The original intent of the real time monitoring bindings was to provide
a mechanism for monitoring MPIRT specific statistics. Upon
request, I have made the parameters less specific to mpi
and more generic, but we should not discount giving advice to
implementors that gives them insight into monitoring MPIRT internals.
In addition, you are recommending that we provide the users the
ability to do RT monitoring that they are accustomed to (FFT,etc).Advice
to implementors should cover both. The latter will have less
detail, since it will be application specific.
I agree with your comments on the old proposal. Do you have any comments
on the new proposal yet?
Regards, Anna