[Qemu-devel] The design choice for how to enable block I/O throttling function in libvirt

[Qemu-devel] The design choice for how to enable block I/O throttling function in libvirt

[Zhi Yong Wu]

HI, folks,

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.

If one new libvirt command "blkiothrottle" is introduced, I plan to
design its usage syntax as below:

virsh # help blkiothrottle
  NAME
    blkiothrottle - Set or display a block disk I/O throttle setting.

  SYNOPSIS
    blkiothrottle <domain> <device> [--bps <number>] [--bps_rd
<number>] [--bps_wr <number>] [--iops <number>] [--iops_rd <number>]
[--iops_wr <number>]

  DESCRIPTION
    Set or display a block disk I/O throttle setting.

  OPTIONS
    [--domain] <string>  domain name, id or uuid
    [--device] <string>  block device
    --bps <number>   total throughput limits in bytes/s
    --bps_rd <number>  read throughput limits in bytes/s
    --bps_wr <number>  write throughput limits in bytes/s
    --iops <number>  total operation limits in numbers/s
    --iops_rd <number>  read operation limits in numbers/s
    --iops_wr <number>  write operation limits in numbers/s


virsh #

2.) If blkiotune command is extended to enable block I/O throttling function.

virsh # help blkiotune
  NAME
    blkiotune - Get or set blkio parameters

  SYNOPSIS
    blkiotune <domain> [--weight <number>] [--config] [--live]
[--current] [--bps <number>] [--bps_rd <number>] [--bps_wr <number>]
[--iops <number>] [--iops_rd <number>] [--iops_wr <number>]

  DESCRIPTION
    Get or set the current blkio parameters for a guest domain.
    To get the blkio parameters use following command:

    virsh # blkiotune <domain>

  OPTIONS
    [--domain] <string>  domain name, id or uuid
    --weight <number>  IO Weight in range [100, 1000]
    --config         affect next boot
    --live           affect running domain
    --current        affect current domain

Welcome to your suggestions or comments about how to choose it. thanks.

-- 
Regards,

Zhi Yong Wu

Re: [Qemu-devel] [libvirt] The design choice for how to enable block I/O throttling function in libvirt

[shu ming]

See commens below.
Zhi Yong Wu:
> HI, folks,
>
> 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.
>
> If one new libvirt command "blkiothrottle" is introduced, I plan to
> design its usage syntax as below:
>
> virsh # help blkiothrottle
>    NAME
>      blkiothrottle - Set or display a block disk I/O throttle setting.
>
>    SYNOPSIS
>      blkiothrottle<domain>  <device>  [--bps<number>] [--bps_rd
> <number>] [--bps_wr<number>] [--iops<number>] [--iops_rd<number>]
> [--iops_wr<number>]
>
>    DESCRIPTION
>      Set or display a block disk I/O throttle setting.
>
>    OPTIONS
>      [--domain]<string>   domain name, id or uuid
>      [--device]<string>   block device
>      --bps<number>    total throughput limits in bytes/s
>      --bps_rd<number>   read throughput limits in bytes/s
>      --bps_wr<number>   write throughput limits in bytes/s
>      --iops<number>   total operation limits in numbers/s
>      --iops_rd<number>   read operation limits in numbers/s
>      --iops_wr<number>   write operation limits in numbers/s
>

How to display the current I/O throttle setting of a specific block 
device here?
I prfer to have less command to be as simple as possible for users.  But 
it seems
that we need another command here instead of having a block IO specific 
command like "iothrottle".
Supposely,  the next step of I/O throttling will be network device 
limit.  Shoud we have another
new command like "niciothrottle"?

Re: [Qemu-devel] [libvirt] The design choice for how to enable block I/O throttling function in libvirt

[Zhi Yong Wu]

On Tue, Aug 30, 2011 at 3:18 PM, shu ming <shuming@linux.vnet.ibm.com> wrote:
> See commens below.
> Zhi Yong Wu:
>>
>> HI, folks,
>>
>> 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.
>>
>> If one new libvirt command "blkiothrottle" is introduced, I plan to
>> design its usage syntax as below:
>>
>> virsh # help blkiothrottle
>>   NAME
>>     blkiothrottle - Set or display a block disk I/O throttle setting.
>>
>>   SYNOPSIS
>>     blkiothrottle<domain>  <device>  [--bps<number>] [--bps_rd
>> <number>] [--bps_wr<number>] [--iops<number>] [--iops_rd<number>]
>> [--iops_wr<number>]
>>
>>   DESCRIPTION
>>     Set or display a block disk I/O throttle setting.
>>
>>   OPTIONS
>>     [--domain]<string>   domain name, id or uuid
>>     [--device]<string>   block device
>>     --bps<number>    total throughput limits in bytes/s
>>     --bps_rd<number>   read throughput limits in bytes/s
>>     --bps_wr<number>   write throughput limits in bytes/s
>>     --iops<number>   total operation limits in numbers/s
>>     --iops_rd<number>   read operation limits in numbers/s
>>     --iops_wr<number>   write operation limits in numbers/s
>>
>
> How to display the current I/O throttle setting of a specific block device
> here?
It will show as below:
virtio0: bps=xxx, bps_rd=xxx, bps_wr=xxx, iops=xxx, iops_rd=xxx, iops_wr=xxx.

> I prfer to have less command to be as simple as possible for users.  But it
> seems
> that we need another command here instead of having a block IO specific
> command like "iothrottle".
I also prefer this, but would like to get other guy's suggestions,
especially maintainers.

> Supposely,  the next step of I/O throttling will be network device limit.
>  Shoud we have another
> new command like "niciothrottle"?
For network device, network cgroup can cover this.
>
>
>



-- 
Regards,

Zhi Yong Wu

Re: [Qemu-devel] [libvirt] The design choice for how to enable block I/O throttling function in libvirt

[shu ming]

Zhi Yong Wu:
> On Tue, Aug 30, 2011 at 3:18 PM, shu ming<shuming@linux.vnet.ibm.com>  wrote:
>> See commens below.
>> Zhi Yong Wu:
>>> HI, folks,
>>>
>>> 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.
>>>
>>> If one new libvirt command "blkiothrottle" is introduced, I plan to
>>> design its usage syntax as below:
>>>
>>> virsh # help blkiothrottle
>>>    NAME
>>>      blkiothrottle - Set or display a block disk I/O throttle setting.
>>>
>>>    SYNOPSIS
>>>      blkiothrottle<domain>    <device>    [--bps<number>] [--bps_rd
>>> <number>] [--bps_wr<number>] [--iops<number>] [--iops_rd<number>]
>>> [--iops_wr<number>]
>>>
>>>    DESCRIPTION
>>>      Set or display a block disk I/O throttle setting.
>>>
>>>    OPTIONS
>>>      [--domain]<string>     domain name, id or uuid
>>>      [--device]<string>     block device
>>>      --bps<number>      total throughput limits in bytes/s
>>>      --bps_rd<number>     read throughput limits in bytes/s
>>>      --bps_wr<number>     write throughput limits in bytes/s
>>>      --iops<number>     total operation limits in numbers/s
>>>      --iops_rd<number>     read operation limits in numbers/s
>>>      --iops_wr<number>     write operation limits in numbers/s
>>>
>> How to display the current I/O throttle setting of a specific block device
>> here?
> It will show as below:
> virtio0: bps=xxx, bps_rd=xxx, bps_wr=xxx, iops=xxx, iops_rd=xxx, iops_wr=xxx.

With which options to the command?  I guess "blkiothrottle <domain> 
<device>" will display the current setting.

Re: [Qemu-devel] [libvirt] The design choice for how to enable block I/O throttling function in libvirt

[Zhi Yong Wu]

On Tue, Aug 30, 2011 at 4:31 PM, shu ming <shuming@linux.vnet.ibm.com> wrote:
> Zhi Yong Wu:
>>
>> On Tue, Aug 30, 2011 at 3:18 PM, shu ming<shuming@linux.vnet.ibm.com>
>>  wrote:
>>>
>>> See commens below.
>>> Zhi Yong Wu:
>>>>
>>>> HI, folks,
>>>>
>>>> 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.
>>>>
>>>> If one new libvirt command "blkiothrottle" is introduced, I plan to
>>>> design its usage syntax as below:
>>>>
>>>> virsh # help blkiothrottle
>>>>   NAME
>>>>     blkiothrottle - Set or display a block disk I/O throttle setting.
>>>>
>>>>   SYNOPSIS
>>>>     blkiothrottle<domain>    <device>    [--bps<number>] [--bps_rd
>>>> <number>] [--bps_wr<number>] [--iops<number>] [--iops_rd<number>]
>>>> [--iops_wr<number>]
>>>>
>>>>   DESCRIPTION
>>>>     Set or display a block disk I/O throttle setting.
>>>>
>>>>   OPTIONS
>>>>     [--domain]<string>     domain name, id or uuid
>>>>     [--device]<string>     block device
>>>>     --bps<number>      total throughput limits in bytes/s
>>>>     --bps_rd<number>     read throughput limits in bytes/s
>>>>     --bps_wr<number>     write throughput limits in bytes/s
>>>>     --iops<number>     total operation limits in numbers/s
>>>>     --iops_rd<number>     read operation limits in numbers/s
>>>>     --iops_wr<number>     write operation limits in numbers/s
>>>>
>>> How to display the current I/O throttle setting of a specific block
>>> device
>>> here?
>>
>> It will show as below:
>> virtio0: bps=xxx, bps_rd=xxx, bps_wr=xxx, iops=xxx, iops_rd=xxx,
>> iops_wr=xxx.
>
> With which options to the command?  I guess "blkiothrottle <domain>
> <device>" will display the current setting.
Right

>
>
>



-- 
Regards,

Zhi Yong Wu

[Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt

[Zhi Yong Wu]

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@gmail.com>
>To: Adam Litke <agl@us.ibm.com>
>Cc: libvir-list@redhat.com, "Daniel P. Berrange" <berrange@redhat.com>, Zhi
> Yong Wu <wuzhy@linux.vnet.ibm.com>, Zhi Yong Wu <zwu.kernel@gmail.com>
>Content-Type: text/plain; charset=ISO-8859-1
>Content-Transfer-Encoding: quoted-printable
>X-Brightmail-Tracker: AAAAAA==
>X-Xagent-From: stefanha@gmail.com
>X-Xagent-To: wuzhy@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@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@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-io-throttling-in-qemu.pdf
>>
>> 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.

Danial and other maintainers,

If you are available, can you make some comments for us?:)


Regards,

Zhi Yong Wu
>
>Stefan

Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt

[Osier Yang]

于 2011年09月01日 11:55, Zhi Yong Wu 写道:
> 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@gmail.com>
>> To: Adam Litke<agl@us.ibm.com>
>> Cc: libvir-list@redhat.com, "Daniel P. Berrange"<berrange@redhat.com>, Zhi
>> Yong Wu<wuzhy@linux.vnet.ibm.com>, Zhi Yong Wu<zwu.kernel@gmail.com>
>> Content-Type: text/plain; charset=ISO-8859-1
>> Content-Transfer-Encoding: quoted-printable
>> X-Brightmail-Tracker: AAAAAA==
>> X-Xagent-From: stefanha@gmail.com
>> X-Xagent-To: wuzhy@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@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@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-io-throttling-in-qemu.pdf
>>>  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.
>
> Danial and other maintainers,
>
> If you are available, can you make some comments for us?:)

Seems you posted to wrong list? This should be discussed in libvir-list
instead.

And if you meant to post to libvir-list, then s/Danial/Daniel/  :-)

>
> Regards,
>
> Zhi Yong Wu
>> Stefan

Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in libvirt

[Zhi Yong Wu]

On Thu, Sep 01, 2011 at 12:21:20PM +0800, Osier Yang wrote:
>Message-ID: <4E5F0840.5010203@redhat.com>
>Date: Thu, 01 Sep 2011 12:21:20 +0800
>From: Osier Yang <jyang@redhat.com>
>User-Agent: Mozilla/5.0 (X11; Linux x86_64;	rv:6.0) Gecko/20110816
> Thunderbird/6.0
>MIME-Version: 1.0
>To: Zhi Yong Wu <wuzhy@linux.vnet.ibm.com>
>References: <CAEH94Li_C=BOe2gV8NyM48njYWMBAo9MTGc1eUOh-Y=cODs6VA@mail.gmail.com>
> <CAJSP0QW1CPCokX=F5z7y==vn1S4wH0VtOaQ7oj4kC7f7uQM4MQ@mail.gmail.com>
> <20110830134636.GB29130@aglitke.rchland.ibm.com>
> <CAJSP0QUHm=y8XJC_KXRg7ufFZt3K_XDDfQb--sxjC+c0GjO8qg@mail.gmail.com>
> <20110901035517.GD16985@f15.cn.ibm.com>
>In-Reply-To: <20110901035517.GD16985@f15.cn.ibm.com>
>Content-Type: text/plain; charset=UTF-8; format=flowed
>X-Scanned-By: MIMEDefang 2.67 on 10.5.11.12
>Content-Transfer-Encoding: quoted-printable
>X-MIME-Autoconverted: from 8bit to quoted-printable by mx1.redhat.com id
> p814MA7o029817
>X-detected-operating-system: by eggs.gnu.org: Genre and OS details not
> recognized.
>X-Received-From: 209.132.183.28
>Cc: Stefan Hajnoczi <stefanha@gmail.com>, Adam Litke <agl@us.ibm.com>, QEMU
> Developers <qemu-devel@nongnu.org>, guijianfeng@cn.fujitsu.com,
> hutao@cn.fujitsu.com
>Subject: Re: [Qemu-devel] [RFC] block I/O throttling: how to enable in
>	libvirt
>X-BeenThere: qemu-devel@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: <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>
>X-Mailman-Copy: yes
>Errors-To: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com@nongnu.org
>Sender: qemu-devel-bounces+wuzhy=linux.vnet.ibm.com@nongnu.org
>X-Brightmail-Tracker: AAAAAA==
>X-Xagent-From: jyang@redhat.com
>X-Xagent-To: wuzhy@linux.vnet.ibm.com
>X-Xagent-Gateway: vmsdvma.vnet.ibm.com (XAGENTU6 at VMSDVMA)
>
>于 2011年09月01日 11:55, Zhi Yong Wu 写道:
>>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@gmail.com>
>>>To: Adam Litke<agl@us.ibm.com>
>>>Cc: libvir-list@redhat.com, "Daniel P. Berrange"<berrange@redhat.com>, Zhi
>>>Yong Wu<wuzhy@linux.vnet.ibm.com>, Zhi Yong Wu<zwu.kernel@gmail.com>
>>>Content-Type: text/plain; charset=ISO-8859-1
>>>Content-Transfer-Encoding: quoted-printable
>>>X-Brightmail-Tracker: AAAAAA==
>>>X-Xagent-From: stefanha@gmail.com
>>>X-Xagent-To: wuzhy@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@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@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-io-throttling-in-qemu.pdf
>>>> 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.
>>
>>Danial and other maintainers,
>>
>>If you are available, can you make some comments for us?:)
>
>Seems you posted to wrong list? This should be discussed in libvir-list
>instead.
No, libvirt-list is where i want to post.
>
>And if you meant to post to libvir-list, then s/Danial/Daniel/  :-)
Sorry, thanks for your correcting, Jintao. We have not met for several years.
>
>>
>>Regards,
>>
>>Zhi Yong Wu
>>>Stefan
>
>