clickhouse 26.6和duckdb 1.6dev的group by cube查询比较

l1t2026-06-22 10:09

对1亿行随机数分组汇总

duckdb 1.6dev

sql 复制代码 
C:\d>duckdb0619
DuckDB v1.6.0-dev9098 (Development Version, 2bfea2aa19)
Enter ".help" for usage hints.
memory D create table ren as select
         ((random()*1000)::int%2+1)::int c1,
         ((random()*1000)::int%100+1)::int c2,
         ((random()*1000)::int%30+1)::int c3,
         ((random()*1000)::int%60+1)::int c4,
         ((random()*1000)::int%5+1)::int c5
         from generate_series(1,1e8::int);
memory D .timer on
memory D create table rc1c2c3c4 as select c1,c2,c3,c4,sum(1)cnt from ren group by cube(c1,c2,c3,c4);
Run Time (s): real 1.593 user 17.390625 sys 0.968750
memory D select count(*) from rc1c2c3c4;
┌──────────────┐
│ count_star() │
│    int64     │
├──────────────┤
│       572973 │
└──────────────┘
Run Time (s): real 0.010 user 0.000000 sys 0.000000

clickhouse 26.6

sql 复制代码 
C:\d>wsl
root@DESKTOP-59T6U68:/mnt/c/d# ./clickhouse
ClickHouse local version 26.6.1.731 (official build).


:) create table ren as select
((rand()*1000)::int%2+1)::int c1,
((rand()*1000)::int%100+1)::int c2,
((rand()*1000)::int%30+1)::int c3,
((rand()*1000)::int%60+1)::int c4,
((rand()*1000)::int%5+1)::int c5
from generate_series(1,100000000);

CREATE TABLE ren
AS SELECT
    CAST(((CAST((rand() * 1000), 'int') % 2) + 1), 'int') AS c1,
    CAST(((CAST((rand() * 1000), 'int') % 100) + 1), 'int') AS c2,
    CAST(((CAST((rand() * 1000), 'int') % 30) + 1), 'int') AS c3,
    CAST(((CAST((rand() * 1000), 'int') % 60) + 1), 'int') AS c4,
    CAST(((CAST((rand() * 1000), 'int') % 5) + 1), 'int') AS c5
FROM generate_series(1, 100000000)

Query id: e6a83d26-e6a9-40ba-8eed-b74f285fbc78

Ok.

100000000 rows in set. Elapsed: 5.758 sec. Processed 100.00 million rows, 800.00 MB (17.37 million rows/s., 138.94 MB/s.)
Peak memory usage: 63.47 MiB.

:) create table rc1c2c3c4 as select c1,c2,c3,c4,sum(1)cnt from ren group by cube(c1,c2,c3,c4);

CREATE TABLE rc1c2c3c4
AS SELECT
    c1,
    c2,
    c3,
    c4,
    sum(1) AS cnt
FROM ren
GROUP BY
    c1,
    c2,
    c3,
    c4
    WITH CUBE

Query id: b2eca8f3-32f2-4668-9786-d69cfd038f53

Ok.

1168 rows in set. Elapsed: 0.322 sec. Processed 100.00 million rows, 1.60 GB (310.67 million rows/s., 4.97 GB/s.)
Peak memory usage: 4.09 MiB.

与duckdb比较，clickhouse生成数据和汇总都快得出奇，但后者的行数明显过少，查看数据。

sql 复制代码 
:) select * from ren;

SELECT *
FROM ren

Query id: a402aca9-009b-4399-9770-5bf3123b31db

         ┌─c1─┬──c2─┬──c3─┬──c4─┬─c5─┐
      1. │  1 │  57 │   7 │  37 │  2 │
      2. │  1 │ -47 │  -7 │  -7 │ -2 │
      3. │  1 │  -3 │ -13 │ -43 │ -3 │
      4. │  1 │ -59 │   1 │   1 │  1 │
      5. │  1 │ -55 │ -25 │ -55 │  0 │
      6. │  1 │   1 │  21 │  21 │  1 │
      7. │  1 │ -75 │  -5 │ -35 │  0 │
      8. │  1 │  93 │  13 │  13 │  3 │
      9. │  1 │  97 │   7 │  37 │  2 │
     10. │  1 │  61 │   1 │   1 │  1 │
     11. │  1 │ -59 │   1 │   1 │  1 │
     12. │  1 │  81 │   1 │   1 │  1 │
     13. │  1 │   5 │  25 │  25 │  5 │
     14. │  1 │ -23 │ -13 │ -43 │ -3 │
     
4227068. │  1 │  49 │  19 │  49 │  4 │
4227069. │  1 │   5 │  25 │  25 │  5 │
4227070. │  1 │ -31 │  -1 │ -31 │ -1 │
4227071. │  1 │  93 │   3 │  33 │  3 │
4227072. │  1 │  77 │  27 │  57 │  2 │
         └─c1─┴──c2─┴──c3─┴──c4─┴─c5─┘
Showed 1000 out of 100000000 rows.

100000000 rows in set. Elapsed: 0.497 sec. Processed 100.00 million rows, 2.00 GB (201.16 million rows/s., 4.02 GB/s.)
Peak memory usage: 188.60 MiB.

:) select * from rc1c2c3c4 limit 10;

SELECT *
FROM rc1c2c3c4
LIMIT 10

Query id: c892b34d-8eb4-46cd-811e-cecddf035987

    ┌─c1─┬─c2─┬─c3─┬─c4─┬────cnt─┐
 1. │  1 │ 93 │ 13 │ 13 │ 667216 │
 2. │  1 │ 81 │ 21 │ 21 │ 666623 │
 3. │  1 │ 41 │  1 │  1 │ 665197 │
 4. │  1 │  5 │  5 │  5 │ 666132 │
 5. │  1 │  9 │ 29 │ 29 │ 666747 │
 6. │  1 │ 77 │ 17 │ 17 │ 666084 │
 7. │  1 │  5 │ 25 │ 25 │ 666766 │
 8. │  1 │ 89 │ 29 │ 29 │ 666258 │
 9. │  1 │ 85 │  5 │  5 │ 667259 │
10. │  1 │ 49 │  9 │  9 │ 666100 │
    └────┴────┴────┴────┴────────┘

10 rows in set. Elapsed: 0.005 sec. Processed 1.17 thousand rows, 28.03 KB (217.09 thousand rows/s., 5.21 MB/s.)
Peak memory usage: 39.17 KiB.

:)     

:) select rand();

SELECT rand()

Query id: 5000b861-343a-4e26-b35c-0f40e4c66415

   ┌─────rand()─┐
1. │ 4067771733 │ -- 4.07 billion
   └────────────┘

1 row in set. Elapsed: 0.003 sec.


create table ren as select
(rand()%2+1)::int c1,
(rand()%100+1)::int c2,
(rand()%30+1)::int c3,
(rand()%60+1)::int c4,
(rand()%5+1)::int c5
from generate_series(1,100000000);


CREATE TABLE ren
AS SELECT
    CAST(((rand() % 2) + 1), 'int') AS c1,
    CAST(((rand() % 100) + 1), 'int') AS c2,
    CAST(((rand() % 30) + 1), 'int') AS c3,
    CAST(((rand() % 60) + 1), 'int') AS c4,
    CAST(((rand() % 5) + 1), 'int') AS c5
FROM generate_series(1, 100000000)

Query id: 8907c2c1-3cb2-4903-a0a1-d350a8407d36

Ok.

100000000 rows in set. Elapsed: 5.601 sec. Processed 100.00 million rows, 800.00 MB (17.85 million rows/s., 142.84 MB/s.)
Peak memory usage: 63.60 MiB.

:) select * from ren limit 20;

SELECT *
FROM ren
LIMIT 20

Query id: 8e3d2756-a3b3-4814-b84d-dbc199c1fa95

    ┌─c1─┬─c2─┬─c3─┬─c4─┬─c5─┐
 1. │  2 │ 26 │ 16 │ 46 │  1 │
 2. │  1 │ 49 │ 19 │ 49 │  4 │
 3. │  1 │ 53 │ 23 │ 53 │  3 │
 4. │  2 │  4 │ 24 │ 24 │  4 │
 5. │  2 │ 78 │ 18 │ 18 │  3 │
 6. │  2 │ 62 │ 12 │ 42 │  2 │
 7. │  1 │  3 │ 13 │ 43 │  3 │
 8. │  1 │ 61 │  1 │  1 │  1 │
 9. │  2 │  2 │ 12 │ 42 │  2 │
10. │  1 │ 29 │ 19 │ 49 │  4 │
11. │  1 │ 93 │  3 │ 33 │  3 │
12. │  2 │ 36 │ 26 │ 56 │  1 │
13. │  1 │ 35 │ 25 │ 55 │  5 │
14. │  2 │ 46 │  6 │  6 │  1 │
15. │  1 │ 39 │ 29 │ 59 │  4 │
16. │  2 │ 84 │  4 │  4 │  4 │
17. │  2 │ 28 │ 18 │ 48 │  3 │
18. │  2 │ 52 │  2 │ 32 │  2 │
19. │  2 │ 40 │ 10 │ 40 │  5 │
20. │  1 │ 27 │ 17 │ 47 │  2 │
    └────┴────┴────┴────┴────┘

20 rows in set. Elapsed: 0.005 sec.

:)
:) select rand(),rand();

SELECT
    rand(),
    rand()

Query id: 1af2ae02-cec7-4703-8bd3-2466b67260da

   ┌─────rand()─┬─────rand()─┐
1. │ 3590268032 │ 3590268032 │ -- 3.59 billion
   └────────────┴────────────┘

负数是整数乘法溢出的结果，rand()返回32位整数，去掉多余的*1000，看出问题了，对20, 60, 100取模的结果都一样，原因是clickhouse在同一行多次调用rand()，返回同一个值，所以从c1到c5, 它们的值都是固定的函数关系，导致分组过少。

而duckdb的同一行多个random()返回不同的值。

sql 复制代码 
memory D select random(),random();
┌─────────────────────┬────────────────────┐
│      random()       │      random()      │
│       double        │       double       │
├─────────────────────┼────────────────────┤
│ 0.46592717838277703 │ 0.7400053681100808 │
└─────────────────────┴────────────────────┘

暂时没找到方法让clickhouse返回不同的值。先把duckdb数据表复制到parquet文件，然后用clickhouse查询此文件。

sql 复制代码 
memory D copy ren to 'ren1e8.parquet';

:) create table rc1c2c3c4 as select c1,c2,c3,c4,sum(1)cnt from file('ren1e8.parquet') group by cube(c1,c2,c3,c4);

CREATE TABLE rc1c2c3c4
AS SELECT
    c1,
    c2,
    c3,
    c4,
    sum(1) AS cnt
FROM file('ren1e8.parquet')
GROUP BY
    c1,
    c2,
    c3,
    c4
    WITH CUBE

Query id: 143fa1f0-b99c-4dae-a727-6944ee250bab

Ok.

572973 rows in set. Elapsed: 1.476 sec. Processed 100.00 million rows, 239.94 MB (67.75 million rows/s., 162.55 MB/s.)
Peak memory usage: 253.44 MiB.

这下返回行数和duckdb完全相同，和duckdb查询内存表的时间相比，快了0.2s。再将文件复制到clickhouse内存表。

sql 复制代码 
:) create table ren as select * from file('ren1e8.parquet');

CREATE TABLE ren
AS SELECT *
FROM file('ren1e8.parquet')

Query id: 0fc6193f-b75d-4ef8-b906-d8e8f2a738a6

Ok.

100000000 rows in set. Elapsed: 5.980 sec. Processed 100.00 million rows, 277.89 MB (16.72 million rows/s., 46.47 MB/s.)
Peak memory usage: 277.83 MiB.

:) create table rc1c2c3c4m as select c1,c2,c3,c4,sum(1)cnt from ren group by cube(c1,c2,c3,c4);

CREATE TABLE rc1c2c3c4m
AS SELECT
    c1,
    c2,
    c3,
    c4,
    sum(1) AS cnt
FROM ren
GROUP BY
    c1,
    c2,
    c3,
    c4
    WITH CUBE

Query id: a5561df0-ad59-4395-9976-5ad60417bfe9

Ok.

572973 rows in set. Elapsed: 1.252 sec. Processed 100.00 million rows, 1.60 GB (79.88 million rows/s., 1.28 GB/s.)
Peak memory usage: 215.22 MiB.

结果又快了0.2秒。

补记：

我把rand()返回同一个值的问题在clickhouse存储库中提问，得到了解答(https://github.com/ClickHouse/ClickHouse/discussions/108051)。很简单，填一个不同的参数即可。

sql 复制代码 
./clickhouse
ClickHouse local version 26.6.1.731 (official build).

:) create table ren as select
(rand(1)%2+1)::int c1,
(rand(2)%100+1)::int c2,
(rand(3)%30+1)::int c3,
(rand(4)%60+1)::int c4,
(rand(5)%5+1)::int c5
from generate_series(1,100000000);

CREATE TABLE ren
AS SELECT
    CAST(((rand(1) % 2) + 1), 'int') AS c1,
    CAST(((rand(2) % 100) + 1), 'int') AS c2,
    CAST(((rand(3) % 30) + 1), 'int') AS c3,
    CAST(((rand(4) % 60) + 1), 'int') AS c4,
    CAST(((rand(5) % 5) + 1), 'int') AS c5
FROM generate_series(1, 100000000)

Query id: b7d52a36-042a-4357-b2dc-c49a3d277b84

Ok.

100000000 rows in set. Elapsed: 5.764 sec. Processed 100.00 million rows, 800.00 MB (17.34 million rows/s., 138.76 MB/s.)
Peak memory usage: 63.60 MiB.

:) create table rc1c2c3c4m as select c1,c2,c3,c4,sum(1)cnt from ren group by cube(c1,c2,c3,c4);

CREATE TABLE rc1c2c3c4m
AS SELECT
    c1,
    c2,
    c3,
    c4,
    sum(1) AS cnt
FROM ren
GROUP BY
    c1,
    c2,
    c3,
    c4
    WITH CUBE

Query id: f391c8e7-9a6b-4cc0-9472-5451f4e48204

Ok.

572973 rows in set. Elapsed: 1.091 sec. Processed 100.00 million rows, 1.60 GB (91.64 million rows/s., 1.47 GB/s.)
Peak memory usage: 215.22 MiB.

:)
热门推荐
01GitHub 镜像站点02幻兽帕鲁 - 服务器管理员权限与 GM 命令完全指南03AI科技热点日报 | 2026年07月01日042026年7月AI圈大地震：GPT-5.6被政府限制、Claude入驻Slack、Anthropic自研芯片052026 年 AI 编程工具终极横评：Cursor vs Claude Code vs Copilot vs Windsurf062026 AI 编程工具终极实战指南：Cursor vs Claude Code vs Copilot，开发者该怎么选？07AI 编程 IDE 全景解析 2026：Agent 全面接管开发链路082026 国产 AI 大模型横评：DeepSeek、通义千问、Kimi、文心一言、星火、豆包谁更能打？092026 年 AI 大模型 & AI 编程工具实战全总结10【AI】2026 年具身智能模型和世界模型总结