Re: single aio thread is migrated crazily by scheduler

From: Srikar Dronamraju
Date: Mon Dec 09 2019 - 22:27:29 EST


* Dave Chinner <david@xxxxxxxxxxxxx> [2019-12-10 10:17:43]:

> On Mon, Dec 09, 2019 at 10:21:22PM +0530, Srikar Dronamraju wrote:
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index 44123b4d14e8..efd740aafa17 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -2664,7 +2664,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
> > */
> > int wake_up_process(struct task_struct *p)
> > {
> > - return try_to_wake_up(p, TASK_NORMAL, 0);
> > + int wake_flags = 0;
> > +
> > + if (is_per_cpu_kthread(p))
> > + wake_flags = WF_KTHREAD;
> > +
> > + return try_to_wake_up(p, TASK_NORMAL, WF_KTHREAD);
>
> This is buggy. It always sets WF_KTHREAD, even for non-kernel
> processes. I think you meant:
>
> return try_to_wake_up(p, TASK_NORMAL, wake_flags);

Yes, I meant the above. Thanks for catching.
Will test with this and repost.

>
> I suspect this bug invalidates the test results presented, too...
>
> -Dave.
> --
> Dave Chinner
> david@xxxxxxxxxxxxx

--
Thanks and Regards
Srikar Dronamraju