Commit 4c77b18c authored Mar 01, 2017 by Peter Zijlstra Committed by Ingo Molnar Mar 02, 2017

sched/fair: Make select_idle_cpu() more aggressive



Kitsunyan reported desktop latency issues on his Celeron 887 because
of commit:

  1b568f0a ("sched/core: Optimize SCHED_SMT")

... even though his CPU doesn't do SMT.

The effect of running the SMT code on a !SMT part is basically a more
aggressive select_idle_cpu(). Removing the avg condition fixed things
for him.

I also know FB likes this test gone, even though other workloads like
having it.

For now, take it out by default, until we get a better idea.

Reported-by: kitsunyan <kitsunyan@inbox.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Chris Mason <clm@fb.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

parent 4977ab6e

kernel/sched/fair.c

+1 −1

Original line number	Diff line number	Diff line
		@@ -5797,7 +5797,7 @@ static int select_idle_cpu(struct task_struct p, struct sched_domain sd, int t
		* Due to large variance we need a large fuzz factor; hackbench in
		* particularly is sensitive here.
		*/
		if ((avg_idle / 512) < avg_cost)
		if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
		return -1;

		time = local_clock();

kernel/sched/features.h

+5 −0

Original line number	Diff line number	Diff line
		@@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
		*/
		SCHED_FEAT(TTWU_QUEUE, true)

		/*
		* When doing wakeups, attempt to limit superfluous scans of the LLC domain.
		*/
		SCHED_FEAT(SIS_AVG_CPU, false)

		#ifdef HAVE_RT_PUSH_IPI
		/*
		* In order to avoid a thundering herd attack of CPUs that are

Admin message