From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752131AbdCPLOh (ORCPT ); Thu, 16 Mar 2017 07:14:37 -0400 Received: from terminus.zytor.com ([65.50.211.136]:43750 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751475AbdCPLOH (ORCPT ); Thu, 16 Mar 2017 07:14:07 -0400 Date: Thu, 16 Mar 2017 04:13:20 -0700 From: tip-bot for Matt Fleming Message-ID: Cc: umgwanakikbuti@gmail.com, morten.rasmussen@arm.com, hpa@zytor.com, peterz@infradead.org, vincent.guittot@linaro.org, tglx@linutronix.de, matt@codeblueprint.co.uk, linux-kernel@vger.kernel.org, fweisbec@gmail.com, mingo@kernel.org, efault@gmx.de, torvalds@linux-foundation.org Reply-To: umgwanakikbuti@gmail.com, hpa@zytor.com, morten.rasmussen@arm.com, vincent.guittot@linaro.org, peterz@infradead.org, tglx@linutronix.de, mingo@kernel.org, matt@codeblueprint.co.uk, fweisbec@gmail.com, linux-kernel@vger.kernel.org, efault@gmx.de, torvalds@linux-foundation.org In-Reply-To: <20170217120731.11868-2-matt@codeblueprint.co.uk> References: <20170217120731.11868-2-matt@codeblueprint.co.uk> To: linux-tip-commits@vger.kernel.org Subject: [tip:sched/core] sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting Git-Commit-ID: 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 X-Mailer: tip-git-log-daemon Robot-ID: Robot-Unsubscribe: Contact to get blacklisted from these emails MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Content-Type: text/plain; charset=UTF-8 Content-Disposition: inline Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Commit-ID: 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 Gitweb: http://git.kernel.org/tip/6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 Author: Matt Fleming AuthorDate: Fri, 17 Feb 2017 12:07:30 +0000 Committer: Ingo Molnar CommitDate: Thu, 16 Mar 2017 09:21:00 +0100 sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting If we crossed a sample window while in NO_HZ we will add LOAD_FREQ to the pending sample window time on exit, setting the next update not one window into the future, but two. This situation on exiting NO_HZ is described by: this_rq->calc_load_update < jiffies < calc_load_update In this scenario, what we should be doing is: this_rq->calc_load_update = calc_load_update [ next window ] But what we actually do is: this_rq->calc_load_update = calc_load_update + LOAD_FREQ [ next+1 window ] This has the effect of delaying load average updates for potentially up to ~9seconds. This can result in huge spikes in the load average values due to per-cpu uninterruptible task counts being out of sync when accumulated across all CPUs. It's safe to update the per-cpu active count if we wake between sample windows because any load that we left in 'calc_load_idle' will have been zero'd when the idle load was folded in calc_global_load(). This issue is easy to reproduce before, commit 9d89c257dfb9 ("sched/fair: Rewrite runnable load and utilization average tracking") just by forking short-lived process pipelines built from ps(1) and grep(1) in a loop. I'm unable to reproduce the spikes after that commit, but the bug still seems to be present from code review. Signed-off-by: Matt Fleming Signed-off-by: Peter Zijlstra (Intel) Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Mike Galbraith Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: Vincent Guittot Fixes: commit 5167e8d ("sched/nohz: Rewrite and fix load-avg computation -- again") Link: http://lkml.kernel.org/r/20170217120731.11868-2-matt@codeblueprint.co.uk Signed-off-by: Ingo Molnar --- kernel/sched/loadavg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index 7296b73..3a55f3f 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -202,8 +202,9 @@ void calc_load_exit_idle(void) struct rq *this_rq = this_rq(); /* - * If we're still before the sample window, we're done. + * If we're still before the pending sample window, we're done. */ + this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -212,7 +213,6 @@ void calc_load_exit_idle(void) * accounted through the nohz accounting, so skip the entire deal and * sync up for the next window. */ - this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update + 10)) this_rq->calc_load_update += LOAD_FREQ; }