Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-09-01 Thread Jiang Biao
Hi, On Tue, 1 Sep 2020 at 21:04, Vincent Guittot wrote: > > On Tue, 1 Sep 2020 at 12:15, Jiang Biao wrote: > > > > Hi, Vincent > > > > Sorry for the late reply.:) > > > > On Fri, 28 Aug 2020 at 20:55, Vincent Guittot > > wrote: > > > > > > On Sun, 23 Aug 2020 at 09:33, Jiang Biao wrote: > > >

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-09-01 Thread Vincent Guittot
On Tue, 1 Sep 2020 at 12:15, Jiang Biao wrote: > > Hi, Vincent > > Sorry for the late reply.:) > > On Fri, 28 Aug 2020 at 20:55, Vincent Guittot > wrote: > > > > On Sun, 23 Aug 2020 at 09:33, Jiang Biao wrote: > > > > > > Hi, Vincent and Peter > > > > > > On Thu, 20 Aug 2020 at 22:09, Vincent Gu

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-09-01 Thread Jiang Biao
Hi, Vincent Sorry for the late reply.:) On Fri, 28 Aug 2020 at 20:55, Vincent Guittot wrote: > > On Sun, 23 Aug 2020 at 09:33, Jiang Biao wrote: > > > > Hi, Vincent and Peter > > > > On Thu, 20 Aug 2020 at 22:09, Vincent Guittot > > wrote: > > > > > > On Thu, 20 Aug 2020 at 15:44, wrote: > >

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-28 Thread Vincent Guittot
On Sun, 23 Aug 2020 at 09:33, Jiang Biao wrote: > > Hi, Vincent and Peter > > On Thu, 20 Aug 2020 at 22:09, Vincent Guittot > wrote: > > > > On Thu, 20 Aug 2020 at 15:44, wrote: > > > > > > > That's been said, not compensating the vruntime for a sched_idle task > > > > makes sense for me. Even i

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-23 Thread Jiang Biao
Hi, Vincent and Peter On Thu, 20 Aug 2020 at 22:09, Vincent Guittot wrote: > > On Thu, 20 Aug 2020 at 15:44, wrote: > > > > > That's been said, not compensating the vruntime for a sched_idle task > > > makes sense for me. Even if that will only help for others task in the > > > same cfs_rq > > >

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Jiang Biao
On Thu, 20 Aug 2020 at 22:09, Vincent Guittot wrote: > > On Thu, 20 Aug 2020 at 15:44, wrote: > > > > > That's been said, not compensating the vruntime for a sched_idle task > > > makes sense for me. Even if that will only help for others task in the > > > same cfs_rq > > > > Yeah, but it is wort

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Jiang Biao
On Thu, 20 Aug 2020 at 20:58, wrote: > > On Thu, Aug 20, 2020 at 02:51:06PM +0200, Vincent Guittot wrote: > > On Thu, 20 Aug 2020 at 14:00, Jiang Biao wrote: > > > > > > From: Jiang Biao > > > > > > Vruntime compensation has been down in place_entity() to > > > boot the waking procedure for fair

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Jiang Biao
On Thu, 20 Aug 2020 at 20:51, Vincent Guittot wrote: > > On Thu, 20 Aug 2020 at 14:00, Jiang Biao wrote: > > > > From: Jiang Biao > > > > Vruntime compensation has been down in place_entity() to > > boot the waking procedure for fair tasks. There is no need to > > s/boot/boost/ ? Yes. -:) > > >

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Vincent Guittot
On Thu, 20 Aug 2020 at 15:44, wrote: > > > That's been said, not compensating the vruntime for a sched_idle task > > makes sense for me. Even if that will only help for others task in the > > same cfs_rq > > Yeah, but it is worth the extra pointer chasing and branches? For that I let Jiang provid

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread peterz
> That's been said, not compensating the vruntime for a sched_idle task > makes sense for me. Even if that will only help for others task in the > same cfs_rq Yeah, but it is worth the extra pointer chasing and branches? Then again, I suppose we started all that with the idle_h_nr_running nonsens

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Vincent Guittot
On Thu, 20 Aug 2020 at 14:58, wrote: > > On Thu, Aug 20, 2020 at 02:51:06PM +0200, Vincent Guittot wrote: > > On Thu, 20 Aug 2020 at 14:00, Jiang Biao wrote: > > > > > > From: Jiang Biao > > > > > > Vruntime compensation has been down in place_entity() to > > > boot the waking procedure for fair

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread peterz
On Thu, Aug 20, 2020 at 02:51:06PM +0200, Vincent Guittot wrote: > On Thu, 20 Aug 2020 at 14:00, Jiang Biao wrote: > > > > From: Jiang Biao > > > > Vruntime compensation has been down in place_entity() to > > boot the waking procedure for fair tasks. There is no need to > > s/boot/boost/ ? > >

Re: [PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Vincent Guittot
On Thu, 20 Aug 2020 at 14:00, Jiang Biao wrote: > > From: Jiang Biao > > Vruntime compensation has been down in place_entity() to > boot the waking procedure for fair tasks. There is no need to s/boot/boost/ ? > do that for SCHED_IDLE task actually. > > Not compensating vruntime for SCHED_IDLE

[PATCH] sched/fair: avoid vruntime compensation for SCHED_IDLE task

2020-08-20 Thread Jiang Biao
From: Jiang Biao Vruntime compensation has been down in place_entity() to boot the waking procedure for fair tasks. There is no need to do that for SCHED_IDLE task actually. Not compensating vruntime for SCHED_IDLE task could make SCHED_IDLE task more harmless for normal tasks. Signed-off-by: J