Hi, I am not sure if it's a real issue or not, but I run a user program
that calls MPI_Comm_spawn to launch on a remote node, the parent
processes got launched via ssh with no problem, but when the child
processes want to launch, I got a message saying that orted is not
found. I've only set my --prefix when I run my spawn job.
If I do the spawn job on local node only, it runs fine. And I can
workaround the issue by manually setting the -mca pls_rsh_orted with the
appropriate path.
But the FAQ says I don't need to put my PATH or LD_LIBRARY_PATH if I
have prefix, so shouldn't the prefix_dir be stashed away for the spawn
child?
======================
on node1, I do mpirun on remote host:
% ./mpirun -np 4 -host node2 -prefix /ompi/trunk/builds/sparc32-g
./mspawn2 -n 1 -C 5 -P 5
Password:
0: ./mspawn2: MPI_APPNUM = 1
2: ./mspawn2: MPI_APPNUM = 1
3: ./mspawn2: MPI_APPNUM = 1
1: ./mspawn2: MPI_APPNUM = 1
Password:
orted: Command not found.
^C^\Quit
--
Thanks,
- Pak Lui
