On Nov 4, 2004, at 12:03 PM, daniel.egloff_at_[hidden] wrote:
> It might be caused by a buggy MPI application which crashes often and
> which we currently
> debugging. Is it possible that this causes sharded memory / semaphores
> to be exhausted?
I don't see a follow-up, so I thought I would chime in. Yes, a
crashing application can cause SYS V semaphores / shared memory to be
exhausted. Running the "lamclean" command (or just re-lambooting) will
cause LAM to release all the SYS V resources it has allocated (as well
as kill all the processes running in the LAM universe). So if you
start seeing the RPI failure messages again, try running lamclean and
see if that clears the error up.
Hope this helps,
Brian
--
Brian Barrett
LAM/MPI developer and all around nice guy
Have an LAM/MPI day: http://www.lam-mpi.org/
|
