qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Stefan Hajnoczi <stefanha@redhat.com>
To: qemu-devel@nongnu.org
Cc: Peter Maydell <peter.maydell@linaro.org>,
	Stefan Hajnoczi <stefanha@redhat.com>,
	"Wangkai (Kevin, C)" <wangkai86@huawei.com>
Subject: [Qemu-devel] [PULL 1/5] tap: fix vcpu long time io blocking on tap
Date: Fri, 19 Dec 2014 13:18:20 +0000	[thread overview]
Message-ID: <1418995104-26262-2-git-send-email-stefanha@redhat.com> (raw)
In-Reply-To: <1418995104-26262-1-git-send-email-stefanha@redhat.com>

From: "Wangkai (Kevin,C)" <wangkai86@huawei.com>

[Adjusted doc comment for grammar.
--Stefan]

Signed-off-by: Wangkai <wangkai86@huawei.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 net/tap.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/tap.c b/net/tap.c
index bde6b58..1fe0edf 100644
--- a/net/tap.c
+++ b/net/tap.c
@@ -189,6 +189,7 @@ static void tap_send(void *opaque)
 {
     TAPState *s = opaque;
     int size;
+    int packets = 0;
 
     while (qemu_can_send_packet(&s->nc)) {
         uint8_t *buf = s->buf;
@@ -210,6 +211,17 @@ static void tap_send(void *opaque)
         } else if (size < 0) {
             break;
         }
+
+        /*
+         * When the host keeps receiving more packets while tap_send() is
+         * running we can hog the QEMU global mutex.  Limit the number of
+         * packets that are processed per tap_send() callback to prevent
+         * stalling the guest.
+         */
+        packets++;
+        if (packets >= 50) {
+            break;
+        }
     }
 }
 
-- 
2.1.0

  reply	other threads:[~2014-12-19 13:19 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-12-19 13:18 [Qemu-devel] [PULL 0/5] Net patches Stefan Hajnoczi
2014-12-19 13:18 ` Stefan Hajnoczi [this message]
2014-12-19 13:18 ` [Qemu-devel] [PULL 2/5] net: don't use set/get_pointer() in set/get_netdev() Stefan Hajnoczi
2014-12-19 13:18 ` [Qemu-devel] [PULL 3/5] net: Fuse g_malloc(); memset() into g_new0() Stefan Hajnoczi
2014-12-19 13:18 ` [Qemu-devel] [PULL 4/5] net: Use g_new() & friends where that makes obvious sense Stefan Hajnoczi
2014-12-19 13:18 ` [Qemu-devel] [PULL 5/5] e1000: defer packets until BM enabled Stefan Hajnoczi
2014-12-19 14:21   ` Michael S. Tsirkin
2014-12-21 23:16 ` [Qemu-devel] [PULL 0/5] Net patches Peter Maydell

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=1418995104-26262-2-git-send-email-stefanha@redhat.com \
    --to=stefanha@redhat.com \
    --cc=peter.maydell@linaro.org \
    --cc=qemu-devel@nongnu.org \
    --cc=wangkai86@huawei.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).