From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751226Ab1AWLTi (ORCPT ); Sun, 23 Jan 2011 06:19:38 -0500 Received: from trent.utfs.org ([194.246.123.103]:47697 "EHLO trent.utfs.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750956Ab1AWLTh (ORCPT ); Sun, 23 Jan 2011 06:19:37 -0500 Date: Sun, 23 Jan 2011 03:19:34 -0800 (PST) From: Christian Kujau To: efault@gmx.de, Michael Witten cc: LKML Subject: Re: 'autogroup' sched code KILLING responsiveness In-Reply-To: Message-ID: References: <4d39ce58.cc7e0e0a.5448.59e4@mx.google.com> User-Agent: Alpine 2.01 (DEB 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII X-AV-Checked: ClamAV using ClamSMTP (127.0.0.1) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sun, 23 Jan 2011 at 02:50, Christian Kujau wrote: > On Fri, 21 Jan 2011 at 10:20, Michael Witten wrote: > > With that code in place, a resource-intensive activity (such as > > compiling the Linux kernel) causes my computer to become > > unresponsive for many seconds at a time; the entire screen > > does not refresh, typed keys are dropped or are handled very > > late, etc (even in Linux's plain virtual consoles). > > Unfortunately, I'd like to add a "me too". 2.6.38-rc1 behaves fine, but > with CONFIG_SCHED_AUTOGROUP=y and doing I/O and CPU intensive work (git > prune/git repack on a Linux git tree), system load goes up to ~13 and > becomes unresponse for some time too. This even happens when I start the > jobs with nice -n10. "unresponsive for some time" turned out to be "system unusable, unless rebooted". When I started the "git repack" with the autogroup feature turned on, load would go to 4 very quickly (as compared to 1 or 2 w/o autogroup), after a while (seconds, minutes) it would go to 10 or 14 and I cannot use the system any more, after a while it goes back to 4 but then it goes up again, the last load number I see is 11.56 and now the system is stuck or so busy that I cannot login any more, not even locally. This happened before with 2.6.38-rc1 & CONFIG_SCHED_AUTOGROUP=y, so it's quite reproducible for me. Christian. > > Without CONFIG_SCHED_AUTOGROUP enabled and doing the same work, > systemload goes up to 1 or maybe 2. > > I'm on UP as well (PowerPC G4), disabling CONFIG_SCHED_AUTOGROUP helps > here too. > > Thanks, > Christian. -- BOFH excuse #356: the daemons! the daemons! the terrible daemons!