DPDK patches and discussions
 help / color / mirror / Atom feed
* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
@ 2014-08-26 11:05 Xie, Huawei
  2014-08-27  0:43 ` Ouyang, Changchun
  2014-09-13  5:27 ` Linhaifeng
  0 siblings, 2 replies; 12+ messages in thread
From: Xie, Huawei @ 2014-08-26 11:05 UTC (permalink / raw)
  To: dev

Hi all:
We are implementing qemu official vhost-user interface into DPDK vhost library, so there would be two coexisting implementations for user space vhost backend.
Pro and cons in my mind:
Existing solution:
Pros:  works with qemu version before 2.1;  Cons: depends on eventfd proxy kernel module and extra maintenance effort
Qemu vhost-user:
               Pros:  qemu official us-vhost interface;     Cons: only available after qemu 2.1

BR.
huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-26 11:05 [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library Xie, Huawei
@ 2014-08-27  0:43 ` Ouyang, Changchun
  2014-08-27  4:39   ` Tetsuya.Mukawa
  2014-09-13  5:27 ` Linhaifeng
  1 sibling, 1 reply; 12+ messages in thread
From: Ouyang, Changchun @ 2014-08-27  0:43 UTC (permalink / raw)
  To: Xie, Huawei, dev

Do we have performance comparison between both implementation?
Thanks
Changchun


-----Original Message-----
From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
Sent: Tuesday, August 26, 2014 7:06 PM
To: dev@dpdk.org
Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library

Hi all:
We are implementing qemu official vhost-user interface into DPDK vhost library, so there would be two coexisting implementations for user space vhost backend.
Pro and cons in my mind:
Existing solution:
Pros:  works with qemu version before 2.1;  Cons: depends on eventfd proxy kernel module and extra maintenance effort Qemu vhost-user:
               Pros:  qemu official us-vhost interface;     Cons: only available after qemu 2.1

BR.
huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  0:43 ` Ouyang, Changchun
@ 2014-08-27  4:39   ` Tetsuya.Mukawa
  2014-08-27  5:01     ` Ouyang, Changchun
  0 siblings, 1 reply; 12+ messages in thread
From: Tetsuya.Mukawa @ 2014-08-27  4:39 UTC (permalink / raw)
  To: Ouyang, Changchun, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani


(2014/08/27 9:43), Ouyang, Changchun wrote:
> Do we have performance comparison between both implementation?
Hi Changchun,

If DPDK applications are running on both guest and host side, the
performance should be almost same, because while transmitting data virt
queues are accessed by virtio-net PMD and libvhost. In libvhost, the
existing vhost implementation and a vhost-user implementation will
shares or uses same code to access virt queues. So I guess the
performance will be almost same.

Thanks,
Tetsuya


> Thanks
> Changchun
>
>
> -----Original Message-----
> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
> Sent: Tuesday, August 26, 2014 7:06 PM
> To: dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
>
> Hi all:
> We are implementing qemu official vhost-user interface into DPDK vhost library, so there would be two coexisting implementations for user space vhost backend.
> Pro and cons in my mind:
> Existing solution:
> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd proxy kernel module and extra maintenance effort Qemu vhost-user:
>                Pros:  qemu official us-vhost interface;     Cons: only available after qemu 2.1
>
> BR.
> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  4:39   ` Tetsuya.Mukawa
@ 2014-08-27  5:01     ` Ouyang, Changchun
  2014-08-27  5:27       ` Tetsuya.Mukawa
  0 siblings, 1 reply; 12+ messages in thread
From: Ouyang, Changchun @ 2014-08-27  5:01 UTC (permalink / raw)
  To: Tetsuya.Mukawa, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani

Hi Tetsuya

Thanks for your response.
Agree with you, the performance should be same as the data path (RX/TX) is not affected,
The difference between implementation only exists in the virtio device creation and destroy stage.

Regards,
Changchun

> -----Original Message-----
> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
> Sent: Wednesday, August 27, 2014 12:39 PM
> To: Ouyang, Changchun; dev@dpdk.org
> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
> Hitoshi Masutani
> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
> DPDK vhost library
> 
> 
> (2014/08/27 9:43), Ouyang, Changchun wrote:
> > Do we have performance comparison between both implementation?
> Hi Changchun,
> 
> If DPDK applications are running on both guest and host side, the
> performance should be almost same, because while transmitting data virt
> queues are accessed by virtio-net PMD and libvhost. In libvhost, the existing
> vhost implementation and a vhost-user implementation will shares or uses
> same code to access virt queues. So I guess the performance will be almost
> same.
> 
> Thanks,
> Tetsuya
> 
> 
> > Thanks
> > Changchun
> >
> >
> > -----Original Message-----
> > From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
> > Sent: Tuesday, August 26, 2014 7:06 PM
> > To: dev@dpdk.org
> > Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
> > support into DPDK vhost library
> >
> > Hi all:
> > We are implementing qemu official vhost-user interface into DPDK vhost
> library, so there would be two coexisting implementations for user space
> vhost backend.
> > Pro and cons in my mind:
> > Existing solution:
> > Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
> proxy kernel module and extra maintenance effort Qemu vhost-user:
> >                Pros:  qemu official us-vhost interface;     Cons: only available after
> qemu 2.1
> >
> > BR.
> > huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  5:01     ` Ouyang, Changchun
@ 2014-08-27  5:27       ` Tetsuya.Mukawa
  2014-08-27  5:56         ` Xie, Huawei
                           ` (2 more replies)
  0 siblings, 3 replies; 12+ messages in thread
From: Tetsuya.Mukawa @ 2014-08-27  5:27 UTC (permalink / raw)
  To: Ouyang, Changchun, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani

Hi Changchun,

(2014/08/27 14:01), Ouyang, Changchun wrote:
> Agree with you, the performance should be same as the data path (RX/TX) is not affected,
> The difference between implementation only exists in the virtio device creation and destroy stage.
Yes, I agree. Also There may be the difference, if a virtio-net driver
on a guest isn't poll mode like a virtio-net device driver in the
kernel. In the case, existing vhost implementation uses the eventfd
kernel module, and vhost-user implementation uses eventfd to kick the
driver. So I guess there will be the difference.

Anyway, about device creation and destruction, the difference will come
from transmission speed between unix domain socket and CUSE. I am not
sure which is faster.

Thanks,
Tetsuya


>
> Regards,
> Changchun
>
>> -----Original Message-----
>> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
>> Sent: Wednesday, August 27, 2014 12:39 PM
>> To: Ouyang, Changchun; dev@dpdk.org
>> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
>> Hitoshi Masutani
>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
>> DPDK vhost library
>>
>>
>> (2014/08/27 9:43), Ouyang, Changchun wrote:
>>> Do we have performance comparison between both implementation?
>> Hi Changchun,
>>
>> If DPDK applications are running on both guest and host side, the
>> performance should be almost same, because while transmitting data virt
>> queues are accessed by virtio-net PMD and libvhost. In libvhost, the existing
>> vhost implementation and a vhost-user implementation will shares or uses
>> same code to access virt queues. So I guess the performance will be almost
>> same.
>>
>> Thanks,
>> Tetsuya
>>
>>
>>> Thanks
>>> Changchun
>>>
>>>
>>> -----Original Message-----
>>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
>>> Sent: Tuesday, August 26, 2014 7:06 PM
>>> To: dev@dpdk.org
>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
>>> support into DPDK vhost library
>>>
>>> Hi all:
>>> We are implementing qemu official vhost-user interface into DPDK vhost
>> library, so there would be two coexisting implementations for user space
>> vhost backend.
>>> Pro and cons in my mind:
>>> Existing solution:
>>> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
>> proxy kernel module and extra maintenance effort Qemu vhost-user:
>>>                Pros:  qemu official us-vhost interface;     Cons: only available after
>> qemu 2.1
>>> BR.
>>> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  5:27       ` Tetsuya.Mukawa
@ 2014-08-27  5:56         ` Xie, Huawei
  2014-08-27  6:07           ` Tetsuya.Mukawa
  2014-08-27  5:58         ` Tetsuya.Mukawa
  2014-08-27  6:00         ` Ouyang, Changchun
  2 siblings, 1 reply; 12+ messages in thread
From: Xie, Huawei @ 2014-08-27  5:56 UTC (permalink / raw)
  To: Tetsuya.Mukawa, Ouyang, Changchun, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani



> -----Original Message-----
> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
> Sent: Wednesday, August 27, 2014 1:28 PM
> To: Ouyang, Changchun; dev@dpdk.org
> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
> Hitoshi Masutani
> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
> DPDK vhost library
> 
> Hi Changchun,
> 
> (2014/08/27 14:01), Ouyang, Changchun wrote:
> > Agree with you, the performance should be same as the data path (RX/TX) is
> not affected,
> > The difference between implementation only exists in the virtio device
> creation and destroy stage.
> Yes, I agree. Also There may be the difference, if a virtio-net driver
> on a guest isn't poll mode like a virtio-net device driver in the
> kernel. In the case, existing vhost implementation uses the eventfd
> kernel module, and vhost-user implementation uses eventfd to kick the
> driver. So I guess there will be the difference.
For virtio-net device driver, there is still no difference. Existing solution creates an eventfd module to install a fd in DPDK process pointing to the eventfd in qemu process. In vhost-user, the UNIX domain socket will do that work, create a new fd, install it in target DPDK server process, and make it point to the eventfd in qemu process.
> 
> Anyway, about device creation and destruction, the difference will come
> from transmission speed between unix domain socket and CUSE. I am not
> sure which is faster.
> 
> Thanks,
> Tetsuya
> 
> 
> >
> > Regards,
> > Changchun
> >
> >> -----Original Message-----
> >> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
> >> Sent: Wednesday, August 27, 2014 12:39 PM
> >> To: Ouyang, Changchun; dev@dpdk.org
> >> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
> >> Hitoshi Masutani
> >> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
> >> DPDK vhost library
> >>
> >>
> >> (2014/08/27 9:43), Ouyang, Changchun wrote:
> >>> Do we have performance comparison between both implementation?
> >> Hi Changchun,
> >>
> >> If DPDK applications are running on both guest and host side, the
> >> performance should be almost same, because while transmitting data virt
> >> queues are accessed by virtio-net PMD and libvhost. In libvhost, the existing
> >> vhost implementation and a vhost-user implementation will shares or uses
> >> same code to access virt queues. So I guess the performance will be almost
> >> same.
> >>
> >> Thanks,
> >> Tetsuya
> >>
> >>
> >>> Thanks
> >>> Changchun
> >>>
> >>>
> >>> -----Original Message-----
> >>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
> >>> Sent: Tuesday, August 26, 2014 7:06 PM
> >>> To: dev@dpdk.org
> >>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
> >>> support into DPDK vhost library
> >>>
> >>> Hi all:
> >>> We are implementing qemu official vhost-user interface into DPDK vhost
> >> library, so there would be two coexisting implementations for user space
> >> vhost backend.
> >>> Pro and cons in my mind:
> >>> Existing solution:
> >>> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
> >> proxy kernel module and extra maintenance effort Qemu vhost-user:
> >>>                Pros:  qemu official us-vhost interface;     Cons: only available after
> >> qemu 2.1
> >>> BR.
> >>> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  5:27       ` Tetsuya.Mukawa
  2014-08-27  5:56         ` Xie, Huawei
@ 2014-08-27  5:58         ` Tetsuya.Mukawa
  2014-08-27  6:00         ` Ouyang, Changchun
  2 siblings, 0 replies; 12+ messages in thread
From: Tetsuya.Mukawa @ 2014-08-27  5:58 UTC (permalink / raw)
  To: Ouyang, Changchun, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani

(2014/08/27 14:27), Tetsuya.Mukawa wrote:
> Hi Changchun,
>
> (2014/08/27 14:01), Ouyang, Changchun wrote:
>> Agree with you, the performance should be same as the data path (RX/TX) is not affected,
>> The difference between implementation only exists in the virtio device creation and destroy stage.
> Yes, I agree. Also There may be the difference, if a virtio-net driver
> on a guest isn't poll mode like a virtio-net device driver in the
> kernel. In the case, existing vhost implementation uses the eventfd
> kernel module, and vhost-user implementation uses eventfd to kick the
> driver. So I guess there will be the difference.
>
> Anyway, about device creation and destruction, the difference will come
> from transmission speed between unix domain socket and CUSE. I am not
> sure which is faster.
Thank for pointing out my misleading expression.

Correct: transmission latency
Incorrect: transmission speed

Tetsuya,


>
> Thanks,
> Tetsuya
>
>
>> Regards,
>> Changchun
>>
>>> -----Original Message-----
>>> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
>>> Sent: Wednesday, August 27, 2014 12:39 PM
>>> To: Ouyang, Changchun; dev@dpdk.org
>>> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
>>> Hitoshi Masutani
>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
>>> DPDK vhost library
>>>
>>>
>>> (2014/08/27 9:43), Ouyang, Changchun wrote:
>>>> Do we have performance comparison between both implementation?
>>> Hi Changchun,
>>>
>>> If DPDK applications are running on both guest and host side, the
>>> performance should be almost same, because while transmitting data virt
>>> queues are accessed by virtio-net PMD and libvhost. In libvhost, the existing
>>> vhost implementation and a vhost-user implementation will shares or uses
>>> same code to access virt queues. So I guess the performance will be almost
>>> same.
>>>
>>> Thanks,
>>> Tetsuya
>>>
>>>
>>>> Thanks
>>>> Changchun
>>>>
>>>>
>>>> -----Original Message-----
>>>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
>>>> Sent: Tuesday, August 26, 2014 7:06 PM
>>>> To: dev@dpdk.org
>>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
>>>> support into DPDK vhost library
>>>>
>>>> Hi all:
>>>> We are implementing qemu official vhost-user interface into DPDK vhost
>>> library, so there would be two coexisting implementations for user space
>>> vhost backend.
>>>> Pro and cons in my mind:
>>>> Existing solution:
>>>> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
>>> proxy kernel module and extra maintenance effort Qemu vhost-user:
>>>>                Pros:  qemu official us-vhost interface;     Cons: only available after
>>> qemu 2.1
>>>> BR.
>>>> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  5:27       ` Tetsuya.Mukawa
  2014-08-27  5:56         ` Xie, Huawei
  2014-08-27  5:58         ` Tetsuya.Mukawa
@ 2014-08-27  6:00         ` Ouyang, Changchun
  2014-08-27  6:09           ` Tetsuya.Mukawa
  2 siblings, 1 reply; 12+ messages in thread
From: Ouyang, Changchun @ 2014-08-27  6:00 UTC (permalink / raw)
  To: Tetsuya.Mukawa, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani



> -----Original Message-----
> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
> Sent: Wednesday, August 27, 2014 1:28 PM
> To: Ouyang, Changchun; dev@dpdk.org
> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
> Hitoshi Masutani
> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
> DPDK vhost library
> 
> Hi Changchun,
> 
> (2014/08/27 14:01), Ouyang, Changchun wrote:
> > Agree with you, the performance should be same as the data path
> > (RX/TX) is not affected, The difference between implementation only
> exists in the virtio device creation and destroy stage.
> Yes, I agree. Also There may be the difference, if a virtio-net driver on a
> guest isn't poll mode like a virtio-net device driver in the kernel. In the case,
> existing vhost implementation uses the eventfd kernel module, and vhost-
> user implementation uses eventfd to kick the driver. So I guess there will be
> the difference.
> 
> Anyway, about device creation and destruction, the difference will come
> from transmission speed between unix domain socket and CUSE. I am not
> sure which is faster.

Yes, it doesn't matter which one is faster for virtio device creation and destroy, 
as it is not in data path. 

> Thanks,
> Tetsuya
> 
> 
> >
> > Regards,
> > Changchun
> >
> >> -----Original Message-----
> >> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
> >> Sent: Wednesday, August 27, 2014 12:39 PM
> >> To: Ouyang, Changchun; dev@dpdk.org
> >> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
> >> Hitoshi Masutani
> >> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
> >> support into DPDK vhost library
> >>
> >>
> >> (2014/08/27 9:43), Ouyang, Changchun wrote:
> >>> Do we have performance comparison between both implementation?
> >> Hi Changchun,
> >>
> >> If DPDK applications are running on both guest and host side, the
> >> performance should be almost same, because while transmitting data
> >> virt queues are accessed by virtio-net PMD and libvhost. In libvhost,
> >> the existing vhost implementation and a vhost-user implementation
> >> will shares or uses same code to access virt queues. So I guess the
> >> performance will be almost same.
> >>
> >> Thanks,
> >> Tetsuya
> >>
> >>
> >>> Thanks
> >>> Changchun
> >>>
> >>>
> >>> -----Original Message-----
> >>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
> >>> Sent: Tuesday, August 26, 2014 7:06 PM
> >>> To: dev@dpdk.org
> >>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
> >>> support into DPDK vhost library
> >>>
> >>> Hi all:
> >>> We are implementing qemu official vhost-user interface into DPDK
> >>> vhost
> >> library, so there would be two coexisting implementations for user
> >> space vhost backend.
> >>> Pro and cons in my mind:
> >>> Existing solution:
> >>> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
> >> proxy kernel module and extra maintenance effort Qemu vhost-user:
> >>>                Pros:  qemu official us-vhost interface;     Cons: only available
> after
> >> qemu 2.1
> >>> BR.
> >>> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  5:56         ` Xie, Huawei
@ 2014-08-27  6:07           ` Tetsuya.Mukawa
  0 siblings, 0 replies; 12+ messages in thread
From: Tetsuya.Mukawa @ 2014-08-27  6:07 UTC (permalink / raw)
  To: Xie, Huawei, Ouyang, Changchun, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani

Hi Xie,

(2014/08/27 14:56), Xie, Huawei wrote:
> For virtio-net device driver, there is still no difference. Existing
> solution creates an eventfd module to install a fd in DPDK process
> pointing to the eventfd in qemu process. In vhost-user, the UNIX
> domain socket will do that work, create a new fd, install it in target
> DPDK server process, and make it point to the eventfd in qemu process. 
Thank you for explanation. I can understand clearly.

Thanks,
Tetsuya

>> Anyway, about device creation and destruction, the difference will come
>> from transmission speed between unix domain socket and CUSE. I am not
>> sure which is faster.
>>
>> Thanks,
>> Tetsuya
>>
>>
>>> Regards,
>>> Changchun
>>>
>>>> -----Original Message-----
>>>> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
>>>> Sent: Wednesday, August 27, 2014 12:39 PM
>>>> To: Ouyang, Changchun; dev@dpdk.org
>>>> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
>>>> Hitoshi Masutani
>>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into
>>>> DPDK vhost library
>>>>
>>>>
>>>> (2014/08/27 9:43), Ouyang, Changchun wrote:
>>>>> Do we have performance comparison between both implementation?
>>>> Hi Changchun,
>>>>
>>>> If DPDK applications are running on both guest and host side, the
>>>> performance should be almost same, because while transmitting data virt
>>>> queues are accessed by virtio-net PMD and libvhost. In libvhost, the existing
>>>> vhost implementation and a vhost-user implementation will shares or uses
>>>> same code to access virt queues. So I guess the performance will be almost
>>>> same.
>>>>
>>>> Thanks,
>>>> Tetsuya
>>>>
>>>>
>>>>> Thanks
>>>>> Changchun
>>>>>
>>>>>
>>>>> -----Original Message-----
>>>>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
>>>>> Sent: Tuesday, August 26, 2014 7:06 PM
>>>>> To: dev@dpdk.org
>>>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
>>>>> support into DPDK vhost library
>>>>>
>>>>> Hi all:
>>>>> We are implementing qemu official vhost-user interface into DPDK vhost
>>>> library, so there would be two coexisting implementations for user space
>>>> vhost backend.
>>>>> Pro and cons in my mind:
>>>>> Existing solution:
>>>>> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
>>>> proxy kernel module and extra maintenance effort Qemu vhost-user:
>>>>>                Pros:  qemu official us-vhost interface;     Cons: only available after
>>>> qemu 2.1
>>>>> BR.
>>>>> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-27  6:00         ` Ouyang, Changchun
@ 2014-08-27  6:09           ` Tetsuya.Mukawa
  0 siblings, 0 replies; 12+ messages in thread
From: Tetsuya.Mukawa @ 2014-08-27  6:09 UTC (permalink / raw)
  To: Ouyang, Changchun, dev
  Cc: Katsuya MATSUBARA, nakajima.yoshihiro, Hitoshi Masutani

Hi Ouyang,


(2014/08/27 15:00), Ouyang, Changchun wrote:
> Yes, it doesn't matter which one is faster for virtio device creation
> and destroy, as it is not in data path. 
I agree with you.

Thanks,
Tetsuya

>> Thanks,
>> Tetsuya
>>
>>
>>> Regards,
>>> Changchun
>>>
>>>> -----Original Message-----
>>>> From: Tetsuya.Mukawa [mailto:mukawa@igel.co.jp]
>>>> Sent: Wednesday, August 27, 2014 12:39 PM
>>>> To: Ouyang, Changchun; dev@dpdk.org
>>>> Cc: Xie, Huawei; Katsuya MATSUBARA; nakajima.yoshihiro@lab.ntt.co.jp;
>>>> Hitoshi Masutani
>>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
>>>> support into DPDK vhost library
>>>>
>>>>
>>>> (2014/08/27 9:43), Ouyang, Changchun wrote:
>>>>> Do we have performance comparison between both implementation?
>>>> Hi Changchun,
>>>>
>>>> If DPDK applications are running on both guest and host side, the
>>>> performance should be almost same, because while transmitting data
>>>> virt queues are accessed by virtio-net PMD and libvhost. In libvhost,
>>>> the existing vhost implementation and a vhost-user implementation
>>>> will shares or uses same code to access virt queues. So I guess the
>>>> performance will be almost same.
>>>>
>>>> Thanks,
>>>> Tetsuya
>>>>
>>>>
>>>>> Thanks
>>>>> Changchun
>>>>>
>>>>>
>>>>> -----Original Message-----
>>>>> From: dev [mailto:dev-bounces@dpdk.org] On Behalf Of Xie, Huawei
>>>>> Sent: Tuesday, August 26, 2014 7:06 PM
>>>>> To: dev@dpdk.org
>>>>> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user
>>>>> support into DPDK vhost library
>>>>>
>>>>> Hi all:
>>>>> We are implementing qemu official vhost-user interface into DPDK
>>>>> vhost
>>>> library, so there would be two coexisting implementations for user
>>>> space vhost backend.
>>>>> Pro and cons in my mind:
>>>>> Existing solution:
>>>>> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
>>>> proxy kernel module and extra maintenance effort Qemu vhost-user:
>>>>>                Pros:  qemu official us-vhost interface;     Cons: only available
>> after
>>>> qemu 2.1
>>>>> BR.
>>>>> huawei

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-08-26 11:05 [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library Xie, Huawei
  2014-08-27  0:43 ` Ouyang, Changchun
@ 2014-09-13  5:27 ` Linhaifeng
  2014-09-16  1:36   ` Xie, Huawei
  1 sibling, 1 reply; 12+ messages in thread
From: Linhaifeng @ 2014-09-13  5:27 UTC (permalink / raw)
  To: Xie, Huawei, dev

when will publish ?

On 2014/8/26 19:05, Xie, Huawei wrote:
> Hi all:
> We are implementing qemu official vhost-user interface into DPDK vhost library, so there would be two coexisting implementations for user space vhost backend.
> Pro and cons in my mind:
> Existing solution:
> Pros:  works with qemu version before 2.1;  Cons: depends on eventfd proxy kernel module and extra maintenance effort
> Qemu vhost-user:
>                Pros:  qemu official us-vhost interface;     Cons: only available after qemu 2.1
> 
> BR.
> huawei
> 
> 

^ permalink raw reply	[flat|nested] 12+ messages in thread

* Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library
  2014-09-13  5:27 ` Linhaifeng
@ 2014-09-16  1:36   ` Xie, Huawei
  0 siblings, 0 replies; 12+ messages in thread
From: Xie, Huawei @ 2014-09-16  1:36 UTC (permalink / raw)
  To: Linhaifeng, dev

Hi Haifeng:
Might be in the release after 1.8.

> -----Original Message-----
> From: Linhaifeng [mailto:haifeng.lin@huawei.com]
> Sent: Saturday, September 13, 2014 1:28 PM
> To: Xie, Huawei; dev@dpdk.org
> Subject: Re: [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support
> into DPDK vhost library
> 
> when will publish ?
> 
> On 2014/8/26 19:05, Xie, Huawei wrote:
> > Hi all:
> > We are implementing qemu official vhost-user interface into DPDK vhost
> library, so there would be two coexisting implementations for user space
> vhost backend.
> > Pro and cons in my mind:
> > Existing solution:
> > Pros:  works with qemu version before 2.1;  Cons: depends on eventfd
> proxy kernel module and extra maintenance effort
> > Qemu vhost-user:
> >                Pros:  qemu official us-vhost interface;     Cons: only available
> after qemu 2.1
> >
> > BR.
> > huawei
> >
> >

^ permalink raw reply	[flat|nested] 12+ messages in thread

end of thread, other threads:[~2014-09-16  1:32 UTC | newest]

Thread overview: 12+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-08-26 11:05 [dpdk-dev] [RFC] lib/librte_vhost: qemu vhost-user support into DPDK vhost library Xie, Huawei
2014-08-27  0:43 ` Ouyang, Changchun
2014-08-27  4:39   ` Tetsuya.Mukawa
2014-08-27  5:01     ` Ouyang, Changchun
2014-08-27  5:27       ` Tetsuya.Mukawa
2014-08-27  5:56         ` Xie, Huawei
2014-08-27  6:07           ` Tetsuya.Mukawa
2014-08-27  5:58         ` Tetsuya.Mukawa
2014-08-27  6:00         ` Ouyang, Changchun
2014-08-27  6:09           ` Tetsuya.Mukawa
2014-09-13  5:27 ` Linhaifeng
2014-09-16  1:36   ` Xie, Huawei

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).