From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from list by lists.gnu.org with archive (Exim 4.71) id 1YcSL8-0003u5-4D for mharc-qemu-trivial@gnu.org; Mon, 30 Mar 2015 01:34:22 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:46146) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YcSL5-0003qj-ND for qemu-trivial@nongnu.org; Mon, 30 Mar 2015 01:34:20 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1YcSL4-0001qf-LK for qemu-trivial@nongnu.org; Mon, 30 Mar 2015 01:34:19 -0400 Received: from v220110690675601.yourvserver.net ([37.221.199.173]:50806) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YcSKz-0001pw-4s; Mon, 30 Mar 2015 01:34:13 -0400 Received: from localhost (v220110690675601.yourvserver.net.local [127.0.0.1]) by v220110690675601.yourvserver.net (Postfix) with ESMTP id 6E5B811810A8; Mon, 30 Mar 2015 07:34:11 +0200 (CEST) X-Virus-Scanned: Debian amavisd-new at weilnetz.de Received: from v220110690675601.yourvserver.net ([127.0.0.1]) by localhost (v220110690675601.yourvserver.net [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id CvlLLOaYpiOk; Mon, 30 Mar 2015 07:33:59 +0200 (CEST) Received: from [192.168.178.24] (p54AC85EB.dip0.t-ipconnect.de [84.172.133.235]) by v220110690675601.yourvserver.net (Postfix) with ESMTPSA id A81C31180041; Mon, 30 Mar 2015 07:33:59 +0200 (CEST) Message-ID: <5518E047.5030303@weilnetz.de> Date: Mon, 30 Mar 2015 07:33:59 +0200 From: Stefan Weil User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:31.0) Gecko/20100101 Icedove/31.5.0 MIME-Version: 1.0 To: Richard Henderson , "Emilio G. Cota" References: <5518742e.451f460a.1d9b.66ce@mx.google.com> In-Reply-To: <5518742e.451f460a.1d9b.66ce@mx.google.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: quoted-printable X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 37.221.199.173 Cc: qemu-trivial , =?UTF-8?B?QWxleCBCZW5uw6ll?= , qemu-devel@nongnu.org Subject: Re: [Qemu-trivial] [Qemu-devel] [PATCH] tcg: optimise memory layout of TCGTemp X-BeenThere: qemu-trivial@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 30 Mar 2015 05:34:20 -0000 Am 29.03.2015 um 23:52 schrieb Richard Henderson: > On Mar 27, 2015 14:09, "Emilio G. Cota" wrote: >> On Fri, Mar 27, 2015 at 09:55:03 +0000, Alex Benn=C3=A9e wrote: >>> Have you been able to measure any performance improvement with these = new >>> structures? In theory, if aligned with cache lines, performance shoul= d >>> improve but real numbers would be nice. >> I haven't benchmarked anything, which makes me very uneasy. All >> I've checked is that the system boots, and FWIW I appreciate no >> difference in boot time. > No decrease in boot time is good. We /know/ we're saving memory, after = all. > =20 >> Is there a benchmark suite to test TCG changes? > No, sorry. > > > r~ Benchmarking TCG with QEMU's system emulation is nearly impossible because operating systems usually contain lots of timer based operations. The TCG interpreter for example is really slow, but a BIOS will boot faster than expected with it. The user mode emulation is much better for benchmarks. Run some command line Linux application which mainly does computations (not file i/o) using user mode emulation on Linux. The OpenSSL package contains bntest which can be used as a benchmark for TCG. Redirect all output to /dev/null when you run it. Binaries for i386 and x86_64 are available from http://qemu.weilnetz.de/test/user/. Stefan From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:46135) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YcSL3-0003q7-CN for qemu-devel@nongnu.org; Mon, 30 Mar 2015 01:34:18 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1YcSKz-0001qA-BC for qemu-devel@nongnu.org; Mon, 30 Mar 2015 01:34:17 -0400 Message-ID: <5518E047.5030303@weilnetz.de> Date: Mon, 30 Mar 2015 07:33:59 +0200 From: Stefan Weil MIME-Version: 1.0 References: <5518742e.451f460a.1d9b.66ce@mx.google.com> In-Reply-To: <5518742e.451f460a.1d9b.66ce@mx.google.com> Content-Type: text/plain; charset=utf-8; format=flowed Content-Transfer-Encoding: quoted-printable Subject: Re: [Qemu-devel] [PATCH] tcg: optimise memory layout of TCGTemp List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Richard Henderson , "Emilio G. Cota" Cc: qemu-trivial , =?UTF-8?B?QWxleCBCZW5uw6ll?= , qemu-devel@nongnu.org Am 29.03.2015 um 23:52 schrieb Richard Henderson: > On Mar 27, 2015 14:09, "Emilio G. Cota" wrote: >> On Fri, Mar 27, 2015 at 09:55:03 +0000, Alex Benn=C3=A9e wrote: >>> Have you been able to measure any performance improvement with these = new >>> structures? In theory, if aligned with cache lines, performance shoul= d >>> improve but real numbers would be nice. >> I haven't benchmarked anything, which makes me very uneasy. All >> I've checked is that the system boots, and FWIW I appreciate no >> difference in boot time. > No decrease in boot time is good. We /know/ we're saving memory, after = all. > =20 >> Is there a benchmark suite to test TCG changes? > No, sorry. > > > r~ Benchmarking TCG with QEMU's system emulation is nearly impossible because operating systems usually contain lots of timer based operations. The TCG interpreter for example is really slow, but a BIOS will boot faster than expected with it. The user mode emulation is much better for benchmarks. Run some command line Linux application which mainly does computations (not file i/o) using user mode emulation on Linux. The OpenSSL package contains bntest which can be used as a benchmark for TCG. Redirect all output to /dev/null when you run it. Binaries for i386 and x86_64 are available from http://qemu.weilnetz.de/test/user/. Stefan