From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:49559)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <stefanha@redhat.com>) id 1UIKh2-0006AJ-62
	for qemu-devel@nongnu.org; Wed, 20 Mar 2013 11:12:50 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <stefanha@redhat.com>) id 1UIKgu-0007Pu-6g
	for qemu-devel@nongnu.org; Wed, 20 Mar 2013 11:12:44 -0400
Received: from mx1.redhat.com ([209.132.183.28]:31860)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <stefanha@redhat.com>) id 1UIKgt-0007Pm-TH
	for qemu-devel@nongnu.org; Wed, 20 Mar 2013 11:12:36 -0400
Date: Wed, 20 Mar 2013 16:12:03 +0100
From: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20130320151203.GA3584@stefanha-thinkpad.muc.redhat.com>
References: <1363770734-30970-1-git-send-email-benoit@irqsave.net>
	<1363770734-30970-2-git-send-email-benoit@irqsave.net>
	<20130320132924.GB14441@stefanha-thinkpad.muc.redhat.com>
	<20130320142842.GA2389@stefanha-thinkpad.muc.redhat.com>
	<20130320145633.GA1473@irqsave.net>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
In-Reply-To: <20130320145633.GA1473@irqsave.net>
Content-Transfer-Encoding: quoted-printable
Subject: Re: [Qemu-devel] [PATCH] block: fix bdrv_exceed_iops_limits wait
 computation
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: =?iso-8859-1?Q?Beno=EEt?= Canet <benoit.canet@irqsave.net>
Cc: kwolf@redhat.com, Stefan Hajnoczi <stefanha@gmail.com>, wuzhy@linux.vnet.ibm.com, qemu-devel@nongnu.org

On Wed, Mar 20, 2013 at 03:56:33PM +0100, Beno=EEt Canet wrote:
> > But I don't understand why bs->slice_time is modified instead of keep=
ing
> > it constant at 100 ms:
> >
> >     bs->slice_time =3D wait_time * BLOCK_IO_SLICE_TIME * 10;
> >     bs->slice_end +=3D bs->slice_time - 3 * BLOCK_IO_SLICE_TIME;
> >     if (wait) {
> >         *wait =3D wait_time * BLOCK_IO_SLICE_TIME * 10;
> >     }
>=20
> In bdrv_exceed_bps_limits there is an equivalent to this with a comment.
>=20
> ---------
>   /* When the I/O rate at runtime exceeds the limits,
>      * bs->slice_end need to be extended in order that the current stat=
istic
>      * info can be kept until the timer fire, so it is increased and tu=
ned
>      * based on the result of experiment.
>      */
>     bs->slice_time =3D wait_time * BLOCK_IO_SLICE_TIME * 10;
>     bs->slice_end +=3D bs->slice_time - 3 * BLOCK_IO_SLICE_TIME;
>     if (wait) {
>         *wait =3D wait_time * BLOCK_IO_SLICE_TIME * 10;
>     }
> ----------

The comment explains why slice_end needs to be extended, but not why
bs->slice_time should be changed (except that it was tuned as the result
of an experiment).

Zhi Yong: Do you remember a reason for modifying bs->slice_time?

Stefan