docker-compose.yml

name: monitoring-stack

services:
  node-exporter:
    image: prom/node-exporter:v1.8.0
    container_name: node-exporter
    restart: always
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    deploy:
      resources:
        limits:
          memory: 512M
    env_file: .env
    command:
      - "--path.procfs=/host/proc"
      - "--path.rootfs=/rootfs"
      - "--path.sysfs=/host/sys"
      - "--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)"
    networks:
      - monitoring
  
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.49.1
    container_name: cadvisor
    restart: always
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:ro
      - /sys:/sys:ro
      - /var/lib/docker/:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    networks:
      - monitoring


  # Automated Bucket Creation for MinIO
  minio:
    image: minio/minio:RELEASE.2025-09-07T16-13-09Z
    container_name: minio
    hostname: minio
    domainname: minio
    env_file: .env
    command: server /data --console-address ":9001"
    restart: always
    healthcheck:
      test: ["CMD", "mc", "ready", "local"]
      interval: 5s
      timeout: 5s
      retries: 10
      start_period: 10s
    volumes:
      - minio-data:/data
    deploy:
      resources:
        limits:
          memory: 512M
    networks:
      - monitoring

  minio-setup:
    image: minio/mc:RELEASE.2025-08-13T08-35-41Z
    container_name: minio-setup
    restart: on-failure
    network_mode: "service:minio"
    depends_on:
      minio:
        condition: service_healthy
    env_file: .env
    entrypoint: >
      /bin/sh -c "
      until (/usr/bin/mc alias set local http://127.0.0.1:9000 $$MINIO_ROOT_USER $$MINIO_ROOT_PASSWORD) do echo '...waiting for minio' && sleep 1; done;
      for bucket in $$(echo $$MINIO_BUCKETS | tr ',' ' '); do
        /usr/bin/mc mb --ignore-existing local/$$bucket;
      done;
      exit 0;
      "

  loki:
    image: grafana/loki:3.0.0
    container_name: loki
    hostname: loki
    domainname: loki
    restart: always
    command:
      - "-config.file=/etc/loki/config.yaml"
      - "-config.expand-env=true"
    env_file: .env
    volumes:
      - ./configs/loki-config.yaml:/etc/loki/config.yaml
      - loki-data:/loki
    depends_on:
      minio-setup:
        condition: service_completed_successfully
    deploy:
      resources:
        limits:
          memory: 1G
    networks:
      - monitoring

  mimir:
    image: grafana/mimir:2.12.0
    container_name: mimir
    hostname: prometheus
    domainname: mimir
    restart: always
    command:
      - "-config.file=/etc/mimir/mimir.yaml"
      - "-config.expand-env=true"
      # Enable the alertmanager and ruler
      - "-target=all,alertmanager,ruler"
    env_file: .env
    volumes:
      - ./configs/mimir-config.yaml:/etc/mimir/mimir.yaml
      - ./configs/alertmanager.yaml:/etc/mimir/alertmanager.yaml
      - ./configs/mimir-rules.yaml:/etc/mimir/rules/anonymous/rules.yaml
      - mimir-data:/data
    depends_on:
      minio-setup:
        condition: service_completed_successfully
    deploy:
      resources:
        limits:
          memory: 1.5G
          cpus: "1.0"
    networks:
      - monitoring

  tempo:
    image: grafana/tempo:2.4.1
    container_name: tempo
    hostname: tempo
    domainname: tempo
    restart: always
    env_file: .env
    command:
      - "-config.file=/etc/tempo/tempo.yaml"
      - "-config.expand-env=true"
    volumes:
      - ./configs/tempo-config.yaml:/etc/tempo/tempo.yaml
      - tempo-data:/var/tempo
    depends_on:
      minio-setup:
        condition: service_completed_successfully
    deploy:
      resources:
        limits:
          memory: 1G
    networks:
      - monitoring

  alloy:
    image: grafana/alloy:v1.1.0
    container_name: alloy
    hostname: alloy
    domainname: alloy
    restart: always
    volumes:
      - ./configs/alloy-config.alloy:/etc/alloy/config.alloy
      - /var/run/docker.sock:/var/run/docker.sock
    command: run --storage.path=/var/lib/alloy/data /etc/alloy/config.alloy
    deploy:
      resources:
        limits:
          memory: 512M
    networks:
      - monitoring

  otel-collector:
    image: otel/opentelemetry-collector-contrib:0.148.0
    container_name: otel-collector
    hostname: otel-collector
    domainname: monitoring
    restart: always
    command:
      - "--config=/etc/otelcol-contrib/config.yaml"
    volumes:
      - ./configs/otel-collector.yml:/etc/otelcol-contrib/config.yaml:ro
    ports:
      - "0.0.0.0:4317:4317"
      - "0.0.0.0:4318:4318"
      - "0.0.0.0:13133:13133"
    depends_on:
      loki:
        condition: service_started
      mimir:
        condition: service_started
      tempo:
        condition: service_started
    deploy:
      resources:
        limits:
          memory: 512M
    networks:
      - monitoring

  grafana:
    image: grafana/grafana:10.4.1
    container_name: grafana
    hostname: grafana
    environment:
      - GF_SECURITY_ADMIN_USER=${GF_ADMIN_USER}
      - GF_SECURITY_ADMIN_PASSWORD=${GF_ADMIN_PASSWORD}
      - GF_SERVER_DOMAIN=monitoring.jojoaddison.local
      - GF_SERVER_ROOT_URL=http://monitoring.jojoaddison.local/
    ports:
      - "127.0.0.1:3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
      # Provisioning Configuration
      - ./configs/grafana-datasources.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
      - ./configs/grafana-dashboards.yaml:/etc/grafana/provisioning/dashboards/dashboards.yaml
      # Dashboard JSON files
      - ./configs/dashboards:/etc/grafana/provisioning/dashboards/json
    deploy:
      resources:
        limits:
          memory: 512M
    networks:
      - monitoring

networks:
  monitoring:
    driver: bridge
    name: monitoring
    external: true

volumes:
  minio-data:
  loki-data:
  mimir-data:
  tempo-data:
  grafana-data: