Failed to execute MPICH2 on multiple machines on ubuntu 12.04 (problem with HYDU_sock_connect)

Question

It's hard for me to run the MPI program on two machines. OS - Ubuntu 12.04. And the MPI implementation is MPICH2

ssh is working fine:

root@ubuntu :/home# ssh 192.168.1.9 root@gpuguy password: Welcome to Ubuntu 12.04.3 LTS (GNU/Linux 3.8.0-29-generic i686) * Documentation: https://help.ubuntu.com/ 131 packages can be updated. 67 updates are security updates. Last login: Thu Oct 24 17:36:25 2013 from ubuntu.local root@gpuguy :~# 

But when I run my MPI programs, this breaks:

 root@ubuntu :/home# mpiexec -f hosts.cfg -n 4 hello root@192.168.1.9 password: [proxy:0: 0@gpuguy ] HYDU_sock_connect (./utils/sock/sock.c:171): unable to get host address for ubuntu (1) [proxy:0: 0@gpuguy ] main (./pm/pmiserv/pmip.c:209): unable to connect to server ubuntu at port 42104 (check for firewalls!) 

I have already disabled the firewall on both machines, so I can successfully execute ssh. But how to solve this problem?

My MPI code successfully runs on the same machine.

Answer 1

For MPICH (or any MPI implementation) to work, you need to configure SSH without a password. I should also mention that you really don't need to register as root to do this work. It is usually a very bad idea to register as root all the time.