I've tried to find anything on this on the mailings list or anywhere
else, but I wasn't able to.
In OpenMPI 1.2.x, I was able to simply run
mpiexec -n 2 hostname
on my Dual core machine without any problems. All MPI tasks inherited
the environment of the calling shell, and no SSH was used whatsoever.
Now, using OpenMPI 1.3.1, it seems to try to use ssh to start the
processes, which on the one hand requires me to enter the
password/passphrase, and furthermore destroys the environment. This make
it much less convenient to use OpenMPI on Multicore machines, compared
What's the reason for this change in behavior? And is there a way to get
back to the old behavior?