Re: [PATCH 19/24] sched/eevdf: Fixup PELT vs DELAYED_DEQUEUE

[Peter Zijlstra <peterz@infradead.org>]

On Wed, Aug 14, 2024 at 09:25:48AM +0200, Peter Zijlstra wrote:
> On Wed, Aug 14, 2024 at 12:18:07AM +0200, Peter Zijlstra wrote:
> > On Tue, Aug 13, 2024 at 02:43:56PM +0200, Valentin Schneider wrote:
> > > On 27/07/24 12:27, Peter Zijlstra wrote:
> > > > Note that tasks that are kept on the runqueue to burn off negative
> > > > lag, are not in fact runnable anymore, they'll get dequeued the moment
> > > > they get picked.
> > > >
> > > > As such, don't count this time towards runnable.
> > > >
> > > > Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> > > > ---
> > > >  kernel/sched/fair.c  |    2 ++
> > > >  kernel/sched/sched.h |    6 ++++++
> > > >  2 files changed, 8 insertions(+)
> > > >
> > > > --- a/kernel/sched/fair.c
> > > > +++ b/kernel/sched/fair.c
> > > > @@ -5388,6 +5388,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, st
> > > >                       if (cfs_rq->next == se)
> > > >                               cfs_rq->next = NULL;
> > > >                       se->sched_delayed = 1;
> > > > +			update_load_avg(cfs_rq, se, 0);
> > > 
> > > Shouldn't this be before setting ->sched_delayed? accumulate_sum() should
> > > see the time delta as spent being runnable.
> > > 
> > > >                       return false;
> > > >               }
> > > >       }
> > > > @@ -6814,6 +6815,7 @@ requeue_delayed_entity(struct sched_enti
> > > >       }
> > > >
> > > >       se->sched_delayed = 0;
> > > > +	update_load_avg(cfs_rq, se, 0);
> > > 
> > > Ditto on the ordering
> > 
> > Bah, so I remember thinking about it and then I obviously go and do it
> > the exact wrong way around eh? Let me double check this tomorrow morning
> > with the brain slightly more awake :/
> 
> OK, so I went over it again and I ended up with the below diff -- which
> assuming I didn't make a giant mess of things *again*, I should go fold
> back into various other patches ...
> 
> ---
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 1b15dbfb1ce5..fa8907f2c716 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -5461,14 +5461,10 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>  {
>  	bool sleep = flags & DEQUEUE_SLEEP;
>  
> +	update_curr(cfs_rq);
> +
>  	if (flags & DEQUEUE_DELAYED) {
> -		/*
> -		 * DEQUEUE_DELAYED is typically called from pick_next_entity()
> -		 * at which point we've already done update_curr() and do not
> -		 * want to do so again.
> -		 */
>  		SCHED_WARN_ON(!se->sched_delayed);
> -		se->sched_delayed = 0;
>  	} else {
>  		bool delay = sleep;
>  		/*

Because repeated update_curr() is harmless (I think I was thinking it
would move the clock, but it doesn't do that), but a missed
update_curr() makes a mess.

> @@ -5479,14 +5475,13 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>  			delay = false;
>  
>  		SCHED_WARN_ON(delay && se->sched_delayed);
> -		update_curr(cfs_rq);
>  
>  		if (sched_feat(DELAY_DEQUEUE) && delay &&
>  		    !entity_eligible(cfs_rq, se)) {
>  			if (cfs_rq->next == se)
>  				cfs_rq->next = NULL;
> -			se->sched_delayed = 1;
>  			update_load_avg(cfs_rq, se, 0);
> +			se->sched_delayed = 1;
>  			return false;
>  		}
>  	}

As you said, update to now, then mark delayed.

> @@ -5536,6 +5531,12 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
>  	if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
>  		update_min_vruntime(cfs_rq);
>  
> +	if (flags & DEQUEUE_DELAYED) {
> +		se->sched_delayed = 0;
> +		if (sched_feat(DELAY_ZERO) && se->vlag > 0)
> +			se->vlag = 0;
> +	}
> +
>  	if (cfs_rq->nr_running == 0)
>  		update_idle_cfs_rq_clock_pelt(cfs_rq);
>  
> @@ -5611,11 +5612,6 @@ pick_next_entity(struct rq *rq, struct cfs_rq *cfs_rq)
>  	struct sched_entity *se = pick_eevdf(cfs_rq);
>  	if (se->sched_delayed) {
>  		dequeue_entities(rq, se, DEQUEUE_SLEEP | DEQUEUE_DELAYED);
> -		SCHED_WARN_ON(se->sched_delayed);
> -		SCHED_WARN_ON(se->on_rq);
> -		if (sched_feat(DELAY_ZERO) && se->vlag > 0)
> -			se->vlag = 0;
> -
>  		return NULL;
>  	}
>  	return se;

Because if we have to clear delayed at the end up dequeue, we might as
well do all of the fixups at that point.

> @@ -6906,7 +6902,7 @@ requeue_delayed_entity(struct sched_entity *se)
>  	struct cfs_rq *cfs_rq = cfs_rq_of(se);
>  
>  	/*
> -	 * se->sched_delayed should imply both: se->on_rq == 1.
> +	 * se->sched_delayed should imply: se->on_rq == 1.
>  	 * Because a delayed entity is one that is still on
>  	 * the runqueue competing until elegibility.
>  	 */

edit fail, somewhere along history.

> @@ -6927,8 +6923,8 @@ requeue_delayed_entity(struct sched_entity *se)
>  		}
>  	}
>  
> -	se->sched_delayed = 0;
>  	update_load_avg(cfs_rq, se, 0);
> +	se->sched_delayed = 0;
>  }

What you said..