mpiexec in 2 nodes
Marchand Aurélia
aurelia.marchand at obspm.fr
Tue Oct 9 09:02:21 EDT 2007
Hi
I have a problem using mpiexec in more than one node.
when I have :
#PBS -l nodes=1:ppn=2
it work well
and when I have :
#PBS -l nodes=quadri3:ppn=1+quadri1:ppn=1
mpiexec --comm=mpich2 /home/marchand/PBS/test/nomProc2.mpich
I have the error :
mpiexec: resolve_exe: using absolute path "/home/marchand/PBS/test/nomProc2.mpich".
mpiexec: accept_pmi_conn: cmd=initack pmiid=0.
mpiexec: accept_pmi_conn: rank 0 (spawn 0) checks in.
mpiexec: accept_pmi_conn: cmd=init pmi_version=1 pmi_subversion=1.
[unset]: connect failed with connection refused
[unset]: Unable to connect to quadri3 on 39045
[unset]: aborting job:
Fatal error in MPI_Init: Other MPI error, error stack:
MPIR_Init_thread(247): Initialization failed
MPID_Init(71)........: channel initialization failed
MPID_Init(274).......: PMI_Init returned -1
mpiexec: process_start_event: evt 2 task 0 on quadri3.
mpiexec: process_start_event: evt 3 task 1 on quadri1.
mpiexec: All 2 tasks (spawn 0) started.
mpiexec: wait_tasks: waiting for quadri3 quadri1.
mpiexec: process_obit_event: evt 5 task 1 on quadri1 stat 1.
mpiexec: wait_tasks: waiting for quadri3.
=>> PBS: job killed: walltime 39 exceeded limit 30
mpiexec: killall: caught signal 15 (Terminated).
mpiexec: kill_tasks: killing all tasks.
mpiexec: wait_tasks: waiting for quadri3.
mpiexec: killall: caught signal 15 (Terminated).
mpiexec: Warning: task 1 exited with status 1.
I use :
torque-2.1.8
mpich2-1.0.5p4
maui-3.2.6p19
Thanks in advance
Aurelia Marchand
--
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Aurélia Marchand
Service Informatique de l'Observatoire
5 place Jules Janssen Tel : 01 45 07 76 24
92195 Meudon Fax : 01 45 07 76 13
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
More information about the mpiexec
mailing list