[mpich-discuss] blocking Receive

[Hiatt, Dave M]

Is there any limit on how long a process can be on a Blocking Receive?  I have a particular app which delivers data from Node 0 and then the other ranks run for an hour or two before results are ready, and a message comes back.  Right now I just have Node 0 sitting on a blocking receive waiting.  I've noticed from time to time I can get a "specified message not available" during this time even in cases when I'm running all the processes locally so that it should all be running via shared memory (Nemesis as I'm on 1.2.1).   What are the likely causes for this message in that circumstances?  This is not a regular problem, but crops up from time to time.

"People get held back by the voice inside em" - K'naan - In the Beginning

Dave M. Hiatt
Director, Risk Analytics
CitiMortgage
1000 Technology Drive
O'Fallon, MO 63368-2240

Telephone:  636-261-1408

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/mpich-discuss/attachments/20100826/55fb0ce3/attachment.htm>