Coroot

name: coroot
services:
  coroot:
    restart: always
    image: ghcr.io/coroot/coroot${LICENSE_KEY:+-ee} # set 'coroot-ee' as the image if LICENSE_KEY is defined
    pull_policy: always
    user: root
    volumes:
      - coroot_data:/data
    ports:
      - 8080:8080
    command:
      - '--data-dir=/data'
      - '--bootstrap-prometheus-url=http://prometheus:9090'
      - '--bootstrap-refresh-interval=15s'
      - '--bootstrap-clickhouse-address=clickhouse:9000'
    environment:
      - LICENSE_KEY=${LICENSE_KEY:-}
    depends_on:
      clickhouse:
        condition: service_healthy
      prometheus:
        condition: service_healthy

  node-agent:
    restart: always
    image: ghcr.io/coroot/coroot-node-agent
    pull_policy: always
    privileged: true
    pid: "host"
    volumes:
      - /sys/kernel/tracing:/sys/kernel/tracing
      - /sys/kernel/debug:/sys/kernel/debug
      - /sys/fs/cgroup:/host/sys/fs/cgroup
      - node_agent_data:/data
    command:
      - '--collector-endpoint=http://coroot:8080'
      - '--cgroupfs-root=/host/sys/fs/cgroup'
      - '--wal-dir=/data'

  cluster-agent:
    restart: always
    image: ghcr.io/coroot/coroot-cluster-agent
    pull_policy: always
    volumes:
      - cluster_agent_data:/data
    command:
      - '--coroot-url=http://coroot:8080'
      - '--metrics-scrape-interval=15s'
      - '--metrics-wal-dir=/data'
    depends_on:
      - coroot

  prometheus:
    restart: always
    image: prom/prometheus:v2.53.5
    volumes:
      - prometheus_data:/prometheus
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
      - '--web.enable-lifecycle'
      - '--web.enable-remote-write-receiver'
    ports:
      - '127.0.0.1:9090:9090'
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:9090/-/healthy"]
      interval: 3s
      timeout: 5s
      retries: 5
      start_period: 10s

  clickhouse:
    restart: always
    image: clickhouse/clickhouse-server:24.3
    environment:
      CLICKHOUSE_SKIP_USER_SETUP: "1"
    volumes:
      - clickhouse_data:/var/lib/clickhouse
      - clickhouse_logs:/var/log/clickhouse-server
    ports:
      - '127.0.0.1:9000:9000'
    ulimits:
      nofile:
        soft: 262144
        hard: 262144
    configs:
      - source: clickhouse_logging
        target: /etc/clickhouse-server/config.d/logging_rules.xml
      - source: clickhouse_user_logging
        target: /etc/clickhouse-server/config.d/user_logging.xml
    healthcheck:
      test: ["CMD", "wget", "--no-verbose", "--tries=1", "--spider", "http://localhost:8123/ping"]
      interval: 3s
      timeout: 5s
      retries: 5
      start_period: 10s

volumes:
  prometheus_data: {}
  clickhouse_data: {}
  clickhouse_logs: {}
  coroot_data: {}
  node_agent_data: {}
  cluster_agent_data: {}

configs:
  clickhouse_logging:
    content: |
      <clickhouse>
        <logger>
            <level>warning</level>
            <console>true</console>
        </logger>
        <query_thread_log remove="remove"/>
        <query_log remove="remove"/>
        <text_log remove="remove"/>
        <trace_log remove="remove"/>
        <metric_log remove="remove"/>
        <asynchronous_metric_log remove="remove"/>
        <session_log remove="remove"/>
        <part_log remove="remove"/>
        <latency_log remove="remove"/>
        <processors_profile_log remove="remove"/>
      </clickhouse>
  clickhouse_user_logging:
    content: |
      <clickhouse>
        <profiles>
          <default>
            <log_queries>0</log_queries>
            <log_query_threads>0</log_query_threads>
            <log_processors_profiles>0</log_processors_profiles>
          </default>
        </profiles>
      </clickhouse>