version: '3.8'

#============================================================================
# FOXHUNT HFT MONITORING STACK
#============================================================================
# Complete monitoring and observability stack:
# - Prometheus (metrics collection)
# - Grafana (visualization and dashboards)
# - AlertManager (alerting and notifications)
# - Loki (log aggregation)
# - Tempo (distributed tracing)
# - cAdvisor (container metrics)
# - Node Exporter (system metrics)
#
# Usage: docker-compose -f docker-compose.monitoring.yml up -d
#============================================================================

services:
  #==========================================================================
  # METRICS COLLECTION
  #==========================================================================

  prometheus:
    image: prom/prometheus:v2.47.0
    container_name: foxhunt-prometheus-monitoring
    hostname: foxhunt-prometheus
    ports:
      - "9090:9090"
    volumes:
      - prometheus-data:/prometheus
      - ./deployment/monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./deployment/monitoring/rules:/etc/prometheus/rules:ro
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=30d'
      - '--storage.tsdb.retention.size=50GB'
      - '--web.console.libraries=/etc/prometheus/console_libraries'
      - '--web.console.templates=/etc/prometheus/consoles'
      - '--web.enable-lifecycle'
      - '--web.enable-admin-api'
      - '--query.max-concurrency=50'
      - '--query.max-samples=50000000'
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 4g
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "5"

  #==========================================================================
  # VISUALIZATION & DASHBOARDS
  #==========================================================================

  grafana:
    image: grafana/grafana:10.1.0
    container_name: foxhunt-grafana-monitoring
    hostname: foxhunt-grafana
    ports:
      - "3000:3000"
    volumes:
      - grafana-data:/var/lib/grafana
      - ./deployment/monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./deployment/monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
      - ./deployment/monitoring/grafana/plugins:/var/lib/grafana/plugins
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD:-admin}
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_SERVER_ROOT_URL=http://localhost:3000
      - GF_INSTALL_PLUGINS=grafana-piechart-panel,grafana-worldmap-panel,grafana-polystat-panel
      - GF_FEATURE_TOGGLES_ENABLE=ngalert
      - GF_ALERTING_ENABLED=true
      - GF_UNIFIED_ALERTING_ENABLED=true
    depends_on:
      prometheus:
        condition: service_healthy
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD-SHELL", "wget --no-verbose --tries=1 --spider http://localhost:3000/api/health || exit 1"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 1g
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  #==========================================================================
  # ALERTING
  #==========================================================================

  alertmanager:
    image: prom/alertmanager:v0.26.0
    container_name: foxhunt-alertmanager-monitoring
    hostname: foxhunt-alertmanager
    ports:
      - "9093:9093"
    volumes:
      - alertmanager-data:/alertmanager
      - ./deployment/monitoring/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=http://localhost:9093'
      - '--cluster.advertise-address=0.0.0.0:9093'
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9093/-/healthy"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 512m
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  #==========================================================================
  # LOG AGGREGATION
  #==========================================================================

  loki:
    image: grafana/loki:2.9.0
    container_name: foxhunt-loki-monitoring
    hostname: foxhunt-loki
    ports:
      - "3100:3100"
    volumes:
      - loki-data:/loki
      - ./deployment/monitoring/loki.yml:/etc/loki/loki.yml:ro
    command: -config.file=/etc/loki/loki.yml
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3100/ready"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 1g
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  promtail:
    image: grafana/promtail:2.9.0
    container_name: foxhunt-promtail-monitoring
    hostname: foxhunt-promtail
    volumes:
      - /var/log:/var/log:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - ./deployment/monitoring/promtail.yml:/etc/promtail/config.yml:ro
    command: -config.file=/etc/promtail/config.yml
    depends_on:
      - loki
    networks:
      - monitoring-network
    restart: unless-stopped
    mem_limit: 256m
    logging:
      driver: "json-file"
      options:
        max-size: "25m"
        max-file: "3"

  #==========================================================================
  # DISTRIBUTED TRACING
  #==========================================================================

  tempo:
    image: grafana/tempo:2.2.0
    container_name: foxhunt-tempo-monitoring
    hostname: foxhunt-tempo
    ports:
      - "3200:3200"   # Tempo HTTP API
      - "9095:9095"   # Tempo gRPC
      - "4317:4317"   # OTLP gRPC
      - "4318:4318"   # OTLP HTTP
    volumes:
      - tempo-data:/var/tempo
      - ./deployment/monitoring/tempo.yml:/etc/tempo/tempo.yml:ro
    command: [ "-config.file=/etc/tempo/tempo.yml" ]
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3200/ready"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 1g
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  #==========================================================================
  # SYSTEM METRICS
  #==========================================================================

  node-exporter:
    image: prom/node-exporter:v1.6.1
    container_name: foxhunt-node-exporter-monitoring
    hostname: foxhunt-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'
      - '--path.rootfs=/rootfs'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9100/metrics"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 256m
    logging:
      driver: "json-file"
      options:
        max-size: "25m"
        max-file: "3"

  #==========================================================================
  # CONTAINER METRICS
  #==========================================================================

  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.47.2
    container_name: foxhunt-cadvisor-monitoring
    hostname: foxhunt-cadvisor
    ports:
      - "8080:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker:/var/lib/docker:ro
      - /dev/disk/:/dev/disk:ro
    privileged: true
    devices:
      - /dev/kmsg:/dev/kmsg
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8080/healthz"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 512m
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

  #==========================================================================
  # UPTIME MONITORING
  #==========================================================================

  uptime-kuma:
    image: louislam/uptime-kuma:1.23.0
    container_name: foxhunt-uptime-kuma-monitoring
    hostname: foxhunt-uptime-kuma
    ports:
      - "3001:3001"
    volumes:
      - uptime-kuma-data:/app/data
    networks:
      - monitoring-network
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:3001"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    mem_limit: 512m
    logging:
      driver: "json-file"
      options:
        max-size: "50m"
        max-file: "5"

#==============================================================================
# NETWORKS
#==============================================================================
networks:
  monitoring-network:
    driver: bridge
    driver_opts:
      com.docker.network.bridge.name: foxhunt-monitoring
    ipam:
      config:
        - subnet: 172.25.0.0/24
          gateway: 172.25.0.1

#==============================================================================
# VOLUMES
#==============================================================================
volumes:
  prometheus-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/foxhunt/monitoring/prometheus
  grafana-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/foxhunt/monitoring/grafana
  alertmanager-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/foxhunt/monitoring/alertmanager
  loki-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/foxhunt/monitoring/loki
  tempo-data:
    driver: local
    driver_opts:
      type: none
      o: bind
      device: /opt/foxhunt/monitoring/tempo
  uptime-kuma-data:
    driver: local