Open MPI logo

MTT Devel Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all MTT Devel mailing list

Subject: Re: [MTT devel] Extracting transparent data from OMPI
From: Jeff Squyres (jsquyres_at_[hidden])
Date: 2008-02-06 10:25:14


On Jan 31, 2008, at 5:07 PM, Josh Hursey wrote:

> For the visualization it would be really nice to see how well tested a
> particular interconnect, resource manager, and/or 'feature' is when
> ramping up to a release. However these peices of information are hard
> to obtain, and in some cases quantify (e.g., what do we mean by
> testing a 'feature'?).
>
> Thinking about this it occurred to me that what we really need is for
> OMPI to tell MTT what it is doing for some of these cases.
> Two examples, MTT cannot tell:
> - which set of compile time options are enabled/disabled
> automatically
> e.g. [ "./configure --with-foo" vs "./configure"]

Yes, this could be done.

> - which BTL(s) or MTL are used to run a test
> e.g. [ "mpirun -mca btl tcp,self foo" vs. "mpirun foo"]

Don't we offer this in a limited way right now with the "network"
field in the MPI details section? I think we hesitated to put OMPI-
specific semantics on that field -- e.g., whether you're using the MX
BTL or MTL is an OMPI issue; you're still using the MX protocol/network.

I suppose we could agument those strings in the OMPI case: mx:mtl and
mx:btl, for example.

So to be clear: does the network field not give you what you need?

> For the configure options we *could* parse the config.log to extract
> this data. The question is, if we did this, what do we want to look?
> And is this something we want to do? Is there another way?

I think having a network-like field for the MPI install section might
be good, and possibly have an OMPI:: funclet to automatically do the
parsing. But we need to be mindful of MPIs that won't have a
configure script, so what information goes there might be dubious (or
just empty?).

>
> For the BTL(s)/MTL this is a much more subtle question since this
> depends on the connectivity of the interfaces on a machine, and the
> runtime selection logic. If we added a parameter to mpirun (e.g. "--
> showme connectivity") that displayed connectivity information to
> stdout (or a file) would this be useful? What should it look like?

Ya, this is on my to-do list. IB CM stuff in the openib BTL has been
consuming my time recently (much more complicated than I originally
thought); I swear I'll be getting to the connectivity map issue before
v1.3...

>
> We have talked about some of this in the past, but I could not find a
> Bug talking about it in MTT.
>
> What do you think about this?
>
> Cheers,
> Josh
> _______________________________________________
> mtt-devel mailing list
> mtt-devel_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/mtt-devel

-- 
Jeff Squyres
Cisco Systems