---
# ------------------------------------------------------------------------------
# FILE: boilerplates/monitoring/compose.yaml
# DESCRIPTION: Combined Prometheus + Grafana + Alertmanager + Node Exporter
#              stack for cinderella-castle (10.1.71.31)
#
# Generated from:
#   boilerplates/prometheus/compose.yaml (prom/prometheus:v3.9.1)
#   boilerplates/grafana/compose.yaml    (grafana/grafana-oss:12.3.3)
#
# Prometheus TSDB on dedicated second disk mounted at /var/lib/prometheus.
# Grafana data on named Docker volume.
# ------------------------------------------------------------------------------

services:

  prometheus:
    image: docker.io/prom/prometheus:v3.9.1
    container_name: prometheus
    restart: unless-stopped
    user: "65534:65534"
    command:
      - --config.file=/etc/prometheus/prometheus.yaml
      - --storage.tsdb.path=/prometheus
      - --storage.tsdb.retention.time=${PROMETHEUS_RETENTION_TIME:-15d}
      - --storage.tsdb.retention.size=${PROMETHEUS_RETENTION_SIZE:-58GB}
      - --web.enable-lifecycle
    ports:
      - "127.0.0.1:9090:9090"
    volumes:
      - /opt/docker/monitoring/prometheus/prometheus.yaml:/etc/prometheus/prometheus.yaml:ro
      - /var/lib/prometheus:/prometheus
    networks:
      - monitoring
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:9090/-/healthy"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 10s

  grafana:
    image: docker.io/grafana/grafana-oss:12.3.3
    container_name: grafana
    restart: unless-stopped
    environment:
      - GF_SECURITY_ADMIN_USER=${GRAFANA_ADMIN_USER:-admin}
      - GF_SECURITY_ADMIN_PASSWORD=${GRAFANA_ADMIN_PASSWORD}
      - GF_SERVER_ROOT_URL=https://grafana.local.mk-labs.cloud
    ports:
      - "3000:3000"
    volumes:
      - grafana_data:/var/lib/grafana
      - /opt/docker/monitoring/grafana/datasource.yml:/etc/grafana/provisioning/datasources/datasource.yml:ro
    networks:
      - monitoring
    depends_on:
      prometheus:
        condition: service_healthy
    healthcheck:
      test: ["CMD", "wget", "--spider", "-q", "http://localhost:3000/api/health"]
      interval: 30s
      timeout: 5s
      retries: 3
      start_period: 15s

  alertmanager:
    image: docker.io/prom/alertmanager:latest
    container_name: alertmanager
    restart: unless-stopped
    command:
      - --config.file=/etc/alertmanager/alertmanager.yml
      - --storage.path=/alertmanager
    ports:
      - "127.0.0.1:9093:9093"
    volumes:
      - /opt/docker/monitoring/alertmanager/alertmanager.yml:/etc/alertmanager/alertmanager.yml:ro
      - alertmanager_data:/alertmanager
    networks:
      - monitoring

  node-exporter:
    image: docker.io/prom/node-exporter:latest
    container_name: node-exporter
    restart: unless-stopped
    pid: host
    command:
      - --path.rootfs=/host
    ports:
      - "9100:9100"
    volumes:
      - /:/host:ro,rslave
    networks:
      - monitoring

networks:
  monitoring:
    driver: bridge
    name: monitoring

volumes:
  grafana_data:
    driver: local
  alertmanager_data:
    driver: local