Commit 50a2a3b2 authored Aug 20, 2015 by Byungchul Park Committed by Ingo Molnar Sep 13, 2015

sched/fair: Have task_move_group_fair() unconditionally add the entity load to the runqueue



Currently we conditionally add the entity load to the rq when moving
the task between cgroups.

This doesn't make sense as we always 'migrate' the task between
cgroups, so we should always migrate the load too.

[ The history here is that we used to only migrate the blocked load
  which was only meaningfull when !queued. ]

Signed-off-by: Byungchul Park <byungchul.park@lge.com>
[ Rewrote the changelog. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: yuyang.du@intel.com
Link: http://lkml.kernel.org/r/1440069720-27038-3-git-send-email-byungchul.park@lge.com


Signed-off-by: Ingo Molnar <mingo@kernel.org>

parent a05e8c51

kernel/sched/fair.c

+4 −5

Original line number	Original line	Diff line number	Diff line
	@@ -8041,14 +8041,13 @@ static void task_move_group_fair(struct task_struct *p, int queued)
	se->vruntime -= cfs_rq_of(se)->min_vruntime;		se->vruntime -= cfs_rq_of(se)->min_vruntime;
	set_task_rq(p, task_cpu(p));		set_task_rq(p, task_cpu(p));
	se->depth = se->parent ? se->parent->depth + 1 : 0;		se->depth = se->parent ? se->parent->depth + 1 : 0;
	if (!queued) {
	cfs_rq = cfs_rq_of(se);		cfs_rq = cfs_rq_of(se);
			if (!queued)
	se->vruntime += cfs_rq->min_vruntime;		se->vruntime += cfs_rq->min_vruntime;

	/* Virtually synchronize task with its new cfs_rq */		/* Virtually synchronize task with its new cfs_rq */
	attach_entity_load_avg(cfs_rq, se);		attach_entity_load_avg(cfs_rq, se);
	}		}
	}

	void free_fair_sched_group(struct task_group *tg)		void free_fair_sched_group(struct task_group *tg)
	{		{