From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([208.118.235.92]:36360)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <lieven-lists@dlhnet.de>) id 1UK7YC-0006Sj-IE
	for qemu-devel@nongnu.org; Mon, 25 Mar 2013 09:35:05 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <lieven-lists@dlhnet.de>) id 1UK7YB-0003Qb-7Z
	for qemu-devel@nongnu.org; Mon, 25 Mar 2013 09:35:00 -0400
Received: from ssl.dlhnet.de ([91.198.192.8]:41176 helo=ssl.dlh.net)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <lieven-lists@dlhnet.de>) id 1UK7YB-0003QO-27
	for qemu-devel@nongnu.org; Mon, 25 Mar 2013 09:34:59 -0400
Message-ID: <51505281.2090108@dlhnet.de>
Date: Mon, 25 Mar 2013 14:34:57 +0100
From: Peter Lieven <lieven-lists@dlhnet.de>
MIME-Version: 1.0
References: <20130317090816.GB28528@redhat.com>
	<0c8d28e0-07d9-499f-920d-7ceca4155aab@mailpro>
	<20130318095308.GD5267@redhat.com>
In-Reply-To: <20130318095308.GD5267@redhat.com>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] slow virtio network with vhost=on and multiple
	cores
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: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Peter Lieven <pl@dlhnet.de>, Stefan Hajnoczi <stefanha@gmail.com>, qemu-devel@nongnu.org, Alexandre DERUMIER <aderumier@odiso.com>, Davide Guerri <d.guerri@unidata.it>, Jan Kiszka <jan.kiszka@web.de>, Dietmar Maurer <dietmar@proxmox.com>

On 18.03.2013 10:53, Michael S. Tsirkin wrote:
> Do you see all interrupts going to the same CPU? If yes is
> irqbalance in guest running?
I  had the same issue today. Problem is irqs are going to all vCPUs. If the smp_affinity is set to one CPU only
performance is OK. irqbalance is running, but it doesn't matter.

Peter