From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from [140.186.70.92] (port=38647 helo=eggs.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1PNpmJ-0002Mm-P4
	for qemu-devel@nongnu.org; Wed, 01 Dec 2010 11:44:03 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <avi@redhat.com>) id 1PNplv-0006lj-QQ
	for qemu-devel@nongnu.org; Wed, 01 Dec 2010 11:43:35 -0500
Received: from mx1.redhat.com ([209.132.183.28]:62495)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <avi@redhat.com>) id 1PNplv-0006l9-Fq
	for qemu-devel@nongnu.org; Wed, 01 Dec 2010 11:43:11 -0500
Message-ID: <4CF67B19.9000308@redhat.com>
Date: Wed, 01 Dec 2010 18:43:05 +0200
From: Avi Kivity <avi@redhat.com>
MIME-Version: 1.0
References: <cover.1290552026.git.quintela@redhat.com>	<411b3f89b6b79b429686bd1b1fa188ba55b6c6f7.1290552026.git.quintela@redhat.com>	<4CF45DE0.8020701@codemonkey.ws>
	<m3r5e2vpgf.fsf@trasno.mitica>	<4CF65FBB.3020406@redhat.com>
	<m3lj49xzhp.fsf@trasno.mitica>	<4CF66FEB.7030602@codemonkey.ws>
	<m3fwuhxxxt.fsf@trasno.mitica> <4CF678E0.9070904@codemonkey.ws>
In-Reply-To: <4CF678E0.9070904@codemonkey.ws>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Subject: [Qemu-devel] Re: [PATCH 10/10] Maintaing number of dirty pages
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.nongnu.org/archive/html/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 <anthony@codemonkey.ws>
Cc: qemu-devel@nongnu.org, Juan Quintela <quintela@redhat.com>

On 12/01/2010 06:33 PM, Anthony Liguori wrote:
>>> BTW, by this logic, even a 1-byte dirty bitmap is only 16mb which can
>>> be read in less than 16ms so where is the reported 24 minute stall
>>> coming from?
>> a) we read the bitmap more than once
>
> Not in a single iteration which is what the "stall" would consist of.
>
>> b) the 1ms is based on "we read" it with longs and optimized, just now
>>     we have to read it by byte and inside the byte.
>
> Byte accesses verse long access doesn't turn 16ms into 24 minutes.

We need actual measurements instead of speculations.  Walking the dirty 
bitmap _did_ _not_ introduce any stalls.  It was the qemu mutex, or 
walking kvm data structures in the kernel, or something.  No amount of 
dirty bitmap optimization will fix it.

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