: unless-stopped networks: - monitoring deploy: resources: limits: memory: 2G reservations: memory: 1G restart_policy: condition: on-failure delay: 5s max_attempts: 3 window: 120s # cAdvisor for container metrics cadvisor: image: gcr.io/cadvisor/cadvisor:v0.49.1 container_name: cadvisor volumes: - /:/rootfs:ro - /var/run:/var/run:ro - /sys:/sys:ro - /var/lib/docker/:/var/lib/docker:ro - /dev/disk/:/dev/disk:ro ports: - "9050:8080" restart: unless-stopped networks: - monitoring privileged: true devices: - /dev/kmsg:/dev/kmsg # Node Exporter for host metrics node-exporter: image: prom/node-exporter:latest container_name: node-exporter 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)($$|/)' ports: - "9060:9100" restart: unless-stopped networks: - monitoring alloy: image: grafana/alloy:latest container_name: alloy volumes: - ./config/config.alloy:/etc/alloy/config.alloy - /home/container_user/logs:/var/log:ro # Read-only mount of host logs - /var/run/docker.sock:/var/run/docker.sock command: - run - --server.http.listen-addr=0.0.0.0:12345 - --storage.path=/var/lib/alloy/data - /etc/alloy/config.alloy ports: - "12345:12345" # Expose the Alloy UI restart: unless-stopped networks: - monitoring volumes: grafana-data: prometheus-data: alloy-data: driver: local loki-data: driver: local alertmanager-data: driver: local networks: monitoring: driver: bridge