From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from [140.186.70.92] (port=53253 helo=eggs.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1PHZxq-0004ch-T4
	for qemu-devel@nongnu.org; Sun, 14 Nov 2010 05:37:40 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <stefanha@gmail.com>) id 1PHZxp-0001J7-SI
	for qemu-devel@nongnu.org; Sun, 14 Nov 2010 05:37:38 -0500
Received: from mail-wy0-f173.google.com ([74.125.82.173]:62852)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <stefanha@gmail.com>) id 1PHZxp-0001Iz-Ny
	for qemu-devel@nongnu.org; Sun, 14 Nov 2010 05:37:37 -0500
Received: by wyj26 with SMTP id 26so5023700wyj.4
	for <qemu-devel@nongnu.org>; Sun, 14 Nov 2010 02:37:36 -0800 (PST)
MIME-Version: 1.0
In-Reply-To: <4CDFBB19.7010702@redhat.com>
References: <1289483242-6069-1-git-send-email-stefanha@linux.vnet.ibm.com>
	<1289483242-6069-3-git-send-email-stefanha@linux.vnet.ibm.com>
	<20101111164518.GA28773@infradead.org>
	<AANLkTi=sHdEsPBBRYVu09HNWCCrP=8NL-+KTnUeJ4UAj@mail.gmail.com>
	<4CDFBB19.7010702@redhat.com>
Date: Sun, 14 Nov 2010 10:37:36 +0000
Message-ID: <AANLkTimFmt+hCt6XsDSz3V8DythW1ueUZWrrasRgpoqf@mail.gmail.com>
Subject: Re: [Qemu-devel] Re: [PATCH 2/3] virtio-pci: Use ioeventfd for
	virtqueue notify
From: Stefan Hajnoczi <stefanha@gmail.com>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: quoted-printable
List-Id: qemu-devel.nongnu.org
List-Unsubscribe: <http://lists.nongnu.org/mailman/listinfo/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: <http://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Avi Kivity <avi@redhat.com>
Cc: Christoph Hellwig <hch@infradead.org>, "Michael S. Tsirkin" <mst@redhat.com>, Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>, kvm@vger.kernel.org, qemu-devel@nongnu.org

On Sun, Nov 14, 2010 at 10:34 AM, Avi Kivity <avi@redhat.com> wrote:
> On 11/12/2010 11:20 AM, Stefan Hajnoczi wrote:
>>
>> > =A0Who guarantees that less common virtio-blk and virtio-net guest dri=
vers
>> > =A0for non-Linux OSes are fine with it? =A0Maybe you should add a feat=
ure
>> > flag
>> > =A0that the guest has to ACK to enable it.
>>
>> Virtio-blk and virtio-net are fine. =A0Both of those devices are
>> expected to operate asynchronously. =A0SeaBIOS and gPXE virtio-net
>> drivers spin but they expect to and it is okay in those environments.
>> They already burn CPU today.
>>
>> Virtio-console expects synchronous virtqueue kick. =A0In Linux,
>> virtio_console.c __send_control_msg() and send_buf() will spin. =A0Qemu
>> userspace is able to complete those requests synchronously so that the
>> guest never actually burns CPU (e.g.
>> hw/virtio-serial-bus.c:send_control_msg()). =A0I don't want to burn CPU
>> in places where we previously didn't.
>
> This is a horrible bug. =A0virtio is an asynchronous API. =A0Some hypervi=
sor
> implementations cannot even provide synchronous notifications.
>
>> It's good that QEMU can decide whether or not to handle virtqueue kick
>> in the vcpu thread. =A0For high performance asynchronous devices like
>> virtio-net and virtio-blk it makes sense to use ioeventfd. =A0For others
>> it may not be useful. =A0I'm not sure a feature bit that exposes this
>> detail to the guest would be useful.
>
> The guest should always assume that virtio devices are asynchronous.

I agree, but let's enable virtio-ioeventfd carefully because bad code
is out there.

Stefan