From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1161141AbcFAIxg (ORCPT ); Wed, 1 Jun 2016 04:53:36 -0400 Received: from mga11.intel.com ([192.55.52.93]:30787 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964797AbcFAIxc (ORCPT ); Wed, 1 Jun 2016 04:53:32 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.26,400,1459839600"; d="scan'208";a="819151027" From: "Huang\, Ying" To: Peter Zijlstra Cc: "Huang\, Ying" , Ingo Molnar , , Mike Galbraith , , Thomas Gleixner , Linus Torvalds Subject: Re: [LKP] [lkp] [sched/fair] 53d3bc773e: hackbench.throughput -32.9% regression References: <87inxud4ex.fsf@yhuang-dev.intel.com> <87eg8id3s3.fsf@yhuang-dev.intel.com> <20160531124151.GK3190@twins.programming.kicks-ass.net> <87eg8h8pwl.fsf@yhuang-dev.intel.com> <20160601084035.GL3190@twins.programming.kicks-ass.net> Date: Wed, 01 Jun 2016 16:53:28 +0800 In-Reply-To: <20160601084035.GL3190@twins.programming.kicks-ass.net> (Peter Zijlstra's message of "Wed, 1 Jun 2016 10:40:35 +0200") Message-ID: <87inxtjnnb.fsf@yhuang-dev.intel.com> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.5 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Peter Zijlstra writes: > On Wed, Jun 01, 2016 at 01:00:10PM +0800, Huang, Ying wrote: >> Hi, Peter, >> >> Peter Zijlstra writes: >> >> > On Tue, May 31, 2016 at 04:34:36PM +0800, Huang, Ying wrote: >> >> Hi, Ingo, >> >> >> >> Part of the regression has been recovered in v4.7-rc1 from -32.9% to >> >> -9.8%. But there is still some regression. Is it possible for fully >> >> restore it? >> > >> > after much searching on how you guys run hackbench... I figured >> > something like: >> > >> > perf bench sched messaging -g 20 --thread -l 60000 >> >> There is a reproduce file attached in the original report email, its >> contents is something like below: >> >> 2016-05-15 08:57:02 echo performance > /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor > > > >> 2016-05-15 09:06:24 /usr/bin/hackbench -g 24 --threads -l 60000 >> >> Hope that will help you for reproduce. > > It did not, because I didn't have the exact same machine and its not > apparent how I should modify -- if at all -- the arguments to be > representative when ran on my machine. > >> > on my IVB-EP (2*10*2) is similar to your IVT thing. >> > >> > And running something like: >> > >> > for i in /sys/devices/system/cpu/cpu*/cpufreq/scaling_governor ; do echo performance > $i ; done >> > perf stat --null --repeat 10 -- perf bench sched messaging -g 20 --thread -l 60000 | grep "seconds time elapsed" >> > >> > gets me: >> > >> > v4.6: >> > >> > 36.786914089 seconds time elapsed ( +- 0.49% ) >> > 37.054017355 seconds time elapsed ( +- 1.05% ) >> > >> > >> > origin/master (v4.7-rc1-ish): >> > >> > 34.757435264 seconds time elapsed ( +- 3.34% ) >> > 35.396252515 seconds time elapsed ( +- 3.38% ) >> > >> > >> > Which doesn't show a regression between v4.6 and HEAD; in fact it shows >> > an improvement. >> >> Yes. For hackbench test, linus/master (v4.7-rc1+) is better than v4.6, >> but it is worse than v4.6-rc7. Details is as below. > > That kernel was broken.. what your point? You mean the commit is a functionality fix? I found the hackbench.throughput for the test is v4.5: 1.4e+5 v4.6-rc1~v4.6-rc7: 1.9e+5 v4.6: 1.3e+5 v4.7-rc1: 1.7e+5 So some commit in v4.6-rc1 introduce some issue but improve the score for the test, which is fixed in v4.6, and some improvement merged by v4.7-rc1? Best Regards, Huang, Ying