From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1MiVuB-0002fg-50
	for qemu-devel@nongnu.org; Tue, 01 Sep 2009 12:08:23 -0400
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1MiVu6-0002ac-BG
	for qemu-devel@nongnu.org; Tue, 01 Sep 2009 12:08:22 -0400
Received: from [199.232.76.173] (port=38523 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1MiVu6-0002aL-2Y
	for qemu-devel@nongnu.org; Tue, 01 Sep 2009 12:08:18 -0400
Received: from mail-px0-f179.google.com ([209.85.216.179]:62771)
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <anthony@codemonkey.ws>) id 1MiVu5-0002pz-KE
	for qemu-devel@nongnu.org; Tue, 01 Sep 2009 12:08:17 -0400
Received: by pxi9 with SMTP id 9so100537pxi.14
	for <qemu-devel@nongnu.org>; Tue, 01 Sep 2009 09:08:15 -0700 (PDT)
Message-ID: <4A9D46EA.8090606@codemonkey.ws>
Date: Tue, 01 Sep 2009 11:08:10 -0500
From: Anthony Liguori <anthony@codemonkey.ws>
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>
In-Reply-To: <20090901155228.GA21781@lst.de>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.gnu.org/pipermail/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Christoph Hellwig <hch@lst.de>
Cc: Kevin Wolf <kwolf@redhat.com>, qemu-devel@nongnu.org

Christoph Hellwig wrote:
> On Tue, Sep 01, 2009 at 03:51:49PM +0200, Kevin Wolf wrote:
>   
>> virtio often issues multiple requests in a row, but each one independently. If
>> the block drivers knew all of the requests, they could optimize the way they
>> handle the requests. See the description of patch 3 for how qcow2 can use this
>> to avoid unnecessary writes to the disk.
>>     
>
> I think this interface is extremly awkward and the layering is wrong.
> Everyone benefits from having one large instead of multiple small
> requests, so if we do get multiple sequential write requests we should
> always merged it at a high level even before starting to issue AIO,
> e.g. do it all in virtio-blk.
>   

Or introduce a helper layer that coalesces requests that lives outside 
of the core block API.

I don't like the interface either although I'm not sure if the 
alternative is better.   A different way to do this would be to have a 
queuing API.   A device would queue requests and then kick the queue.  
This is closer to how virtio-blk works.

Regards,

Anthony Liguori