From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1Mis7v-0001MW-Hb for qemu-devel@nongnu.org; Wed, 02 Sep 2009 11:52:03 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1Mis7q-0001KB-Eh for qemu-devel@nongnu.org; Wed, 02 Sep 2009 11:52:02 -0400 Received: from [199.232.76.173] (port=40839 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Mis7q-0001K5-93 for qemu-devel@nongnu.org; Wed, 02 Sep 2009 11:51:58 -0400 Received: from mx1.redhat.com ([209.132.183.28]:26385) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1Mis7o-000462-Uf for qemu-devel@nongnu.org; Wed, 02 Sep 2009 11:51:58 -0400 Message-ID: <4A9E9457.9090904@redhat.com> Date: Wed, 02 Sep 2009 17:50:47 +0200 From: Kevin Wolf MIME-Version: 1.0 Subject: Re: [Qemu-devel] [PATCH 0/3] block: Handle multiple write requests at once References: <1251813112-17408-1-git-send-email-kwolf@redhat.com> <20090901155228.GA21781@lst.de> <4A9E1E4F.4080901@redhat.com> <20090902154347.GA23891@lst.de> In-Reply-To: <20090902154347.GA23891@lst.de> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit List-Id: qemu-devel.nongnu.org List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Christoph Hellwig Cc: qemu-devel@nongnu.org Christoph Hellwig schrieb: > On Wed, Sep 02, 2009 at 09:27:11AM +0200, Kevin Wolf wrote: >>> Of course using a sane filesystem in the guest would also fix it, >>> but the point of virtualization is at least partially to keep all >>> that old crap working nicely. >> Not sure what your definition of "old crap" is, but ext3 seems to meet >> it. I don't think it's irrelevant. > > Even ext3 should not do it as the elevator would merge the requests. > Do you happen to run a kernel which accidentally turned on the misnamed > and misguided SSD flag on for virtio? That would explain sending > lots tiny I/Os. You can checks this with a: > > cat /sys/block/vd*/queue/rotational > > if a 0 turns up somewhere we have the problem. It's a RHEL 5.3 installation, and the kernel doesn't seem to even provide this file. However, I think I read that this is an issue of relatively new kernels, so probably not? What could matter, though, is that the installer uses LVM for the standard layout which I'm using. Does this make a difference in that respect? Kevin