From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from mailman by lists.gnu.org with tmda-scanned (Exim 4.43)
	id 1MGYAz-0002DS-Oe
	for qemu-devel@nongnu.org; Tue, 16 Jun 2009 08:54:09 -0400
Received: from exim by lists.gnu.org with spam-scanned (Exim 4.43)
	id 1MGYAu-00027L-Ud
	for qemu-devel@nongnu.org; Tue, 16 Jun 2009 08:54:09 -0400
Received: from [199.232.76.173] (port=51445 helo=monty-python.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1MGYAu-00026j-IY
	for qemu-devel@nongnu.org; Tue, 16 Jun 2009 08:54:04 -0400
Received: from mx2.redhat.com ([66.187.237.31]:44648)
	by monty-python.gnu.org with esmtp (Exim 4.60)
	(envelope-from <avi@redhat.com>) id 1MGYAu-0005EA-1m
	for qemu-devel@nongnu.org; Tue, 16 Jun 2009 08:54:04 -0400
Message-ID: <4A3795F4.9080507@redhat.com>
Date: Tue, 16 Jun 2009 15:54:12 +0300
From: Avi Kivity <avi@redhat.com>
MIME-Version: 1.0
References: <4A36B025.2080602@us.ibm.com> <4A37618E.6040606@redhat.com>
	<4A379504.4080100@us.ibm.com>
In-Reply-To: <4A379504.4080100@us.ibm.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Subject: [Qemu-devel] Re: Live migration broken when under heavy IO
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: Anthony Liguori <aliguori@us.ibm.com>
Cc: "qemu-devel@nongnu.org" <qemu-devel@nongnu.org>, kvm-devel <kvm@vger.kernel.org>

On 06/16/2009 03:50 PM, Anthony Liguori wrote:
> Avi Kivity wrote:
>>> Does anyone have a clever idea how to fix this without just waiting 
>>> for all IO requests to complete?
>>
>> What's wrong with waiting for requests to complete?  It should take a 
>> few tens of milliseconds.
>
> An alternative would be to attempt to cancel the requests.  This 
> incurs no non-deterministic latency.

Yes, that's even better (though without linux-aio, it's equivalent).

>
> The tricky bit is that this has to happen at the device layer because 
> the opaques cannot be saved in a meaningful way.
>

Do you mean the device has to record all cancelled requests and replay 
them?  I think we can do it at the block layer (though we have to avoid 
it for nested requests).

-- 
error compiling committee.c: too many arguments to function