From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:56860)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <a175818323@gmail.com>) id 1aLpUO-00016n-4B
	for qemu-devel@nongnu.org; Wed, 20 Jan 2016 04:55:44 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <a175818323@gmail.com>) id 1aLpUN-00056C-8A
	for qemu-devel@nongnu.org; Wed, 20 Jan 2016 04:55:44 -0500
Received: from mail-oi0-x235.google.com ([2607:f8b0:4003:c06::235]:34558)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <a175818323@gmail.com>) id 1aLpUN-000562-2X
	for qemu-devel@nongnu.org; Wed, 20 Jan 2016 04:55:43 -0500
Received: by mail-oi0-x235.google.com with SMTP id k206so2093298oia.1
	for <qemu-devel@nongnu.org>; Wed, 20 Jan 2016 01:55:42 -0800 (PST)
MIME-Version: 1.0
Date: Wed, 20 Jan 2016 17:55:42 +0800
Message-ID: <CAMxP3BS8s7CUERwAMemm-0rqzAycwZ9syJC9Mi6HaSVY2hZpMQ@mail.gmail.com>
From: Bob Chen <a175818323@gmail.com>
Content-Type: multipart/alternative; boundary=001a11407ac23c517f0529c0fd50
Subject: [Qemu-devel] cgroup blkio weight has no effect on qemu
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

--001a11407ac23c517f0529c0fd50
Content-Type: text/plain; charset=UTF-8

Hi folks,

Could you enlighten me how to achieve proportional IO sharing by using
cgroup, instead of qemu's io-throttling?

My qemu config is like: -drive
file=$DISKFILe,if=none,format=qcow2,cache=none,aio=native -device
virtio-blk-pci...

Test command inside vm is like: dd if=/dev/vdc of=/dev/null iflag=direct

Cgroup blkio weight of the qemu process is properly configured as well.

But no matter how change the proportion, such as vm1=400 and vm2=100, I can
only get the equal IO speed.

Wondering cgroup blkio.weight or blkio.weight_device has no effect on qemu?


PS. cache=writethrough aio=threads is also tested, the same results.


- Bob

--001a11407ac23c517f0529c0fd50
Content-Type: text/html; charset=UTF-8
Content-Transfer-Encoding: quoted-printable

<div dir=3D"ltr"><div>Hi folks,</div><div><br></div><div>Could you enlighte=
n me how to achieve proportional IO sharing by using cgroup, instead of qem=
u&#39;s io-throttling?</div><div><br></div><div>My qemu config is like: -dr=
ive file=3D$DISKFILe,if=3Dnone,format=3Dqcow2,cache=3Dnone,aio=3Dnative -de=
vice virtio-blk-pci...</div><div><br></div><div>Test command inside vm is l=
ike: dd if=3D/dev/vdc of=3D/dev/null iflag=3Ddirect</div><div><br></div><di=
v>Cgroup blkio weight of the qemu process is properly configured as well.</=
div><div><br></div><div>But no matter how change the proportion, such as vm=
1=3D400 and vm2=3D100, I can only get the equal IO speed.</div><div><br></d=
iv><div>Wondering cgroup blkio.weight or blkio.weight_device has no effect =
on qemu?</div><div><br></div><div><br></div><div>PS. cache=3Dwritethrough a=
io=3Dthreads is also tested, the same results.=C2=A0</div><div><br></div><d=
iv><br></div><div>- Bob</div></div>

--001a11407ac23c517f0529c0fd50--