Newsgroups: comp.parallel.pvm
From: "Lawrence L. Chan" <lchan@cs.ucla.edu>
Subject: Flow Control in pvm
Organization: UCLA Computer Science Dept.
Date: 3 May 1995 03:50:09 GMT
Mime-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Transfer-Encoding: 7bit
Message-ID: <3o6uhh$7qb@delphi.cs.ucla.edu>

Hi,

I'm currently using pvm to develop a parallel query processing system on
a network of SUN and HP workstations.  I'd like to know more about pvm's
flow control mechanism.

Let's say I have 2 tasks, task A and task B, and task A is just sending data
to task B.  If task A is much much faster than task B, will pvm guarantee
that all messages are safely buffered and that no messages are being lost?
What if there's not enough memory on the machine task A is running, and thus
no buffers are available?  If there's any flow control mechanism in pvm, how
is it done?

Thanks a lot for the help in advance.

Lawrence Chan
lchan@cs.ucla.edu


