From: Yongji Xie <xieyongji@bytedance.com>
To: Maxime Coquelin <maxime.coquelin@redhat.com>
Cc: dev@dpdk.org, David Marchand <david.marchand@redhat.com>,
chenbo.xia@intel.com, mkp@redhat.com, fbl@redhat.com,
Jason Wang <jasowang@redhat.com>,
cunming.liang@intel.com, echaudro@redhat.com,
Eugenio Perez Martin <eperezma@redhat.com>,
Adrian Moreno Zapata <amorenoz@redhat.com>
Subject: Re: [RFC 00/27] Add VDUSE support to Vhost library
Date: Thu, 6 Apr 2023 11:44:59 +0800 [thread overview]
Message-ID: <CACycT3vYgsDrFpPH0s-_1D5O2+LdY-feeFyn5e4XO08CHaM2cg@mail.gmail.com> (raw)
In-Reply-To: <20230331154259.1447831-1-maxime.coquelin@redhat.com>
Hi Maxime,
On Fri, Mar 31, 2023 at 11:43 PM Maxime Coquelin
<maxime.coquelin@redhat.com> wrote:
>
> This series introduces a new type of backend, VDUSE,
> to the Vhost library.
>
> VDUSE stands for vDPA device in Userspace, it enables
> implementing a Virtio device in userspace and have it
> attached to the Kernel vDPA bus.
>
> Once attached to the vDPA bus, it can be used either by
> Kernel Virtio drivers, like virtio-net in our case, via
> the virtio-vdpa driver. Doing that, the device is visible
> to the Kernel networking stack and is exposed to userspace
> as a regular netdev.
>
> It can also be exposed to userspace thanks to the
> vhost-vdpa driver, via a vhost-vdpa chardev that can be
> passed to QEMU or Virtio-user PMD.
>
> While VDUSE support is already available in upstream
> Kernel, a couple of patches are required to support
> network device type:
>
> https://gitlab.com/mcoquelin/linux/-/tree/vduse_networking_poc
>
> In order to attach the created VDUSE device to the vDPA
> bus, a recent iproute2 version containing the vdpa tool is
> required.
>
> Usage:
> ======
>
> 1. Probe required Kernel modules
> # modprobe vdpa
> # modprobe vduse
> # modprobe virtio-vdpa
>
> 2. Build (require vduse kernel headers to be available)
> # meson build
> # ninja -C build
>
> 3. Create a VDUSE device (vduse0) using Vhost PMD with
> testpmd (with 4 queue pairs in this example)
> # ./build/app/dpdk-testpmd --no-pci --vdev=net_vhost0,iface=/dev/vduse/vduse0,queues=4 --log-level=*:9 -- -i --txq=4 --rxq=4
>
> 4. Attach the VDUSE device to the vDPA bus
> # vdpa dev add name vduse0 mgmtdev vduse
> => The virtio-net netdev shows up (eth0 here)
> # ip l show eth0
> 21: eth0: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq state UP mode DEFAULT group default qlen 1000
> link/ether c2:73:ea:a7:68:6d brd ff:ff:ff:ff:ff:ff
>
> 5. Start/stop traffic in testpmd
> testpmd> start
> testpmd> show port stats 0
> ######################## NIC statistics for port 0 ########################
> RX-packets: 11 RX-missed: 0 RX-bytes: 1482
> RX-errors: 0
> RX-nombuf: 0
> TX-packets: 1 TX-errors: 0 TX-bytes: 62
>
> Throughput (since last show)
> Rx-pps: 0 Rx-bps: 0
> Tx-pps: 0 Tx-bps: 0
> ############################################################################
> testpmd> stop
>
> 6. Detach the VDUSE device from the vDPA bus
> # vdpa dev del vduse0
>
> 7. Quit testpmd
> testpmd> quit
>
> Known issues & remaining work:
> ==============================
> - Fix issue in FD manager (still polling while FD has been removed)
> - Add Netlink support in Vhost library
> - Support device reconnection
> - Support packed ring
> - Enable & test more Virtio features
> - Provide performance benchmark results
>
Nice work! Thanks for bringing VDUSE to the network area. I wonder if
you have some plan to support userspace memory registration [1]? I
think this feature can benefit the performance since an extra data
copy could be eliminated in our case.
[1] https://lwn.net/Articles/902809/
Thanks,
Yongji
next prev parent reply other threads:[~2023-04-12 6:57 UTC|newest]
Thread overview: 79+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-31 15:42 Maxime Coquelin
2023-03-31 15:42 ` [RFC 01/27] vhost: fix missing guest notif stat increment Maxime Coquelin
2023-04-24 2:57 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 02/27] vhost: fix invalid call FD handling Maxime Coquelin
2023-04-24 2:58 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 03/27] vhost: fix IOTLB entries overlap check with previous entry Maxime Coquelin
2023-04-17 19:15 ` Mike Pattrick
2023-04-24 2:58 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 04/27] vhost: add helper of IOTLB entries coredump Maxime Coquelin
2023-04-24 2:59 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 05/27] vhost: add helper for IOTLB entries shared page check Maxime Coquelin
2023-04-17 19:39 ` Mike Pattrick
2023-04-19 9:35 ` Maxime Coquelin
2023-04-19 14:52 ` Mike Pattrick
2023-04-24 2:59 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 06/27] vhost: don't dump unneeded pages with IOTLB Maxime Coquelin
2023-04-20 17:11 ` Mike Pattrick
2023-04-24 3:00 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 07/27] vhost: change to single IOTLB cache per device Maxime Coquelin
2023-04-25 6:19 ` Xia, Chenbo
2023-05-03 13:47 ` Maxime Coquelin
2023-03-31 15:42 ` [RFC 08/27] vhost: add offset field to IOTLB entries Maxime Coquelin
2023-04-25 6:20 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 09/27] vhost: add page size info to IOTLB entry Maxime Coquelin
2023-04-25 6:20 ` Xia, Chenbo
2023-05-03 13:57 ` Maxime Coquelin
2023-03-31 15:42 ` [RFC 10/27] vhost: retry translating IOVA after IOTLB miss Maxime Coquelin
2023-05-05 5:07 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 11/27] vhost: introduce backend ops Maxime Coquelin
2023-05-05 5:07 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 12/27] vhost: add IOTLB cache entry removal callback Maxime Coquelin
2023-05-05 5:07 ` Xia, Chenbo
2023-05-25 11:20 ` Maxime Coquelin
2023-03-31 15:42 ` [RFC 13/27] vhost: add helper for IOTLB misses Maxime Coquelin
2023-03-31 15:42 ` [RFC 14/27] vhost: add helper for interrupt injection Maxime Coquelin
2023-05-05 5:07 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 15/27] vhost: add API to set max queue pairs Maxime Coquelin
2023-05-05 5:07 ` Xia, Chenbo
2023-05-25 11:23 ` Maxime Coquelin
2023-03-31 15:42 ` [RFC 16/27] net/vhost: use " Maxime Coquelin
2023-05-05 5:07 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 17/27] vhost: add control virtqueue support Maxime Coquelin
2023-05-09 5:29 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 18/27] vhost: add VDUSE device creation and destruction Maxime Coquelin
2023-05-09 5:31 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 19/27] vhost: add VDUSE callback for IOTLB miss Maxime Coquelin
2023-05-09 5:31 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 20/27] vhost: add VDUSE callback for IOTLB entry removal Maxime Coquelin
2023-05-09 5:32 ` Xia, Chenbo
2023-05-25 11:35 ` Maxime Coquelin
2023-03-31 15:42 ` [RFC 21/27] vhost: add VDUSE callback for IRQ injection Maxime Coquelin
2023-05-09 5:33 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 22/27] vhost: add VDUSE events handler Maxime Coquelin
2023-05-09 5:34 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 23/27] vhost: add support for virtqueue state get event Maxime Coquelin
2023-05-09 5:34 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 24/27] vhost: add support for VDUSE status set event Maxime Coquelin
2023-05-09 5:34 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 25/27] vhost: add support for VDUSE IOTLB update event Maxime Coquelin
2023-05-09 5:35 ` Xia, Chenbo
2023-05-25 11:43 ` Maxime Coquelin
2023-03-31 15:42 ` [RFC 26/27] vhost: add VDUSE device startup Maxime Coquelin
2023-05-09 5:35 ` Xia, Chenbo
2023-03-31 15:42 ` [RFC 27/27] vhost: add multiqueue support to VDUSE Maxime Coquelin
2023-05-09 5:35 ` Xia, Chenbo
2023-04-06 3:44 ` Yongji Xie [this message]
2023-04-06 8:16 ` [RFC 00/27] Add VDUSE support to Vhost library Maxime Coquelin
2023-04-06 11:04 ` Yongji Xie
2023-04-12 11:33 ` Ferruh Yigit
2023-04-12 15:28 ` Maxime Coquelin
2023-04-12 19:40 ` Morten Brørup
2023-04-13 7:08 ` Xia, Chenbo
2023-04-13 7:58 ` Morten Brørup
2023-04-13 7:59 ` Maxime Coquelin
2023-04-14 10:48 ` Ferruh Yigit
2023-04-14 12:06 ` Maxime Coquelin
2023-04-14 14:25 ` Ferruh Yigit
2023-04-17 3:10 ` Jason Wang
2023-05-05 5:53 ` Xia, Chenbo
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CACycT3vYgsDrFpPH0s-_1D5O2+LdY-feeFyn5e4XO08CHaM2cg@mail.gmail.com \
--to=xieyongji@bytedance.com \
--cc=amorenoz@redhat.com \
--cc=chenbo.xia@intel.com \
--cc=cunming.liang@intel.com \
--cc=david.marchand@redhat.com \
--cc=dev@dpdk.org \
--cc=echaudro@redhat.com \
--cc=eperezma@redhat.com \
--cc=fbl@redhat.com \
--cc=jasowang@redhat.com \
--cc=maxime.coquelin@redhat.com \
--cc=mkp@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).