Re: [PATCH 2/2] sched/fair: Simple runqueue order on migrate

From: Tim Chen <tim.c.chen@linux.intel.com>
To: Abel Wu <wuyun.abel@bytedance.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Ingo Molnar <mingo@elte.hu>, Juri Lelli <juri.lelli@redhat.com>
Cc: Yu Chen <yu.c.chen@intel.com>,
	Walter Mack <walter.mack@intel.com>, Mel Gorman <mgorman@suse.de>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 2/2] sched/fair: Simple runqueue order on migrate
Date: Tue, 29 Mar 2022 07:26:05 -0700	[thread overview]
Message-ID: <ebc9718f41b9294fe46129cafe3edffdbcc024e3.camel@linux.intel.com> (raw)
In-Reply-To: <3a24ba8c-b00d-2f9b-95c9-b8aba1b51493@bytedance.com>

On Tue, 2022-03-29 at 18:09 +0800, Abel Wu wrote:
> > 
> 
> >   
> > +static void place_entity_migrate(struct cfs_rq *cfs_rq, struct sched_entity *se)
> > +{
> > +	if (!sched_feat(PLACE_MIGRATE))
> > +		return;
> > +
> > +	if (cfs_rq->nr_running < se->migrated) {
> > +		/*
> > +		 * Migrated to a shorter runqueue, go first because
> > +		 * we were under-served on the old runqueue.
> > +		 */
> > +		se->vruntime = cfs_rq->min_vruntime;
> > +		return;
> > +	}
> > +
> > +	/*
> > +	 * Migrated to a longer runqueue, go last because
> > +	 * we got over-served on the old runqueue.
> > +	 */
> > +	se->vruntime = cfs_rq->min_vruntime + sched_vslice(cfs_rq, se);
> > +}
> 
> Should se->migrated be cleared after place_entity_migrate?
> 

It is cleared in update_stats_curr_start() before we actually run the task.
If the task gets migrated again before we run it, the se->migrated will also
be updated in migrate_task_rq_fair().  Looks like there is no need to
clear it here.

Tim