From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:45268)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <mst@redhat.com>) id 1TkwQv-0005r1-No
	for qemu-devel@nongnu.org; Tue, 18 Dec 2012 07:38:12 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <mst@redhat.com>) id 1TkwQs-0006BC-Oo
	for qemu-devel@nongnu.org; Tue, 18 Dec 2012 07:38:05 -0500
Received: from mx1.redhat.com ([209.132.183.28]:24002)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <mst@redhat.com>) id 1TkwQs-0006B6-HU
	for qemu-devel@nongnu.org; Tue, 18 Dec 2012 07:38:02 -0500
Date: Tue, 18 Dec 2012 14:41:10 +0200
From: "Michael S. Tsirkin" <mst@redhat.com>
Message-ID: <20121218124110.GA25463@redhat.com>
References: <cover.1355833220.git.mst@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <cover.1355833220.git.mst@redhat.com>
Subject: Re: [Qemu-devel] [PATCH 0/3] virtio: don't poll masked vectors with
	irqfd
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Asias He <asias@redhat.com>
Cc: Jan Kiszka <jan.kiszka@siemens.com>, Marcelo Tosatti <mtosatti@redhat.com>, qemu-devel@nongnu.org, kvm@vger.kernel.org, Peter Maydell <peter.maydell@linaro.org>

On Tue, Dec 18, 2012 at 02:20:20PM +0200, Michael S. Tsirkin wrote:
> At the moment when vector is masked virtio will poll it
> in userspace, even if it is handled by irqfd.
> This is done in order to update pending bits, but
> it's not really required until someone reads the pending bits.
> On the other hand this read results in extra io thread wakeups.
> 
> As we only implement the pending bits as a compatibility
> feature (read - real drivers don't use it), we can defer
> the irqfd poll until the read actually happens.
> 
> This does not seem to affect vhost-net speed
> in simple benchmarks but could help block: both
> vhost-blk and dataplane when using irqfd,
> and I also think this is cleaner than enabling/disabling
> notifiers all the time.
> 
> This will also be the basis for future optimizations.

Note: this is on top of the typesafe bindings patch v3
I sent previously.
You can get the whole bundle from:
git://git.kernel.org/pub/scm/virt/kvm/mst/qemu.git pci

-- 
MST