linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Phil Auld <pauld@redhat.com>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
	Waiman Long <longman@redhat.com>, Ingo Molnar <mingo@kernel.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	stable@vger.kernel.org
Subject: Re: [PATCH] sched: Fix nr_uninterruptible race causing increasing load average
Date: Fri, 9 Jul 2021 13:38:20 +0200	[thread overview]
Message-ID: <YOg1LHSDknjobJfR@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <YOb82exzMcrOxfHa@lorien.usersys.redhat.com>

On Thu, Jul 08, 2021 at 09:25:45AM -0400, Phil Auld wrote:
> Hi Peter,
> 
> On Thu, Jul 08, 2021 at 09:26:26AM +0200 Peter Zijlstra wrote:
> > On Wed, Jul 07, 2021 at 03:04:57PM -0400, Phil Auld wrote:
> > > On systems with weaker memory ordering (e.g. power) commit dbfb089d360b
> > > ("sched: Fix loadavg accounting race") causes increasing values of load
> > > average (via rq->calc_load_active and calc_load_tasks) due to the wakeup
> > > CPU not always seeing the write to task->sched_contributes_to_load in
> > > __schedule(). Missing that we fail to decrement nr_uninterruptible when
> > > waking up a task which incremented nr_uninterruptible when it slept.
> > > 
> > > The rq->lock serialization is insufficient across different rq->locks.
> > > 
> > > Add smp_wmb() to schedule and smp_rmb() before the read in
> > > ttwu_do_activate().
> > 
> > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > > index 4ca80df205ce..ced7074716eb 100644
> > > --- a/kernel/sched/core.c
> > > +++ b/kernel/sched/core.c
> > > @@ -2992,6 +2992,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
> > >  
> > >  	lockdep_assert_held(&rq->lock);
> > >  
> > > +	/* Pairs with smp_wmb in __schedule() */
> > > +	smp_rmb();
> > >  	if (p->sched_contributes_to_load)
> > >  		rq->nr_uninterruptible--;
> > >  
> > 
> > Is this really needed ?! (this question is a big fat clue the comment is
> > insufficient). AFAICT try_to_wake_up() has a LOAD-ACQUIRE on p->on_rq
> > and hence the p->sched_contributed_to_load must already happen after.
> >
> 
> Yes, it is needed.  We've got idle power systems with load average of 530.21.
> Calc_load_tasks is 530, and the sum of both nr_uninterruptible and
> calc_load_active across all the runqueues is 530. Basically monotonically
> non-decreasing load average. With the patch this no longer happens.

Have you tried without the rmb here? Do you really need both barriers?

  reply	other threads:[~2021-07-09 11:38 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-07 19:04 [PATCH] sched: Fix nr_uninterruptible race causing increasing load average Phil Auld
2021-07-08  7:26 ` Peter Zijlstra
2021-07-08  7:48   ` Peter Zijlstra
2021-07-08  7:54     ` Peter Zijlstra
2021-07-08 14:54       ` Phil Auld
2021-07-09 12:57         ` Peter Zijlstra
2021-07-11 13:19           ` Phil Auld
2021-07-08 13:25   ` Phil Auld
2021-07-09 11:38     ` Peter Zijlstra [this message]
2021-07-11 12:57       ` Phil Auld
2021-07-23 13:38       ` Phil Auld
2021-07-28 15:45         ` Phil Auld

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=YOg1LHSDknjobJfR@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=longman@redhat.com \
    --cc=mingo@kernel.org \
    --cc=pauld@redhat.com \
    --cc=stable@vger.kernel.org \
    --cc=vincent.guittot@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).