On Dec 13, 2005, at 9:41 AM, Dilani Perera wrote:
> My program works fine for upto 12 processors. But when its more
> than that
> it gives the following error. What can be the reason ?
>
>
> nuthatch% mpirun -v -np 14 /users/cs/grad/dilani/Research_2005/out
> A2000.txt
> 5074 /users/cs/grad/dilani/Research_2005/out running on n0 (o)
[snipped]
> PID 5074 failed on node n0 (134.153.50.235) due to signal 15.
I'm assuming that this is a linux system -- signal 15 is ENOTBLK.
> nuthatch% size :2000,
> size: ':2000,': No such file
> nuthatch% cs/grad/dilani/Research_2005/out A2000.txt
> <
> /bin/ksh: nuthatch%: not found
> nuthatch% 5074 /users/cs/grad/dilani/Research_2005/out running on
> n0 (o)
> /bin/ksh: syntax error: `(' unexpected
> nuthatch% 31791 /users/cs/grad/dilani/Research_2005/out running on n1
> /bin/ksh: 31791: not found
I think that this is your real error -- perhaps the A2000.txt file
was not found, or it was too small, and the Fortran read statements
aborted? I'm not sure why ksh is reporting that a variety of numbers
are not being found -- that seems to indicate that ksh is somehow
trying to execute applications named 31791, etc. Are you trying to
fork/exec something from your Fortran application?
In any case, it *looks* like this is a Fortran file error -- not an
MPI error...
--
{+} Jeff Squyres
{+} The Open MPI Project
{+} http://www.open-mpi.org/
|
