From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from [140.186.70.92] (port=49662 helo=eggs.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1OPhd2-0003G4-4y
	for qemu-devel@nongnu.org; Fri, 18 Jun 2010 15:53:29 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.69)
	(envelope-from <anthony@codemonkey.ws>) id 1OPhd0-00082K-W8
	for qemu-devel@nongnu.org; Fri, 18 Jun 2010 15:53:28 -0400
Received: from mail-yx0-f173.google.com ([209.85.213.173]:55988)
	by eggs.gnu.org with esmtp (Exim 4.69)
	(envelope-from <anthony@codemonkey.ws>) id 1OPhd0-000828-U2
	for qemu-devel@nongnu.org; Fri, 18 Jun 2010 15:53:26 -0400
Received: by yxn35 with SMTP id 35so258395yxn.4
	for <qemu-devel@nongnu.org>; Fri, 18 Jun 2010 12:53:25 -0700 (PDT)
Message-ID: <4C1BCEB0.6050601@codemonkey.ws>
Date: Fri, 18 Jun 2010 14:53:20 -0500
From: Anthony Liguori <anthony@codemonkey.ws>
MIME-Version: 1.0
Subject: Re: [Qemu-devel] smp broken in tcg mode with --enable-io-thread?
References: <4C1BA0B4.2010803@siemens.com>
In-Reply-To: <4C1BA0B4.2010803@siemens.com>
Content-Type: text/plain; charset=ISO-8859-15; format=flowed
Content-Transfer-Encoding: 7bit
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: Jan Kiszka <jan.kiszka@siemens.com>
Cc: Glauber Costa <glommer@redhat.com>, Marcelo Tosatti <mtosatti@redhat.com>, qemu-devel <qemu-devel@nongnu.org>

On 06/18/2010 11:37 AM, Jan Kiszka wrote:
> Hi,
>
> looks like SMP in emulation mode is broken once --enable-io-thread is
> turned on. Linux SMP guests lock up early during boot, often the whole
> QEMU process becomes uncontrollable after a while. That's at least the
> case here with x86 targets. The problem disappears when using
> -enable-kvm or building without --enable-io-thread.
>    

That's unfortunate.  I've been thinking we should enable io thread by 
default but this sort of regression would certainly prevent that.

Glauber/Marcelo, any guesses about what's happening?

Regards,

Anthony Liguori

> It's not on my critical path (ie. no time to go into details), I just
> stumbled over it and wanted to drop a note.
>
> Jan
>
>