MPIRT monitoring

Anna Rounbehler (anna@sky.com)
Thu, 12 Sep 1996 15:29:31 -0400

> First, it is not clear to me whether a standard should specify this
> kind of functionality. Normally, I would think not, but since
> performance is presumably such an integral part of real-time programs, I
> imagine you could argue that any real-time program will have calls to
> similar functionality in its code, so therefore, standardizing the
> interface will improve program portability. I will leave this issue to
> be debated later

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