Meaning of TiDB Dashboard Coprocessor Read Panel

Translated
1

Note:
This topic has been translated from a Chinese forum by GPT and might contain errors.

Original topic: tidb dashboard coprocessor读取面板含义

| username: TiDBer_SHQw04Jz

To improve efficiency, please provide the following information. Clear problem descriptions can be resolved more quickly:

【TiDB Usage Environment】Production, Testing, Research
Production
【TiDB Version】
5.x
【Encountered Problem】
Can you help explain the meanings of each row under the “Slow Query — Coprocessor Read” panel in the TiDB dashboard? It would help in analyzing the issue. For example:

Cumulative coprocessor request count
Average visible version count per SQL query
Average encountered version count per SQL query
RocksDB deleted key scan count
RocksDB key scan count

【Reproduction Path】What operations were performed to encounter the problem
【Problem Phenomenon and Impact】

【Attachments】

Please provide the version information of each component, such as cdc/tikv, which can be obtained by executing cdc version/tikv-server --version.

2
| username: wakaka | Original post link

The coprocessor is the module in TiKV that reads data and performs computations.

3
| username: tidb狂热爱好者 | Original post link

Could you please help explain the approximate meaning of each row under the “Slow Query - Coprocessor Read” panel in the TiDB dashboard? It would help in analyzing the issue. For example:

  • Cumulative coprocessor request count: The actual number of key-value pairs needed.
  • Average visible version count per SQL query: If there are many deleted versions, it will be greater than the cumulative coprocessor request count.
  • Average encountered version count per SQL query: If there are many deleted versions, it will be greater than the cumulative coprocessor request count.
  • RocksDB deleted key scan count: If there are many deleted versions, even though the data has been deleted, it will still be scanned if not yet reclaimed.
  • RocksDB key scan count: The number of keys scanned.
4
| username: Lucien-卢西恩 | Original post link

Hello, you can refer to the documentation on slow queries. It contains some simple explanations that might answer your question. 慢查询日志 | PingCAP 文档中心