概述

Elasticsearch以其优秀的分布式架构与全文搜索引擎等特点在机器数据的存储、分析领域广为使用，但随着数据量的增长，其聚合分析性能已无法满足业务需求。而ClickHouse作为一个高性能的OLAP列式数据库管理系统有望解决这一痛点。

本文是对ClickHouse与Elasticsearch聚合性能的简单对比测试。主要关注查询语句的响应时间，暂不考虑资源占用情况。

测试环境

使用ClickHouse官方提供的测试数据集，共67G，约6亿行。

测试数据集.png

其中，ClickHouse使用LO_ORDERDATE字段作为分区键，使用LO_ORDERDATE, LO_ORDERKEY作为排序键。

测试内容

某字段出现次数TOP 10

# ClickHouse
SELECT LO_SHIPMODE,COUNT() FROM lineorder GROUP BY LO_SHIPMODE ORDER BY COUNT() DESC LIMIT 10

# Elasticsearch
GET lineorder/_search
{
  "aggs": {
    "1": {
      "terms": {
        "field": "LO_SHIPMODE.keyword",
        "order": {
          "_count": "desc"
        },
        "size": 10
      }
    }
  },
  "size": 0
}

某字段按年进行计数

# ClickHouse
SELECT toYear(LO_ORDERDATE),COUNT() FROM lineorder GROUP BY toYear(LO_ORDERDATE) FORMAT PrettyCompactMonoBlock

# Elasticsearch
GET lineorder/_search
{
  "aggs": {
    "2": {
      "date_histogram": {
        "field": "LO_ORDERDATE",
        "calendar_interval":"1y",
        "format":"yyyy-MM-dd"
      }
    }
  },
  "size": 0
}

多个字段按年进行统计

# ClickHouse
SELECT LO_ORDERDATE,LO_ORDERKEY,LO_SHIPMODE,LO_ORDERPRIORITY,LO_COMMITDATE FROM lineorder WHERE LO_ORDERDATE >= '1992-01-01' AND LO_ORDERDATE < '1993-01-01' ORDER BY LO_ORDERDATE  LIMIT 500

# Elasticsearch
GET lineorder/_search
{
  "size": 500,
  "sort": [
    {
      "timestamp": {
        "order": "desc",
        "unmapped_type": "boolean"
      }
    }
  ],
  "query": {
    "bool": {
      "must": [],
      "filter": [
        {
          "match_all": {}
        },
        {
          "match_all": {}
        },
        {
          "range": {
            "LO_ORDERDATE": {
              "gte": "1992-01-01",
              "lte": "1993-01-01",
              "format": "strict_date_optional_time"
            }
          }
        }
      ],
      "should": [],
      "must_not": []
    }
  }
}

基于时间的多字段聚合

# ClickHouse
SELECT toYear(LO_ORDERDATE),LO_SHIPMODE,COUNT() FROM lineorder GROUP BY toYear(LO_ORDERDATE),LO_SHIPMODE ORDER BY toYear(LO_ORDERDATE) FORMAT PrettyCompactMonoBlock

# Elasticsearch
GET lineorder/_search
{
  "aggs": {
    "3": {
      "terms": {
        "field": "LO_SHIPMODE.keyword",
        "order": {
          "_count": "desc"
        },
        "size": 10
      },
      "aggs": {
        "2": {
          "date_histogram": {
            "field": "LO_ORDERDATE",
            "calendar_interval": "1y",
            "time_zone": "Asia/Shanghai",
            "min_doc_count": 1
          }
        }
      }
    }
  },
  "size": 0
}

基于时间的多字段聚合

# ClickHouse
SELECT toYear(LO_ORDERDATE),LO_SHIPMODE,COUNT() FROM lineorder GROUP BY toYear(LO_ORDERDATE),LO_SHIPMODE ORDER BY toYear(LO_ORDERDATE) FORMAT PrettyCompactMonoBlock

# Elasticsearch
GET lineorder/_search
{
  "aggs": {
    "3": {
      "terms": {
        "field": "LO_SHIPMODE.keyword",
        "order": {
          "_count": "desc"
        },
        "size": 10
      },
      "aggs": {
        "2": {
          "date_histogram": {
            "field": "LO_ORDERDATE",
            "calendar_interval": "1y",
            "time_zone": "Asia/Shanghai",
            "min_doc_count": 1
          }
        }
      }
    }
  },
  "size": 0
}

聚合嵌套（非时间字段）

# ClickHouse
SELECT LO_SHIPMODE,COUNT(LO_SHIPMODE),LO_ORDERPRIORITY,COUNT(LO_ORDERPRIORITY) FROM lineorder GROUP BY LO_SHIPMODE,LO_ORDERPRIORITY ORDER BY COUNT(LO_SHIPMODE),COUNT(LO_ORDERPRIORITY) LIMIT 5 BY LO_SHIPMODE,LO_ORDERPRIORITY

# Elasticsearch
GET lineorder/_search
{
  "aggs": {
    "2": {
      "terms": {
        "field": "LO_SHIPMODE.keyword",
        "order": {
          "_count": "desc"
        },
        "size": 5
      },
      "aggs": {
        "3": {
          "terms": {
            "field": "LO_ORDERPRIORITY.keyword",
            "order": {
              "_count": "desc"
            },
            "size": 5
          }
        }
      }
    }
  },
  "size": 0
}

测试结论

相同数据量下，ClickHouse的聚合性能都要优于Elasticsearch，且如果基于排序键进行聚合，性能更好，是ES的数倍。
此外，ClickHouse的SummaryMergeTree、AggregatingMergeTree表引擎支持后台自动聚合数据，所以在某些场景下其聚合分析性能会更优。