How is the cache hit rate of the Coprocessor calculated?

Translated
4
| username: 人如其名 | Original post link

The cache hit rate is the ratio of cop_task cache hits to the total number of cop_tasks, which is cop_task(cache hits)/total_cop_task. Whether the cache is hit depends on the region version information in TiKV (it is speculated that a new version is generated when the data in the region changes, and if the version does not change, it is a hit). After a hit, TiDB’s copr_cache uses the key generated by the cop_task request (copRequest) to find the value from the last request. Network overhead is unavoidable, but there is no need to rescan the data in TiKV.