Re: [Xen-users] Xen system hang or freeze

[Nick Anderson <nick@xxxxxxxxxxxx>]

On Tue, May 05, 2009 at 09:00:06AM -0400, Peter Booth wrote:
> Martin,
> You and Nick both see this problem on a system with eight cores.
> You have 4 domUs, Nick has 3 domUs.
> I think a reasonable hypothesis is that this is some kind of resource  
> starvation/livelock/deadlock scenario.
> Some questions that might help see  how similar your scenario and Nick's 
> are:
> 1. How many vcpus does each of your domUs have?
> 2. Do you define pinning, cap or weight for your domUs?
> 3. Does sar on the guests show a high %steal before the problem occurred 
> ?
> 4. Do you limit the number of vcpus that Dom0 has? If not, I would  
> suggest that you try this an dsee if the problem occurs when you know  
> that there should be free vcpus for each of your domUs.

I started monitoring %steal with my zenoss install. This weekend I had
another odd occurrence. My steal did not jump but my host did not spin
out of control either. One vm with apache on it just went nutty. Any
time apache was running (and there was traffic) apache would just
start hogging the cpu. But the cpu time was being spent in system not
in user. I restarted the virtual machine several times to no avail.
Ultimately I decided to try rebooting the host. After the host was
rebooted my problems went away again. I can only suspect something to
have gone wonky with xens network driver. I wrote a little wrapper for
sar if anyone is interested. All it does is return the single
statistic for a 1 second period that you might be looking for. I just
stick it in my snmp as exec lines so I can easily expose the sar
metrics for zenoss.
-- 
Nick Anderson <nick@xxxxxxxxxxxx>
http://www.cmdln.org


_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users