From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1Lrx7S-0006mY-OB
	for qemu-devel@nongnu.org; Thu, 09 Apr 2009 12:28:50 -0400
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1Lrx7N-0006iC-OX
	for qemu-devel@nongnu.org; Thu, 09 Apr 2009 12:28:50 -0400
Received: from [199.232.76.173] (port=41588 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1Lrx7N-0006ht-H6
	for qemu-devel@nongnu.org; Thu, 09 Apr 2009 12:28:45 -0400
Received: from wa-out-1112.google.com ([209.85.146.180]:44260)
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <anthony@codemonkey.ws>) id 1Lrx7N-0002Yn-59
	for qemu-devel@nongnu.org; Thu, 09 Apr 2009 12:28:45 -0400
Received: by wa-out-1112.google.com with SMTP id m33so526223wag.18
	for <qemu-devel@nongnu.org>; Thu, 09 Apr 2009 09:28:44 -0700 (PDT)
Message-ID: <49DE2235.7050904@codemonkey.ws>
Date: Thu, 09 Apr 2009 11:28:37 -0500
From: Anthony Liguori <anthony@codemonkey.ws>
MIME-Version: 1.0
Subject: Re: [Qemu-devel] buffer alignment for block backends
References: <49DCA80A.1020808@eu.citrix.com>	<49DCF2C0.9070704@codemonkey.ws>	<49DDC66F.2000404@eu.citrix.com>	<49DDF3FF.8050706@codemonkey.ws>	<49DDF877.8090805@eu.citrix.com>	<49DDFE1A.9040202@redhat.com>	<20090409152107.GE5457@const.bordeaux.inria.fr>
	<49DE193B.50703@redhat.com>
In-Reply-To: <49DE193B.50703@redhat.com>
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: <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: qemu-devel@nongnu.org

Gerd Hoffmann wrote:
>>> The xen block protocol can handle unaligned requests just fine.
>>
>> Not completely arbitrarily aligned requests. They need to be
>> sector-aligned.
>
> Agreed.  Sector-alignment you have anyway, thats why I didn't wrote 
> that explicitly.

But even sector-alignment is not guaranteed for the buffers in the 
bdrv_* API.

You can implement a backend that just implements aio_read/aio_write and 
you'll always get sector-aligned offsets, but the actual data buffers 
may have any alignment.

Regards,

Anthony Liguori

> cheers,
>   Gerd
>
>
>