All phases MPI install Test build Test run
Date range:
Hardware:
OS:
MPI name:
MPI version:
Suite:
Test:
np:
Command:
Org:
Local username:
Platform name:
[Reset form]  [Start over]        [Preferences]  [Advanced]
Current time (GMT):2014-10-24 13:28:14
Date range (GMT): 2014-07-15 13:23:40 - 2014-07-16 13:23:40
Phase(s):Test run  (Via Direct Access)
Result:Fail only
Number of rows:6
Absolute date range:Create permalink

#
1
Date range
2014-07-16 10:42:48
Org
nvidia
Platform name
ivy cluster
Hardware
x86_64
OS
Linux
MPI name
ompi-v1.8
MPI version
1.8.2rc2r32247
Suite
ibm
Test
win_allocate_shared_mpifh
np
4
Command
mpirun --host drossetti-ivy0,drossetti-ivy0,drossetti-ivy1,drossetti-ivy1 -np 4 --mca
btl_openib_want_cuda_gdr 1 --mca coll_ml_disable_allgather 1 --mca
btl_openib_warn_default_gid_prefix 0 --prefix
/ivylogin/home/rvandevaart/mtt/mtt-scratch-3/installs/Wjgx/install
onesided/win_allocate_shared_mpifh 
Launcher
mpirun
Resource Manager
none
Runtime Parameters

Network

Description

Exit value
71
Signal
-1
Duration
00:00:01
Client serial
1125480
Result message
Failed; exit status: 71
Stdout
[drossetti-ivy0:11603] *** An error occurred in MPI_Win_allocate_shared
[drossetti-ivy0:11603] *** reported by process [8361541633,0]
[drossetti-ivy0:11603] *** on communicator MPI_COMM_WORLD
[drossetti-ivy0:11603] *** MPI_ERR_RMA_SHARED: Memory cannot be shared
[drossetti-ivy0:11603] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[62051,1],0]
  Exit code:    71
[drossetti-ivy0.nvidia.com:11600] 3 more processes have sent help message help-mpi-errors.txt /
mpi_errors_are_fatal
Stderr

Environment

#
2
Date range
2014-07-16 10:42:49
Org
nvidia
Platform name
ivy cluster
Hardware
x86_64
OS
Linux
MPI name
ompi-v1.8
MPI version
1.8.2rc2r32247
Suite
ibm
Test
win_allocate_shared_mpifh
np
4
Command
mpirun --host drossetti-ivy0,drossetti-ivy0,drossetti-ivy1,drossetti-ivy1 -np 4 --mca btl
sm,tcp,self --mca coll_ml_disable_allgather 1 --mca btl_openib_warn_default_gid_prefix 0 --prefix
/ivylogin/home/rvandevaart/mtt/mtt-scratch-3/installs/Wjgx/install
onesided/win_allocate_shared_mpifh 
Launcher
mpirun
Resource Manager
none
Runtime Parameters

Network

Description

Exit value
71
Signal
-1
Duration
00:00:01
Client serial
1125480
Result message
Failed; exit status: 71
Stdout
[drossetti-ivy0:11634] *** An error occurred in MPI_Win_allocate_shared
[drossetti-ivy0:11634] *** reported by process [8361082881,0]
[drossetti-ivy0:11634] *** on communicator MPI_COMM_WORLD
[drossetti-ivy0:11634] *** MPI_ERR_RMA_SHARED: Memory cannot be shared
[drossetti-ivy0:11634] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[62044,1],0]
  Exit code:    71
[drossetti-ivy0.nvidia.com:11631] 3 more processes have sent help message help-mpi-errors.txt /
mpi_errors_are_fatal
Stderr

Environment

#
3
Date range
2014-07-16 10:43:12
Org
nvidia
Platform name
ivy cluster
Hardware
x86_64
OS
Linux
MPI name
ompi-v1.8
MPI version
1.8.2rc2r32247
Suite
ibm
Test
win_allocate_shared
np
4
Command
mpirun --host drossetti-ivy0,drossetti-ivy0,drossetti-ivy1,drossetti-ivy1 -np 4 --mca
btl_openib_want_cuda_gdr 1 --mca coll_ml_disable_allgather 1 --mca
btl_openib_warn_default_gid_prefix 0 --prefix
/ivylogin/home/rvandevaart/mtt/mtt-scratch-3/installs/Wjgx/install onesided/win_allocate_shared 
Launcher
mpirun
Resource Manager
none
Runtime Parameters

Network

Description

Exit value
71
Signal
-1
Duration
00:00:01
Client serial
1125480
Result message
Failed; exit status: 71
Stdout
[drossetti-ivy0:12124] *** An error occurred in MPI_Win_allocate_shared
[drossetti-ivy0:12124] *** reported by process [8328445953,0]
[drossetti-ivy0:12124] *** on communicator MPI_COMM_WORLD
[drossetti-ivy0:12124] *** MPI_ERR_RMA_SHARED: Memory cannot be shared
[drossetti-ivy0:12124] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[61546,1],3]
  Exit code:    71
[drossetti-ivy0.nvidia.com:12121] 3 more processes have sent help message help-mpi-errors.txt /
mpi_errors_are_fatal
Stderr

Environment

#
4
Date range
2014-07-16 10:43:13
Org
nvidia
Platform name
ivy cluster
Hardware
x86_64
OS
Linux
MPI name
ompi-v1.8
MPI version
1.8.2rc2r32247
Suite
ibm
Test
win_allocate_shared
np
4
Command
mpirun --host drossetti-ivy0,drossetti-ivy0,drossetti-ivy1,drossetti-ivy1 -np 4 --mca btl
sm,tcp,self --mca coll_ml_disable_allgather 1 --mca btl_openib_warn_default_gid_prefix 0 --prefix
/ivylogin/home/rvandevaart/mtt/mtt-scratch-3/installs/Wjgx/install onesided/win_allocate_shared 
Launcher
mpirun
Resource Manager
none
Runtime Parameters

Network

Description

Exit value
71
Signal
-1
Duration
00:00:01
Client serial
1125480
Result message
Failed; exit status: 71
Stdout
[drossetti-ivy0:12155] *** An error occurred in MPI_Win_allocate_shared
[drossetti-ivy0:12155] *** reported by process [8326414337,0]
[drossetti-ivy0:12155] *** on communicator MPI_COMM_WORLD
[drossetti-ivy0:12155] *** MPI_ERR_RMA_SHARED: Memory cannot be shared
[drossetti-ivy0:12155] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[61515,1],0]
  Exit code:    71
[drossetti-ivy0.nvidia.com:12152] 3 more processes have sent help message help-mpi-errors.txt /
mpi_errors_are_fatal
Stderr

Environment

#
5
Date range
2014-07-16 10:44:23
Org
nvidia
Platform name
ivy cluster
Hardware
x86_64
OS
Linux
MPI name
ompi-v1.8
MPI version
1.8.2rc2r32247
Suite
ibm
Test
win_allocate_shared_usempi
np
4
Command
mpirun --host drossetti-ivy0,drossetti-ivy0,drossetti-ivy1,drossetti-ivy1 -np 4 --mca
btl_openib_want_cuda_gdr 1 --mca coll_ml_disable_allgather 1 --mca
btl_openib_warn_default_gid_prefix 0 --prefix
/ivylogin/home/rvandevaart/mtt/mtt-scratch-3/installs/Wjgx/install
onesided/win_allocate_shared_usempi 
Launcher
mpirun
Resource Manager
none
Runtime Parameters

Network

Description

Exit value
71
Signal
-1
Duration
00:00:01
Client serial
1125480
Result message
Failed; exit status: 71
Stdout
[drossetti-ivy0:13561] *** An error occurred in MPI_Win_allocate_shared
[drossetti-ivy0:13561] *** reported by process [8250523649,0]
[drossetti-ivy0:13561] *** on communicator MPI_COMM_WORLD
[drossetti-ivy0:13561] *** MPI_ERR_RMA_SHARED: Memory cannot be shared
[drossetti-ivy0:13561] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[60357,1],2]
  Exit code:    71
[drossetti-ivy0.nvidia.com:13558] 3 more processes have sent help message help-mpi-errors.txt /
mpi_errors_are_fatal
Stderr

Environment

#
6
Date range
2014-07-16 10:44:25
Org
nvidia
Platform name
ivy cluster
Hardware
x86_64
OS
Linux
MPI name
ompi-v1.8
MPI version
1.8.2rc2r32247
Suite
ibm
Test
win_allocate_shared_usempi
np
4
Command
mpirun --host drossetti-ivy0,drossetti-ivy0,drossetti-ivy1,drossetti-ivy1 -np 4 --mca btl
sm,tcp,self --mca coll_ml_disable_allgather 1 --mca btl_openib_warn_default_gid_prefix 0 --prefix
/ivylogin/home/rvandevaart/mtt/mtt-scratch-3/installs/Wjgx/install
onesided/win_allocate_shared_usempi 
Launcher
mpirun
Resource Manager
none
Runtime Parameters

Network

Description

Exit value
71
Signal
-1
Duration
00:00:00
Client serial
1125480
Result message
Failed; exit status: 71
Stdout
[drossetti-ivy0:13593] *** An error occurred in MPI_Win_allocate_shared
[drossetti-ivy0:13593] *** reported by process [8223326209,0]
[drossetti-ivy0:13593] *** on communicator MPI_COMM_WORLD
[drossetti-ivy0:13593] *** MPI_ERR_RMA_SHARED: Memory cannot be shared
[drossetti-ivy0:13593] *** MPI_ERRORS_ARE_FATAL (processes in this communicator will now abort,
-------------------------------------------------------
Primary job  terminated normally, but 1 process returned
a non-zero exit code.. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
mpirun detected that one or more processes exited with non-zero status, thus causing
the job to be terminated. The first process to do so was:

  Process name: [[59942,1],0]
  Exit code:    71
[drossetti-ivy0.nvidia.com:13589] 3 more processes have sent help message help-mpi-errors.txt /
mpi_errors_are_fatal
Stderr

Environment



Time: 0.73 sec. (PHP: 0.106 / SQL: 0.624)

Overall MTT contribution graph (updated nightly): All Time or 1 Year Window