[ofa-general] perfquery causes kernel to be stuck in ib_unregister_mad_agent() function

Or Gerlitz ogerlitz at voltaire.com
Tue Apr 29 04:17:05 PDT 2008


Jean-Francois.Neyroud wrote:
> If I attemp to query at the same time the performance counters on all 
> nodes on a cluster ( 40 nodes) .
> perfquery causes kernel to be stuck in ib_unregister_mad_agent() 
> function.
> Impossible to send CTRL-C or CTRL-Z to perfquery, it is stuck in the 
> kernel.
maybe with
$ dmesg -c
$ echo 1 > /proc/sysrq-trigger
$ echo t > /proc/sysrq-trigger

and then looking on the related kernel threads stacks from the dmesg (eg 
of ib_madX threads, etc) you would get more info that you can share.

Or.





More information about the general mailing list