Andrej,

it seems only flux is a PMIx option, which is very suspicious.

can you check other components are available?

ls -l /usr/local/lib/openmpi/mca_pmix_*.so

will list them.

Cheers,

Gilles

On Mon, Feb 1, 2021 at 10:53 PM Andrej Prsa via devel
<devel@lists.open-mpi.org> wrote:
>
> Hi Gilles,
>
> > what is your mpirun command line?
> > is mpirun invoked from a batch allocation?
>
> I call mpirun directly; here's a full output:
>
> andrej@terra:~/system/tests/MPI$ mpirun --mca ess_base_verbose 10 --mca
> pmix_base_verbose 10 -np 4 python testmpi.py
> [terra:203257] mca: base: components_register: registering framework ess
> components
> [terra:203257] mca: base: components_register: found loaded component slurm
> [terra:203257] mca: base: components_register: component slurm has no
> register or open function
> [terra:203257] mca: base: components_register: found loaded component env
> [terra:203257] mca: base: components_register: component env has no
> register or open function
> [terra:203257] mca: base: components_register: found loaded component pmi
> [terra:203257] mca: base: components_register: component pmi has no
> register or open function
> [terra:203257] mca: base: components_register: found loaded component tool
> [terra:203257] mca: base: components_register: component tool register
> function successful
> [terra:203257] mca: base: components_register: found loaded component hnp
> [terra:203257] mca: base: components_register: component hnp has no
> register or open function
> [terra:203257] mca: base: components_register: found loaded component
> singleton
> [terra:203257] mca: base: components_register: component singleton
> register function successful
> [terra:203257] mca: base: components_open: opening ess components
> [terra:203257] mca: base: components_open: found loaded component slurm
> [terra:203257] mca: base: components_open: component slurm open function
> successful
> [terra:203257] mca: base: components_open: found loaded component env
> [terra:203257] mca: base: components_open: component env open function
> successful
> [terra:203257] mca: base: components_open: found loaded component pmi
> [terra:203257] mca: base: components_open: component pmi open function
> successful
> [terra:203257] mca: base: components_open: found loaded component tool
> [terra:203257] mca: base: components_open: component tool open function
> successful
> [terra:203257] mca: base: components_open: found loaded component hnp
> [terra:203257] mca: base: components_open: component hnp open function
> successful
> [terra:203257] mca: base: components_open: found loaded component singleton
> [terra:203257] mca: base: components_open: component singleton open
> function successful
> [terra:203257] mca:base:select: Auto-selecting ess components
> [terra:203257] mca:base:select:(  ess) Querying component [slurm]
> [terra:203257] mca:base:select:(  ess) Querying component [env]
> [terra:203257] mca:base:select:(  ess) Querying component [pmi]
> [terra:203257] mca:base:select:(  ess) Querying component [tool]
> [terra:203257] mca:base:select:(  ess) Querying component [hnp]
> [terra:203257] mca:base:select:(  ess) Query of component [hnp] set
> priority to 100
> [terra:203257] mca:base:select:(  ess) Querying component [singleton]
> [terra:203257] mca:base:select:(  ess) Selected component [hnp]
> [terra:203257] mca: base: close: component slurm closed
> [terra:203257] mca: base: close: unloading component slurm
> [terra:203257] mca: base: close: component env closed
> [terra:203257] mca: base: close: unloading component env
> [terra:203257] mca: base: close: component pmi closed
> [terra:203257] mca: base: close: unloading component pmi
> [terra:203257] mca: base: close: component tool closed
> [terra:203257] mca: base: close: unloading component tool
> [terra:203257] mca: base: close: component singleton closed
> [terra:203257] mca: base: close: unloading component singleton
> [terra:203257] mca: base: components_register: registering framework
> pmix components
> [terra:203257] mca: base: components_register: found loaded component flux
> [terra:203257] mca: base: components_register: component flux register
> function successful
> [terra:203257] mca: base: components_open: opening pmix components
> [terra:203257] mca: base: components_open: found loaded component flux
> [terra:203257] mca:base:select: Auto-selecting pmix components
> [terra:203257] mca:base:select:( pmix) Querying component [flux]
> [terra:203257] mca:base:select:( pmix) No component selected!
> [terra:203257] [[47344,0],0] ORTE_ERROR_LOG: Not found in file
> ess_hnp_module.c at line 320
> --------------------------------------------------------------------------
> It looks like orte_init failed for some reason; your parallel process is
> likely to abort.  There are many reasons that a parallel process can
> fail during orte_init; some of which are due to configuration or
> environment problems.  This failure appears to be an internal failure;
> here's some additional information (which may only be relevant to an
> Open MPI developer):
>
>    opal_pmix_base_select failed
>    --> Returned value Not found (-13) instead of ORTE_SUCCESS
> --------------------------------------------------------------------------
>
> Thanks,
> Andrej
>

Reply via email to