Description of problem: Once we echo 0 > /proc/pid/sched, the wait_start will be cleared. And if the task is excatly waiting in run queue, the wait_max will be much greater than the actual value, closing to the boot time. Version-Release number of selected component (if applicable): devel-5.10 How reproducible: echo 0 > /proc/[pid]/sched Steps to Reproduce: 1.echo 0 > /proc/[pid]/sched 2.cat /proc/[pid]/sched | grep wait_max Actual results: 54768574.070401 Expected results: 29.999171
The PR Link: https://gitee.com/anolis/cloud-kernel/pulls/3582