[Wien] MPI Error

Peter Blaha pblaha at theochem.tuwien.ac.at
Sat Jun 19 13:49:56 CEST 2021


Definitely, it has nothing to do with MPI_REMOTE.

apparently, your ssh setup does not transfer the "environment".

There are 2 solutions:

If you want to run k-parallel only on one node, simply put
USE_REMOTE=0   in parallel_options. However, with this you are not able 
to use more nodes in one k-parallel job.

configure your own config files for   ssh/sshd  in .ssh/config (and I 
believe .sshd/config)
You can direct ssh to send your environment and the sshd to accept it.
The default behavior is configured by the sysadmin in 
/etc/ssh/ssh_config and sshd_config. These files you cannot change, but 
you can override these settings.
Most likely, you need a   SendEnv PATH   and  AcceptEnv PATH in the 2 
files, maybe some more variables.

See   man ssh_config   and   man sshd_config

Am 19.06.2021 um 12:59 schrieb leila mollabashi:
> Dear all WIEN2k users,
> 
>>The recommended option for  mpi version 2 (all modern mpis) is to set
> MPI_REMOTE to zero. The mpirun command will be issued on the original
> node, but the lapw1_mpi executables will run as given in .machines.
> 
>>This should solve your problem.
> 
> Now mpi and k-point parallel simultaneously run but k-point parallel 
> without mpi does not work using interactive mode or in interactive mode 
> by “set mpijob=1” in submit.sh script.  For example, with the following 
> .machines file:
> 
> 1:e2236
> 
> 1:e2236
> 
> 1:e2236
> 
> 1:e2236
> 
> the following error appeared:
> 
> bash: lapw1: command not found
> 
> My question is whether I can use two different installations of wien2k 
> for performing two different calculations at the same time?
> 
> Sincerely yours,
> 
> Leila
> 
> 
> On Sat, May 29, 2021 at 7:07 PM Peter Blaha 
> <pblaha at theochem.tuwien.ac.at <mailto:pblaha at theochem.tuwien.ac.at>> wrote:
> 
>     The difference beteen lapw0para and lapw1para is that
>     lapw0para always executes mpirun on the original node, lapw1para
>     maybe not.
> 
>     The behavior of lapw1para depends on MPI_REMOTE (set in
>     WIEN2k_parallel_options in w2k21.1 (or parallel_options earlier).
>     With MPI_REMOTE=1 it will first issue a   ssh nodename and there it
>     does
>     the mpirun. This does not work with your settings (probably because you
>     do not load the modules in your .bashrc (or .cshrc), but only in your
>     slurm-job and your system does not transfer the environment with ssh.
> 
>     The recommended option for mpi version 2 (all modern mpis) is to set
>     MPI_REMOTE to zero. The mpirun command will be issued on the original
>     node, but the lapw1_mpi executables will run as given in .machines.
> 
>     This should solve your problem.
> 
>     Am 29.05.2021 um 08:39 schrieb leila mollabashi:
>      > Dear all wien2k users,
>      > Following the previous comment referring me to the admin, I
>     contacted
>      > the cluster admin. By the comment of the admin, I recompiled Wien2k
>      > successfully using the cluster modules.
>      >>Once the blacs problem has been fixed,
>      > For example, is the following correct?
>      > libmkl_blacs_openmpi_lp64.so =>
>      >
>     /opt/exp_soft/local/generic/intel/mkl/lib/intel64/libmkl_blacs_openmpi_lp64.so
> 
>      > (0x00002b21efe03000)
>      >>the next step is to run lapw0 in
>      > sequential and parallel mode.
>      >>Add:
>      > x lapw0     and check the case.output0 and case.scf0 files (copy
>     them to
>      > a different name) as well as the message from the queuing system. ...
>      > The “x lapw0” and “mpirun -np 4 $WIENROOT/lapw0_mpi lapw0.def” are
>      > interactively executed correctly.
>      > The “x lapw0 -p” is also correctly executed using the following
>      > “.machines” file:
>      > lapw0:e0017:4
>      >>The same thing could be made with lapw1
>      > The “x lapw1” and “mpirun -np 4 $WIENROOT/lapw1_mpi lapw1.def”
>     are also
>      > correctly executed interactively with no problem. But “x lapw1
>     -p” stops
>      > when I use the following “.machines” file:
>      > 1:e0017:2
>      > 1:e0017:2
>      > bash: mpirun: command not found
>      > The output files are gathered into https://files.fm/u/7cssehdck
>     <https://files.fm/u/7cssehdck>
>      > <https://files.fm/u/7cssehdck <https://files.fm/u/7cssehdck>>.
>      > Would you, please, help me to fix the parallel problem too?
>      > Sincerely yours,
>      > Leila
>      >
>      >
>      > _______________________________________________
>      > Wien mailing list
>      > Wien at zeus.theochem.tuwien.ac.at
>     <mailto:Wien at zeus.theochem.tuwien.ac.at>
>      > http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>     <http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien>
>      > SEARCH the MAILING-LIST at:
>     http://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/index.html
>     <http://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/index.html>
>      >
> 
>     -- 
>     --------------------------------------------------------------------------
>     Peter BLAHA, Inst.f. Materials Chemistry, TU Vienna, A-1060 Vienna
>     Phone: +43-1-58801-165300             FAX: +43-1-58801-165982
>     Email: blaha at theochem.tuwien.ac.at
>     <mailto:blaha at theochem.tuwien.ac.at>    WIEN2k: http://www.wien2k.at
>     <http://www.wien2k.at>
>     WWW: http://www.imc.tuwien.ac.at <http://www.imc.tuwien.ac.at>
>     -------------------------------------------------------------------------
>     _______________________________________________
>     Wien mailing list
>     Wien at zeus.theochem.tuwien.ac.at <mailto:Wien at zeus.theochem.tuwien.ac.at>
>     http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
>     <http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien>
>     SEARCH the MAILING-LIST at:
>     http://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/index.html
>     <http://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/index.html>
> 
> 
> _______________________________________________
> Wien mailing list
> Wien at zeus.theochem.tuwien.ac.at
> http://zeus.theochem.tuwien.ac.at/mailman/listinfo/wien
> SEARCH the MAILING-LIST at:  http://www.mail-archive.com/wien@zeus.theochem.tuwien.ac.at/index.html
> 

-- 
--------------------------------------------------------------------------
Peter BLAHA, Inst.f. Materials Chemistry, TU Vienna, A-1060 Vienna
Phone: +43-1-58801-165300             FAX: +43-1-58801-165982
Email: blaha at theochem.tuwien.ac.at    WIEN2k: http://www.wien2k.at
WWW:   http://www.imc.tuwien.ac.at
-------------------------------------------------------------------------


More information about the Wien mailing list