|
[Sponsors] |
[OpenFOAM.org] supercomputer parallel problem (I can not subjob!) |
|
LinkBack | Thread Tools | Search this Thread | Display Modes |
October 12, 2015, 09:45 |
supercomputer parallel problem (I can not subjob!)
|
#1 | |
Senior Member
Freedom
Join Date: May 2014
Posts: 209
Rep Power: 12 |
Dear foamers,
I am installing OF2.3.0 on supercomputer. But I suffer the same problem as others who had posted like: http://www.cfd-online.com/Forums/ope...entos-5-a.html. But the thing of my case is different , so I decide to post a new thread and wish someone reply me accordingly. OF can run successfully with mpirun -np 4 interFoam -parallel on main(manage) node, but when I submit job to computing node the following error emerging. Quote:
The openmpi is : openmpi 1.6.5 The supercomputer has been installed icc 14.0.0 itself. The bash file in my home is like this: Code:
export LANG=C export LD_LIBRARY_PATH=$HOME/software/gmp/lib:$HOME/software/mpfr/lib:$HOME/software/mpc/lib:$LD_LIBRARY_PATH export LD_LIBRARY_PATH=$HOME/software/gcc/lib64:$LD_LIBRARY_PATH export PATH=$HOME/software/gcc/bin:$PATH export PATH=$HOME/software/cmake-2.8.12.2/bin:$PATH #######openmpi##### export PATH=$HOME/OpenFOAM/ThirdParty-2.3.0/openmpi-1.6.5/bin:$PATH export MPI_PATH=$HOME/software/openmpi-1.6.5/lib export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HOME/software/openmpi-1.6.5/lib source $HOME/OpenFOAM/OpenFOAM-2.3.0/etc/bashrc Best regards, Wen |
||
October 12, 2015, 17:37 |
|
#2 |
Retired Super Moderator
Bruno Santos
Join Date: Mar 2009
Location: Lisbon, Portugal
Posts: 10,975
Blog Entries: 45
Rep Power: 128 |
Quick answer: Without and example of the job schedule script it's a bit hard to diagnose the problem, but my guess is that you're missing the source command to OpenFOAM's "bashrc" file for activating OpenFOAM's shell environment.
In essence: Code:
source $HOME/OpenFOAM/OpenFOAM-2.3.0/etc/bashrc mpirun -np 4 interFoam -parallel |
|
October 12, 2015, 21:25 |
|
#3 |
Senior Member
Freedom
Join Date: May 2014
Posts: 209
Rep Power: 12 |
Thank you for your quick answer, Bruno. Yes, I have sourced the bash of OF and the mpirun works fine on the main node. But when I submit the job to the computing node, the error in my last thread appears (The supercomputer is a distributed memory system.). Furthermore, I run foamInstallation command, the checking is OK.
Best regards, Wen |
|
October 17, 2015, 10:36 |
|
#4 |
Retired Super Moderator
Bruno Santos
Join Date: Mar 2009
Location: Lisbon, Portugal
Posts: 10,975
Blog Entries: 45
Rep Power: 128 |
Quick answer: OK, then what are the exact detailed steps you use for running the job?
One of the points of failure is somewhere in how you launch the job, but if you don't describe all of the steps you take, it's really hard to diagnose. The other possibility is that the installation is not available in the supercomputer, because the installation folder might not be visible for all other nodes. |
|
|
|
Similar Threads | ||||
Thread | Thread Starter | Forum | Replies | Last Post |
problem during mpi in server: expected Scalar, found on line 0 the word 'nan' | muth | OpenFOAM Running, Solving & CFD | 3 | August 27, 2018 04:18 |
damBreak case parallel run problem | behzad-cfd | OpenFOAM Running, Solving & CFD | 5 | August 2, 2015 17:18 |
problem for parallel processing | minaret | OpenFOAM Running, Solving & CFD | 14 | January 19, 2015 23:41 |
Problem on Parallel Run Setup | Hamidur Rahman | CFX | 0 | September 23, 2007 17:11 |
cfx4 parallel sover Problem!! HELP | Richard.A | CFX | 2 | August 3, 2002 03:54 |