[mpich-devel] detecting mpirun mismatch

[Jeff Squyres (jsquyres)]

Is there something we should put between OMPI and MPICH such that one can detect such a mismatch like this?

Might be worth thinking about.  We get users doing this not infrequently, too.



On Apr 22, 2014, at 5:58 PM, Jeff Hammond <jeff.science at gmail.com> wrote:

> PMI is specific to MPICH-family, right?  The problem that was observed
> had to do with MPICH/OpenMPI mixing.  'mpirun -np 2' led to two copies
> of the application running in serial...
> 
> If PMI implementations are version specific, should they not export
> PMI_VERSION to the environment so bad pairings can be detected?
> 
> Thanks,
> 
> Jeff
> 
> On Tue, Apr 22, 2014 at 4:52 PM, Balaji, Pavan <balaji at anl.gov> wrote:
>> Jeff,
>> 
>> Do you need to know if it’s Hydra or if it’s a PMI server?  Any PMI server can work with any PMI client.  Ideally, they’ll negotiate on the PMI version to use, but a bad client/server might assume a particular version.
>> 
>> You can make sure it’s a PMI server by checking for PMI environment variables.  Either PMI_FD or PMI_PORT will need to be set.
>> 
>>  — Pavan
>> 
>> On Apr 22, 2014, at 4:48 PM, Jeff Hammond <jeff.science at gmail.com> wrote:
>> 
>>> Does anyone know of a good way to detect when the user has built an
>>> MPI application with mpicc from implementation A and tries to launch
>>> with mpirun/mpiexec from implementation B?
>>> 
>>> I know that inside of the application, I can use either
>>> MPI_Get_library_version or preprocessor info to know what
>>> implementation I am using.  But can I discover anything about mpirun
>>> inside of the application?  Is there anything in the environment that
>>> I can query to know if my PM is Hydra, for example?  If not, can that
>>> be added?
>>> 
>>> This is a relatively common user error that leads to very bad things
>>> in some cases so it would be nice to be able to detect it and throw a
>>> warning/error.
>>> 
>>> Thanks,
>>> 
>>> Jeff
>>> 
>>> --
>>> Jeff Hammond
>>> jeff.science at gmail.com
>> 
> 
> 
> 
> -- 
> Jeff Hammond
> jeff.science at gmail.com


-- 
Jeff Squyres
jsquyres at cisco.com
For corporate legal information go to: http://www.cisco.com/web/about/doing_business/legal/cri/