From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([2001:4830:134:3::10]:49497) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UsbMz-00047h-06 for qemu-devel@nongnu.org; Fri, 28 Jun 2013 12:17:57 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1UsbMy-0003rV-1L for qemu-devel@nongnu.org; Fri, 28 Jun 2013 12:17:56 -0400 Received: from mail.avalus.com ([2001:41c8:10:1dd::10]:54072) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1UsbMx-0003rO-RV for qemu-devel@nongnu.org; Fri, 28 Jun 2013 12:17:55 -0400 Date: Fri, 28 Jun 2013 17:17:37 +0100 From: Alex Bligh Message-ID: <624B402D40D846D55A77B826@nimrod.local> In-Reply-To: <20941.26905.519774.239644@mariner.uk.xensource.com> References: <4FE65DE3CFE5553A443BD09F@nimrod.local> <20941.26905.519774.239644@mariner.uk.xensource.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Content-Disposition: inline Subject: Re: [Qemu-devel] [PATCH v2] xen_disk: support "direct-io-safe" backend option Reply-To: Alex Bligh List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Ian Jackson Cc: xen-devel@lists.xensource.com, Anthony Liguori , Stefano Stabellini , qemu-devel@nongnu.org, Alex Bligh , Paolo Bonzini --On 28 June 2013 11:44:41 +0100 Ian Jackson wrote: >> Looks useful. Are you planning to do this for both emulated and pv >> disks? > > Emulated disks don't have the same problem because they don't try to > use O_DIRECT on pages shared with the guest via the Xen grant table > mechanism. I should have been more specific. The original thread maintained emulated disks always had O_DIRECT turned off, despite the fact the rationale for using O_DIRECT for PV disks was that not using O_DIRECT in some circumstances might be unsafe, because it was the only way to get any decent performance out of them. I think we ran the 'no O_DIRECT might be unsafe' argument to ground, but if the rationale for Stefano's patch is not just speed but additional safety (for instance against the host dying and losing the page cache for file systems that have barriers switched off), then there is an argument to use it for emulated disks too. But as Stefano says: --On 28 June 2013 11:56:29 +0100 Stefano Stabellini wrote: > This is PV only, at least for the moment: emulated disks always use > writeback caching. > From the performance point of view, making this change for IDE disks is > not very important (because IDE is slow anyway). ... perhaps 'who cares'. -- Alex Bligh From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alex Bligh Subject: Re: [PATCH v2] xen_disk: support "direct-io-safe" backend option Date: Fri, 28 Jun 2013 17:17:37 +0100 Message-ID: <624B402D40D846D55A77B826@nimrod.local> References: <4FE65DE3CFE5553A443BD09F@nimrod.local> <20941.26905.519774.239644@mariner.uk.xensource.com> Reply-To: Alex Bligh Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20941.26905.519774.239644@mariner.uk.xensource.com> Content-Disposition: inline List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org Sender: qemu-devel-bounces+gceq-qemu-devel=gmane.org@nongnu.org To: Ian Jackson Cc: xen-devel@lists.xensource.com, Anthony Liguori , Stefano Stabellini , qemu-devel@nongnu.org, Alex Bligh , Paolo Bonzini List-Id: xen-devel@lists.xenproject.org --On 28 June 2013 11:44:41 +0100 Ian Jackson wrote: >> Looks useful. Are you planning to do this for both emulated and pv >> disks? > > Emulated disks don't have the same problem because they don't try to > use O_DIRECT on pages shared with the guest via the Xen grant table > mechanism. I should have been more specific. The original thread maintained emulated disks always had O_DIRECT turned off, despite the fact the rationale for using O_DIRECT for PV disks was that not using O_DIRECT in some circumstances might be unsafe, because it was the only way to get any decent performance out of them. I think we ran the 'no O_DIRECT might be unsafe' argument to ground, but if the rationale for Stefano's patch is not just speed but additional safety (for instance against the host dying and losing the page cache for file systems that have barriers switched off), then there is an argument to use it for emulated disks too. But as Stefano says: --On 28 June 2013 11:56:29 +0100 Stefano Stabellini wrote: > This is PV only, at least for the moment: emulated disks always use > writeback caching. > From the performance point of view, making this change for IDE disks is > not very important (because IDE is slow anyway). ... perhaps 'who cares'. -- Alex Bligh