From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756862AbcJGUhc (ORCPT ); Fri, 7 Oct 2016 16:37:32 -0400 Received: from mail-oi0-f66.google.com ([209.85.218.66]:33782 "EHLO mail-oi0-f66.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753254AbcJGUhY (ORCPT ); Fri, 7 Oct 2016 16:37:24 -0400 MIME-Version: 1.0 In-Reply-To: <57F80400.9040503@canonical.com> References: <57F7F9AF.2010609@canonical.com> <57F80400.9040503@canonical.com> From: Linus Torvalds Date: Fri, 7 Oct 2016 13:37:15 -0700 X-Google-Sender-Auth: 7TotMiH_I8U96peWEhX5988--R4 Message-ID: Subject: Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes To: Joseph Salisbury Cc: Peter Zijlstra , Mike Galbraith , Thomas Gleixner , LKML , Ingo Molnar Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Oct 7, 2016 at 1:22 PM, Joseph Salisbury wrote: > > Yes, CONFIG_SCHED_AUTOGROUP is enabled in the Ubuntu kernel. However, > that config was also enable in the Ubuntu 4.4 kerrnels without seeing > this issue. I can try disabling the config in the 4.8 based kernel and > see if that changes things. No, that wouldn't make any sense. I just wanted to know that the option was enabled, because that option really *should* help buffer other processes from one session that is a CPU hog. So something is seriously wrong in that situation if other things get very choppy. Of course, the fact that it apparently happens on one particular machine only means that it's hard to figure out what triggers it. Maybe some unlucky combination of cpufreq and thermal throttling by the hardware, coupled with the scheduler change. Peter? Linus