Help running CP2K 5.1 jobs with Sungrid Engine queuing

Jerry Tanoury jerryt... at gmail.com
Fri Feb 16 20:43:48 UTC 2018


Hi,
I have successfully built a popt version of CP2K 5.1, and it passed all 
regtests except for two.  The arch and error files are attached.  However, 
when I try to run this on our cluster (SGE queuing), the job either 
crashes, or only runs on 1 core when requesting 4 cores.  My submit script 
is attached, as well as the error output file from SGE.  

A few things about the submit script:
- I source the intel compilers and libs, as well as openmpi before 
submitting.  So, all required paths are passed to the nodes with #$ -V.
- When I do not set OMPI_MCA_mpi_warn_on_fork 0, the job crashes with the 
warning below.  

--------------------------------------------------------------------------
A process has executed an operation involving a call to the
"fork()" system call to create a child process.  Open MPI is currently
operating in a condition that could result in memory corruption or
other system errors; your job may hang, crash, or produce silent
data corruption.  The use of fork() (or system() or other calls that
create child processes) is strongly discouraged.

The process that invoked fork was:

  Local host:          [[25312,1],0] (PID 5268)

If you are *absolutely sure* that your application will successfully
and correctly survive a call to fork(), you may disable this warning
by setting the mpi_warn_on_fork MCA parameter to 0.
--------------------------------------------------------------------------

Is there anyone experienced with running CP2K jobs using SGE queuing?

Does anyone have a SGE submit script that works, and/or do I need to set up 
a unique pe for CP2K?

Thank you for the help,
Jerry
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20180216/a509e87f/attachment.htm>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: CP2K_gnu-mkl.popt
Type: application/octet-stream
Size: 1861 bytes
Desc: not available
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20180216/a509e87f/attachment.obj>
-------------- next part --------------
Summary of the regression tester run from 2018-02-16_09-43-10 using CP2K_gnu-mkl popt 
Number of FAILED  tests 2
Number of WRONG   tests 0
Number of CORRECT tests 2990
Number of NEW     tests 19
Total number of   tests 3011
-------------- next part --------------
A non-text attachment was scrubbed...
Name: error_summary
Type: application/octet-stream
Size: 3644 bytes
Desc: not available
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20180216/a509e87f/attachment-0001.obj>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: runcp2k.csh
Type: text/x-csh
Size: 232 bytes
Desc: not available
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20180216/a509e87f/attachment.csh>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: error_file
Type: application/octet-stream
Size: 1023 bytes
Desc: not available
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20180216/a509e87f/attachment-0002.obj>


More information about the CP2K-user mailing list