[mvapich-discuss] mvapich-0.9.8 Bus error

[Rene Salmon]

Hi,




> 
> 1. The version of OFED you compiled MVAPICH with and the one installed
> on the machines is the same?

Yes. I only have one version of OFED install on all machines and it is
version 1.1.


> 
> 2. What is the application you are running on the 8 nodes? Can you
> verify if cpi runs fine on 8 nodes?

Some of the nodes I have are 2 CPU dual core nodes.  All I am trying to run
is the cpi.c code that is in the mvapich examples directory.

If I log into one of the 2CPU dual core nodes and I try to run the cpi.c
code here is what I get.

mpi/mvapich> mpirun_rsh -np 2 compute-01-02-ib compute-01-02-ib ./a.out
/usr/X11R6/bin/xauth:  error in locking authority file
/u00/rsalmon/.Xauthority
Process 0 on compute-01-02
Process 1 on compute-01-02
pi is approximately 3.1415926544231318, Error is 0.0000000008333387
wall clock time = 0.000221

works fine for np=2.  I get the bus error for np=4.

mpi/mvapich> mpirun_rsh -np 4 compute-01-02-ib compute-01-02-ib
compute-01-02-ib compute-01-02-ib ./a.out
/usr/X11R6/bin/xauth:  error in locking authority file
/u00/rsalmon/.Xauthority
/usr/X11R6/bin/xauth:  error in locking authority file
/u00/rsalmon/.Xauthority
/usr/X11R6/bin/xauth:  error in locking authority file
/u00/rsalmon/.Xauthority
Bus error
Bus error
Bus error
Bus error


Thanks
Rene


>
        Rene Salmon
        Tulane University
        Center for Computational Science
        http://www.ccs.tulane.edu
        rsalmon at tulane.edu
        Tel 504-862-8393
        Fax 504-862-8392