From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?iso-8859-15?Q?Ren=E9?= Pfeiffer Subject: I/O performance of VirtIO Date: Mon, 12 Oct 2009 22:49:03 +0200 Message-ID: <20091012204901.GA10688@nightfall.luchs.at> Mime-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha1; protocol="application/pgp-signature"; boundary="VS++wcV0S1rZb1Fb" To: kvm@vger.kernel.org Return-path: Received: from gilean.luchs.at ([62.116.64.105]:56393 "EHLO gilean.luchs.at" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752996AbZJLVAk (ORCPT ); Mon, 12 Oct 2009 17:00:40 -0400 Received: from localhost (localhost [127.0.0.1]) by gilean.luchs.at (Postfix) with ESMTP id 5E183C20 for ; Mon, 12 Oct 2009 22:49:12 +0200 (CEST) Received: from gilean.luchs.at ([127.0.0.1]) by localhost (gilean.luchs.at [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id FZmF+t9C-H8v for ; Mon, 12 Oct 2009 22:49:11 +0200 (CEST) Received: from nightfall.luchs.at (nightfall.luchs.at [62.116.64.107]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "nightfall.luchs.at", Issuer "luchs.at CA" (verified OK)) by gilean.luchs.at (Postfix) with ESMTPS id CF855BB5 for ; Mon, 12 Oct 2009 22:49:11 +0200 (CEST) Received: from nightfall.luchs.at (localhost [127.0.0.1]) by nightfall.luchs.at (Postfix) with ESMTP id 7C4311300A7 for ; Mon, 12 Oct 2009 22:49:11 +0200 (CEST) Received: from nightfall.luchs.at (localhost [127.0.0.1]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by nightfall.luchs.at (Postfix) with ESMTPS id 1D29A1300A4 for ; Mon, 12 Oct 2009 22:49:11 +0200 (CEST) Content-Disposition: inline Sender: kvm-owner@vger.kernel.org List-ID: --VS++wcV0S1rZb1Fb Content-Type: text/plain; charset=iso-8859-15 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable Hello! I just tested qemu-kvm-0.11.0 with the KVM module of kernel 2.6.31.1. I noticed that the I/O performance of an unattended stock Debian Lenny install dropped somehow. The test machines ran with kvm-88 and 2.6.30.x before. The difference is very noticeable (went from about 5 minutes up to 15-25 minutes). The two test machines have different CPUs (one is an Intel Core2 CPU, the other runs with an AMD Athlon 64 X2 Dual). Is this the effect of added code regarding caching/data integrity to the VirtIO block layer or somewhere else? The qemu-system-x86_64 seems to hang a lot more in heavy I/O (showing 'D' in top/htop). The command line is quite straight-forward: qemu-system-x86_64 -drive file=3Ddebian.qcow2,if=3Dvirtio,boot=3Don -cdrom \ /srv/isos/debian-502-i386-netinst.iso -smp 2 -boot d -m 512 -net nic \ -net user -usb Installation was repeated multiple times, every time the test machines hat no other load. The effect is the same with a Windows XP guest running without VirtIO. Best, Ren=E9. --=20 )\._.,--....,'``. fL Let GNU/Linux work for you while you take a nap. /, _.. \ _\ (`._ ,. R. Pfeiffer + http://web.luchs= =2Eat/ `._.-(,_..'--(,_..'`-.;.' - System administration + Consulting + Teaching - Got mail delivery problems? http://web.luchs.at/information/blockedmail.php --VS++wcV0S1rZb1Fb Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.9 (GNU/Linux) iD8DBQFK05Y9cjShfQp7h4YRAhuaAJ91OgofWARImV0A4gluZD7YB+q0JQCgqU6i JDWqLn02lGnzzgkxpSIPWqg= =X+dm -----END PGP SIGNATURE----- --VS++wcV0S1rZb1Fb--