From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mga14.intel.com ([192.55.52.115]:24862 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S2387938AbeGMCHb (ORCPT ); Thu, 12 Jul 2018 22:07:31 -0400 From: "Huang\, Ying" To: Chris Mason Cc: Josef Bacik , David Sterba , , Subject: Re: [LKP] [lkp-robot] [mm] 9092c71bb7: blogbench.write_score -12.3% regression References: <20180408015739.GN3845@yexl-desktop> <876036apgx.fsf@yhuang-dev.intel.com> <878t7t3k3s.fsf@yhuang-dev.intel.com> <87h8m6m9ld.fsf@yhuang-dev.intel.com> <878t7ai08v.fsf@yhuang-dev.intel.com> Date: Fri, 13 Jul 2018 09:55:11 +0800 In-Reply-To: (Chris Mason's message of "Wed, 20 Jun 2018 08:38:45 -0400") Message-ID: <87zhyvew74.fsf@yhuang-dev.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=ascii Sender: linux-btrfs-owner@vger.kernel.org List-ID: Hi, Chris, Chris Mason writes: > On 19 Jun 2018, at 23:51, Huang, Ying wrote: >>>> "Huang, Ying" writes: >>>> >>>>> Hi, Josef, >>>>> >>>>> Do you have time to take a look at the regression? >>>>> >>>>> kernel test robot writes: >>>>> >>>>>> Greeting, >>>>>> >>>>>> FYI, we noticed a -12.3% regression of blogbench.write_score and >>>>>> a +9.6% improvement >>>>>> of blogbench.read_score due to commit: >>>>>> >>>>>> >>>>>> commit: 9092c71bb724dba2ecba849eae69e5c9d39bd3d2 ("mm: use >>>>>> sc->priority for slab shrink targets") >>>>>> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git >>>>>> master >>>>>> >>>>>> in testcase: blogbench >>>>>> on test machine: 16 threads Intel(R) Xeon(R) CPU D-1541 @ >>>>>> 2.10GHz with 8G memory >>>>>> with following parameters: >>>>>> >>>>>> disk: 1SSD >>>>>> fs: btrfs >>>>>> cpufreq_governor: performance >>>>>> >>>>>> test-description: Blogbench is a portable filesystem benchmark >>>>>> that tries to reproduce the load of a real-world busy file >>>>>> server. >>>>>> test-url: > > I'm surprised, this patch is a big win in production here at FB. I'll > have to reproduce these results to better understand what is going on. > My first guess is that since we have fewer inodes in slab, we're > reading more inodes from disk in order to do the writes. > > But that should also make our read scores lower. Any update on this? Best Regards, Huang, Ying From mboxrd@z Thu Jan 1 00:00:00 1970 Content-Type: multipart/mixed; boundary="===============8844143904912476573==" MIME-Version: 1.0 From: Huang, Ying To: lkp@lists.01.org Subject: Re: [lkp-robot] [mm] 9092c71bb7: blogbench.write_score -12.3% regression Date: Fri, 13 Jul 2018 09:55:11 +0800 Message-ID: <87zhyvew74.fsf@yhuang-dev.intel.com> In-Reply-To: List-Id: --===============8844143904912476573== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Hi, Chris, Chris Mason writes: > On 19 Jun 2018, at 23:51, Huang, Ying wrote: >>>> "Huang, Ying" writes: >>>> >>>>> Hi, Josef, >>>>> >>>>> Do you have time to take a look at the regression? >>>>> >>>>> kernel test robot writes: >>>>> >>>>>> Greeting, >>>>>> >>>>>> FYI, we noticed a -12.3% regression of blogbench.write_score and >>>>>> a +9.6% improvement >>>>>> of blogbench.read_score due to commit: >>>>>> >>>>>> >>>>>> commit: 9092c71bb724dba2ecba849eae69e5c9d39bd3d2 ("mm: use >>>>>> sc->priority for slab shrink targets") >>>>>> https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git >>>>>> master >>>>>> >>>>>> in testcase: blogbench >>>>>> on test machine: 16 threads Intel(R) Xeon(R) CPU D-1541 @ >>>>>> 2.10GHz with 8G memory >>>>>> with following parameters: >>>>>> >>>>>> disk: 1SSD >>>>>> fs: btrfs >>>>>> cpufreq_governor: performance >>>>>> >>>>>> test-description: Blogbench is a portable filesystem benchmark >>>>>> that tries to reproduce the load of a real-world busy file >>>>>> server. >>>>>> test-url: > > I'm surprised, this patch is a big win in production here at FB. I'll > have to reproduce these results to better understand what is going on. > My first guess is that since we have fewer inodes in slab, we're > reading more inodes from disk in order to do the writes. > > But that should also make our read scores lower. Any update on this? Best Regards, Huang, Ying --===============8844143904912476573==--