bzzz/infrastructure/monitoring/docker-compose.monitoring.yml

version: '3.8'

services:
  # Prometheus for metrics collection
  prometheus:
    image: prom/prometheus:v2.48.0
    networks:
      - tengig
      - monitoring
    ports:
      - "9090:9090"
    volumes:
      - /rust/bzzz-v2/config/prometheus:/etc/prometheus:ro
      - /rust/bzzz-v2/data/prometheus:/prometheus
    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.external-url=https://prometheus.deepblack.cloud'
    configs:
      - source: prometheus_config
        target: /etc/prometheus/prometheus.yml
      - source: prometheus_rules
        target: /etc/prometheus/rules.yml
    deploy:
      replicas: 1
      placement:
        constraints:
          - node.hostname == walnut
      resources:
        limits:
          memory: 4G
          cpus: '2.0'
        reservations:
          memory: 2G
          cpus: '1.0'
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.prometheus.rule=Host(`prometheus.deepblack.cloud`)"
        - "traefik.http.services.prometheus.loadbalancer.server.port=9090"
        - "traefik.http.routers.prometheus.tls=true"

  # Grafana for visualization  
  grafana:
    image: grafana/grafana:10.2.0
    networks:
      - tengig
      - monitoring
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD__FILE=/run/secrets/grafana_admin_password
      - GF_SERVER_ROOT_URL=https://grafana.deepblack.cloud
      - GF_SERVER_DOMAIN=grafana.deepblack.cloud
      - GF_ANALYTICS_REPORTING_ENABLED=false
      - GF_ANALYTICS_CHECK_FOR_UPDATES=false
      - GF_USERS_ALLOW_SIGN_UP=false
      - GF_INSTALL_PLUGINS=grafana-piechart-panel,grafana-worldmap-panel
    volumes:
      - /rust/bzzz-v2/data/grafana:/var/lib/grafana
      - /rust/bzzz-v2/config/grafana/provisioning:/etc/grafana/provisioning:ro
    secrets:
      - grafana_admin_password
    deploy:
      replicas: 1
      placement:
        constraints:
          - node.hostname == walnut
      resources:
        limits:
          memory: 2G
          cpus: '1.0'
        reservations:
          memory: 1G
          cpus: '0.5'
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.grafana.rule=Host(`grafana.deepblack.cloud`)"
        - "traefik.http.services.grafana.loadbalancer.server.port=3000"
        - "traefik.http.routers.grafana.tls=true"

  # AlertManager for alerting
  alertmanager:
    image: prom/alertmanager:v0.26.0
    networks:
      - tengig
      - monitoring
    ports:
      - "9093:9093"
    volumes:
      - /rust/bzzz-v2/data/alertmanager:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/config.yml'
      - '--storage.path=/alertmanager'
      - '--web.external-url=https://alerts.deepblack.cloud'
    configs:
      - source: alertmanager_config
        target: /etc/alertmanager/config.yml
    deploy:
      replicas: 1
      placement:
        constraints:
          - node.hostname == ironwood
      resources:
        limits:
          memory: 1G
          cpus: '0.5'
        reservations:
          memory: 512M
          cpus: '0.25'
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.alertmanager.rule=Host(`alerts.deepblack.cloud`)"
        - "traefik.http.services.alertmanager.loadbalancer.server.port=9093"
        - "traefik.http.routers.alertmanager.tls=true"

  # Node Exporter for system metrics
  node-exporter:
    image: prom/node-exporter:v1.6.1
    networks:
      - monitoring
    ports:
      - "9100:9100"
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
      - /etc/hostname:/etc/nodename:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.rootfs=/rootfs'
      - '--path.sysfs=/host/sys'
      - '--collector.filesystem.mount-points-exclude=^/(sys|proc|dev|host|etc)($$|/)'
      - '--collector.textfile.directory=/var/lib/node_exporter/textfile_collector'
    deploy:
      mode: global
      resources:
        limits:
          memory: 256M
          cpus: '0.5'
        reservations:
          memory: 128M
          cpus: '0.25'

  # cAdvisor for container metrics
  cadvisor:
    image: gcr.io/cadvisor/cadvisor:v0.47.0
    networks:
      - monitoring
    ports:
      - "8080:8080"
    volumes:
      - /:/rootfs:ro
      - /var/run:/var/run:rw
      - /sys:/sys:ro
      - /var/lib/docker:/var/lib/docker:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
    command:
      - '--housekeeping_interval=10s'
      - '--docker_only=true'
      - '--disable_metrics=percpu,process,sched,tcp,udp,disk,diskIO,accelerator,hugetlb,referenced_memory,cpu_topology,resctrl'
    deploy:
      mode: global
      resources:
        limits:
          memory: 512M
          cpus: '0.5'
        reservations:
          memory: 256M
          cpus: '0.25'

  # BZZZ P2P Metrics Exporter
  bzzz-p2p-exporter:
    image: registry.home.deepblack.cloud/bzzz/p2p-exporter:v2.0.0
    networks:
      - monitoring
      - bzzz-internal
    ports:
      - "9200:9200"
    environment:
      - BZZZ_AGENT_ENDPOINTS=http://bzzz-v2_bzzz-agent:9000
      - DHT_BOOTSTRAP_NODES=walnut:9101,ironwood:9102,acacia:9103
      - METRICS_PORT=9200
      - SCRAPE_INTERVAL=30s
    deploy:
      replicas: 1
      placement:
        constraints:
          - node.hostname == acacia
      resources:
        limits:
          memory: 512M
          cpus: '0.5'

  # DHT Network Monitor
  dht-monitor:
    image: registry.home.deepblack.cloud/bzzz/dht-monitor:v2.0.0
    networks:
      - monitoring
      - bzzz-internal
    ports:
      - "9201:9201"
    environment:
      - DHT_BOOTSTRAP_NODES=walnut:9101,ironwood:9102,acacia:9103
      - MONITOR_PORT=9201
      - PEER_CHECK_INTERVAL=60s
    deploy:
      replicas: 1
      resources:
        limits:
          memory: 256M
          cpus: '0.25'

  # Content Store Monitor  
  content-monitor:
    image: registry.home.deepblack.cloud/bzzz/content-monitor:v2.0.0
    networks:
      - monitoring
      - bzzz-internal
    ports:
      - "9202:9202"
    environment:
      - CONTENT_STORE_PATH=/rust/bzzz-v2/data/blobs
      - MONITOR_PORT=9202
      - CHECK_INTERVAL=300s
    volumes:
      - /rust/bzzz-v2/data/blobs:/data/blobs:ro
    deploy:
      replicas: 1
      resources:
        limits:
          memory: 256M
          cpus: '0.25'

  # OpenAI Cost Monitor
  openai-cost-monitor:
    image: registry.home.deepblack.cloud/bzzz/openai-cost-monitor:v2.0.0
    networks:
      - monitoring
      - bzzz-internal
    ports:
      - "9203:9203"
    environment:
      - POSTGRES_HOST=bzzz-v2_postgres
      - POSTGRES_DB=bzzz_v2
      - POSTGRES_USER=bzzz
      - MONITOR_PORT=9203
      - COST_ALERT_THRESHOLD=100.00
    secrets:
      - postgres_password
    deploy:
      replicas: 1
      resources:
        limits:
          memory: 256M
          cpus: '0.25'

  # Log aggregation with Loki
  loki:
    image: grafana/loki:2.9.0
    networks:
      - monitoring
    ports:
      - "3100:3100"
    volumes:
      - /rust/bzzz-v2/data/loki:/loki
    command: -config.file=/etc/loki/local-config.yaml
    configs:
      - source: loki_config
        target: /etc/loki/local-config.yaml
    deploy:
      replicas: 1
      placement:
        constraints:
          - node.hostname == acacia
      resources:
        limits:
          memory: 2G
          cpus: '1.0'
        reservations:
          memory: 1G
          cpus: '0.5'

  # Promtail for log shipping
  promtail:
    image: grafana/promtail:2.9.0
    networks:
      - monitoring
    volumes:
      - /var/log:/var/log:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /rust/bzzz-v2/logs:/app/logs:ro
    command: -config.file=/etc/promtail/config.yml
    configs:
      - source: promtail_config
        target: /etc/promtail/config.yml
    deploy:
      mode: global
      resources:
        limits:
          memory: 256M
          cpus: '0.25'

  # Jaeger for distributed tracing
  jaeger:
    image: jaegertracing/all-in-one:1.49
    networks:
      - tengig
      - monitoring
    ports:
      - "16686:16686"
      - "14268:14268"
    environment:
      - COLLECTOR_OTLP_ENABLED=true
      - SPAN_STORAGE_TYPE=badger
      - BADGER_EPHEMERAL=false
      - BADGER_DIRECTORY_VALUE=/badger/data
      - BADGER_DIRECTORY_KEY=/badger/key
    volumes:
      - /rust/bzzz-v2/data/jaeger:/badger
    deploy:
      replicas: 1
      placement:
        constraints:
          - node.hostname == ironwood
      resources:
        limits:
          memory: 1G
          cpus: '0.5'
      labels:
        - "traefik.enable=true"
        - "traefik.http.routers.jaeger.rule=Host(`tracing.deepblack.cloud`)"
        - "traefik.http.services.jaeger.loadbalancer.server.port=16686"
        - "traefik.http.routers.jaeger.tls=true"

networks:
  tengig:
    external: true
  monitoring:
    driver: overlay
    attachable: true
  bzzz-internal:
    external: true

secrets:
  grafana_admin_password:
    external: true
    name: bzzz_grafana_admin_password
  postgres_password:
    external: true
    name: bzzz_postgres_password

configs:
  prometheus_config:
    external: true
    name: bzzz_prometheus_config
  prometheus_rules:
    external: true
    name: bzzz_prometheus_rules
  alertmanager_config:
    external: true
    name: bzzz_alertmanager_config
  loki_config:
    external: true
    name: bzzz_loki_config
  promtail_config:
    external: true
    name: bzzz_promtail_config