threadnet-operating/monitoring/docker-compose.yml

services:
  prometheus:
    image: prom/prometheus:v3.3.1
    container_name: prometheus
    restart: unless-stopped
    volumes:
      - ./prometheus/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - ./prometheus/alerts.yml:/etc/prometheus/alerts.yml:ro
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--storage.tsdb.retention.time=45d'
      - '--storage.tsdb.retention.size=15GB'
      # Remote-Write-Receiver: k3s-Cluster und Matrix-Server pushen hierher.
      # ACHTUNG: Port 9090 ist oeffentlich und ohne Auth erreichbar --
      # per Hetzner Cloud Firewall auf die Absender-IPs einschraenken!
      - '--web.enable-remote-write-receiver'
    ports:
      - "9090:9090"
    networks:
      - traefik

  alertmanager:
    image: prom/alertmanager:v0.28.1
    container_name: alertmanager
    restart: unless-stopped
    volumes:
      - ./alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager_data:/alertmanager
    command:
      - '--config.file=/etc/alertmanager/alertmanager.yml'
      - '--storage.path=/alertmanager'
    # bewusst kein oeffentlicher Port - nur Prometheus/Receiver im traefik-Netz
    networks:
      - traefik

  # Alertmanager-Webhook -> Matrix (wartung-Raum), gleiche Machart wie
  # maintenance-notify (gitops Issue #24). Secrets kommen aus .env.
  matrix-alerts:
    image: python:3.13-slim
    container_name: matrix-alerts
    restart: unless-stopped
    environment:
      - MATRIX_HOMESERVER=${MATRIX_ALERT_HOMESERVER}
      - MATRIX_ROOM_ID=${MATRIX_ALERT_ROOM_ID}
      - MATRIX_TOKEN=${MATRIX_ALERT_TOKEN}
    volumes:
      - ./alertmanager/matrix-alerts.py:/app/matrix-alerts.py:ro
    command: python3 /app/matrix-alerts.py
    networks:
      - traefik

  loki:
    image: grafana/loki:3.7.1
    container_name: loki
    restart: unless-stopped
    volumes:
      - ./loki/loki-config.yaml:/etc/loki/local-config.yaml:ro
      - loki_data:/loki
    command: -config.file=/etc/loki/local-config.yaml
    # Port 3100 oeffentlich: externe Alloys pushen Logs hierher.
    # Ebenfalls per Firewall auf bekannte Absender-IPs einschraenken.
    ports:
      - "3100:3100"
    networks:
      - traefik

  alloy:
    image: grafana/alloy:v1.16.0
    container_name: alloy
    restart: unless-stopped
    volumes:
      - ./alloy/config.alloy:/etc/alloy/config.alloy:ro
      - /var/log:/var/log:ro
      - /var/lib/docker/containers:/var/lib/docker/containers:ro
      - /var/run/docker.sock:/var/run/docker.sock:ro
      # Muss persistent sein, sonst ist die Positions-Datei nach jedem
      # Recreate weg und Alloy liest alle Container-Logs von vorn. Loki
      # weist die alten Eintraege dann ab (reject_old_samples, Default 7d).
      - alloy_data:/var/lib/alloy
    command: run --storage.path=/var/lib/alloy/data /etc/alloy/config.alloy
    cap_add:
      - DAC_READ_SEARCH
      - NET_RAW
    networks:
      - traefik
    depends_on:
      - prometheus
      - loki

  grafana:
    image: grafana/grafana:12.0.0
    container_name: grafana
    restart: unless-stopped
    environment:
      # Greift nur beim allerersten Start mit leerem Volume.
      # Der Live-Admin ist davon unabhaengig (Passwortaenderungen in der UI).
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
    volumes:
      - grafana_data:/var/lib/grafana
      - ./grafana/provisioning:/etc/grafana/provisioning:ro
      - ./grafana/dashboards:/var/lib/grafana/dashboards:ro
    labels:
      - "traefik.enable=true"
      - "traefik.docker.network=traefik"
      - "traefik.http.routers.grafana.rule=Host(`selendis.axion1337.de`)"
      - "traefik.http.routers.grafana.entrypoints=websecure"
      - "traefik.http.routers.grafana.tls.certresolver=letsencrypt"
      - "traefik.http.services.grafana.loadbalancer.server.port=3000"
    depends_on:
      - prometheus
      - loki
    networks:
      - traefik

  node-exporter:
    image: prom/node-exporter:v1.9.1
    container_name: node-exporter
    restart: unless-stopped
    volumes:
      - /proc:/host/proc:ro
      - /sys:/host/sys:ro
      - /:/rootfs:ro
    command:
      - '--path.procfs=/host/proc'
      - '--path.sysfs=/host/sys'
      - '--path.rootfs=/rootfs'
      - '--web.listen-address=:9100'
      - '--web.disable-exporter-metrics'
    ports:
      - "9100:9100"
    networks:
      - traefik

volumes:
  prometheus_data:
  alertmanager_data:
  grafana_data:
  loki_data:
  alloy_data:

networks:
  traefik:
    external: true