I am giving a series of talks here about OMPI 1.3, beginning with a
description of the user-oriented features - i.e., cmd line options,
etc. In working on the presentation, and showing a draft to some
users, questions arose about two options: --display-map and --display-
allocation. To be fair, Greg Watson had raised similar questions before.
The questions revolve around the fact that the data provided by those
options contains a lot of stuff that, while immensely useful to an
OMPI developer, are of no use to a user and actually cause confusion.
What we propose, therefore, is to revise these options:
--display-map: displays a list of nodes, to include node name and
state and a list of the procs on that node. For each proc, show the
MPI rank, local and node ranks, any slot list for that proc (if
given), and state.
--display-allocation: displays a list of nodes to include node name,
slot info, username (if given), and state ("unknown" if not known)
We would then add two new options that show the broader output we have
today: --debug-display-map, and --debug-display-allocation.
Anybody have heartburn and/or comments on this? If not, I plan to make
the change by the end of the week.