EuroMPI 2015 Call for participation
EuroMPI 2015 in-cooperation status with ACM and SIGHPC in Bordeaux
France, 21st - 23rd September, 2015.
The prime annual meeting for researchers, developers, and students in
message-passing parallel computing with MPI and related paradigms.
Deadline of ea
> regardless of number of nodes
No, this is not true. I was referring to this specific test, which was the
one that preventing me from thinking about FQDN, and the DN is different in
this case. As I clearly stated in my original question - "The issue only
exposes itself when more than 2 nodes are
is name resolution working on *all* the nodes ?
orted might be ssh'ed in a tree fashion.
that means orted can either be ssh'ed by the node running mpirun or any
other node.
from n0009.scs00, can you make sure
ssh n0189.mako0 ssh n0198.mako0 echo ok
ssh n0233.mako0 ssh n0198.mako0 echo ok
both work
Yes all cross-node ssh works perfectly and this is our production system
which have been running for years. I've done all of these testing and was
puzzled by the inconsistent behavior that I observed. But enabling FQDN
resolves the issue so I am just trying to understand why the inconsistency
exist
can you try
mpirun --mca plm_rsh_no_tree_spawn 1 ...
without the FQDN and see if it helps ?
just to be clear, i can understand the following command
ssh n0189.mako0 ssh n0198 echo ok
does not work and has never worked before
what about the following command :
ssh n0189 ssh n0198.mako0 echo ok
my
