[PATCH] sched/fair: don't use waker's cpu if the waker of sync wake-up is interrupt

[Song Bao Hua (Barry Song)]

> -----Original Message-----
> From: Mike Galbraith [mailto:efault at gmx.de]
> Sent: Tuesday, April 27, 2021 5:55 PM
> To: Song Bao Hua (Barry Song) <song.bao.hua at hisilicon.com>;
> vincent.guittot at linaro.org; mingo at redhat.com; peterz at infradead.org;
> dietmar.eggemann at arm.com; rostedt at goodmis.org; bsegall at google.com;
> mgorman at suse.de
> Cc: valentin.schneider at arm.com; juri.lelli at redhat.com; bristot at redhat.com;
> linux-arm-kernel at lists.infradead.org; linux-kernel at vger.kernel.org; xuwei (O)
> <xuwei5 at huawei.com>; Zengtao (B) <prime.zeng at hisilicon.com>;
> guodong.xu at linaro.org; yangyicong <yangyicong at huawei.com>; Liguozhu (Kenneth)
> <liguozhu at hisilicon.com>; linuxarm at openeuler.org; wanghuiqiang
> <wanghuiqiang at huawei.com>; xieyongjia (A) <xieyongjia1 at huawei.com>
> Subject: Re: [PATCH] sched/fair: don't use waker's cpu if the waker of sync
> wake-up is interrupt
> 
> On Tue, 2021-04-27 at 04:44 +0000, Song Bao Hua (Barry Song) wrote:
> >
> >
> > I agree sync hint might have been overused by other kernel subsystem.
> > But this patch will at least fix a case: sync waker is interrupt,
> > in this case, the existing task has nothing to do with waker and wakee,
> > so this case should be excluded from wake_affine_idle().
> 
> I long ago tried filtering interrupt wakeups, and met some surprises.
> Wakeup twiddling always managing to end up being a rob Peter to pay
> Paul operation despite our best efforts, here's hoping that your pile
> of stolen cycles is small enough to escape performance bot notice :)

Would you like to share the link you did before to filter interrupt
wakeups?

The wake up path has hundreds of lines of code, so I don't expect that
reading preempt_count will cause visible performance losses to bot. But
who knows :-)

> 
> 	-Mike

Thanks
Barry