[torqueusers] Transforming node names in $PBS_NODEFILE and $PBS_GPUFILE

Lloyd Brown lloyd_brown at byu.edu
Tue Sep 4 13:37:48 MDT 2012


A lot will depend on what MPI implementation you're using.  Even if
you're able to transform your nodefiles in some fashion, that would
imply that you're using the IPoIB components for your main job
communication.  This means you will have very little latency advantage
over GigE, and significantly reduced IB bandwidth as well (although
probably still better than GigE; just not as good as IB can do).  IPoIB
is a good option for when you have no other option, but it's definitely
not as good performance as you can get out of IB.

A much better solution, in my opinion, is to use an MPI implementation
that can speak native IB verbs directly.  My personal preference is
OpenMPI, which, if compiled correctly, will find the fastest
communication medium available (IB before GigE).  And then, despite
what's in the $PBS_NODEFILE, the job communication will generally go
over the that fastest network.  Only minimal job setup and status
information is communicated over GigE.




Lloyd Brown
Systems Administrator
Fulton Supercomputing Lab
Brigham Young University
http://marylou.byu.edu

On 09/04/2012 01:24 PM, Dave Ulrick wrote:
> I am trying to figure out a way to populate these files with the IB node 
> names so MPI traffic will use IB instead of GigE.


More information about the torqueusers mailing list