From: Sasha Levin <levinsasha928@gmail.com>
To: linux-kernel@vger.kernel.org
Cc: Sasha Levin <levinsasha928@gmail.com>,
Rusty Russell <rusty@rustcorp.com.au>,
"Michael S. Tsirkin" <mst@redhat.com>,
virtualization@lists.linux-foundation.org, kvm@vger.kernel.org
Subject: [PATCH] virtio-ring: Use threshold for switching to indirect descriptors
Date: Tue, 29 Nov 2011 11:33:16 +0200 [thread overview]
Message-ID: <1322559196-11139-1-git-send-email-levinsasha928@gmail.com> (raw)
Currently if VIRTIO_RING_F_INDIRECT_DESC is enabled we will use indirect
descriptors even if we have plenty of space in the ring. This means that
we take a performance hit at all times due to the overhead of creating
indirect descriptors.
With this patch, we will use indirect descriptors only if we have less than
either 16, or 12% of the total amount of descriptors available.
I did basic performance benchmark on virtio-net with vhost enabled.
Before:
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 4563.92
After:
Recv Send Send
Socket Socket Message Elapsed
Size Size Size Time Throughput
bytes bytes bytes secs. 10^6bits/sec
87380 16384 16384 10.00 5353.28
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Cc: kvm@vger.kernel.org
Signed-off-by: Sasha Levin <levinsasha928@gmail.com>
---
drivers/virtio/virtio_ring.c | 12 ++++++++++--
1 files changed, 10 insertions(+), 2 deletions(-)
diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
index c7a2c20..5e0ce15 100644
--- a/drivers/virtio/virtio_ring.c
+++ b/drivers/virtio/virtio_ring.c
@@ -82,6 +82,7 @@ struct vring_virtqueue
/* Host supports indirect buffers */
bool indirect;
+ unsigned int indirect_threshold;
/* Host publishes avail event idx */
bool event;
@@ -176,8 +177,9 @@ int virtqueue_add_buf_gfp(struct virtqueue *_vq,
BUG_ON(data == NULL);
/* If the host supports indirect descriptor tables, and we have multiple
- * buffers, then go indirect. FIXME: tune this threshold */
- if (vq->indirect && (out + in) > 1 && vq->num_free) {
+ * buffers, then go indirect. */
+ if (vq->indirect && (out + in) > 1 &&
+ (vq->num_free < vq->indirect_threshold)) {
head = vring_add_indirect(vq, sg, out, in, gfp);
if (likely(head >= 0))
goto add_head;
@@ -485,6 +487,12 @@ struct virtqueue *vring_new_virtqueue(unsigned int num,
#endif
vq->indirect = virtio_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC);
+ /*
+ * Use indirect descriptors only when we have less than either 12%
+ * or 16 of the descriptors in the ring available.
+ */
+ if (vq->indirect)
+ vq->indirect_threshold = max(16U, num >> 3);
vq->event = virtio_has_feature(vdev, VIRTIO_RING_F_EVENT_IDX);
/* No callback? Tell other side not to bother us. */
--
1.7.8.rc3
next reply other threads:[~2011-11-29 9:34 UTC|newest]
Thread overview: 41+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-11-29 9:33 Sasha Levin [this message]
2011-11-29 12:56 ` Michael S. Tsirkin
2011-11-29 13:34 ` Sasha Levin
2011-11-29 13:54 ` Michael S. Tsirkin
2011-11-29 14:21 ` Sasha Levin
2011-11-29 14:54 ` Michael S. Tsirkin
2011-11-29 14:58 ` Avi Kivity
2011-11-30 16:11 ` Sasha Levin
2011-11-30 16:17 ` Sasha Levin
2011-12-01 2:42 ` Rusty Russell
2011-12-01 7:58 ` Michael S. Tsirkin
2011-12-01 8:09 ` Sasha Levin
2011-12-01 10:26 ` Michael S. Tsirkin
2011-12-02 0:46 ` Rusty Russell
2011-12-03 11:50 ` Sasha Levin
2011-12-04 11:06 ` Michael S. Tsirkin
2011-12-04 15:15 ` Michael S. Tsirkin
2011-12-04 11:52 ` Avi Kivity
2011-12-04 12:01 ` Michael S. Tsirkin
2011-12-04 12:06 ` Avi Kivity
2011-12-04 15:11 ` Michael S. Tsirkin
2011-12-04 15:16 ` Avi Kivity
2011-12-04 16:00 ` Michael S. Tsirkin
2011-12-04 16:33 ` Avi Kivity
2011-12-05 0:10 ` Rusty Russell
2011-12-05 9:52 ` Avi Kivity
2011-12-06 5:07 ` Rusty Russell
2011-12-06 9:58 ` Avi Kivity
2011-12-06 12:03 ` Rusty Russell
2011-12-07 13:37 ` Avi Kivity
2011-12-04 12:13 ` Sasha Levin
2011-12-04 16:22 ` Michael S. Tsirkin
2011-12-04 17:34 ` Sasha Levin
2011-12-04 17:37 ` Avi Kivity
2011-12-04 17:39 ` Sasha Levin
2011-12-04 18:23 ` Sasha Levin
2011-12-07 14:02 ` Sasha Levin
2011-12-07 15:48 ` Michael S. Tsirkin
2011-12-08 9:44 ` Rusty Russell
2011-12-08 10:37 ` Sasha Levin
2011-12-09 5:33 ` Rusty Russell
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=1322559196-11139-1-git-send-email-levinsasha928@gmail.com \
--to=levinsasha928@gmail.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mst@redhat.com \
--cc=rusty@rustcorp.com.au \
--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®