[mpiwg-tools] pvar attribute questions

[Mohror, Kathryn]

Hi Junchao,

If the pvar is restarted by the first session, what will be read into this pvar?
I think it is 90. But this value of high watermark did not happen in the live period of the pvar in the first session. So the value 90 doesn't make sense.

It should be 50, because the value of the variable is not updated when it is stopped.

I don't know how to let a watermark pvar show different values in different sessions. For COUNTER, TIMER, AGGREGATE pvars, I know we can compute delta between current value and start value. But for watermark pvars, the approach does not apply.

I suppose it depends on how you implement it. If it doesn't make sense in your implementation, you don't need to expose watermark variables that are non-continuous.

BTW, I could not understand why a pvar may be writable (i.e., not readonly) from the user?  Could someone give me an example.

You may want to reset the variable to its starting value so that you can measure it during a specific time period. I can't think of an example off the top of my head for using pvar_write on a variable. (Maybe setting to 0?) If I remember right, we included it for generality. If you don't want to allow a tool to write to a variable, you can just return MPI_T_ERR_PVAR_NO_WRITE.

Kathryn



On Fri, Aug 30, 2013 at 5:11 PM, Mohror, Kathryn <mohror1 at llnl.gov<mailto:mohror1 at llnl.gov>> wrote:
Hi Martin and Junchao,

Sorry, I can't respond to the list at the moment (LOFT settings) and I was trying to answer when Kathryn was sending her answer - feel free to repost on the list if it makes sense.

Okay, I'm cc'ing the list so others benefit from your point.

I agree with her interpretation - that was our intention. I agree, though, that probably doesn't make sense and hence I generally don't expect MPI implementations to offer high/low watermarks as non-continnous variables, but that's up to them.

It could make sense though. You could possibly have a non-continuous variable that is the high watermark of some metric (e.g., messages in the unexpected queue) so that you could query it for specific time periods. But, you're right, it's up to the implementation to decide what is offered.

Kathryn


Martin



On Aug 30, 2013, at 11:48 PM, "Mohror, Kathryn" <mohror1 at llnl.gov<mailto:mohror1 at llnl.gov>>
 wrote:

Hi Junchao,

I'm trying to understand MPI3 MPI_T performance variables (pvar).  The standard defines pvar sessions, pvar classes (e.g.,COUNTER, HIGHWATERMARK etc), and continuous pvars, readonly pvars.I was wondering if there is any relevance between these concepts. The standard doesn't say that.

For instance, for a highwatermark pvar, I guess it should be continuous. Otherwise, suppose a pvar session starts this pvar, then stops it, and then restarts it.  How can I keep track of this pvar? Let's say during the live period of the pvar, the high watermark is 50. After the pvar is stopped, it went up to as high as 90 (since it may be alive in other pvar sessions). So, when I restart the pvar, what value should I read?

If a variable is not continuous then its value is not updated when it is stopped. So in your example the value would be 50 in the session that stopped the variable and 90 in any sessions that still had the variable live at the time it reached that value. There's a bit more explanation on page 579 starting at line 21. Does that help?

Kathryn


Thanks
--Junchao Zhang

_______________________________________________
mpiwg-tools mailing list
mpiwg-tools at lists.mpi-forum.org<mailto:mpiwg-tools at lists.mpi-forum.org>
http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-tools

______________________________________________________________
Kathryn Mohror, kathryn at llnl.gov<mailto:kathryn at llnl.gov>, http://people.llnl.gov/mohror1
CASC @ Lawrence Livermore National Laboratory, Livermore, CA, USA




_______________________________________________
mpiwg-tools mailing list
mpiwg-tools at lists.mpi-forum.org<mailto:mpiwg-tools at lists.mpi-forum.org>
http://lists.mpi-forum.org/mailman/listinfo.cgi/mpiwg-tools


______________________________________________________________
Kathryn Mohror, kathryn at llnl.gov<mailto:kathryn at llnl.gov>, http://people.llnl.gov/mohror1
CASC @ Lawrence Livermore National Laboratory, Livermore, CA, USA






______________________________________________________________
Kathryn Mohror, kathryn at llnl.gov<mailto:kathryn at llnl.gov>, http://people.llnl.gov/mohror1
CASC @ Lawrence Livermore National Laboratory, Livermore, CA, USA




-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpi-forum.org/pipermail/mpiwg-tools/attachments/20130830/d00c86cd/attachment-0001.html>