> I also noticed another bug in the scheduler:
> A slots=2 max-slots=2
> B slots=2 max-slots=2
> 'mpirun -np 5' quits with an over-subscription error
> 'mpirun -np 3 --host B' hangs and just chews up CPU cycles forever
Just as a quick followup on the 'hang' seen above. This was filed as
ticket #27 in our bug tracker:
And was fixed in subversion (trunk r10131) and moved to the v1.1 and v1.0
branches. The current tarballs on the website should have this fix.
Thanks for finding that bug.