qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Ming Lei <ming.lei@canonical.com>
To: Peter Maydell <peter.maydell@linaro.org>,
	qemu-devel@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
	Stefan Hajnoczi <stefanha@redhat.com>
Cc: Kevin Wolf <kwolf@redhat.com>, Ming Lei <ming.lei@canonical.com>,
	Fam Zheng <famz@redhat.com>,
	"Michael S. Tsirkin" <mst@redhat.com>
Subject: [Qemu-devel] [PATCH 2/2] virtio-blk: dataplane: notify guest as a batch
Date: Fri,  4 Jul 2014 20:27:34 +0800	[thread overview]
Message-ID: <1404476854-23773-3-git-send-email-ming.lei@canonical.com> (raw)
In-Reply-To: <1404476854-23773-1-git-send-email-ming.lei@canonical.com>

Now requests are submitted as a batch, so it is natural
to notify guest as a batch too.

This may supress interrupt  notification to VM:

	- in my test, decreased by ~13K/sec

Signed-off-by: Ming Lei <ming.lei@canonical.com>
---
 hw/block/dataplane/virtio-blk.c |   13 ++++++++++++-
 hw/block/virtio-blk.c           |    1 +
 include/hw/virtio/virtio-blk.h  |    1 +
 3 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/hw/block/dataplane/virtio-blk.c b/hw/block/dataplane/virtio-blk.c
index e88862d..9d36659 100644
--- a/hw/block/dataplane/virtio-blk.c
+++ b/hw/block/dataplane/virtio-blk.c
@@ -45,6 +45,8 @@ struct VirtIOBlockDataPlane {
     AioContext *ctx;
     EventNotifier host_notifier;    /* doorbell */
 
+    VirtIOBlockReq *last_submit;
+
     /* Operation blocker on BDS */
     Error *blocker;
     void (*saved_complete_request)(struct VirtIOBlockReq *req,
@@ -67,7 +69,10 @@ static void complete_request_vring(VirtIOBlockReq *req, unsigned char status)
 
     vring_push(&req->dev->dataplane->vring, &req->elem,
                req->qiov.size + sizeof(*req->in));
-    notify_guest(req->dev->dataplane);
+
+    if (req->last) {
+        notify_guest(req->dev->dataplane);
+    }
 }
 
 static void handle_notify(EventNotifier *e)
@@ -101,6 +106,8 @@ static void handle_notify(EventNotifier *e)
                                                         req->elem.index);
 
             virtio_blk_handle_request(req, &mrb);
+
+            s->last_submit = req;
         }
 
         virtio_submit_multiwrite(s->blk->conf.bs, &mrb);
@@ -116,6 +123,10 @@ static void handle_notify(EventNotifier *e)
             break;
         }
     }
+
+    if (s->last_submit) {
+        s->last_submit->last = true;
+    }
     bdrv_io_unplug(s->blk->conf.bs);
 }
 
diff --git a/hw/block/virtio-blk.c b/hw/block/virtio-blk.c
index 02cd6b0..86b37f7 100644
--- a/hw/block/virtio-blk.c
+++ b/hw/block/virtio-blk.c
@@ -35,6 +35,7 @@ VirtIOBlockReq *virtio_blk_alloc_request(VirtIOBlock *s)
     req->dev = s;
     req->qiov.size = 0;
     req->next = NULL;
+    req->last = false;
     return req;
 }
 
diff --git a/include/hw/virtio/virtio-blk.h b/include/hw/virtio/virtio-blk.h
index 992da26..07659c3 100644
--- a/include/hw/virtio/virtio-blk.h
+++ b/include/hw/virtio/virtio-blk.h
@@ -150,6 +150,7 @@ typedef struct VirtIOBlockReq {
     QEMUIOVector qiov;
     struct VirtIOBlockReq *next;
     BlockAcctCookie acct;
+    bool last;
 } VirtIOBlockReq;
 
 #define DEFINE_VIRTIO_BLK_FEATURES(_state, _field) \
-- 
1.7.9.5

  parent reply	other threads:[~2014-07-04 12:28 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-07-04 12:27 [Qemu-devel] [PATCH 0/2] virtio-blk: dataplane: one fix plus one optimization Ming Lei
2014-07-04 12:27 ` [Qemu-devel] [PATCH 1/2] virtio-blk: data-plane: fix save/set .complete_request in start Ming Lei
2014-07-04 12:27 ` Ming Lei [this message]
2014-07-04 12:55   ` [Qemu-devel] [PATCH 2/2] virtio-blk: dataplane: notify guest as a batch Paolo Bonzini
2014-07-04 14:52     ` Ming Lei
2014-07-04 15:48       ` Paolo Bonzini
2014-07-04 15:57         ` Ming Lei
2014-07-04 16:09           ` Paolo Bonzini
2014-07-05  4:21             ` Ming Lei

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=1404476854-23773-3-git-send-email-ming.lei@canonical.com \
    --to=ming.lei@canonical.com \
    --cc=famz@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=stefanha@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).