Re: [PATCH v2] sched: Queue task on wakelist in the same llc if the wakee cpu is idle

[Mel Gorman <mgorman@suse.de>]

On Tue, May 31, 2022 at 12:50:49PM +0100, Valentin Schneider wrote:
> >> With all that in mind, I'm curious whether your patch is functionaly close
> >> to the below.
> >> 
> >> ---
> >> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> >> index 66c4e5922fe1..ffd43264722a 100644
> >> --- a/kernel/sched/core.c
> >> +++ b/kernel/sched/core.c
> >> @@ -3836,7 +3836,7 @@ static inline bool ttwu_queue_cond(int cpu, int wake_flags)
> >>   	 * the soon-to-be-idle CPU as the current CPU is likely busy.
> >>   	 * nr_running is checked to avoid unnecessary task stacking.
> >>   	 */
> >> -	if ((wake_flags & WF_ON_CPU) && cpu_rq(cpu)->nr_running <= 1)
> >> +	if (cpu_rq(cpu)->nr_running <= 1)
> >>   		return true;
> >>   
> >>   	return false;
> >
> > It's a little different. This may bring extra IPIs when nr_running == 1 
> > and the current task on wakee cpu is not the target wakeup task (i.e., 
> > rq->curr == another_task && rq->curr != p). Then this another_task may 
> > be disturbed by IPI which is not expected. So IMO the promise by 
> > WF_ON_CPU is necessary.
> 
> You're right, actually taking a second look at that WF_ON_CPU path,
> shouldn't the existing condition be:
> 
> 	if ((wake_flags & WF_ON_CPU) && !cpu_rq(cpu)->nr_running)
> 
> ? Per the p->on_rq and p->on_cpu ordering, if we have WF_ON_CPU here then
> we must have !p->on_rq, so the deactivate has happened, thus the task
> being alone on the rq implies nr_running==0.
> 
> @Mel, do you remember why you went for <=1 here? I couldn't find any clues
> on the original posting.
> 

I don't recall exactly why I went with <= 1 there but I may not have
considered the memory ordering of on_rq and nr_running and the comment
above it is literally what I was thinking at the time. I think you're
right and that check can be !cpu_rq(cpu)->nr_running.

-- 
Mel Gorman
SUSE Labs