From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:49591)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <famz@redhat.com>) id 1XCknX-0005oB-Su
	for qemu-devel@nongnu.org; Thu, 31 Jul 2014 03:29:18 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <famz@redhat.com>) id 1XCknR-00084t-NB
	for qemu-devel@nongnu.org; Thu, 31 Jul 2014 03:29:11 -0400
Received: from mx1.redhat.com ([209.132.183.28]:24149)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <famz@redhat.com>) id 1XCknR-00084X-GE
	for qemu-devel@nongnu.org; Thu, 31 Jul 2014 03:29:05 -0400
Date: Thu, 31 Jul 2014 15:29:21 +0800
From: Fam Zheng <famz@redhat.com>
Message-ID: <20140731072921.GA10278@T430.nay.redhat.com>
References: <1401958066-22118-1-git-send-email-famz@redhat.com>
	<20140617024507.GA3359@T430.redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20140617024507.GA3359@T430.redhat.com>
Subject: Re: [Qemu-devel] [PATCH v4 0/5] This series adds iotest case for IO
 throttling.
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/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: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>, Benoit Canet <benoit@irqsave.net>, Stefan Hajnoczi <stefanha@redhat.com>

On Tue, 06/17 10:45, Fam Zheng wrote:
> On Thu, 06/05 16:47, Fam Zheng wrote:
> > There is a change in qemu-io sub-commands "aio_read" and "aio_write", which
> > makes the aio requests accounted and the statistics reflected in blockstats.
> > 
> > Note that IO throttling implementation allows overcommiting of requests, so the
> > actual IO happened in a time unit may be a bit larger than given limits. In the
> > test case, the stats numbers are compared against 110%, to make room for such
> > flexibility in order to improve determinism.
> > 
> > v4: Rebase to master. Add Benoit's rev-by lines to all the patches.
> 
> Ping?

Ping.