[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Condor-users] machine_count



Hello all....
I am configuring MPI.(on 4 nodes)

When 'machine_count=1' ,sends the job to a remote machine, and everything
works fine, but when machine_count > 1 does not work

when machine_coun = 1 , always works well, regardless of which node you
run...

the output of the output file is:

p0_2666:  p4_error: Child process exited while making connection to remote
process on g10.dic.umag.cl: 0
p0_2666: (4.023960) net_send: could not write to fd=4, errno = 32
rm_2663: (-) net_recv failed for fd = 3
rm_2663:  p4_error: net_recv read, errno = : 104

I need ideas please!!!!!!
Grasias