Content-Type: multipart/mixed; boundary="===============4638935876354386936==" MIME-Version: 1.0 From: Gu Zheng To: lkp@lists.01.org Subject: Re: [aio] 6098b45b32e: 2200.00% xfstests.generic.239.seconds Date: Mon, 15 Dec 2014 10:58:43 +0800 Message-ID: <548E4E63.70302@cn.fujitsu.com> In-Reply-To: <1418605329.5745.141.camel@linux.intel.com> List-Id: --===============4638935876354386936== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Hi Huang, On 12/15/2014 09:02 AM, Huang Ying wrote: > FYI, we noticed the below changes on > = > commit 6098b45b32e6baeacc04790773ced9340601d511 ("aio: block exit_aio() u= ntil all context requests are completed") This patch added a wait step (which is lacked before) for all submitted aio missions (iocbs) to complete in exit_aio(), so the cost-time increasing is expected. Thanks, Gu > = > = > testbox/testcase/testparams: vm-vp-2G/xfstests/4HDD-btrfs-generic-quick > = > 2ff396be602f10b5 6098b45b32e6baeacc04790773 = > ---------------- -------------------------- = > %stddev %change %stddev > \ | \ = > 26352 =C2=B1 9% -13.6% 22774 =C2=B1 1% vmstat.system.cs > 10342 =C2=B1 6% -12.3% 9066 =C2=B1 0% vmstat.system.in > 37 =C2=B1 4% -12.1% 32 =C2=B1 3% time.percent_of_c= pu_this_job_got > 1197 =C2=B1 2% -14.2% 1028 =C2=B1 0% vmstat.io.bi > 18470 =C2=B1 2% -10.1% 16609 =C2=B1 1% vmstat.io.bo > 157 =C2=B1 3% +13.7% 179 =C2=B1 0% time.elapsed_time > = > vm-vp-2G: qemu-system-x86_64 -enable-kvm -cpu Penryn > Memory: 2G > = > xfstests.generic.239.seconds > = > 30 ++-----------O------------------------------------------------------= ---+ > | O O O O = | > 25 ++ O = | > | O O O O O O O O O O O O = | > | O = | > 20 O+ = | > | = | > 15 ++ = | > | = | > 10 ++ = | > | = | > | = | > 5 ++ = | > | = | > 0 *+-*-*--*-*--*-*--*-*--*-*--*-*--*--*-*--*-*--*-*--*-*--*-*--*-*--*-= *--* > = > = > [*] bisect-good sample > [O] bisect-bad sample > = > To reproduce: > = > apt-get install ruby ruby-oj > git clone git://git.kernel.org/pub/scm/linux/kernel/git/wfg/lkp-tests.git > cd lkp-tests > bin/setup-local job.yaml # the job file attached in this email > bin/run-local job.yaml > = > = > Disclaimer: > Results have been estimated based on internal Intel analysis and are prov= ided > for informational purposes only. Any difference in system hardware or sof= tware > design or configuration may affect actual performance. > = > = > Thanks, > Fengguang > = > = > = > = > _______________________________________________ > LKP mailing list > LKP(a)linux.intel.com > = --===============4638935876354386936==--