12:05 a.m.
----- Forwarded message from Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com> -----
Date: Thu, 1 Sep 2011 11:55:17 +0800
From: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>
To: Stefan Hajnoczi <stefanha(a)gmail.com>
Cc: "Daniel P. Berrange" <berrange(a)redhat.com>, Stefan Hajnoczi
<stefanha(a)gmail.com>, Adam Litke <agl(a)us.ibm.com>, Zhi Yong Wu
<wuzhy(a)linux.vnet.ibm.com>, QEMU Developers <qemu-devel(a)nongnu.org>,
guijianfeng(a)cn.fujitsu.com, hutao(a)cn.fujitsu.com
Subject: [RFC] block I/O throttling: how to enable in libvirt
Message-ID: <20110901035517.GD16985(a)f15.cn.ibm.com>
References: <CAEH94Li_C=BOe2gV8NyM48njYWMBAo9MTGc1eUOh-Y=cODs6VA(a)mail.gmail.com>
<CAJSP0QW1CPCokX=F5z7y==vn1S4wH0VtOaQ7oj4kC7f7uQM4MQ(a)mail.gmail.com>
<20110830134636.GB29130(a)aglitke.rchland.ibm.com>
<CAJSP0QUHm=y8XJC_KXRg7ufFZt3K_XDDfQb--sxjC+c0GjO8qg(a)mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <CAJSP0QUHm=y8XJC_KXRg7ufFZt3K_XDDfQb--sxjC+c0GjO8qg(a)mail.gmail.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
X-Xagent-From: wuzhy(a)linux.vnet.ibm.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: vmsdvma.vnet.ibm.com (XAGENTU7 at VMSDVMA)
On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
Subject: Re: The design choice for how to enable block I/O throttling
function in libvirt
From: Stefan Hajnoczi <stefanha(a)gmail.com>
To: Adam Litke <agl(a)us.ibm.com>
Cc: libvir-list(a)redhat.com, "Daniel P. Berrange" <berrange(a)redhat.com>,
Zhi
Yong Wu <wuzhy(a)linux.vnet.ibm.com>, Zhi Yong Wu <zwu.kernel(a)gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Brightmail-Tracker: AAAAAA==
X-Xagent-From: stefanha(a)gmail.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: bldgate.vnet.ibm.com (XAGENTU7 at BLDGATE)
On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>> On Tue, Aug 30, 2011 at 3:55 AM, Zhi Yong Wu <zwu.kernel(a)gmail.com> wrote:
>> > I am trying to enable block I/O throttling function in libvirt. But
>> > currently i met some design questions, and don't make sure if we
>> > should extend blkiotune to support block I/O throttling or introduce
>> > one new libvirt command "blkiothrottle" to cover it or not. If
you
>> > have some better idea, pls don't hesitate to drop your comments.
>>
>> A little bit of context: this discussion is about adding libvirt
>> support for QEMU disk I/O throttling.
>
> Thanks for the additional context Stefan.
>
>> Today libvirt supports the cgroups blkio-controller, which handles
>> proportional shares and throughput/iops limits on host block devices.
>> blkio-controller does not support network file systems (NFS) or other
>> QEMU remote block drivers (curl, Ceph/rbd, sheepdog) since they are
>> not host block devices. QEMU I/O throttling works with all types of
>> -drive and therefore complements blkio-controller.
>
> The first question that pops into my mind is: Should a user need to understand
> when to use the cgroups blkio-controller vs. the QEMU I/O throttling method? In
> my opinion, it would be nice if libvirt had a single interface for block I/O
> throttling and libvirt would decide which mechanism to use based on the type of
> device and the specific limits that need to be set.
Yes, I agree it would be simplest to pick the right mechanism,
depending on the type of throttling the user wants. More below.
>> I/O throttling can be applied independently to each -drive attached to
>> a guest and supports throughput/iops limits. For more information on
>> this QEMU feature and a comparison with blkio-controller, see Ryan
>> Harper's KVM Forum 2011 presentation:
>
>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>
> From the presentation, it seems that both the cgroups method the the qemu method
> offer comparable control (assuming a block device) so it might possible to apply
> either method from the same API in a transparent manner. Am I correct or are we
> suggesting that the Qemu throttling approach should always be used for Qemu
> domains?
QEMU I/O throttling does not provide a proportional share mechanism.
So you cannot assign weights to VMs and let them receive a fraction of
the available disk time. That is only supported by cgroups
blkio-controller because it requires a global view which QEMU does not
have.
So I think the two are complementary:
If proportional share should be used on a host block device, use
cgroups blkio-controller.
Otherwise use QEMU I/O throttling.
Stefan,
Do you agree with introducing one new libvirt command blkiothrottle now?
If so, i will work on the code draft to make it work.
Daniel and other maintainers,
If you are available, can you make some comments for us?:)
Regards,
Zhi Yong Wu
Stefan
----- End forwarded message -----
3:11 a.m.
On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
>> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>>> I/O throttling can be applied independently to each -drive attached to
>>> a guest and supports throughput/iops limits. For more information on
>>> this QEMU feature and a comparison with blkio-controller, see Ryan
>>> Harper's KVM Forum 2011 presentation:
>>
>>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>>
>> From the presentation, it seems that both the cgroups method the the qemu
method
>> offer comparable control (assuming a block device) so it might possible to
apply
>> either method from the same API in a transparent manner. Am I correct or are
we
>> suggesting that the Qemu throttling approach should always be used for Qemu
>> domains?
>
>QEMU I/O throttling does not provide a proportional share mechanism.
>So you cannot assign weights to VMs and let them receive a fraction of
>the available disk time. That is only supported by cgroups
>blkio-controller because it requires a global view which QEMU does not
>have.
>
>So I think the two are complementary:
>
>If proportional share should be used on a host block device, use
>cgroups blkio-controller.
>Otherwise use QEMU I/O throttling.
Stefan,
Do you agree with introducing one new libvirt command blkiothrottle now?
If so, i will work on the code draft to make it work.
No, I think that the blkiotune command should be extended to support
QEMU I/O throttling. This is not new functionality, we already have
cgroups blkio-controller support today. Therefore I think it makes
sense to keep a unified interface instead of adding a new command.
Stefan
3:49 a.m.
On Thu, Sep 01, 2011 at 09:11:49AM +0100, Stefan Hajnoczi wrote:
On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
> >On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
> >> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
> >>> I/O throttling can be applied independently to each -drive attached to
> >>> a guest and supports throughput/iops limits. For more information on
> >>> this QEMU feature and a comparison with blkio-controller, see Ryan
> >>> Harper's KVM Forum 2011 presentation:
> >>
> >>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
> >>
> >> From the presentation, it seems that both the cgroups method the the qemu
method
> >> offer comparable control (assuming a block device) so it might possible to
apply
> >> either method from the same API in a transparent manner. Am I correct or
are we
> >> suggesting that the Qemu throttling approach should always be used for
Qemu
> >> domains?
> >
> >QEMU I/O throttling does not provide a proportional share mechanism.
> >So you cannot assign weights to VMs and let them receive a fraction of
> >the available disk time. That is only supported by cgroups
> >blkio-controller because it requires a global view which QEMU does not
> >have.
> >
> >So I think the two are complementary:
> >
> >If proportional share should be used on a host block device, use
> >cgroups blkio-controller.
> >Otherwise use QEMU I/O throttling.
> Stefan,
>
> Do you agree with introducing one new libvirt command blkiothrottle now?
> If so, i will work on the code draft to make it work.
No, I think that the blkiotune command should be extended to support
QEMU I/O throttling. This is not new functionality, we already have
cgroups blkio-controller support today. Therefore I think it makes
sense to keep a unified interface instead of adding a new command.
Agreed, the virDomainGetBlkioParameters/virDomainSetBlkioParameters
APIs, and blkio virsh command are intended to be a generic interface
for setting any block related tuning parameters, regardless of what
the underling implementation is. So any use of QEMU I/O throttling
features should be added to those APIs/commands.
Daniel
--
|: http://berrange.com -o- http://www.flickr.com/photos/dberrange/ :|
|: http://libvirt.org -o- http://virt-manager.org :|
|: http://autobuild.org -o- http://search.cpan.org/~danberr/ :|
|: http://entangle-photo.org -o- http://live.gnome.org/gtk-vnc :|
9:03 p.m.
On Thu, Sep 01, 2011 at 09:49:34AM +0100, Daniel P. Berrange wrote:
From: "Daniel P. Berrange" <berrange(a)redhat.com>
To: Stefan Hajnoczi <stefanha(a)gmail.com>
Cc: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>, libvir-list(a)redhat.com,
agl(a)us.ibm.com, qemu-devel(a)nongnu.org, guijianfeng(a)cn.fujitsu.com,
hutao(a)cn.fujitsu.com, zwu.kernel(a)gmail.com
Subject: Re: [RFC] block I/O throttling: how to enable in libvirt
Message-ID: <20110901084934.GA14462(a)redhat.com>
Reply-To: "Daniel P. Berrange" <berrange(a)redhat.com>
References: <20110901050531.GB17963(a)f15.cn.ibm.com>
<20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
User-Agent: Mutt/1.5.21 (2010-09-15)
X-Scanned-By: MIMEDefang 2.67 on 10.5.11.12
X-Brightmail-Tracker: AAAAAA==
X-Xagent-From: berrange(a)redhat.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: emeavsc.vnet.ibm.com (XAGENTU at EMEAVSC)
On Thu, Sep 01, 2011 at 09:11:49AM +0100, Stefan Hajnoczi wrote:
> On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
> > On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
> > >On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
> > >> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
> > >>> I/O throttling can be applied independently to each -drive attached
to
> > >>> a guest and supports throughput/iops limits. For more information
on
> > >>> this QEMU feature and a comparison with blkio-controller, see Ryan
> > >>> Harper's KVM Forum 2011 presentation:
> > >>
> > >>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
> > >>
> > >> From the presentation, it seems that both the cgroups method the the
qemu method
> > >> offer comparable control (assuming a block device) so it might possible
to apply
> > >> either method from the same API in a transparent manner. Am I correct
or are we
> > >> suggesting that the Qemu throttling approach should always be used for
Qemu
> > >> domains?
> > >
> > >QEMU I/O throttling does not provide a proportional share mechanism.
> > >So you cannot assign weights to VMs and let them receive a fraction of
> > >the available disk time. That is only supported by cgroups
> > >blkio-controller because it requires a global view which QEMU does not
> > >have.
> > >
> > >So I think the two are complementary:
> > >
> > >If proportional share should be used on a host block device, use
> > >cgroups blkio-controller.
> > >Otherwise use QEMU I/O throttling.
> > Stefan,
> >
> > Do you agree with introducing one new libvirt command blkiothrottle now?
> > If so, i will work on the code draft to make it work.
>
> No, I think that the blkiotune command should be extended to support
> QEMU I/O throttling. This is not new functionality, we already have
> cgroups blkio-controller support today. Therefore I think it makes
> sense to keep a unified interface instead of adding a new command.
Agreed, the virDomainGetBlkioParameters/virDomainSetBlkioParameters
APIs, and blkio virsh command are intended to be a generic interface
for setting any block related tuning parameters, regardless of what
the underling implementation is. So any use of QEMU I/O throttling
features should be added to those APIs/commands.
thanks for your suggestions.
Regards,
Zhi Yong Wu
Daniel
--
|: http://berrange.com -o- http://www.flickr.com/photos/dberrange/ :|
|: http://libvirt.org -o- http://virt-manager.org :|
|: http://autobuild.org -o- http://search.cpan.org/~danberr/ :|
|: http://entangle-photo.org -o- http://live.gnome.org/gtk-vnc :|
8:16 p.m.
On 2011-9-1 16:11, Stefan Hajnoczi wrote:
On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>> On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
>>> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>>>> I/O throttling can be applied independently to each -drive attached to
>>>> a guest and supports throughput/iops limits. For more information on
>>>> this QEMU feature and a comparison with blkio-controller, see Ryan
>>>> Harper's KVM Forum 2011 presentation:
>>>
>>>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>>>
>>> From the presentation, it seems that both the cgroups method the the qemu
method
>>> offer comparable control (assuming a block device) so it might possible to
apply
>>> either method from the same API in a transparent manner. Am I correct or are
we
>>> suggesting that the Qemu throttling approach should always be used for Qemu
>>> domains?
>>
>> QEMU I/O throttling does not provide a proportional share mechanism.
>> So you cannot assign weights to VMs and let them receive a fraction of
>> the available disk time. That is only supported by cgroups
>> blkio-controller because it requires a global view which QEMU does not
>> have.
>>
>> So I think the two are complementary:
>>
>> If proportional share should be used on a host block device, use
>> cgroups blkio-controller.
>> Otherwise use QEMU I/O throttling.
> Stefan,
>
> Do you agree with introducing one new libvirt command blkiothrottle now?
> If so, i will work on the code draft to make it work.
No, I think that the blkiotune command should be extended to support
QEMU I/O throttling. This is not new functionality, we already have
cgroups blkio-controller support today. Therefore I think it makes
sense to keep a unified interface instead of adding a new command.
Agreed.
Proportional controlling interfaces and throttling interfaces are all
the same cgroup subsystem. So Just extend blkiotune to add new options
to support throttling tuning.
Thanks,
Gui
Stefan
8:58 p.m.
New subject: [libvirt] [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt
On Fri, Sep 02, 2011 at 09:16:59AM +0800, Gui Jianfeng wrote:
Message-ID: <4E602E8B.6010900(a)cn.fujitsu.com>
Date: Fri, 02 Sep 2011 09:16:59 +0800
From: Gui Jianfeng <guijianfeng(a)cn.fujitsu.com>
User-Agent: Mozilla/5.0 (Windows NT 5.1; rv:6.0) Gecko/20110812
Thunderbird/6.0
MIME-Version: 1.0
To: Stefan Hajnoczi <stefanha(a)gmail.com>, Zhi Yong Wu
<wuzhy(a)linux.vnet.ibm.com>
References: <20110901050531.GB17963(a)f15.cn.ibm.com>
<20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
In-Reply-To: <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
X-MIMETrack: Itemize by SMTP Server on mailserver/fnst(Release 8.5.1FP4|July
25, 2010) at 2011-09-02 09:15:49, Serialize by Router on
mailserver/fnst(Release 8.5.1FP4|July 25, 2010) at 2011-09-02 09:15:52,
Serialize complete at 2011-09-02 09:15:52
Content-Transfer-Encoding: 7bit
Content-Type: text/plain; charset=ISO-8859-1
X-detected-operating-system: by eggs.gnu.org: FreeBSD 6.x (1)
X-Received-From: 222.73.24.84
Cc: libvir-list(a)redhat.com, hutao(a)cn.fujitsu.com, qemu-devel(a)nongnu.org,
zwu.kernel(a)gmail.com, agl(a)us.ibm.com
Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
libvirt
X-BeenThere: qemu-devel(a)nongnu.org
X-Mailman-Version: 2.1.14
Precedence: list
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: </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>
X-Mailman-Copy: yes
Errors-To: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
Sender: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
X-Brightmail-Tracker: AAAAAA==
X-Xagent-From: guijianfeng(a)cn.fujitsu.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: vmsdvm9.vnet.ibm.com (XAGENTU at VMSDVM9)
On 2011-9-1 16:11, Stefan Hajnoczi wrote:
> On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
>> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>>> On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
>>>> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>>>>> I/O throttling can be applied independently to each -drive attached
to
>>>>> a guest and supports throughput/iops limits. For more information
on
>>>>> this QEMU feature and a comparison with blkio-controller, see Ryan
>>>>> Harper's KVM Forum 2011 presentation:
>>>>
>>>>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>>>>
>>>> From the presentation, it seems that both the cgroups method the the qemu
method
>>>> offer comparable control (assuming a block device) so it might possible
to apply
>>>> either method from the same API in a transparent manner. Am I correct or
are we
>>>> suggesting that the Qemu throttling approach should always be used for
Qemu
>>>> domains?
>>>
>>> QEMU I/O throttling does not provide a proportional share mechanism.
>>> So you cannot assign weights to VMs and let them receive a fraction of
>>> the available disk time. That is only supported by cgroups
>>> blkio-controller because it requires a global view which QEMU does not
>>> have.
>>>
>>> So I think the two are complementary:
>>>
>>> If proportional share should be used on a host block device, use
>>> cgroups blkio-controller.
>>> Otherwise use QEMU I/O throttling.
>> Stefan,
>>
>> Do you agree with introducing one new libvirt command blkiothrottle now?
>> If so, i will work on the code draft to make it work.
>
> No, I think that the blkiotune command should be extended to support
> QEMU I/O throttling. This is not new functionality, we already have
> cgroups blkio-controller support today. Therefore I think it makes
> sense to keep a unified interface instead of adding a new command.
Agreed.
Proportional controlling interfaces and throttling interfaces are all
the same cgroup subsystem. So Just extend blkiotune to add new options
to support throttling tuning.
Hi, Gui,
QEMU block I/O throttling is not relative to cgroup subsystem, i think.
anyway, thanks for your sugguests.
Regards,
Zhi Yong Wu
Thanks,
Gui
>
> Stefan
>
>
9:27 p.m.
New subject: [libvirt] [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt
On 2011-9-2 9:58, Zhi Yong Wu wrote:
On Fri, Sep 02, 2011 at 09:16:59AM +0800, Gui Jianfeng wrote:
> Message-ID: <4E602E8B.6010900(a)cn.fujitsu.com>
> Date: Fri, 02 Sep 2011 09:16:59 +0800
> From: Gui Jianfeng <guijianfeng(a)cn.fujitsu.com>
> User-Agent: Mozilla/5.0 (Windows NT 5.1; rv:6.0) Gecko/20110812
> Thunderbird/6.0
> MIME-Version: 1.0
> To: Stefan Hajnoczi <stefanha(a)gmail.com>, Zhi Yong Wu
> <wuzhy(a)linux.vnet.ibm.com>
> References: <20110901050531.GB17963(a)f15.cn.ibm.com>
> <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
> In-Reply-To: <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
> X-MIMETrack: Itemize by SMTP Server on mailserver/fnst(Release 8.5.1FP4|July
> 25, 2010) at 2011-09-02 09:15:49, Serialize by Router on
> mailserver/fnst(Release 8.5.1FP4|July 25, 2010) at 2011-09-02 09:15:52,
> Serialize complete at 2011-09-02 09:15:52
> Content-Transfer-Encoding: 7bit
> Content-Type: text/plain; charset=ISO-8859-1
> X-detected-operating-system: by eggs.gnu.org: FreeBSD 6.x (1)
> X-Received-From: 222.73.24.84
> Cc: libvir-list(a)redhat.com, hutao(a)cn.fujitsu.com, qemu-devel(a)nongnu.org,
> zwu.kernel(a)gmail.com, agl(a)us.ibm.com
> Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
> libvirt
> X-BeenThere: qemu-devel(a)nongnu.org
> X-Mailman-Version: 2.1.14
> Precedence: list
> 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: </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>
> X-Mailman-Copy: yes
> Errors-To: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
> Sender: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
> X-Brightmail-Tracker: AAAAAA==
> X-Xagent-From: guijianfeng(a)cn.fujitsu.com
> X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
> X-Xagent-Gateway: vmsdvm9.vnet.ibm.com (XAGENTU at VMSDVM9)
>
> On 2011-9-1 16:11, Stefan Hajnoczi wrote:
>> On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
>>> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>>>> On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com>
wrote:
>>>>> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>>>>>> I/O throttling can be applied independently to each -drive
attached to
>>>>>> a guest and supports throughput/iops limits. For more
information on
>>>>>> this QEMU feature and a comparison with blkio-controller, see
Ryan
>>>>>> Harper's KVM Forum 2011 presentation:
>>>>>
>>>>>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>>>>>
>>>>> From the presentation, it seems that both the cgroups method the the
qemu method
>>>>> offer comparable control (assuming a block device) so it might
possible to apply
>>>>> either method from the same API in a transparent manner. Am I
correct or are we
>>>>> suggesting that the Qemu throttling approach should always be used
for Qemu
>>>>> domains?
>>>>
>>>> QEMU I/O throttling does not provide a proportional share mechanism.
>>>> So you cannot assign weights to VMs and let them receive a fraction of
>>>> the available disk time. That is only supported by cgroups
>>>> blkio-controller because it requires a global view which QEMU does not
>>>> have.
>>>>
>>>> So I think the two are complementary:
>>>>
>>>> If proportional share should be used on a host block device, use
>>>> cgroups blkio-controller.
>>>> Otherwise use QEMU I/O throttling.
>>> Stefan,
>>>
>>> Do you agree with introducing one new libvirt command blkiothrottle now?
>>> If so, i will work on the code draft to make it work.
>>
>> No, I think that the blkiotune command should be extended to support
>> QEMU I/O throttling. This is not new functionality, we already have
>> cgroups blkio-controller support today. Therefore I think it makes
>> sense to keep a unified interface instead of adding a new command.
>
> Agreed.
> Proportional controlling interfaces and throttling interfaces are all
> the same cgroup subsystem. So Just extend blkiotune to add new options
> to support throttling tuning.
Hi, Gui,
QEMU block I/O throttling is not relative to cgroup subsystem, i think.
anyway, thanks for your sugguests.
Ahh, I misunderstand you before. I thought you mentioned the blkio cgroup throttling
interfaces.
Ok, I think QEmu I/O throttling has similar semantic with blkio cgroup. So extending
blkiotune command is preferred, IMHO.
Thanks,
Gui
Regards,
Zhi Yong Wu
>
> Thanks,
> Gui
>
>>
>> Stefan
>>
>>
>
>
>
9:09 p.m.
New subject: [libvirt] [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt
On Thu, Sep 01, 2011 at 09:11:49AM +0100, Stefan Hajnoczi wrote:
Date: Thu, 1 Sep 2011 09:11:49 +0100
From: Stefan Hajnoczi <stefanha(a)gmail.com>
To: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>
Message-ID: <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
References: <20110901050531.GB17963(a)f15.cn.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <20110901050531.GB17963(a)f15.cn.ibm.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6 (newer, 2)
X-Received-From: 74.125.82.173
Cc: libvir-list(a)redhat.com, guijianfeng(a)cn.fujitsu.com, agl(a)us.ibm.com,
qemu-devel(a)nongnu.org, zwu.kernel(a)gmail.com, hutao(a)cn.fujitsu.com
Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
libvirt
X-BeenThere: qemu-devel(a)nongnu.org
X-Mailman-Version: 2.1.14
Precedence: list
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: </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>
X-Mailman-Copy: yes
Errors-To: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
Sender: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
x-cbid: 11090108-7282-0000-0000-0000010970B0
X-IBM-ISS-SpamDetectors: Score=0; BY=0; FL=0; FP=0; FZ=0; HX=0; KW=0; PH=0;
SC=0; ST=0; TS=0; UL=0; ISC=
X-IBM-ISS-DetailInfo: BY=3.00000211; HX=3.00000168; KW=3.00000007;
PH=3.00000001; SC=3.00000001; SDB=6.00067104; UDB=6.00020326;
UTC=2011-09-01 08:12:15
X-Xagent-From: stefanha(a)gmail.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: vmsdvm6.vnet.ibm.com (XAGENTU5 at VMSDVM6)
On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
> >On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
> >> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
> >>> I/O throttling can be applied independently to each -drive attached to
> >>> a guest and supports throughput/iops limits. For more information on
> >>> this QEMU feature and a comparison with blkio-controller, see Ryan
> >>> Harper's KVM Forum 2011 presentation:
> >>
> >>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
> >>
> >> From the presentation, it seems that both the cgroups method the the qemu
method
> >> offer comparable control (assuming a block device) so it might possible to
apply
> >> either method from the same API in a transparent manner. Am I correct or
are we
> >> suggesting that the Qemu throttling approach should always be used for Qemu
> >> domains?
> >
> >QEMU I/O throttling does not provide a proportional share mechanism.
> >So you cannot assign weights to VMs and let them receive a fraction of
> >the available disk time. That is only supported by cgroups
> >blkio-controller because it requires a global view which QEMU does not
> >have.
> >
> >So I think the two are complementary:
> >
> >If proportional share should be used on a host block device, use
> >cgroups blkio-controller.
> >Otherwise use QEMU I/O throttling.
> Stefan,
>
> Do you agree with introducing one new libvirt command blkiothrottle now?
> If so, i will work on the code draft to make it work.
No, I think that the blkiotune command should be extended to support
QEMU I/O throttling. This is not new functionality, we already have
cgroups blkio-controller support today. Therefore I think it makes
sense to keep a unified interface instead of adding a new command.
QEMU I/O
throttling currently don't support those options of blkiotune, such as --live,
--config and --current.If those bps/iops settings are modified, it will immediately take
effect.
Regards,
Zhi Yong Wu
Stefan
3:50 a.m.
New subject: [libvirt] [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt
On Fri, Sep 2, 2011 at 3:09 AM, Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com> wrote:
On Thu, Sep 01, 2011 at 09:11:49AM +0100, Stefan Hajnoczi wrote:
>Date: Thu, 1 Sep 2011 09:11:49 +0100
>From: Stefan Hajnoczi <stefanha(a)gmail.com>
>To: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>
>Message-ID: <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
>References: <20110901050531.GB17963(a)f15.cn.ibm.com>
>MIME-Version: 1.0
>Content-Type: text/plain; charset=iso-8859-1
>Content-Disposition: inline
>Content-Transfer-Encoding: 8bit
>In-Reply-To: <20110901050531.GB17963(a)f15.cn.ibm.com>
>User-Agent: Mutt/1.5.21 (2010-09-15)
>X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6 (newer, 2)
>X-Received-From: 74.125.82.173
>Cc: libvir-list(a)redhat.com, guijianfeng(a)cn.fujitsu.com, agl(a)us.ibm.com,
> qemu-devel(a)nongnu.org, zwu.kernel(a)gmail.com, hutao(a)cn.fujitsu.com
>Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
> libvirt
>X-BeenThere: qemu-devel(a)nongnu.org
>X-Mailman-Version: 2.1.14
>Precedence: list
>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: </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>
>X-Mailman-Copy: yes
>Errors-To: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
>Sender: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
>x-cbid: 11090108-7282-0000-0000-0000010970B0
>X-IBM-ISS-SpamDetectors: Score=0; BY=0; FL=0; FP=0; FZ=0; HX=0; KW=0; PH=0;
> SC=0; ST=0; TS=0; UL=0; ISC=
>X-IBM-ISS-DetailInfo: BY=3.00000211; HX=3.00000168; KW=3.00000007;
> PH=3.00000001; SC=3.00000001; SDB=6.00067104; UDB=6.00020326;
> UTC=2011-09-01 08:12:15
>X-Xagent-From: stefanha(a)gmail.com
>X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
>X-Xagent-Gateway: vmsdvm6.vnet.ibm.com (XAGENTU5 at VMSDVM6)
>
>On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
>> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>> >On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
>> >> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>> >>> I/O throttling can be applied independently to each -drive attached
to
>> >>> a guest and supports throughput/iops limits. For more information
on
>> >>> this QEMU feature and a comparison with blkio-controller, see Ryan
>> >>> Harper's KVM Forum 2011 presentation:
>> >>
>> >>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>> >>
>> >> From the presentation, it seems that both the cgroups method the the
qemu method
>> >> offer comparable control (assuming a block device) so it might possible
to apply
>> >> either method from the same API in a transparent manner. Am I correct
or are we
>> >> suggesting that the Qemu throttling approach should always be used for
Qemu
>> >> domains?
>> >
>> >QEMU I/O throttling does not provide a proportional share mechanism.
>> >So you cannot assign weights to VMs and let them receive a fraction of
>> >the available disk time. That is only supported by cgroups
>> >blkio-controller because it requires a global view which QEMU does not
>> >have.
>> >
>> >So I think the two are complementary:
>> >
>> >If proportional share should be used on a host block device, use
>> >cgroups blkio-controller.
>> >Otherwise use QEMU I/O throttling.
>> Stefan,
>>
>> Do you agree with introducing one new libvirt command blkiothrottle now?
>> If so, i will work on the code draft to make it work.
>
>No, I think that the blkiotune command should be extended to support
>QEMU I/O throttling. This is not new functionality, we already have
>cgroups blkio-controller support today. Therefore I think it makes
>sense to keep a unified interface instead of adding a new command.
QEMU I/O throttling currently don't support those options of blkiotune, such as
--live, --config and --current.If those bps/iops settings are modified, it will
immediately take effect.
The --live, --config, and --current options are implemented inside
libvirt and do not require hypervisor support. Take a look at
src/qemu/qemu_driver.c:qemuDomainSetBlkioParameters() to see how these
options are implemented for blkiotune today.
Stefan
4:50 a.m.
New subject: [libvirt] [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt
On Fri, Sep 02, 2011 at 09:50:42AM +0100, Stefan Hajnoczi wrote:
Date: Fri, 2 Sep 2011 09:50:42 +0100
Message-ID: <CAJSP0QWc9OcOKxG3jGgYD3r5f=2Fqv3SNVcrARc2Tm0YmP+gyg(a)mail.gmail.com>
Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
libvirt
From: Stefan Hajnoczi <stefanha(a)gmail.com>
To: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>
Cc: libvir-list(a)redhat.com
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
X-Brightmail-Tracker: AAAAAA==
X-Xagent-From: stefanha(a)gmail.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: vmsdvm4.vnet.ibm.com (XAGENTU5 at VMSDVM4)
On Fri, Sep 2, 2011 at 3:09 AM, Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com> wrote:
> On Thu, Sep 01, 2011 at 09:11:49AM +0100, Stefan Hajnoczi wrote:
>>Date: Thu, 1 Sep 2011 09:11:49 +0100
>>From: Stefan Hajnoczi <stefanha(a)gmail.com>
>>To: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>
>>Message-ID: <20110901081149.GB14245(a)stefanha-thinkpad.localdomain>
>>References: <20110901050531.GB17963(a)f15.cn.ibm.com>
>>MIME-Version: 1.0
>>Content-Type: text/plain; charset=iso-8859-1
>>Content-Disposition: inline
>>Content-Transfer-Encoding: 8bit
>>In-Reply-To: <20110901050531.GB17963(a)f15.cn.ibm.com>
>>User-Agent: Mutt/1.5.21 (2010-09-15)
>>X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.6 (newer, 2)
>>X-Received-From: 74.125.82.173
>>Cc: libvir-list(a)redhat.com, guijianfeng(a)cn.fujitsu.com, agl(a)us.ibm.com,
>> qemu-devel(a)nongnu.org, zwu.kernel(a)gmail.com, hutao(a)cn.fujitsu.com
>>Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
>> libvirt
>>X-BeenThere: qemu-devel(a)nongnu.org
>>X-Mailman-Version: 2.1.14
>>Precedence: list
>>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: </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>
>>X-Mailman-Copy: yes
>>Errors-To: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
>>Sender: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com(a)nongnu.org
>>x-cbid: 11090108-7282-0000-0000-0000010970B0
>>X-IBM-ISS-SpamDetectors: Score=0; BY=0; FL=0; FP=0; FZ=0; HX=0; KW=0; PH=0;
>> SC=0; ST=0; TS=0; UL=0; ISC=
>>X-IBM-ISS-DetailInfo: BY=3.00000211; HX=3.00000168; KW=3.00000007;
>> PH=3.00000001; SC=3.00000001; SDB=6.00067104; UDB=6.00020326;
>> UTC=2011-09-01 08:12:15
>>X-Xagent-From: stefanha(a)gmail.com
>>X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
>>X-Xagent-Gateway: vmsdvm6.vnet.ibm.com (XAGENTU5 at VMSDVM6)
>>
>>On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
>>> On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>>> >On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com>
wrote:
>>> >> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>>> >>> I/O throttling can be applied independently to each -drive
attached to
>>> >>> a guest and supports throughput/iops limits. For more
information on
>>> >>> this QEMU feature and a comparison with blkio-controller, see
Ryan
>>> >>> Harper's KVM Forum 2011 presentation:
>>> >>
>>> >>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>>> >>
>>> >> From the presentation, it seems that both the cgroups method the the
qemu method
>>> >> offer comparable control (assuming a block device) so it might
possible to apply
>>> >> either method from the same API in a transparent manner. Am I
correct or are we
>>> >> suggesting that the Qemu throttling approach should always be used
for Qemu
>>> >> domains?
>>> >
>>> >QEMU I/O throttling does not provide a proportional share mechanism.
>>> >So you cannot assign weights to VMs and let them receive a fraction of
>>> >the available disk time. That is only supported by cgroups
>>> >blkio-controller because it requires a global view which QEMU does not
>>> >have.
>>> >
>>> >So I think the two are complementary:
>>> >
>>> >If proportional share should be used on a host block device, use
>>> >cgroups blkio-controller.
>>> >Otherwise use QEMU I/O throttling.
>>> Stefan,
>>>
>>> Do you agree with introducing one new libvirt command blkiothrottle now?
>>> If so, i will work on the code draft to make it work.
>>
>>No, I think that the blkiotune command should be extended to support
>>QEMU I/O throttling. This is not new functionality, we already have
>>cgroups blkio-controller support today. Therefore I think it makes
>>sense to keep a unified interface instead of adding a new command.
> QEMU I/O throttling currently don't support those options of blkiotune, such as
--live, --config and --current.If those bps/iops settings are modified, it will
immediately take effect.
The --live, --config, and --current options are implemented inside
libvirt and do not require hypervisor support. Take a look at
src/qemu/qemu_driver.c:qemuDomainSetBlkioParameters() to see how these
options are implemented for blkiotune today.
I have understood this, thanks.
BTW: i have seen your comments against block I/O throttling patchset, and will respond
next week.
Regards,
Zhi Yong Wu
Stefan
9:14 p.m.
On Thu, Sep 01, 2011 at 01:05:31PM +0800, Zhi Yong Wu wrote:
----- Forwarded message from Zhi Yong Wu
<wuzhy(a)linux.vnet.ibm.com> -----
Date: Thu, 1 Sep 2011 11:55:17 +0800
From: Zhi Yong Wu <wuzhy(a)linux.vnet.ibm.com>
To: Stefan Hajnoczi <stefanha(a)gmail.com>
Cc: "Daniel P. Berrange" <berrange(a)redhat.com>, Stefan Hajnoczi
<stefanha(a)gmail.com>, Adam Litke <agl(a)us.ibm.com>, Zhi Yong Wu
<wuzhy(a)linux.vnet.ibm.com>, QEMU Developers <qemu-devel(a)nongnu.org>,
guijianfeng(a)cn.fujitsu.com, hutao(a)cn.fujitsu.com
Subject: [RFC] block I/O throttling: how to enable in libvirt
Message-ID: <20110901035517.GD16985(a)f15.cn.ibm.com>
References: <CAEH94Li_C=BOe2gV8NyM48njYWMBAo9MTGc1eUOh-Y=cODs6VA(a)mail.gmail.com>
<CAJSP0QW1CPCokX=F5z7y==vn1S4wH0VtOaQ7oj4kC7f7uQM4MQ(a)mail.gmail.com>
<20110830134636.GB29130(a)aglitke.rchland.ibm.com>
<CAJSP0QUHm=y8XJC_KXRg7ufFZt3K_XDDfQb--sxjC+c0GjO8qg(a)mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <CAJSP0QUHm=y8XJC_KXRg7ufFZt3K_XDDfQb--sxjC+c0GjO8qg(a)mail.gmail.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
X-Xagent-From: wuzhy(a)linux.vnet.ibm.com
X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
X-Xagent-Gateway: vmsdvma.vnet.ibm.com (XAGENTU7 at VMSDVMA)
On Wed, Aug 31, 2011 at 08:18:19AM +0100, Stefan Hajnoczi wrote:
>Subject: Re: The design choice for how to enable block I/O throttling
> function in libvirt
>From: Stefan Hajnoczi <stefanha(a)gmail.com>
>To: Adam Litke <agl(a)us.ibm.com>
>Cc: libvir-list(a)redhat.com, "Daniel P. Berrange"
<berrange(a)redhat.com>, Zhi
> Yong Wu <wuzhy(a)linux.vnet.ibm.com>, Zhi Yong Wu <zwu.kernel(a)gmail.com>
>Content-Type: text/plain; charset=ISO-8859-1
>Content-Transfer-Encoding: quoted-printable
>X-Brightmail-Tracker: AAAAAA==
>X-Xagent-From: stefanha(a)gmail.com
>X-Xagent-To: wuzhy(a)linux.vnet.ibm.com
>X-Xagent-Gateway: bldgate.vnet.ibm.com (XAGENTU7 at BLDGATE)
>
>On Tue, Aug 30, 2011 at 2:46 PM, Adam Litke <agl(a)us.ibm.com> wrote:
>> On Tue, Aug 30, 2011 at 09:53:33AM +0100, Stefan Hajnoczi wrote:
>>> On Tue, Aug 30, 2011 at 3:55 AM, Zhi Yong Wu <zwu.kernel(a)gmail.com>
wrote:
>>> > I am trying to enable block I/O throttling function in libvirt. But
>>> > currently i met some design questions, and don't make sure if we
>>> > should extend blkiotune to support block I/O throttling or introduce
>>> > one new libvirt command "blkiothrottle" to cover it or not. If
you
>>> > have some better idea, pls don't hesitate to drop your comments.
>>>
>>> A little bit of context: this discussion is about adding libvirt
>>> support for QEMU disk I/O throttling.
>>
>> Thanks for the additional context Stefan.
>>
>>> Today libvirt supports the cgroups blkio-controller, which handles
>>> proportional shares and throughput/iops limits on host block devices.
>>> blkio-controller does not support network file systems (NFS) or other
>>> QEMU remote block drivers (curl, Ceph/rbd, sheepdog) since they are
>>> not host block devices. QEMU I/O throttling works with all types of
>>> -drive and therefore complements blkio-controller.
>>
>> The first question that pops into my mind is: Should a user need to understand
>> when to use the cgroups blkio-controller vs. the QEMU I/O throttling method? In
>> my opinion, it would be nice if libvirt had a single interface for block I/O
>> throttling and libvirt would decide which mechanism to use based on the type of
>> device and the specific limits that need to be set.
>
>Yes, I agree it would be simplest to pick the right mechanism,
>depending on the type of throttling the user wants. More below.
>
>>> I/O throttling can be applied independently to each -drive attached to
>>> a guest and supports throughput/iops limits. For more information on
>>> this QEMU feature and a comparison with blkio-controller, see Ryan
>>> Harper's KVM Forum 2011 presentation:
>>
>>>
http://www.linux-kvm.org/wiki/images/7/72/2011-forum-keep-a-limit-on-it-i...
>>
>> From the presentation, it seems that both the cgroups method the the qemu method
>> offer comparable control (assuming a block device) so it might possible to apply
>> either method from the same API in a transparent manner. Am I correct or are we
>> suggesting that the Qemu throttling approach should always be used for Qemu
>> domains?
>
>QEMU I/O throttling does not provide a proportional share mechanism.
>So you cannot assign weights to VMs and let them receive a fraction of
>the available disk time. That is only supported by cgroups
>blkio-controller because it requires a global view which QEMU does not
>have.
>
>So I think the two are complementary:
>
>If proportional share should be used on a host block device, use
>cgroups blkio-controller.
>Otherwise use QEMU I/O throttling.
Stefan,
Do you agree with introducing one new libvirt command blkiothrottle now?
If so, i will work on the code draft to make it work.
Daniel and other maintainers,
If you are available, can you make some comments for us?:)
HI, Adam,
Now stefan, Daniel, and Gui all suggest extending blkiotune to keep libivrt unified
interface. What do you think of it?
Regards,
Zhi Yong Wu
Regards,
Zhi Yong Wu
>
>Stefan
----- End forwarded message -----
--
libvir-list mailing list
libvir-list(a)redhat.com
https://www.redhat.com/mailman/listinfo/libvir-list
4830
days inactive
4831
days old
10 comments
4 participants
participants (4)
-
Daniel P. Berrange -
Gui Jianfeng -
Stefan Hajnoczi -
Zhi Yong Wu