Re: [PATCH 1/1] Sched/fair: Improve the accuracy of sched_stat_wait statistics

2020-10-15 Thread Peter Zijlstra
On Thu, Oct 15, 2020 at 02:48:46PM +0800, qianjun.ker...@gmail.com wrote: > From: jun qian > > When the sched_schedstat changes from 0 to 1, some sched se maybe > already in the runqueue, the se->statistics.wait_start will be 0. > So it will let the (rq_of(cfs_rq)) - se->statistics.wait_start) >

[PATCH 1/1] Sched/fair: Improve the accuracy of sched_stat_wait statistics

2020-10-15 Thread qianjun . kernel
From: jun qian When the sched_schedstat changes from 0 to 1, some sched se maybe already in the runqueue, the se->statistics.wait_start will be 0. So it will let the (rq_of(cfs_rq)) - se->statistics.wait_start) wrong. We need to avoid this scenario. Signed-off-by: jun qian Reviewed-by: Yafang

Re: [PATCH 1/1] Sched/fair: Improve the accuracy of sched_stat_wait statistics

2020-10-15 Thread Yafang Shao
On Wed, Oct 14, 2020 at 9:19 PM Peter Zijlstra wrote: > > On Fri, Oct 09, 2020 at 05:25:30PM +0800, qianjun.ker...@gmail.com wrote: > > From: jun qian > > > > When the sched_schedstat changes from 0 to 1, some sched se maybe > > already in the runqueue, the se->statistics.wait_start will be 0. >

Re: [PATCH 1/1] Sched/fair: Improve the accuracy of sched_stat_wait statistics

2020-10-14 Thread Peter Zijlstra
On Fri, Oct 09, 2020 at 05:25:30PM +0800, qianjun.ker...@gmail.com wrote: > From: jun qian > > When the sched_schedstat changes from 0 to 1, some sched se maybe > already in the runqueue, the se->statistics.wait_start will be 0. > So it will let the (rq_of(cfs_rq)) - se->statistics.wait_start) >

[PATCH 1/1] Sched/fair: Improve the accuracy of sched_stat_wait statistics

2020-10-09 Thread qianjun . kernel
From: jun qian When the sched_schedstat changes from 0 to 1, some sched se maybe already in the runqueue, the se->statistics.wait_start will be 0. So it will let the (rq_of(cfs_rq)) - se->statistics.wait_start) wrong. We need to avoid this scenario. Signed-off-by: jun qian Signed-off-by: