Imbalanced read results in instability of sysbench select_random_ranges/select_random_points performance (-25%~8%) #4529
Description
Bug Report
Imbalanced read results in instability of sysbench select_range_point performance (-25%~8%, compared with the baseline)
What did you do?
- Deploy a cluster
- Turn on prepare plan cache
- Run sysbench select_range_point
What did you expect to see?
The TPS of multiple tests are stable.
What did you see instead?
TPS：37778
TPS：54453
What version of PD are you using (pd-server -V)?
commit ae23d40