From mboxrd@z Thu Jan  1 00:00:00 1970
From: Andrew Evans <andrewe@yahoo-inc.com>
Subject: more xenoprof woes (active domains not working)
Date: Thu, 28 Jan 2010 17:25:17 -0800
Message-ID: <4B6238FD.8090906@yahoo-inc.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Return-path: <xen-devel-bounces@lists.xensource.com>
List-Unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xensource.com>
List-Help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-Subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
Sender: xen-devel-bounces@lists.xensource.com
Errors-To: xen-devel-bounces@lists.xensource.com
To: xen-devel@lists.xensource.com
List-Id: xen-devel@lists.xenproject.org

(whoops, accidentally hit Ctrl-Enter while trying to paste, sorry!)

Hi,

I've been trying to get xenoprof working on a Xen 3.4.2 system running a
RHEL 5 dom0 kernel and RHEL 4 in the (only) domU.

I rebuilt Xen 3.4.2 with this patch as instructed in other messages to
this list:

http://lists.xensource.com/archives/html/xen-devel/2009-12/msg00709.html

That temporarily fixed the

(XEN) xenoprof: operation 9 failed for dom 0 (status : -1)

error seen in Xen dmesg when trying to start profiling an active domain.
Now that dreaded error is back, and I have no idea why: the version of
Xen that's booted hasn't changed, the patch has been applied to the
sources, the installed xen.gz in /boot matches the one built from the
patched sources byte-for-byte.

I'm following the instructions from
http://xenoprof.sourceforge.net/xenoprof_2.0.txt, specifically:

     1) On the initiator domain
         > opcontrol --reset
           (clear out any previous data of current session)
         > opcontrol --start-daemon
                     [--active-domains=<active_list>]
                     [--passive-domains=<passive_list>] ...
           (start OProfile daemon and specify the set of active and
           passive domains in the session)

     2) On each active domain
         > opcontrol --reset
         > opcontrol --start
         (indicates domain is ready to process performance events)
     3) On initiator
         > opcontrol --start
         (Multi-domain profiling session starts)
         (This is only successful if all active domains are ready)

I've rebooted the machine several times, but the error persists.

I'm going to try xen-unstable to see if that works, but is there
anything else I can try to get this working with 3.4.2? We have a number
of 3.3.1 systems that I'd like to be able to do active profiling of
domUs on.

thanks,

-Andrew