compose.monitoring.yml

services:
  prometheus:
    image: docker.io/prom/prometheus:${PROMETHEUS_VERSION:-v3.4.2}
    restart: always
    user: root
    command:
      - --web.console.templates=/usr/share/prometheus/consoles
      - --config.file=/etc/prometheus/prometheus.yml
      - --web.enable-lifecycle
      - --web.listen-address=:9090
      - --storage.tsdb.path=/prometheus/data
      - --config.auto-reload-interval=30s
      - --auto-gomaxprocs
      - --storage.tsdb.retention.size=${PROMETHEUS_RETENTION_SIZE:-15GB} # this full docker compose should use around 100MB per day for 30s scrape interval
      - --storage.tsdb.retention.time=${PROMETHEUS_RETENTION_TIME:-15d}
    expose:
      - 9090
    ports:
      - ${PROMETHEUS_LISTEN_ADDR:-127.0.0.1}:${PROMETHEUS_PORT:-9090}:9090
    volumes:
      - prometheus_tsdb:/prometheus:rw
      - ./files/prometheus:/etc/prometheus:Z
      # healthcheck:
      #   test: ["CMD", "nc", "-zv", "-w", "10", "localhost", "9090"]
      #   interval: 30s
      #   timeout: 10s
      #   retries: 10
      #   start_period: 10s
    logging:
      driver: "json-file"
    labels:
      container_tag: "${COMPOSE_PROJECT_NAME:-rocketchat}#prometheus"
  node-exporter:
    image: docker.io/prom/node-exporter:${NODE_EXPORTER_VERSION:-v1.9.1}
    restart: always
    privileged: true # Required for accessing host metrics
    network_mode: host # Allows Node Exporter to access host network interfaces directly
    pid: host # Allows Node Exporter to access host process information
    volumes:
      - /sys:/host/sys:ro # Mounts the /sys filesystem for system metrics
      - /proc:/host/proc:ro # Mounts the /proc filesystem for process metrics
      - /dev:/host/dev:ro # Mounts the /dev filesystem for device metrics
    command:
      - --path.procfs=/host/proc
      - --path.sysfs=/host/sys
      - --collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)
    expose:
      - 9100
    logging:
      driver: "json-file"
    labels:
      container_tag: "${COMPOSE_PROJECT_NAME:-rocketchat}#node-exporter"

  loki:
    image: docker.io/grafana/loki:3.6
    command: -config.file=/etc/loki/config.yaml -config.expand-env=true
    user: "0"
    volumes:
      - ./files/loki/config.yaml:/etc/loki/config.yaml:z
      - loki_data:/data/loki:rw
    logging:
      driver: "json-file"
    labels:
      container_tag: "${COMPOSE_PROJECT_NAME:-rocketchat}#loki"

  opentelemetry-logs-collector:
    image: docker.io/otel/opentelemetry-collector-contrib:0.143.0
    command: ["--config=/etc/otel-collector-config.yaml"]
    user: "0"
    volumes:
      - ./files/opentelemetry/config.yaml:/etc/otel-collector-config.yaml:z
    logging:
      driver: none
    # volumes:
    #   - ./files/opentelemetry/config.yaml:/etc/otel-collector-config.yaml:ro
    #   - ${CONTAINER_LOGS_PATH:/var/lib/docker/containers}:/hostfs/storage:ro,z
    #   - ${DOCKER_SOCK_PATH:/var/run/docker.sock}:/var/run/docker.sock:ro,z

  grafana:
    image: docker.io/grafana/grafana:${GRAFANA_VERSION:-12.0.2}
    restart: always
    expose:
      - 3000
    ports:
      - "${GRAFANA_BIND_IP:-0.0.0.0}:${GRAFANA_HOST_PORT:-5050}:3000"
    volumes:
      - grafana_data:/var/lib/grafana:Z
      - ./files/grafana/dashboards:/dashboards:Z
      - ./files/grafana/provisioning/:/etc/grafana/provisioning:Z
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-rc-admin}
      - GF_AUTH_ANONYMOUS_ENABLED=false
      - GF_AUTH_ANONYMOUS_ORG_ROLE=Viewer
      - GF_AUTH_ANONYMOUS_ORG_NAME=Main Org.
      - GF_SERVER_SERVE_FROM_SUB_PATH=true
      - GF_SERVER_ROOT_URL=http://${GRAFANA_DOMAIN}${GRAFANA_PATH}/
    logging:
      driver: "json-file"
    labels:
      container_tag: "${COMPOSE_PROJECT_NAME:-rocketchat}#grafana"

volumes:
  prometheus_tsdb: { driver: local }
  prometheus_config: { driver: local }
  grafana_data: { driver: local }
  loki_data: { driver: local }