[dpdk-users] VIRTIO for containers

[Tan, Jianfeng]

> -----Original Message-----
> From: Avi Cohen (A) [mailto:avi.cohen at huawei.com]
> Sent: Sunday, July 9, 2017 11:32 PM
> To: Tan, Jianfeng; dpdk-ovs at lists.01.org; users at dpdk.org
> Subject: RE: VIRTIO for containers
> 
> Thanks you Jianfeng - pls see inline marked  [Avi Cohen (A)]
> 
> > -----Original Message-----
> > From: Tan, Jianfeng [mailto:jianfeng.tan at intel.com]
> > Sent: Monday, 03 July, 2017 10:22 AM
> > To: Avi Cohen (A); dpdk-ovs at lists.01.org; users at dpdk.org
> > Subject: RE: VIRTIO for containers
> >
> >
> >
> > > -----Original Message-----
> > > From: Avi Cohen (A) [mailto:avi.cohen at huawei.com]
> > > Sent: Wednesday, June 28, 2017 2:45 PM
> > > To: Tan, Jianfeng; dpdk-ovs at lists.01.org; users at dpdk.org
> > > Subject: RE: VIRTIO for containers
> > >
> > > Thank you Jianfeng
> > >
> > > > -----Original Message-----
> > > > From: Tan, Jianfeng [mailto:jianfeng.tan at intel.com]
> > > > Sent: Tuesday, 27 June, 2017 5:22 PM
> > > > To: Avi Cohen (A); dpdk-ovs at lists.01.org; users at dpdk.org
> > > > Subject: Re: VIRTIO for containers
> > > >
> > > >
> > > >
> > > > On 6/26/2017 8:06 PM, Avi Cohen (A) wrote:
> > > > > Thank You Jianfeng
> > > > >
> > > > >> We have developed virtio-user + vhost-kernel as the backend. In
> > > > >> that scenario, you can add the tap interface into a container
> > > > >> network
> > > > namespace.
> > > > >> And there's a vhost kthread to push the data out to user space.
> > > > >>
> > > > >> And I cannot guarantee the performance as it has diametric model
> > > > >> in VM
> > > > >> (virtio) - OVS-DPDK (vhost).
> > > > >>
> > > > > [Avi Cohen (A)]
> > > > > Can you refer to a document how to run this setup?
> > > >
> > > > Please refer to
> > > >
> http://dpdk.org/doc/guides/howto/virtio_user_as_exceptional_path.htm
> > > > l
> > > >
> > > [Avi Cohen (A)]
> > > My setup includes a container and ovs-dpdk , i still not sure about:
> > >  - How to set the virtio backend port in the ovs-dpdk ?
> >
> > For OVS-DPDK, you need a version above 2.7.0. Below command is used to
> > create a virtio-user port with vhost-kernel backend:
> > # ovs-vsctl add-port br0 virtiouser0 -- set Interface virtiouser0 type=dpdk
> > options:dpdk-devargs=virtio_user0,path=/dev/vhost-net
> >
> > >  - How to set the container with the virtio frontend ?
> >
> > No, containers will not hold the virtio frontend in this case. Above ovs-vsctl
> > command will generate a virtio-user port in OVS, and a tap interface in
> > kernel, you can assign the tap interface into a net namespace of some
> > container so that its networking flow will go through OVS-DPDK then to
> > outside.
> [Avi Cohen (A)]
> Thanks you Jianfeng
> I've tested it and the performance looks very good compared to native ovs.
> I have 1 more question:
> You wrote " there's a vhost kthread to push the data out to user space " -
> Is that mean a copy from userspace to kernel (and viceversa) or there is a
> zero-copy mmap  like in AF_PACKET which handles TX/RX rings in userspace ?
> Best Regards
> avi

So far it needs data copy at least from kernel to user path; there's an experimental feature, named experimental_zcopytx, to avoid data copy, but not very useful due to the implementation limitation.

Packet mmap (similar to AF_PACKET) is exactly the direction we were discussing for the further optimization. Plus, an optimized vhost thread model (current thread model is: one thread for one rx-tx queue pair) is also considered.

Thanks,
Jianfeng

> >
> > Thanks,
> > Jianfeng
> >
> > > Best Regards
> > > avi
> > >
> > > > Thanks,
> > > > Jianfeng
> > > >
> > > > > Best Regards
> > > > > avi
> > > > >>> I've tested the performance of a container connected to OVS-
> DPDK
> > > > >>> via vdev-af_packet  and processed by virtual PMD, and its
> > > > >>> performance is good [uses mmap'ed to userspace  - zero copy
> > > > >>> RX/TX ring buffer] but not good as  the performance  of a  VM
> > > > >>> connected to OVS-DPDK (@host) via vhost-user virtio.
> > > > >>> Best Regards
> > > > >>> avi
> > > > >>>
> > > > >>>> -----Original Message-----
> > > > >>>> From: Tan, Jianfeng [mailto:jianfeng.tan at intel.com]
> > > > >>>> Sent: Monday, 26 June, 2017 6:15 AM
> > > > >>>> To: Avi Cohen (A); dpdk-ovs at lists.01.org; users at dpdk.org
> > > > >>>> Subject: RE: VIRTIO for containers
> > > > >>>>
> > > > >>>> Hi Avi,
> > > > >>>>
> > > > >>>>> -----Original Message-----
> > > > >>>>> From: users [mailto:users-bounces at dpdk.org] On Behalf Of Avi
> > > Cohen
> > > > >>>>> (A)
> > > > >>>>> Sent: Sunday, June 25, 2017 11:13 PM
> > > > >>>>> To: dpdk-ovs at lists.01.org; users at dpdk.org
> > > > >>>>> Subject: [dpdk-users] VIRTIO for containers
> > > > >>>>>
> > > > >>>>> Hello,
> > > > >>>>> Does  anyone know the status of this project
> > > > >>>>> http://dpdk.org/ml/archives/dev/2015-November/027732.html
> -
> > > > >>>>> Implementing a virtio device for containers ?
> > > > >>>> It has been upstreamed since v16.07. Here is a howto doc:
> > > > >>>>
> > > > >>>
> > > >
> > http://dpdk.org/doc/guides/howto/virtio_user_for_container_networking.
> > > > >>> h
> > > > >>>> tml
> > > > >>>>
> > > > >>>>
> > > > >>>> Thanks,
> > > > >>>> Jianfeng
> > > > >>>>
> > > > >>>>> Best Regards
> > > > >>>>> avi