From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43) id 1Kp5FP-0006mn-9T for qemu-devel@nongnu.org; Sun, 12 Oct 2008 14:00:55 -0400 Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43) id 1Kp5FN-0006mM-Os for qemu-devel@nongnu.org; Sun, 12 Oct 2008 14:00:54 -0400 Received: from [199.232.76.173] (port=34403 helo=monty-python.gnu.org) by lists.gnu.org with esmtp (Exim 4.43) id 1Kp5FN-0006mJ-HC for qemu-devel@nongnu.org; Sun, 12 Oct 2008 14:00:53 -0400 Received: from yw-out-1718.google.com ([74.125.46.157]:43012) by monty-python.gnu.org with esmtp (Exim 4.60) (envelope-from ) id 1Kp5FN-0005uR-18 for qemu-devel@nongnu.org; Sun, 12 Oct 2008 14:00:53 -0400 Received: by yw-out-1718.google.com with SMTP id 6so311574ywa.82 for ; Sun, 12 Oct 2008 11:00:52 -0700 (PDT) Message-ID: <48F23B50.6080402@codemonkey.ws> Date: Sun, 12 Oct 2008 13:00:48 -0500 From: Anthony Liguori MIME-Version: 1.0 Subject: Re: [Qemu-devel] [RFC] Disk integrity in QEMU References: <48EE38B9.2050106@codemonkey.ws> <48EF1D55.7060307@redhat.com> <48F0E83E.2000907@redhat.com> <48F10DFD.40505@codemonkey.ws> <20081012004401.GA9763@acer.localdomain> <48F1CF9E.9030500@redhat.com> <48F20BBC.1040708@il.qumranet.com> <20081012153546.GD18814@shareable.org> In-Reply-To: <20081012153546.GD18814@shareable.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit 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 , kvm-devel , Laurent Vivier Jamie Lokier wrote: > Dor Laor wrote: > >> Actually this is what happens on mainline qemu with cache=off. >> > > Have I understood right that cache=off on a qcow2 image only uses > O_DIRECT for the leaf image, and the chain of base images don't use > O_DIRECT? > Yeah, that's a bug IMHO and in my patch to add O_DSYNC, I fix that. I think an argument for O_DIRECT in a leaf and wb in the leaf is seriously flawed... Regards, Anthony Liguori > Sometimes on a memory constrained host, where the (collective) guest > memory is nearly as big as the host memory, I'm not sure this is what > I want. > > -- Jamie > > >