> Hello James,
>
> something quite interesting happened during my stability tests. GPLPV
> 0.11.0.213 which I consider stable, showed the same hang as the newer
> GPLPV versions. I now try to find out why even the stable 0.11.0.213
hangs> when it was and is stable on our production systems. There are 3
possible> causes: Xen 4.1.1 vs Xen 4.0.1, dom0 2.6.32.36 vs 2.6.32.18 and CPU
Xeon E3-> 1230 vs Xeon X3450 [and board X9SCM-F vs. X8SIL-F].
>
> The attached log show debugkeys for the hang. I find lines 64-66 quite
> interesting where is shows that there is an event channel upcall
pending on> the hung VM2, no problems on VM1 (line 52-54). Could that be a hint to
the> real problem?
>
Could be, or it could just be a side effect - eg the machine has hung
and can''t process any further events that come through.
One thing I thought of... virtualisation gives an interesting
opportunity to exaggerate race conditions. If you have 8 vCPU''s in a
DomU but only let one or two physical CPUs service those 8 vCPU''s, then
it can give rise to race conditions which could only be rarely seen (or
never seen) in normal operation. It''s awful for performance but if you
could try that and see if it gives rise to crashes a bit more frequently
it might help us track down the problem.
Thanks
James
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xensource.com
http://lists.xensource.com/xen-devel