From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from [140.186.70.92] (port=37446 helo=eggs.gnu.org)
	by lists.gnu.org with esmtp (Exim 4.43) id 1OH9hR-00059J-EK
	for qemu-devel@nongnu.org; Wed, 26 May 2010 02:02:42 -0400
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.69)
	(envelope-from <prerna@linux.vnet.ibm.com>) id 1OH9hQ-0002d4-4R
	for qemu-devel@nongnu.org; Wed, 26 May 2010 02:02:41 -0400
Received: from e23smtp08.au.ibm.com ([202.81.31.141]:34909)
	by eggs.gnu.org with esmtp (Exim 4.69)
	(envelope-from <prerna@linux.vnet.ibm.com>) id 1OH9hP-0002ck-HB
	for qemu-devel@nongnu.org; Wed, 26 May 2010 02:02:40 -0400
Received: from d23relay05.au.ibm.com (d23relay05.au.ibm.com [202.81.31.247])
	by e23smtp08.au.ibm.com (8.14.3/8.13.1) with ESMTP id o4Q62Z6Y016314
	for <qemu-devel@nongnu.org>; Wed, 26 May 2010 16:02:35 +1000
Received: from d23av04.au.ibm.com (d23av04.au.ibm.com [9.190.235.139])
	by d23relay05.au.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id
	o4Q62YfX1622162
	for <qemu-devel@nongnu.org>; Wed, 26 May 2010 16:02:36 +1000
Received: from d23av04.au.ibm.com (loopback [127.0.0.1])
	by d23av04.au.ibm.com (8.14.3/8.13.1/NCO v10.0 AVout) with ESMTP id
	o4Q62XAn009235
	for <qemu-devel@nongnu.org>; Wed, 26 May 2010 16:02:34 +1000
Message-ID: <4BFCB977.1010408@linux.vnet.ibm.com>
Date: Wed, 26 May 2010 11:32:31 +0530
From: Prerna Saxena <prerna@linux.vnet.ibm.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Subject: [Qemu-devel] Tracing concerns for concurrent execution
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: qemu-devel@nongnu.org
Cc: Maneesh Soni <maneesh@linux.vnet.ibm.com>, Anthony Liguori <aliguori@us.ibm.com>, Ananth <ananth@linux.vnet.ibm.com>, Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>

Hi,
I am writing a tracing back-end that logs tracepoint-based traces to 
qemu-internal global buffers.
I had zeroed in on a lockless buffer for logging traces(to prevent 
slowdowns 'cos of locks held while tracing). However, I'm not sure if 
qemu threads might need some synchronisation to access the global trace 
buffer.
I think the vcpu threads run lock-step, but this lock-step behaviour is 
not guaranteed for some other types of threads, such as the aio helper 
threads ? Also, can there be concurrency issues while tracing dynamic 
translator ?
While I'm doing my study, it would be good to have some pointers on what 
assumptions can / not be made for concurrent thread execution in qemu, 
and what could be done to safeguard tracing in such hot-paths ?

Regards,
-- 
Prerna Saxena

Linux Technology Centre,
IBM Systems and Technology Lab,
Bangalore, India