From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mout.gmx.net ([212.227.17.21]:49813 "EHLO mout.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1732003AbfAPEr2 (ORCPT ); Tue, 15 Jan 2019 23:47:28 -0500 Subject: Re: Any way to detect performance in a test case? References: <20190116035745.GO4205@dastard> From: Qu Wenruo Message-ID: <643f7899-e010-2694-4af6-960f0fc6e5cc@gmx.com> Date: Wed, 16 Jan 2019 12:47:21 +0800 MIME-Version: 1.0 In-Reply-To: <20190116035745.GO4205@dastard> Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="AfyQeGeXtT51bNcVUWTnBHWaeL9d8u7yf" Sender: fstests-owner@vger.kernel.org To: Dave Chinner Cc: fstests List-ID: This is an OpenPGP/MIME signed message (RFC 4880 and 3156) --AfyQeGeXtT51bNcVUWTnBHWaeL9d8u7yf Content-Type: multipart/mixed; boundary="8M24MvevtqswUzL7XoeLd2kQ98fbtAa66"; protected-headers="v1" From: Qu Wenruo To: Dave Chinner Cc: fstests Message-ID: <643f7899-e010-2694-4af6-960f0fc6e5cc@gmx.com> Subject: Re: Any way to detect performance in a test case? References: <20190116035745.GO4205@dastard> In-Reply-To: <20190116035745.GO4205@dastard> --8M24MvevtqswUzL7XoeLd2kQ98fbtAa66 Content-Type: text/plain; charset=utf-8 Content-Language: en-US Content-Transfer-Encoding: quoted-printable On 2019/1/16 =E4=B8=8A=E5=8D=8811:57, Dave Chinner wrote: > On Wed, Jan 16, 2019 at 09:59:40AM +0800, Qu Wenruo wrote: >> Hi, >> >> Is there any way to detect (huge) performance regression in a test cas= e? >> >> By huge performance regression, I mean some operation takes from less >> than 10s to around 400s. >> >> There is existing runtime accounting, but we can't do it inside a test= >> case (or can we?) >> >> So is there any way to detect huge performance regression in a test ca= se? >=20 > Just run your normal performance monitoring tools while the test is > running to see what has changed. Is it IO, memory, CPU, lock > contention or somethign else that is the problem? pcp, strace, top, > iostat, perf, etc all work just fine for finding perf regressions > reported by test cases... Sorry for the misunderstanding. I mean if it's possible for a test case to just fail when hitting some big performance regression. E.g. one operation should finish in 30s, but when it takes over 300s, it's definitely a big regression. But considering how many different hardware/VM the test may be run on, I'm not really confident if this is possible. Thanks, Qu >=20 > Cheers, >=20 > Dave. >=20 --8M24MvevtqswUzL7XoeLd2kQ98fbtAa66-- --AfyQeGeXtT51bNcVUWTnBHWaeL9d8u7yf Content-Type: application/pgp-signature; name="signature.asc" Content-Description: OpenPGP digital signature Content-Disposition: attachment; filename="signature.asc" -----BEGIN PGP SIGNATURE----- iQEzBAEBCAAdFiEELd9y5aWlW6idqkLhwj2R86El/qgFAlw+t1kACgkQwj2R86El /qgxTAf/TDMYi8Z31s0GfC0qSgMJlLQBbOYQT90BGNqrBF1y+saIMlxYCe8Nk5ZV tvLdYUBQkFbn3UGsOUj/QRWxIWGjHeCWGediVY2MldtT3K1G5AL5IKkHgRibE9fH xjOgDu9e2PU9KtBwbodBp1JLKS4iweF40QGof6HK4Zze53TxZaRBLzPZVUHbTgtL bspKRsjXzNU9p3UUdTbHwhNXo/Kg4czBWdE4Xz5JRvu+SEN8RnVWmXzDpX3GpXK3 vTZ9uPsQtHZ60oBLTJmBnblCalX7OHVWwuLksJFlqmLZf8YF8ysMrG6gzhPAuWnt WIJS/IwB+jOiUnVgQK0Mqu5i98toFw== =Hy+f -----END PGP SIGNATURE----- --AfyQeGeXtT51bNcVUWTnBHWaeL9d8u7yf--