[CP2K-user] [CP2K:18616] MPI and Containers

Krack Matthias matthias.krack at psi.ch
Wed Apr 5 16:35:00 UTC 2023


Hi

I have just checked in a README file<https://github.com/mkrack/cp2k/blob/master/tools/apptainer/README.md> for CP2K & Apptainer which might give some hints.

Best

Matthias

On 05.04.23, 16:11, "cp2k at googlegroups.com" <cp2k at googlegroups.com> wrote:
Hello List,

I have successfully built 2023.1 from the dockerfile that's included
with the source code. I have converted the container to singularity
and run that on our cluster.

Now, I'd like to use cp2k with MPI. I've followed the "hybrid"
approach where srun starts multiple containers on multiple nodes, and
the MPI inside the container works with the MPI on the hosts (and PMI,
and Slurm) to start up the application:
srun -vv --ntasks 2 /apps/local/cp2k/2022.2/cp2k.sif cp2k.psmp \
  -i H2O-64.inp -o cp2k_002.out

However, this does not seem to work:

GLOBAL| MPI I/O enabled T
GLOBAL| Total number of message passing processes 1
GLOBAL| Number of threads for this process 32
GLOBAL| This output is from process 0

I have also included a simple test program inside the same container,
and this seems to work (although there's an error message):

> --------------------------------------------------------------------------
> A requested component was not found, or was unable to be opened.  This
> means that this component is either not installed or is unable to be
> used on your system (e.g., sometimes this means that shared libraries
> that the component requires are unable to be found/loaded).  Note that
> PMIx stopped checking at the first component that it did not find.
>
> Host:      node77-62
> Framework: psec
> Component: munge
> --------------------------------------------------------------------------
>
> [node77-62:2545390] PMIX ERROR: ERROR in file
> ../../../../../../src/mca/gds/ds12/gds_ds12_lock_pthread.c at line 169
> Hello, I am rank 0/2
> Hello, I am rank 1/2


How would I go about debugging the MPI startup of cp2k?
Of course, any other ideas are welcome, too.

Thanks,

A.
--
Ansgar Esztermann
Sysadmin Dep. Theoretical and Computational Biophysics
https://www.mpinat.mpg.de/person/11315/3883774

--
You received this message because you are subscribed to the Google Groups "cp2k" group.
To unsubscribe from this group and stop receiving emails from it, send an email to cp2k+unsubscribe at googlegroups.com<mailto:cp2k+unsubscribe at googlegroups.com>.
To view this discussion on the web visit https://groups.google.com/d/msgid/cp2k/ZC2BKBhkpDe0mQOe%40aeszter.mpibpc.intern.

-- 
You received this message because you are subscribed to the Google Groups "cp2k" group.
To unsubscribe from this group and stop receiving emails from it, send an email to cp2k+unsubscribe at googlegroups.com.
To view this discussion on the web visit https://groups.google.com/d/msgid/cp2k/ZRAP278MB0827F1CA115078D83BEF6233F4909%40ZRAP278MB0827.CHEP278.PROD.OUTLOOK.COM.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.cp2k.org/archives/cp2k-user/attachments/20230405/99cb398d/attachment-0001.htm>


More information about the CP2K-user mailing list