qps is continuously affected during the simulated pd log disk io delay 1s which last for 10mins
Bug Report
What did you do?
1、run workload 2、simulated pd log disk io delay 1s which last for 10mins
What did you expect to see?
no effort on workload
What did you see instead?
qps is continuously affected during the simulated pd log disk io delay 1s which last for 10mins
What version of PD are you using (pd-server -V)?
./pd-server -V Release Version: v8.5.4 Edition: Community Git Commit Hash: b448fca08722ffcafde9e15bf0594425c6930f14 Git Branch: HEAD UTC Build Time: 2025-09-23 03:08:08 2025-10-03T17:38:00.715+0800 INFO k8s/client.go:141 it should be noted that a long-running command will not be interrupted even the use case has ended. For more information, please refer to https://github.com/pingcap/test-infra/discussions/129
/severity major /assign bufferflies
ref: https://github.com/pingcap/tidb/issues/35007