[padb] (version-dependent?) problem with ORTE

Dave Love d.love at liverpool.ac.uk
Sun Dec 5 19:16:11 GMT 2010


I reported a while ago that I couldn't make ORTE work, and I've found
out why.  With open-mpi 1.4.1 or 1.4.2, the problem is that the format
padb expects from ompi-ps is wrong.  I assume it's changed at some
stage.  Here's a (truncated) sample:

-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: ompi-ps.out
URL: <http://pittman.org.uk/pipermail/padb-devel_pittman.org.uk/attachments/20101205/d817130d/attachment.ksh>
-------------- next part --------------

The following patch fixes it for me, but presumably it will break
whatever version the support was done for originally, so I don't know
what to do for a real patch.  Maybe you need to match patterns in the
records, rather than just checking the number of fields?  Let me know if
I can provide any more info to help disambiguate things.

-------------- next part --------------
A non-text attachment was scrubbed...
Name: padb.diff
Type: text/x-diff
Size: 731 bytes
Desc: padb diff for OMPI 1.4.2
URL: <http://pittman.org.uk/pipermail/padb-devel_pittman.org.uk/attachments/20101205/d817130d/attachment.bin>
-------------- next part --------------

By the way, in case it catches other people, I need to run with
OMPI_MCA_orte_allocation_required=0 in the environment to defeat what we
have in the open-mpi configuration:

  # mpirun requires an SGE allocation, i.e. can't just run it on the head.
  orte_allocation_required = 1


More information about the padb-devel mailing list