[Spread-users] Load balancing with group communication

[Van Gale]

I realize this can be a pretty complicated question since multiple papers
have been written on the subject, but I'm hoping someone on this list can
provide some basic clues to help me out.

I have an application that I'd like to use Spread for messaging between
components/objects.  Sometimes the components fit nicely into the Spread
mold, like logging components or databse replication.  Sometimes though, I
only want one member of the group to process the message.  In other words,
more of a message queue model.

Unfortunately, the most promising looking paper, "S. Dolev, R. Segala, and
A.A. Shvartsman, Dynamic Load Balancing with Group Communication, Proc. of
6th International Colloquium on Structured Information and Communication
Complexity, 1999", seems to be unavailable online.

Another paper, "B. Chlebus, D. Kowalski, A. Lingas, The Do-All Problem in
Broadcast Networks", has an algorithm that seems interesting but gets hairy
when I start thinking about partitioning and it has some steps that aren't
needed in a group view system.  They suggest an algorithm they call
TWO-LISTS which basically keeps a list of tasks and a list of stations, and
the stations perform the tasks in order.  Something simple like this would
work for me if I can get past partitioning issues.

Anyone have any pointers or ideas to help me out here?

Van