[Bioclusters] re: mpiblast problems

Neil Saunders bioclusters@bioinformatics.org
Wed, 4 Aug 2004 12:18:11 +1000

>If you simply skip the one node which seems to stall, does the run 
>work?  For PBS, you might need to create a queue which skips this node, 
>or simply mark the node down using pbsnode.

Thanks for the suggestion.  I suspect that the nodes are working fine.  
And I am not too concerned with mpiBLAST compilation/setup, which has 
worked fine on this and other clusters.  What really intrigues me is the 
error message that I posted previously:

Unknown message tag (-32766) received by 1
UUnknUkUnknknonwonwonwown nm nm nm mesessessesssagaegaegaege t at at
atag g( g( g( (-3-23-23-232767667667666) )r )r )r
reececeeceeceiivevievievedd b db db byy 2 y3 y4 5

No typos - it appears exactly as shown above.  It suggests to me an MPI 
problem, but my grasp of MPI internals is slim - I just wondered if 
anyone else has ever seen something similar and what it could mean.

 School of Biotechnology and Biomolecular Sciences,
 The University of New South Wales,
 Sydney 2052,