ClickHouse/docs/en/operations/utilities/clickhouse-benchmark.md

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

165 lines
6.6 KiB
Markdown
Raw Normal View History

2020-04-03 13:23:32 +00:00
---
2022-08-28 14:53:34 +00:00
slug: /en/operations/utilities/clickhouse-benchmark
sidebar_position: 61
sidebar_label: clickhouse-benchmark
2020-04-03 13:23:32 +00:00
---
# clickhouse-benchmark
Connects to a ClickHouse server and repeatedly sends specified queries.
2020-12-30 13:33:47 +00:00
**Syntax**
``` bash
$ clickhouse-benchmark --query ["single query"] [keys]
```
or
2020-03-20 10:10:48 +00:00
``` bash
$ echo "single query" | clickhouse-benchmark [keys]
```
2020-03-20 10:10:48 +00:00
or
2020-03-20 10:10:48 +00:00
``` bash
$ clickhouse-benchmark [keys] <<< "single query"
```
If you want to send a set of queries, create a text file and place each query on the individual string in this file. For example:
2020-03-20 10:10:48 +00:00
``` sql
2020-12-30 13:33:47 +00:00
SELECT * FROM system.numbers LIMIT 10000000;
SELECT 1;
```
2020-12-30 13:33:47 +00:00
Then pass this file to a standard input of `clickhouse-benchmark`:
2020-03-20 10:10:48 +00:00
``` bash
2020-12-30 17:36:06 +00:00
clickhouse-benchmark [keys] < queries_file;
```
2020-03-18 18:43:51 +00:00
## Keys {#clickhouse-benchmark-keys}
2021-07-29 15:20:55 +00:00
- `--query=QUERY` — Query to execute. If this parameter is not passed, `clickhouse-benchmark` will read queries from standard input.
2021-01-13 23:16:40 +00:00
- `-c N`, `--concurrency=N` — Number of queries that `clickhouse-benchmark` sends simultaneously. Default value: 1.
- `-d N`, `--delay=N` — Interval in seconds between intermediate reports (to disable reports set 0). Default value: 1.
2021-01-20 15:38:35 +00:00
- `-h HOST`, `--host=HOST` — Server host. Default value: `localhost`. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-h` keys.
2021-01-13 23:16:40 +00:00
- `-p N`, `--port=N` — Server port. Default value: 9000. For the [comparison mode](#clickhouse-benchmark-comparison-mode) you can use multiple `-p` keys.
- `-i N`, `--iterations=N` — Total number of queries. Default value: 0 (repeat forever).
2020-12-30 13:33:47 +00:00
- `-r`, `--randomize` — Random order of queries execution if there is more than one input query.
- `-s`, `--secure` — Using `TLS` connection.
2021-01-13 23:16:40 +00:00
- `-t N`, `--timelimit=N` — Time limit in seconds. `clickhouse-benchmark` stops sending queries when the specified time limit is reached. Default value: 0 (time limit disabled).
2020-12-30 13:33:47 +00:00
- `--confidence=N` — Level of confidence for T-test. Possible values: 0 (80%), 1 (90%), 2 (95%), 3 (98%), 4 (99%), 5 (99.5%). Default value: 5. In the [comparison mode](#clickhouse-benchmark-comparison-mode) `clickhouse-benchmark` performs the [Independent two-sample Students t-test](https://en.wikipedia.org/wiki/Student%27s_t-test#Independent_two-sample_t-test) to determine whether the two distributions arent different with the selected level of confidence.
- `--cumulative` — Printing cumulative data instead of data per interval.
- `--database=DATABASE_NAME` — ClickHouse database name. Default value: `default`.
2020-12-30 13:33:47 +00:00
- `--json=FILEPATH``JSON` output. When the key is set, `clickhouse-benchmark` outputs a report to the specified JSON-file.
- `--user=USERNAME` — ClickHouse user name. Default value: `default`.
- `--password=PSWD` — ClickHouse user password. Default value: empty string.
- `--stacktrace` — Stack traces output. When the key is set, `clickhouse-bencmark` outputs stack traces of exceptions.
2020-12-30 13:33:47 +00:00
- `--stage=WORD` — Query processing stage at server. ClickHouse stops query processing and returns an answer to `clickhouse-benchmark` at the specified stage. Possible values: `complete`, `fetch_columns`, `with_mergeable_state`. Default value: `complete`.
- `--help` — Shows the help message.
If you want to apply some [settings](../../operations/settings/index.md) for queries, pass them as a key `--<session setting name>= SETTING_VALUE`. For example, `--max_memory_usage=1048576`.
2020-03-18 18:43:51 +00:00
## Output {#clickhouse-benchmark-output}
By default, `clickhouse-benchmark` reports for each `--delay` interval.
Example of the report:
2020-03-20 10:10:48 +00:00
``` text
Queries executed: 10.
localhost:9000, queries 10, QPS: 6.772, RPS: 67904487.440, MiB/s: 518.070, result RPS: 67721584.984, result MiB/s: 516.675.
2020-03-20 10:10:48 +00:00
0.000% 0.145 sec.
10.000% 0.146 sec.
20.000% 0.146 sec.
30.000% 0.146 sec.
40.000% 0.147 sec.
50.000% 0.148 sec.
60.000% 0.148 sec.
70.000% 0.148 sec.
80.000% 0.149 sec.
90.000% 0.150 sec.
95.000% 0.150 sec.
99.000% 0.150 sec.
99.900% 0.150 sec.
99.990% 0.150 sec.
```
In the report you can find:
- Number of queries in the `Queries executed:` field.
2020-03-20 10:10:48 +00:00
- Status string containing (in order):
- Endpoint of ClickHouse server.
- Number of processed queries.
2020-12-30 13:33:47 +00:00
- QPS: How many queries the server performed per second during a period specified in the `--delay` argument.
- RPS: How many rows the server reads per second during a period specified in the `--delay` argument.
- MiB/s: How many mebibytes the server reads per second during a period specified in the `--delay` argument.
- result RPS: How many rows placed by the server to the result of a query per second during a period specified in the `--delay` argument.
- result MiB/s. How many mebibytes placed by the server to the result of a query per second during a period specified in the `--delay` argument.
- Percentiles of queries execution time.
## Comparison Mode {#clickhouse-benchmark-comparison-mode}
2020-03-20 10:10:48 +00:00
`clickhouse-benchmark` can compare performances for two running ClickHouse servers.
To use the comparison mode, specify endpoints of both servers by two pairs of `--host`, `--port` keys. Keys matched together by position in arguments list, the first `--host` is matched with the first `--port` and so on. `clickhouse-benchmark` establishes connections to both servers, then sends queries. Each query addressed to a randomly selected server. The results are shown for each server separately.
2020-03-18 18:43:51 +00:00
## Example {#clickhouse-benchmark-example}
2020-03-20 10:10:48 +00:00
``` bash
$ echo "SELECT * FROM system.numbers LIMIT 10000000 OFFSET 10000000" | clickhouse-benchmark -i 10
```
2020-03-20 10:10:48 +00:00
``` text
Loaded 1 queries.
Queries executed: 6.
localhost:9000, queries 6, QPS: 6.153, RPS: 123398340.957, MiB/s: 941.455, result RPS: 61532982.200, result MiB/s: 469.459.
2020-03-20 10:10:48 +00:00
0.000% 0.159 sec.
10.000% 0.159 sec.
20.000% 0.159 sec.
30.000% 0.160 sec.
40.000% 0.160 sec.
50.000% 0.162 sec.
60.000% 0.164 sec.
70.000% 0.165 sec.
80.000% 0.166 sec.
90.000% 0.166 sec.
95.000% 0.167 sec.
99.000% 0.167 sec.
99.900% 0.167 sec.
99.990% 0.167 sec.
Queries executed: 10.
localhost:9000, queries 10, QPS: 6.082, RPS: 121959604.568, MiB/s: 930.478, result RPS: 60815551.642, result MiB/s: 463.986.
2020-03-20 10:10:48 +00:00
0.000% 0.159 sec.
10.000% 0.159 sec.
20.000% 0.160 sec.
30.000% 0.163 sec.
40.000% 0.164 sec.
50.000% 0.165 sec.
60.000% 0.166 sec.
70.000% 0.166 sec.
80.000% 0.167 sec.
90.000% 0.167 sec.
95.000% 0.170 sec.
99.000% 0.172 sec.
99.900% 0.172 sec.
99.990% 0.172 sec.
```
2020-12-30 13:33:47 +00:00
[Original article](https://clickhouse.com/docs/en/operations/utilities/clickhouse-benchmark.md) <!--hide-->