From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933666Ab3E1IuP (ORCPT ); Tue, 28 May 2013 04:50:15 -0400 Received: from moutng.kundenserver.de ([212.227.126.186]:62101 "EHLO moutng.kundenserver.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933623Ab3E1IuN (ORCPT ); Tue, 28 May 2013 04:50:13 -0400 Message-ID: <1369730970.5857.132.camel@marge.simpson.net> Subject: Re: [PATCH v2] sched: wake-affine throttle From: Mike Galbraith To: Michael Wang Cc: Peter Zijlstra , LKML , Ingo Molnar , Alex Shi , Namhyung Kim , Paul Turner , Andrew Morton , "Nikunj A. Dadhania" , Ram Pai Date: Tue, 28 May 2013 10:49:30 +0200 In-Reply-To: <51A45B23.4050403@linux.vnet.ibm.com> References: <5164DCE7.8080906@linux.vnet.ibm.com> <519AE7F2.706@linux.vnet.ibm.com> <20130522084947.GQ26912@twins.programming.kicks-ass.net> <519C8F24.5060207@linux.vnet.ibm.com> <1369234551.5916.40.camel@marge.simpson.net> <51A43A63.4090703@linux.vnet.ibm.com> <1369722552.5857.72.camel@marge.simpson.net> <51A45B23.4050403@linux.vnet.ibm.com> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.3 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 X-Provags-ID: V02:K0:/Oye76xcYKHSZgbYSC6/jxoig412+T+7p1Y20EEOD6b c/38riB/27jXsmsc1YKEJL6Pr5OBYlw97Hpha+qL689QXw3lKS VFSHAiy1fHAheYMqNKseMpx7GsnA9YdQBoOoZLuZ8GKQov+Wm2 Wj9xR3Ic9gOIlMQ1/nOTLqchKcSii2mIMuxIsGZ0S6KwdOy9Mt aFhoSPcHm7n03X5P81UKftLG9dDmZXWPbo/7r35N5Pb/chHsVt tLoHi0k9qiapb9RYNKoGNNfsYZyMXO1/g9HZ2vlCatgCTGay9O OgMU9pWjj97swCEaeIJVX7i2H34KDWi/tzJx7+jZBIpJLI80Cl Et4x4gjj5rQY7LfMpXkLsyxNRVqJI1GSUp4xu4xHGkotraMATC jfYFscdclMxBA== Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, 2013-05-28 at 15:22 +0800, Michael Wang wrote: > On 05/28/2013 02:29 PM, Mike Galbraith wrote: > > On Tue, 2013-05-28 at 13:02 +0800, Michael Wang wrote: > >> On 05/22/2013 10:55 PM, Mike Galbraith wrote: > >>> On Wed, 2013-05-22 at 17:25 +0800, Michael Wang wrote: > >>> > >>>> I've not test the hackbench with wakeup-buddy before, will do it this > >>>> time, I suppose the 15% illegal income will suffered, anyway, it's > >>>> illegal :) > >>> > >>> On a 4 socket 40 core (+SMT) box, hackbench wasn't too happy. > >> > >> I've done more test and now I got the reason of regression... > >> > >> The writer and reader in hackbench is N:N, prev writer will write all > >> the fd then switch to next writer and repeat the same work, so it's > >> impossible to setup the buddy relationship by just record the last one, > >> and we have to record all the waker/wakee in history, but that means > >> unacceptable memory overhead... > > > > Yeah, that's why I was thinking we'd need a dinky/fast as hell FIFO of > > tokens or such to bind waker/wakee more or less reliably. Making such a > > scheme cheap enough could be hard. > > > >> So this buddy idea seems to be bad... > >> > >> I think a better way may should be allowing pull in most time, but > >> filter the very bad cases carefully. > > > > Any way that is cheap, and fairly accurately recognizes when we're being > > stupid will help. First and foremost, it has to be dirt cheap :) > > > >> For workload like pgbench, we actually just need to avoid pull if that > >> will damage the 'mother' thread, which is busy and be relied by many > >> 'child'. > > > > Yeah, 'mom' is the key player. If we can cheaply recognize mom, that > > should get us a generic improvement. Not as good as being able to > > recognize the size of her+brood as size changes, but better anyway. > > That's right, I'm trying to rely on the frequency of a task switching > it's wakee in the new idea, it's really cheap and somewhat reliable, I > appreciate if you could pay an eye on the new patch and let me know you > opinion :) I'll feed it to my 40 core box, hopefully soon. -Mike