From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754866Ab1AUW1z (ORCPT ); Fri, 21 Jan 2011 17:27:55 -0500 Received: from mailout-de.gmx.net ([213.165.64.22]:45817 "HELO mailout-de.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with SMTP id S1754839Ab1AUW1y (ORCPT ); Fri, 21 Jan 2011 17:27:54 -0500 X-Authenticated: #14349625 X-Provags-ID: V01U2FsdGVkX1+ClfNusryCedSVDwFo7lKUZ0+eh3huWkz2nrdHNs DDGBk3uT0dbXef Subject: Re: 'autogroup' sched code KILLING responsiveness From: Mike Galbraith To: Michael Witten Cc: linux-kernel@vger.kernel.org In-Reply-To: <4d39ce58.cc7e0e0a.5448.59e4@mx.google.com> References: <4d39ce58.cc7e0e0a.5448.59e4@mx.google.com> Content-Type: text/plain; charset="UTF-8" Date: Fri, 21 Jan 2011 23:27:50 +0100 Message-ID: <1295648870.23779.15.camel@marge.simson.net> Mime-Version: 1.0 X-Mailer: Evolution 2.30.1.2 Content-Transfer-Encoding: 7bit X-Y-GMX-Trusted: 0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 2011-01-21 at 10:20 -0800, Michael Witten wrote: > Bisecting shows that this commit: > > 5091faa449ee0b7d73bc296a93bca9540fc51d0a > sched: Add 'autogroup' scheduling feature: automated per session task groups > Date: Tue Nov 30 14:18:03 2010 +0100 > > is the reason that my computer has become unusable. > > 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). That's not what I'm experiencing with a UP kernel... marge:~> time perf stat -a sh -c 'true' Performance counter stats for 'sh -c true': 49580 cache-misses # 5.170 M/sec (scaled from 37.28%) 336112 cache-references # 35.048 M/sec (scaled from 78.81%) 185857 branch-misses # 21.019 % (scaled from 62.83%) 884249 branches # 92.204 M/sec (scaled from 21.25%) 12672552 instructions # 0.553 IPC (scaled from 58.38%) 22896301 cycles # 2387.490 M/sec (scaled from 58.38%) 410 page-faults # 0.043 M/sec 0 CPU-migrations # 0.000 M/sec 13 context-switches # 0.001 M/sec 9.590115 task-clock-msecs # 1.005 CPUs 0.009540836 seconds time elapsed real 0m0.020s user 0m0.000s sys 0m0.000s marge:~> It took 20 ms to do the above and get it to my screen while the below was running (among others). I've got a make -j 100 running as I write this, and don't even notice that it's running. Can you provide some information such as hardware description, configuration, and perhaps measurements demonstrating the problem? top - 22:34:38 up 33 min, 22 users, load average: 104.07, 101.73, 78.13 Tasks: 675 total, 101 running, 574 sleeping, 0 stopped, 0 zombie Cpu(s): 95.2%us, 4.8%sy, 0.0%ni, 0.0%id, 0.0%wa, 0.0%hi, 0.0%si, 0.0%st PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ P COMMAND 6770 root 20 0 401m 79m 29m R 46.9 1.0 3:22.66 0 mplayer 6100 root 20 0 449m 94m 18m S 2.9 1.2 1:33.82 0 Xorg 7486 root 20 0 374m 46m 17m S 2.9 0.6 0:54.02 0 konsole 7752 root 20 0 104m 66m 8072 R 1.0 0.8 0:01.76 0 cc1 9796 root 20 0 89764 49m 8028 R 1.0 0.6 0:01.21 0 cc1 9928 root 20 0 98916 59m 8164 R 1.0 0.7 0:01.18 0 cc1 10321 root 20 0 88788 49m 8116 R 1.0 0.6 0:01.06 0 cc1 10619 root 20 0 89736 50m 8068 R 1.0 0.6 0:01.00 0 cc1 11356 root 20 0 19764 8152 2300 S 1.0 0.1 0:00.01 0 as 11597 root 20 0 97212 56m 7924 R 1.0 0.7 0:00.65 0 cc1 12203 root 20 0 79332 40m 7588 R 1.0 0.5 0:00.48 0 cc1 12209 root 20 0 80760 40m 7536 R 1.0 0.5 0:00.47 0 cc1 12247 root 20 0 85252 46m 7752 R 1.0 0.6 0:00.46 0 cc1 12510 root 20 0 82192 40m 5184 R 1.0 0.5 0:00.36 0 cc1 12612 root 20 0 81172 39m 5192 R 1.0 0.5 0:00.33 0 cc1 12615 root 20 0 81160 38m 4360 R 1.0 0.5 0:00.33 0 cc1