From: "Michael S. Tsirkin" <mst@redhat.com>
To: Jason Wang <jasowang@redhat.com>
Cc: kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH net-next 00/12] XDP batching for TUN/vhost_net
Date: Fri, 25 May 2018 20:53:10 +0300 [thread overview]
Message-ID: <20180525205219-mutt-send-email-mst@kernel.org> (raw)
In-Reply-To: <1526893473-20128-1-git-send-email-jasowang@redhat.com>
On Mon, May 21, 2018 at 05:04:21PM +0800, Jason Wang wrote:
> Hi all:
>
> We do not support XDP batching for TUN since it can only receive one
> packet a time from vhost_net. This series tries to remove this
> limitation by:
>
> - introduce a TUN specific msg_control that can hold a pointer to an
> array of XDP buffs
> - try copy and build XDP buff in vhost_net
> - store XDP buffs in an array and submit them once for every N packets
> from vhost_net
> - since TUN can only do native XDP for datacopy packet, to simplify
> the logic, split datacopy out logic and only do batching for
> datacopy.
I like how this rework looks. Pls go ahead and repost as
non-RFC.
> With this series, TX PPS can improve about 34% from 2.9Mpps to
> 3.9Mpps when doing xdp_redirect_map between TAP and ixgbe.
>
> Thanks
>
> Jason Wang (12):
> vhost_net: introduce helper to initialize tx iov iter
> vhost_net: introduce vhost_exceeds_weight()
> vhost_net: introduce vhost_has_more_pkts()
> vhost_net: split out datacopy logic
> vhost_net: batch update used ring for datacopy TX
> tuntap: enable premmption early
> tuntap: simplify error handling in tun_build_skb()
> tuntap: tweak on the path of non-xdp case in tun_build_skb()
> tuntap: split out XDP logic
> vhost_net: build xdp buff
> vhost_net: passing raw xdp buff to tun
> vhost_net: batch submitting XDP buffers to underlayer sockets
>
> drivers/net/tun.c | 226 +++++++++++++++++++++++++++----------
> drivers/vhost/net.c | 297 ++++++++++++++++++++++++++++++++++++++++++++-----
> include/linux/if_tun.h | 7 ++
> 3 files changed, 444 insertions(+), 86 deletions(-)
>
> --
> 2.7.4
prev parent reply other threads:[~2018-05-25 17:53 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-05-21 9:04 [RFC PATCH net-next 00/12] XDP batching for TUN/vhost_net Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 01/12] vhost_net: introduce helper to initialize tx iov iter Jason Wang
2018-05-21 16:24 ` Jesse Brandeburg
2018-05-22 12:26 ` Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 02/12] vhost_net: introduce vhost_exceeds_weight() Jason Wang
2018-05-21 16:29 ` Jesse Brandeburg
2018-05-22 12:27 ` Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 03/12] vhost_net: introduce vhost_has_more_pkts() Jason Wang
2018-05-21 16:39 ` Jesse Brandeburg
2018-05-22 12:31 ` Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 04/12] vhost_net: split out datacopy logic Jason Wang
2018-05-21 16:46 ` Jesse Brandeburg
2018-05-22 12:39 ` Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 05/12] vhost_net: batch update used ring for datacopy TX Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 06/12] tuntap: enable premmption early Jason Wang
2018-05-21 14:32 ` Michael S. Tsirkin
2018-05-21 9:04 ` [RFC PATCH net-next 07/12] tuntap: simplify error handling in tun_build_skb() Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 08/12] tuntap: tweak on the path of non-xdp case " Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 09/12] tuntap: split out XDP logic Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 10/12] vhost_net: build xdp buff Jason Wang
2018-05-21 16:56 ` Jesse Brandeburg
2018-05-21 22:21 ` Michael S. Tsirkin
2018-05-22 12:41 ` Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 11/12] vhost_net: passing raw xdp buff to tun Jason Wang
2018-05-21 9:04 ` [RFC PATCH net-next 12/12] vhost_net: batch submitting XDP buffers to underlayer sockets Jason Wang
2018-05-21 14:33 ` Michael S. Tsirkin
2018-05-25 17:53 ` Michael S. Tsirkin [this message]
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=20180525205219-mutt-send-email-mst@kernel.org \
--to=mst@redhat.com \
--cc=jasowang@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=virtualization@lists.linux-foundation.org \
/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).