From mboxrd@z Thu Jan  1 00:00:00 1970
From: Rusty Russell <rusty@rustcorp.com.au>
Subject: Re: [PATCH 3/9] kvm: qemu: Remove virtio_net tx ring-full heuristic
Date: Fri, 25 Jul 2008 10:30:39 +1000
Message-ID: <200807251030.39301.rusty@rustcorp.com.au>
References: <1216899979-32532-1-git-send-email-markmc@redhat.com> <1216899979-32532-4-git-send-email-markmc@redhat.com> <48890ECD.10104@qumranet.com>
Mime-Version: 1.0
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
Cc: Mark McLoughlin <markmc@redhat.com>, kvm@vger.kernel.org,
	Herbert Xu <herbert@gondor.apana.org.au>
To: Dor Laor <dor.laor@qumranet.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from ozlabs.org ([203.10.76.45]:45799 "EHLO ozlabs.org"
	rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP
	id S1755116AbYGYAan (ORCPT <rfc822;kvm@vger.kernel.org>);
	Thu, 24 Jul 2008 20:30:43 -0400
In-Reply-To: <48890ECD.10104@qumranet.com>
Content-Disposition: inline
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Friday 25 July 2008 09:22:53 Dor Laor wrote:
> Mark McLoughlin wrote:
> >  	vq->vring.used->flags &= ~VRING_USED_F_NO_NOTIFY;
> >  	qemu_del_timer(n->tx_timer);
> >  	n->tx_timer_active = 0;
>
> As stated by newer messages, we should handle the first tx notification
> if the timer wasn't active to shorten latency.
> Cheers, Dor

Here's what lguest does at the moment.  Basically, we cut the timeout a tiny 
bit each time, until we get *fewer* packets than last time.  Then we bump it 
up again.

Rough, but seems to work (it should be a per-device var of course, not a 
static).

@@ -921,6 +922,7 @@ static void handle_net_output(int fd, st
 	unsigned int head, out, in, num = 0;
 	int len;
 	struct iovec iov[vq->vring.num];
+	static int last_timeout_num;
 
 	if (!timeout)
 		net_xmit_notify++;
@@ -941,6 +943,14 @@ static void handle_net_output(int fd, st
 	/* Block further kicks and set up a timer if we saw anything. */
 	if (!timeout && num)
 		block_vq(vq);
+
+	if (timeout) {
+		if (num < last_timeout_num)
+			timeout_usec += 10;
+		else if (timeout_usec > 1)
+			timeout_usec--;
+		last_timeout_num = num;
+	}
 }