Content-Type: multipart/mixed; boundary="===============8926560277064794810==" MIME-Version: 1.0 From: Yin Fengwei To: lkp@lists.01.org Subject: Re: [fs] a0918006f9: netperf.Throughput_tps -11.6% regression Date: Thu, 11 Nov 2021 11:29:59 +0800 Message-ID: <00da8188-8b8f-d1c0-ad8c-dfd79e52f289@intel.com> In-Reply-To: <95966337-b36e-f45e-6b16-f433bcb90c4d@digikod.net> List-Id: --===============8926560277064794810== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable On 11/10/2021 4:52 PM, Micka=C3=ABl Sala=C3=BCn wrote: >>> ---------------- --------------------------- >>> %stddev %change %stddev >>> \ | \ >>> 555600 -0.1% 555305 netperf.Throughput_total_= tps >>> 34725 -0.1% 34706 netperf.Throughput_tps >>> >>> >>> Fengwei also helped review these results and commented: >>> I suppose these three CPUs have different cache policy. It also could be >>> related with netperf throughput testing. >> Does moving the syscall implementation somewhere else change things? >> That's a _huge_ performance change for something that isn't even called. >> What's going on here? > This regression doesn't make sense. I guess this is the result of a > flaky netperf test, maybe because the test machine was overloaded at > that time. I agree the test result looks strange. But I don't think the test machine or test methodology has issue. It's not possible the test box is overloaded when test case is running. We did test several times (> 12 times) on differ= ent days. Thanks. Regards Yin, Fengwei --===============8926560277064794810==--