Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933355AbdGCORd (ORCPT ); Mon, 3 Jul 2017 10:17:33 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:36922 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933057AbdGCNpj (ORCPT ); Mon, 3 Jul 2017 09:45:39 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Matt Fleming , "Peter Zijlstra (Intel)" , Frederic Weisbecker , Linus Torvalds , Mike Galbraith , Mike Galbraith , Morten Rasmussen , Thomas Gleixner , Vincent Guittot , Ingo Molnar Subject: [PATCH 4.9 142/172] sched/loadavg: Avoid loadavg spikes caused by delayed NO_HZ accounting Date: Mon, 3 Jul 2017 15:35:22 +0200 Message-Id: <20170703133420.980724143@linuxfoundation.org> X-Mailer: git-send-email 2.13.2 In-Reply-To: <20170703133414.260777365@linuxfoundation.org> References: <20170703133414.260777365@linuxfoundation.org> User-Agent: quilt/0.65 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3041 Lines: 84 4.9-stable review patch. If anyone has any objections, please let me know. ------------------ From: Matt Fleming commit 6e5f32f7a43f45ee55c401c0b9585eb01f9629a8 upstream. 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 Signed-off-by: Greg Kroah-Hartman --- kernel/sched/loadavg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -201,8 +201,9 @@ 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; @@ -211,7 +212,6 @@ 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; }