I explained the change in the commit message to r19097, but just in
case you missed it, here is an abridged version:
Per the July technical meeting:
Standardize the handling of the orte launch agent option across PLMs.
This has been a consistent complaint I have received - each PLM would
register its own MCA param to get input on the launch agent for remote
nodes (in fact, one or two didn't, but most did). This would then get
handled in various and contradictory ways.
Some PLMs would accept only a one-word input. Others accepted multi-
word args such as "valgrind orted", but then some would error by
putting any prefix specified on the cmd line in front of the incorrect
argument.
For example, while using the rsh launcher, if you specified "valgrind
orted" as your launch agent and had "--prefix foo" on you cmd line,
you would attempt to execute "ssh foo/valgrind orted" - which
obviously wouldn't work.
This was all -very- confusing to users, who had to know which PLM was
being used so they could even set the right mca param in the first
place! And since we don't warn about non-recognized or non-used mca
params, half of the time they would wind up not doing what they
thought they were telling us to do.
What I've done in r19097 is standardize things for a consistent
interface and user experience. The biggest change is that you can now
specify "--launch-agent foo" on the mpirun cmd line. The corresponding
mca param is orte_launch_agent. This can be a multi-word value.
One benefit of this is actually rather useful for developers. I have
found it rather annoying that I cannot tell the orteds to give me
debugging output without getting deluged by corresponding output from
mpirun. For example, setting --debug-devel on the mpirun cmd line will
give me debugging output from the orteds, but also a considerable
amount from mpirun.
However, now you can do --launch-agent "orted --debug", and only the
orteds will see the option.
Of course, you can also do "valgrind [options] orted", or "valgrind
[options] orted --debug", or whatever you like.
I did my best to ensure this works across all environments. However, I
can't compile all the PLMs, so there may be an error somewhere - my
apologies in advance.
As always, please let me know if you see something.
Ralph
