创建/配置

version: '3.8'

services:
  clickhouse:
    image: docker.io/clickhouse/clickhouse-server
    container_name: clickhouse
    restart: always
    user: "101:101"
    environment:
      CLICKHOUSE_DB: default
      CLICKHOUSE_USER: ${CLICKHOUSE_USER:-clickhouse}
      CLICKHOUSE_PASSWORD: ${CLICKHOUSE_PASSWORD:-clickhouse} # CHANGEME
    volumes:
      - clickhouse_data:/var/lib/clickhouse
      - clickhouse_logs:/var/log/clickhouse-server
    ports:
      - 127.0.0.1:8123:8123
      - 127.0.0.1:9000:9000
    healthcheck:
      test: wget --no-verbose --tries=1 --spider http://localhost:8123/ping || exit 1
      interval: 5s
      timeout: 5s
      retries: 10
      start_period: 1s
    networks:
      - langfuse-network

volumes:
  clickhouse_data:
    driver: local
  clickhouse_logs:
    driver: local

networks:
  langfuse-network:
    name: langfuse-network
    driver: bridge

系统日志配置

• 在上面的配置中的volumns 中增加配置项目：

  • ./config/disable_system_logs.xml:/etc/clickhouse-server/config.d/disable_system_logs.xml
  • 前面是本地文件路径，后面是映射的容器内部配置文件路径

• 完全禁用

<clickhouse>
    <!-- 完全禁用所有系统日志表 -->
    <asynchronous_metric_log remove="1"/>
    <backup_log remove="1"/>
    <error_log remove="1"/>
    <metric_log remove="1"/>
    <query_metric_log remove="1"/>
    <query_thread_log remove="1" />  
    <query_log remove="1" />
    <query_views_log remove="1" />
    <part_log remove="1"/>
    <session_log remove="1"/>
    <text_log remove="1" />
    <trace_log remove="1"/>
    <crash_log remove="1"/>
    <opentelemetry_span_log remove="1"/>
    <zookeeper_log remove="1"/>
    <processors_profile_log remove="1"/>
    <latency_log remove="1"/>
    <background_schedule_pool_log remove="1"/>
    <aggregated_zookeeper_log remove="1"/>
    <zookeeper_connection_log remove="1"/>
</clickhouse>

• 部分禁用

<clickhouse>
    <!-- 只禁用最占空间的几个 -->
    <trace_log remove="1"/>        <!-- 这个最大，禁用 -->
    <text_log remove="1"/>          <!-- 这个也大，禁用 -->
    <metric_log remove="1"/>        <!-- 指标日志，禁用 -->
    
    <!-- 保留 query_log 和 part_log（但建议设置 TTL） -->
    <query_log>
        <ttl>event_date + INTERVAL 7 DAY DELETE</ttl>
        <partition_by>toYYYYMM(event_date)</partition_by>
    </query_log>
    <part_log>
        <ttl>event_date + INTERVAL 7 DAY DELETE</ttl>
        <partition_by>toYYYYMM(event_date)</partition_by>
    </part_log>
</clickhouse>

数据查询

磁盘占用

SELECT  
    database,  
    table,  
    formatReadableSize(sum(bytes_on_disk)) AS total_size,  
    sum(rows) AS total_rows,  
    count() AS part_count  
FROM system.parts  
WHERE active = 1  
GROUP BY database, table  
ORDER BY sum(bytes_on_disk) DESC;