Hi Gilles, I'm currently testing and here are some preliminary results:
On Thu, Mar 23, 2017 at 10:33 AM, Gilles Gouaillardet <gilles.gouaillar...@gmail.com> wrote: > Can you please try > mpirun --mca btl tcp,self ... this failed to produce the program output, there were lots of errors like this: [pax11-00][[54124,1],31][btl_tcp_endpoint.c:803:mca_btl_tcp_endpoint_complete_connect] connect() to 192.168.225.202 failed: Connection timed out (110) I had to terminate the job. That's why I have added the option --mca btl_tcp_if_exclude ib0 . In this case, the program started to produce output, but started hanging early on with this error: [pax11-00][[61232,1],31][btl_tcp_endpoint.c:803:mca_btl_tcp_endpoint_complete_connect] connect() to 127.0.0.1 failed: Connection refused (111) [pax11-01][[61232,1],63][btl_tcp_endpoint.c:649:mca_btl_tcp_endpoint_recv_connect_ack] received unexpected process identifier [[61232,1],33] I have aborted that job as well. > And if it works > mpirun --mca btl openib,self ... This is running fine so far but will take some more time. Regards, Götz _______________________________________________ users mailing list users@lists.open-mpi.org https://rfd.newmexicoconsortium.org/mailman/listinfo/users
