From: Stefan Hajnoczi <stefanha@redhat.com>
To: qemu-devel@nongnu.org
Cc: borntraeger@de.ibm.com, Paolo Bonzini <pbonzini@redhat.com>,
Karl Rister <krister@redhat.com>, Fam Zheng <famz@redhat.com>,
Stefan Hajnoczi <stefanha@redhat.com>
Subject: [Qemu-devel] [PATCH v4 11/13] virtio: disable virtqueue notifications during polling
Date: Thu, 1 Dec 2016 19:26:50 +0000 [thread overview]
Message-ID: <20161201192652.9509-12-stefanha@redhat.com> (raw)
In-Reply-To: <20161201192652.9509-1-stefanha@redhat.com>
This is a performance optimization to eliminate vmexits during polling.
It also avoids spurious ioeventfd processing after polling ends.
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
hw/virtio/virtio.c | 18 ++++++++++++++++++
1 file changed, 18 insertions(+)
diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c
index 79b5c36..d40711a 100644
--- a/hw/virtio/virtio.c
+++ b/hw/virtio/virtio.c
@@ -2053,6 +2053,13 @@ static void virtio_queue_host_notifier_aio_read(EventNotifier *n)
}
}
+static void virtio_queue_host_notifier_aio_poll_begin(EventNotifier *n)
+{
+ VirtQueue *vq = container_of(n, VirtQueue, host_notifier);
+
+ virtio_queue_set_notification(vq, 0);
+}
+
static bool virtio_queue_host_notifier_aio_poll(void *opaque)
{
EventNotifier *n = opaque;
@@ -2066,6 +2073,14 @@ static bool virtio_queue_host_notifier_aio_poll(void *opaque)
return true;
}
+static void virtio_queue_host_notifier_aio_poll_end(EventNotifier *n)
+{
+ VirtQueue *vq = container_of(n, VirtQueue, host_notifier);
+
+ /* Caller polls once more after this to catch requests that race with us */
+ virtio_queue_set_notification(vq, 1);
+}
+
void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx,
VirtIOHandleOutput handle_output)
{
@@ -2074,6 +2089,9 @@ void virtio_queue_aio_set_host_notifier_handler(VirtQueue *vq, AioContext *ctx,
aio_set_event_notifier(ctx, &vq->host_notifier, true,
virtio_queue_host_notifier_aio_read,
virtio_queue_host_notifier_aio_poll);
+ aio_set_event_notifier_poll(ctx, &vq->host_notifier,
+ virtio_queue_host_notifier_aio_poll_begin,
+ virtio_queue_host_notifier_aio_poll_end);
} else {
aio_set_event_notifier(ctx, &vq->host_notifier, true, NULL, NULL);
/* Test and clear notifier before after disabling event,
--
2.9.3
next prev parent reply other threads:[~2016-12-01 19:27 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-12-01 19:26 [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 01/13] aio: add flag to skip fds to aio_dispatch() Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 02/13] aio: add AioPollFn and io_poll() interface Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 03/13] aio: add polling mode to AioContext Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 04/13] virtio: poll virtqueues for new buffers Stefan Hajnoczi
2016-12-05 0:54 ` Fam Zheng
2016-12-05 10:14 ` Stefan Hajnoczi
2016-12-05 10:59 ` Paolo Bonzini
2016-12-05 14:46 ` Stefan Hajnoczi
2016-12-05 15:22 ` Paolo Bonzini
2016-12-06 9:28 ` Stefan Hajnoczi
2016-12-05 11:12 ` Christian Borntraeger
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 05/13] linux-aio: poll ring for completions Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 06/13] iothread: add polling parameters Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 07/13] virtio-blk: suppress virtqueue kick during processing Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 08/13] virtio-scsi: " Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 09/13] virtio: turn vq->notification into a nested counter Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 10/13] aio: add .io_poll_begin/end() callbacks Stefan Hajnoczi
2016-12-01 19:26 ` Stefan Hajnoczi [this message]
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 12/13] aio: self-tune polling time Stefan Hajnoczi
2016-12-05 20:06 ` Christian Borntraeger
2016-12-06 9:20 ` Stefan Hajnoczi
2016-12-06 10:12 ` Christian Borntraeger
2016-12-06 17:22 ` Stefan Hajnoczi
2016-12-01 19:26 ` [Qemu-devel] [PATCH v4 13/13] iothread: add poll-grow and poll-shrink parameters Stefan Hajnoczi
2016-12-02 8:27 ` [Qemu-devel] [PATCH v4 00/13] aio: experimental virtio-blk polling mode Paolo Bonzini
2016-12-02 11:11 ` Stefan Hajnoczi
2016-12-05 10:25 ` Fam Zheng
2016-12-05 14:56 ` Stefan Hajnoczi
2016-12-05 16:40 ` Karl Rister
2016-12-06 9:27 ` Stefan Hajnoczi
2016-12-05 11:19 ` Christian Borntraeger
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=20161201192652.9509-12-stefanha@redhat.com \
--to=stefanha@redhat.com \
--cc=borntraeger@de.ibm.com \
--cc=famz@redhat.com \
--cc=krister@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.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).