From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from eggs.gnu.org ([140.186.70.92]:43742) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QM53Z-0007XK-8X for qemu-devel@nongnu.org; Mon, 16 May 2011 17:10:26 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1QM53Y-0007tR-75 for qemu-devel@nongnu.org; Mon, 16 May 2011 17:10:25 -0400 Received: from mail-gw0-f45.google.com ([74.125.83.45]:34277) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1QM53Y-0007tJ-4m for qemu-devel@nongnu.org; Mon, 16 May 2011 17:10:24 -0400 Received: by gwb19 with SMTP id 19so1989466gwb.4 for ; Mon, 16 May 2011 14:10:23 -0700 (PDT) Message-ID: <4DD192BD.3030200@codemonkey.ws> Date: Mon, 16 May 2011 16:10:21 -0500 From: Anthony Liguori MIME-Version: 1.0 References: <20110516181023.7142.33402.sendpatchset@skannery> <20110516202354.GA8955@lst.de> In-Reply-To: <20110516202354.GA8955@lst.de> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Subject: Re: [Qemu-devel] [RFC Patch 0/3]Qemu: Enable dynamic cache change through qemu monitor List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: Christoph Hellwig Cc: Kevin Wolf , Supriya Kannery , qemu-devel@nongnu.org, Prerna Saxena On 05/16/2011 03:23 PM, Christoph Hellwig wrote: > Why are you even trying this again? As explained very clearly last time you > can't change from a writeback-style to a write-through style I/O from > the monitor without creating massive data integrity problems. To further clarify: Today cache=none|writethrough|writeback does two things. It: 1) Changes the WCE flag that's visible to the guest 2) Determines whether the host page cache is used for doing guest I/O As Christoph is very correct in pointing out, we cannot change (1) at run time because this is guest visible. You will break a guest if you do this. But it's still desirable to be able to change (2) at run time. Before we can do this properly though, we need to separate out the logic for setting (1) vs. (2). And ideally, we would allow (1) to be changed by the guest itself at run time which allows for full dynamic control. This is what he's referring to below. Regards, Anthony Liguori See my > patchset that allows changing this from the guest for how it should be > done - I just need to get back and revisit the virtio protocol support > for it. > >