Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: [OMPI users] OpenMPI and OAR issues
From: Andrea Pellegrini (andrea.pellegrini_at_[hidden])
Date: 2008-11-06 14:55:54


Hi all,
I'm trying to run an openmpi application on a oar cluster. I think the
cluster is configured correctly but I still have problems when I run
mpirun:

apellegr_at_m45-037:~$ mpirun -prefix /n/poolfs/z/home/apellegr/openmpi
-machinefile $OAR_FILE_NODES -mca pls_rsh_agent "oarsh" -np 10
/n/poolfs/z/home/apellegr/mpi_test/hello_world.x86 bash: -c: line 0:
syntax error near unexpected token `('
bash: -c: line 0: ` set path = ( /n/poolfs/z/home/apellegr/openmpi/bin
$path ) ; if ( $?LD_LIBRARY_PATH == 1 ) set OMPI_have_llp ; if (
$?LD_LIBRARY_PATH == 0 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib ; if ( $?OMPI_have_llp == 1 )
setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.4
--num_procs 5 --vpid_start 0 --nodename m45-040.pool --universe
apellegr_at_m45-037.pool:default-universe-29482 --nsreplica
"0.0.0;tcp://10.11.45.37:36790" --gprreplica
"0.0.0;tcp://10.11.45.37:36790"'
bash: -c: line 0: syntax error near unexpected token `('
bash: -c: line 0: ` set path = ( /n/poolfs/z/home/apellegr/openmpi/bin
$path ) ; if ( $?LD_LIBRARY_PATH == 1 ) set OMPI_have_llp ; if (
$?LD_LIBRARY_PATH == 0 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib ; if ( $?OMPI_have_llp == 1 )
setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.2
--num_procs 5 --vpid_start 0 --nodename m45-038.pool --universe
apellegr_at_m45-037.pool:default-universe-29482 --nsreplica
"0.0.0;tcp://10.11.45.37:36790" --gprreplica
"0.0.0;tcp://10.11.45.37:36790"'
[m45-037.pool:29482] ERROR: A daemon on node m45-038.pool failed to
start as expected.
[m45-037.pool:29482] ERROR: There may be more information available from
[m45-037.pool:29482] ERROR: the remote shell (see above).
[m45-037.pool:29482] ERROR: The daemon exited unexpectedly with status 2.
bash: -c: line 0: syntax error near unexpected token `('
bash: -c: line 0: ` set path = ( /n/poolfs/z/home/apellegr/openmpi/bin
$path ) ; if ( $?LD_LIBRARY_PATH == 1 ) set OMPI_have_llp ; if (
$?LD_LIBRARY_PATH == 0 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib ; if ( $?OMPI_have_llp == 1 )
setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.3
--num_procs 5 --vpid_start 0 --nodename m45-039.pool --universe
apellegr_at_m45-037.pool:default-universe-29482 --nsreplica
"0.0.0;tcp://10.11.45.37:36790" --gprreplica
"0.0.0;tcp://10.11.45.37:36790"'
[m45-037.pool:29482] ERROR: A daemon on node m45-039.pool failed to
start as expected.
[m45-037.pool:29482] ERROR: There may be more information available from
[m45-037.pool:29482] ERROR: the remote shell (see above).
[m45-037.pool:29482] ERROR: The daemon exited unexpectedly with status 2.
[m45-037.pool:29482] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../orte/mca/pls/base/pls_base_orted_cmds.c at line 275
[m45-037.pool:29482] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../../orte/mca/pls/rsh/pls_rsh_module.c at line 1158
[m45-037.pool:29482] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../../orte/mca/errmgr/hnp/errmgr_hnp.c at line 90
[m45-037.pool:29482] ERROR: A daemon on node m45-040.pool failed to
start as expected.
[m45-037.pool:29482] ERROR: There may be more information available from
[m45-037.pool:29482] ERROR: the remote shell (see above).
[m45-037.pool:29482] ERROR: The daemon exited unexpectedly with status 2.
[m45-037.pool:29482] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../orte/mca/pls/base/pls_base_orted_cmds.c at line 188
[m45-037.pool:29482] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../../orte/mca/pls/rsh/pls_rsh_module.c at line 1190
--------------------------------------------------------------------------
mpirun was unable to cleanly terminate the daemons for this job.
Returned value Timeout instead of ORTE_SUCCESS.
--------------------------------------------------------------------------
apellegr_at_m45-037:~$

If I run it with the option "-mca pls_rsh_debug 1" I get:

apellegr_at_m45-037:~$ mpirun -prefix /n/poolfs/z/home/apellegr/openmpi
-machinefile $OAR_FILE_NODES -mca pls_rsh_debug 1 -mca pls_rsh_agent
"oarsh" -np 10 /n/poolfs/z/home/apellegr/mpi_test/hello_world.x86
[m45-037.pool:29473] pls:rsh: local shell: 2 (tcsh)
[m45-037.pool:29473] pls:rsh: assuming same remote shell as local shell
[m45-037.pool:29473] pls:rsh: remote shell: 2 (tcsh)
[m45-037.pool:29473] pls:rsh: final template argv:
[m45-037.pool:29473] pls:rsh: /usr/bin/oarsh <template> orted
--bootproxy 1 --name <template> --num_procs 5 --vpid_start 0 --nodename
<template> --universe apellegr_at_m45-037.pool:default-universe-29473
--nsreplica "0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477"
[m45-037.pool:29473] pls:rsh: launching on node m45-037.pool
[m45-037.pool:29473] pls:rsh: m45-037.pool is a LOCAL node
[m45-037.pool:29473] pls:rsh: reset PATH:
/n/poolfs/z/home/apellegr/openmpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/X11R6/bin:/n/poolfs/z/home/apellegr/openmpi/bin:/n/poolfs/z/home/apellegr/openssl/bin

[m45-037.pool:29473] pls:rsh: reset LD_LIBRARY_PATH:
/n/poolfs/z/home/apellegr/openmpi/lib
[m45-037.pool:29473] pls:rsh: changing to directory /home/apellegr
[m45-037.pool:29473] pls:rsh: executing:
(/n/poolfs/z/home/apellegr/openmpi/bin/orted) orted --bootproxy 1 --name
0.0.1 --num_procs 5 --vpid_start 0 --nodename m45-037.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477" --set-sid [OAR_JOBID=597856
HOST=m45-037.pool TERM=xterm SHELL=/bin/tcsh
OAR_WORKING_DIRECTORY=/home/apellegr SSH_CLIENT=10.11.0.4 50481 6667
OAR_USER=apellegr GROUP=csestudents USER=apellegr SUDO_USER=oar
OAR_WORKDIR=/home/apellegr SUDO_UID=30143 HOSTTYPE=i486-linux
USERNAME=apellegr OAR_JOB_NAME= OAR_NODE_FILE=/var/lib/oar/597856
OAR_RESOURCE_PROPERTIES_FILE=/var/lib/oar/597856_resources
MAIL=/var/mail/oar
PATH=/n/poolfs/z/home/apellegr/openmpi/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/X11R6/bin:/n/poolfs/z/home/apellegr/openmpi/bin:/n/poolfs/z/home/apellegr/openssl/bin
OAR_PROJECT_NAME=default OAR_JOB_WALLTIME_SECONDS=7200
PWD=/home/apellegr HOME=/home/apellegr SUDO_COMMAND=OAR SHLVL=2
OAR_FILE_NODES=/var/lib/oar/597856 OSTYPE=linux VENDOR=intel
OAR_JOB_WALLTIME=2:0:0 MACHTYPE=i486 LOGNAME=apellegr
OAR_NODEFILE=/var/lib/oar/597856 OAR_RESOURCE_FILE=/var/lib/oar/597856
SUDO_GID=390 OAR_JOB_ID=597856 OAR_O_WORKDIR=/home/apellegr
_=/n/poolfs/z/home/apellegr/openmpi/bin/mpirun
OLDPWD=/home/apellegr/openmpi
OMPI_MCA_rds_hostfile_path=/var/lib/oar/597856 OMPI_MCA_pls_rsh_debug=1
OMPI_MCA_pls_rsh_agent=oarsh
LD_LIBRARY_PATH=/n/poolfs/z/home/apellegr/openmpi/lib OMPI_MCA_seed=0]
[m45-037.pool:29473] pls:rsh: launching on node m45-038.pool
[m45-037.pool:29473] pls:rsh: m45-038.pool is a REMOTE node
[m45-037.pool:29473] pls:rsh: executing: (//usr/bin/oarsh)
/usr/bin/oarsh m45-038.pool set path = (
/n/poolfs/z/home/apellegr/openmpi/bin $path ) ; if ( $?LD_LIBRARY_PATH
== 1 ) set OMPI_have_llp ; if ( $?LD_LIBRARY_PATH == 0 ) setenv
LD_LIBRARY_PATH /n/poolfs/z/home/apellegr/openmpi/lib ; if (
$?OMPI_have_llp == 1 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.2
--num_procs 5 --vpid_start 0 --nodename m45-038.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477" [OAR_JOBID=597856 HOST=m45-037.pool
TERM=xterm SHELL=/bin/tcsh OAR_WORKING_DIRECTORY=/home/apellegr
SSH_CLIENT=10.11.0.4 50481 6667 OAR_USER=apellegr GROUP=csestudents
USER=apellegr SUDO_USER=oar OAR_WORKDIR=/home/apellegr SUDO_UID=30143
HOSTTYPE=i486-linux USERNAME=apellegr OAR_JOB_NAME=
OAR_NODE_FILE=/var/lib/oar/597856
OAR_RESOURCE_PROPERTIES_FILE=/var/lib/oar/597856_resources
MAIL=/var/mail/oar
PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/X11R6/bin:/n/poolfs/z/home/apellegr/openmpi/bin:/n/poolfs/z/home/apellegr/openssl/bin
OAR_PROJECT_NAME=default OAR_JOB_WALLTIME_SECONDS=7200
PWD=/home/apellegr HOME=/home/apellegr SUDO_COMMAND=OAR SHLVL=2
OAR_FILE_NODES=/var/lib/oar/597856 OSTYPE=linux VENDOR=intel
OAR_JOB_WALLTIME=2:0:0 MACHTYPE=i486 LOGNAME=apellegr
OAR_NODEFILE=/var/lib/oar/597856 OAR_RESOURCE_FILE=/var/lib/oar/597856
SUDO_GID=390 OAR_JOB_ID=597856 OAR_O_WORKDIR=/home/apellegr
_=/n/poolfs/z/home/apellegr/openmpi/bin/mpirun
OLDPWD=/home/apellegr/openmpi
OMPI_MCA_rds_hostfile_path=/var/lib/oar/597856 OMPI_MCA_pls_rsh_debug=1
OMPI_MCA_pls_rsh_agent=oarsh OMPI_MCA_seed=0]
bash: -c: line 0: syntax error near unexpected token `('
bash: -c: line 0: ` set path = ( /n/poolfs/z/home/apellegr/openmpi/bin
$path ) ; if ( $?LD_LIBRARY_PATH == 1 ) set OMPI_have_llp ; if (
$?LD_LIBRARY_PATH == 0 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib ; if ( $?OMPI_have_llp == 1 )
setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.2
--num_procs 5 --vpid_start 0 --nodename m45-038.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477"'
[m45-037.pool:29473] pls:rsh: launching on node m45-039.pool
[m45-037.pool:29473] ERROR: A daemon on node m45-038.pool failed to
start as expected.
[m45-037.pool:29473] ERROR: There may be more information available from
[m45-037.pool:29473] ERROR: the remote shell (see above).
[m45-037.pool:29473] ERROR: The daemon exited unexpectedly with status 2.
[m45-037.pool:29473] pls:rsh: m45-039.pool is a REMOTE node
[m45-037.pool:29473] pls:rsh: executing: (//usr/bin/oarsh)
/usr/bin/oarsh m45-039.pool set path = (
/n/poolfs/z/home/apellegr/openmpi/bin $path ) ; if ( $?LD_LIBRARY_PATH
== 1 ) set OMPI_have_llp ; if ( $?LD_LIBRARY_PATH == 0 ) setenv
LD_LIBRARY_PATH /n/poolfs/z/home/apellegr/openmpi/lib ; if (
$?OMPI_have_llp == 1 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.3
--num_procs 5 --vpid_start 0 --nodename m45-039.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477" [OAR_JOBID=597856 HOST=m45-037.pool
TERM=xterm SHELL=/bin/tcsh OAR_WORKING_DIRECTORY=/home/apellegr
SSH_CLIENT=10.11.0.4 50481 6667 OAR_USER=apellegr GROUP=csestudents
USER=apellegr SUDO_USER=oar OAR_WORKDIR=/home/apellegr SUDO_UID=30143
HOSTTYPE=i486-linux USERNAME=apellegr OAR_JOB_NAME=
OAR_NODE_FILE=/var/lib/oar/597856
OAR_RESOURCE_PROPERTIES_FILE=/var/lib/oar/597856_resources
MAIL=/var/mail/oar
PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/X11R6/bin:/n/poolfs/z/home/apellegr/openmpi/bin:/n/poolfs/z/home/apellegr/openssl/bin
OAR_PROJECT_NAME=default OAR_JOB_WALLTIME_SECONDS=7200
PWD=/home/apellegr HOME=/home/apellegr SUDO_COMMAND=OAR SHLVL=2
OAR_FILE_NODES=/var/lib/oar/597856 OSTYPE=linux VENDOR=intel
OAR_JOB_WALLTIME=2:0:0 MACHTYPE=i486 LOGNAME=apellegr
OAR_NODEFILE=/var/lib/oar/597856 OAR_RESOURCE_FILE=/var/lib/oar/597856
SUDO_GID=390 OAR_JOB_ID=597856 OAR_O_WORKDIR=/home/apellegr
_=/n/poolfs/z/home/apellegr/openmpi/bin/mpirun
OLDPWD=/home/apellegr/openmpi
OMPI_MCA_rds_hostfile_path=/var/lib/oar/597856 OMPI_MCA_pls_rsh_debug=1
OMPI_MCA_pls_rsh_agent=oarsh OMPI_MCA_seed=0]
bash: -c: line 0: syntax error near unexpected token `('
bash: -c: line 0: ` set path = ( /n/poolfs/z/home/apellegr/openmpi/bin
$path ) ; if ( $?LD_LIBRARY_PATH == 1 ) set OMPI_have_llp ; if (
$?LD_LIBRARY_PATH == 0 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib ; if ( $?OMPI_have_llp == 1 )
setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.3
--num_procs 5 --vpid_start 0 --nodename m45-039.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477"'
[m45-037.pool:29473] pls:rsh: launching on node m45-040.pool
[m45-037.pool:29473] ERROR: A daemon on node m45-039.pool failed to
start as expected.
[m45-037.pool:29473] ERROR: There may be more information available from
[m45-037.pool:29473] ERROR: the remote shell (see above).
[m45-037.pool:29473] ERROR: The daemon exited unexpectedly with status 2.
[m45-037.pool:29473] pls:rsh: m45-040.pool is a REMOTE node
[m45-037.pool:29473] pls:rsh: executing: (//usr/bin/oarsh)
/usr/bin/oarsh m45-040.pool set path = (
/n/poolfs/z/home/apellegr/openmpi/bin $path ) ; if ( $?LD_LIBRARY_PATH
== 1 ) set OMPI_have_llp ; if ( $?LD_LIBRARY_PATH == 0 ) setenv
LD_LIBRARY_PATH /n/poolfs/z/home/apellegr/openmpi/lib ; if (
$?OMPI_have_llp == 1 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.4
--num_procs 5 --vpid_start 0 --nodename m45-040.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477" [OAR_JOBID=597856 HOST=m45-037.pool
TERM=xterm SHELL=/bin/tcsh OAR_WORKING_DIRECTORY=/home/apellegr
SSH_CLIENT=10.11.0.4 50481 6667 OAR_USER=apellegr GROUP=csestudents
USER=apellegr SUDO_USER=oar OAR_WORKDIR=/home/apellegr SUDO_UID=30143
HOSTTYPE=i486-linux USERNAME=apellegr OAR_JOB_NAME=
OAR_NODE_FILE=/var/lib/oar/597856
OAR_RESOURCE_PROPERTIES_FILE=/var/lib/oar/597856_resources
MAIL=/var/mail/oar
PATH=/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin:/usr/X11R6/bin:/n/poolfs/z/home/apellegr/openmpi/bin:/n/poolfs/z/home/apellegr/openssl/bin
OAR_PROJECT_NAME=default OAR_JOB_WALLTIME_SECONDS=7200
PWD=/home/apellegr HOME=/home/apellegr SUDO_COMMAND=OAR SHLVL=2
OAR_FILE_NODES=/var/lib/oar/597856 OSTYPE=linux VENDOR=intel
OAR_JOB_WALLTIME=2:0:0 MACHTYPE=i486 LOGNAME=apellegr
OAR_NODEFILE=/var/lib/oar/597856 OAR_RESOURCE_FILE=/var/lib/oar/597856
SUDO_GID=390 OAR_JOB_ID=597856 OAR_O_WORKDIR=/home/apellegr
_=/n/poolfs/z/home/apellegr/openmpi/bin/mpirun
OLDPWD=/home/apellegr/openmpi
OMPI_MCA_rds_hostfile_path=/var/lib/oar/597856 OMPI_MCA_pls_rsh_debug=1
OMPI_MCA_pls_rsh_agent=oarsh OMPI_MCA_seed=0]
bash: -c: line 0: syntax error near unexpected token `('
bash: -c: line 0: ` set path = ( /n/poolfs/z/home/apellegr/openmpi/bin
$path ) ; if ( $?LD_LIBRARY_PATH == 1 ) set OMPI_have_llp ; if (
$?LD_LIBRARY_PATH == 0 ) setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib ; if ( $?OMPI_have_llp == 1 )
setenv LD_LIBRARY_PATH
/n/poolfs/z/home/apellegr/openmpi/lib:$LD_LIBRARY_PATH ;
/n/poolfs/z/home/apellegr/openmpi/bin/orted --bootproxy 1 --name 0.0.4
--num_procs 5 --vpid_start 0 --nodename m45-040.pool --universe
apellegr_at_m45-037.pool:default-universe-29473 --nsreplica
"0.0.0;tcp://10.11.45.37:55477" --gprreplica
"0.0.0;tcp://10.11.45.37:55477"'
[m45-037.pool:29473] ERROR: A daemon on node m45-040.pool failed to
start as expected.
[m45-037.pool:29473] ERROR: There may be more information available from
[m45-037.pool:29473] ERROR: the remote shell (see above).
[m45-037.pool:29473] ERROR: The daemon exited unexpectedly with status 2.
[m45-037.pool:29473] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../orte/mca/pls/base/pls_base_orted_cmds.c at line 188
[m45-037.pool:29473] [0,0,0] ORTE_ERROR_LOG: Timeout in file
../../../../../orte/mca/pls/rsh/pls_rsh_module.c at line 1190
--------------------------------------------------------------------------
mpirun was unable to cleanly terminate the daemons for this job.
Returned value Timeout instead of ORTE_SUCCESS.
--------------------------------------------------------------------------
apellegr_at_m45-037:~$

Can anybody help me?
Thanks,
~Andrea