From: Jason Wang <jasowang@redhat.com>
To: mst@redhat.com, jasowang@redhat.com
Cc: kvm@vger.kernel.org, virtualization@lists.linux-foundation.org,
netdev@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [RFC PATCH net-next 05/12] vhost_net: batch update used ring for datacopy TX
Date: Mon, 21 May 2018 17:04:26 +0800 [thread overview]
Message-ID: <1526893473-20128-6-git-send-email-jasowang@redhat.com> (raw)
In-Reply-To: <1526893473-20128-1-git-send-email-jasowang@redhat.com>
Like commit e2b3b35eb989 ("vhost_net: batch used ring update in rx"),
this patches implements batch used ring update for datacopy TX
(zerocopy has already done some kind of batching).
Testpmd transmission from guest to ixgbe via XDP_REDIRECT shows about
15% improvement from 2.8Mpps to 3.2Mpps.
Signed-off-by: Jason Wang <jasowang@redhat.com>
---
drivers/vhost/net.c | 13 ++++++++++++-
1 file changed, 12 insertions(+), 1 deletion(-)
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 4682fcc..f0639d7 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -511,6 +511,7 @@ static void handle_tx_copy(struct vhost_net *net)
struct socket *sock;
struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
int sent_pkts = 0;
+ s16 nheads = 0;
mutex_lock(&vq->mutex);
sock = vq->private_data;
@@ -550,6 +551,9 @@ static void handle_tx_copy(struct vhost_net *net)
if (len < 0)
break;
+ vq->heads[nheads].id = cpu_to_vhost32(vq, head);
+ vq->heads[nheads].len = 0;
+
total_len += len;
if (total_len < VHOST_NET_WEIGHT &&
vhost_has_more_pkts(net, vq)) {
@@ -568,13 +572,20 @@ static void handle_tx_copy(struct vhost_net *net)
if (err != len)
pr_debug("Truncated TX packet: "
" len %d != %zd\n", err, len);
- vhost_add_used_and_signal(&net->dev, vq, head, 0);
+ if (++nheads == VHOST_RX_BATCH) {
+ vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+ nheads);
+ nheads = 0;
+ }
if (vhost_exceeds_weight(++sent_pkts, total_len)) {
vhost_poll_queue(&vq->poll);
break;
}
}
out:
+ if (nheads)
+ vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+ nheads);
mutex_unlock(&vq->mutex);
}
--
2.7.4
next prev parent reply other threads:[~2018-05-21 9:05 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 ` Jason Wang [this message]
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 ` [RFC PATCH net-next 00/12] XDP batching for TUN/vhost_net Michael S. Tsirkin
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=1526893473-20128-6-git-send-email-jasowang@redhat.com \
--to=jasowang@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--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
all inboxes | Powered by JetHome®