From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1KqVOn-0002jT-Td for qemu-devel@nongnu.org; Thu, 16 Oct 2008 12:08:30 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1KqVOk-0002hx-Ao for qemu-devel@nongnu.org; Thu, 16 Oct 2008 12:08:29 -0400 Received: from [199.232.76.173] (port=44653 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1KqVOk-0002hl-41 for qemu-devel@nongnu.org; Thu, 16 Oct 2008 12:08:26 -0400 Received: from ecfrec.frec.bull.fr ([129.183.4.8]:52731) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1KqVOj-0007Q6-I3 for qemu-devel@nongnu.org; Thu, 16 Oct 2008 12:08:25 -0400 Subject: Re: [Qemu-devel] Re: [RFC] Disk integrity in QEMU From: Laurent Vivier In-Reply-To: <48F74511.8080700@codemonkey.ws> References: <48EE38B9.2050106@codemonkey.ws> <20081013170610.GF21410@us.ibm.com> <6A99DBA5-D422-447D-BF9D-019FB394E6C6@lvivier.info> <20081013194328.GJ21410@us.ibm.com> <148FE536-F397-4F51-AE3F-C94E4F1F5D4E@lvivier.info> <20081013210509.GL21410@us.ibm.com> <1224076205.4150.17.camel@frecb07144> <1224152681.4168.5.camel@frecb07144> <48F74511.8080700@codemonkey.ws> Content-Type: text/plain; charset=UTF-8 Date: Thu, 16 Oct 2008 18:08:19 +0200 Message-Id: <1224173299.4168.26.camel@frecb07144> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Reply-To: qemu-devel@nongnu.org List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: qemu-devel@nongnu.org Cc: Chris Wright , Mark McLoughlin , Ryan Harper Le jeudi 16 octobre 2008 =C3=A0 08:43 -0500, Anthony Liguori a =C3=A9crit= : > Laurent Vivier wrote: > > Hi, > > > > I've made a benchmark using a database: > > mysql and sysbench in OLTP mode. > > > > cache=3Doff seems to be the best choice in this case... > > =20 >=20 > It would be interesting for you to run the same workload under KVM. It is done under KVM... and I've just double checked these values. > > mysql database > > http://sysbench.sourceforge.net > > > > sysbench --test=3Doltp > > > > 200,000 requests on 2,000,000 rows table. > > > > | total time | per-request stat (ms) | > > | (seconds) | min | avg | max | > > -----------------+------------+-------+-------+-------+ > > baremetal | 208.6237 | 2.5 | 16.7 | 942.6 | > > -----------------+------------+-------+-------+-------+ > > cache=3Don | 642.2962 | 2.5 | 51.4 | 326.9 | > > -----------------+------------+-------+-------+-------+ > > cache=3Don,O_DSYNC | 646.6570 | 2.7 | 51.7 | 347.0 | > > -----------------+------------+-------+-------+-------+ > > cache=3Doff | 635.4424 | 2.9 | 50.8 | 399.5 | > > -----------------+------------+-------+-------+-------+ > > =20 >=20 > Because you're talking about 1/3% of native performance. This means=20 > that you may be dominated by things like CPU overhead verses actual IO=20 > throughput. Yes, but as it is KVM I have no explanation... I've another interesting result with scsi-generic : -----------------+------------+-------+-------+-------+ scsi-generic | 634.1303 | 2.8 | 50.7 | 308.6 | -----------------+------------+-------+-------+-------+ Regards, Laurent --=20 ------------------ Laurent.Vivier@bull.net ------------------ "Tout ce qui est impossible reste =C3=A0 accomplir" Jules Verne "Things are only impossible until they're not" Jean-Luc Picard