I think Bob is thinking of a kind of distributed 
processing more than clustering. Clustering 
seems (at least to me) to reduce the utility of 
the hardware used for other purposes. A 
distributed processing type that is less "life
changing" for workstations is nice when you 
still want to use those workstation for other 
things.

Examples would be distributed.net, Seti at Home
(the search-for-aliens-in-static one), and 
programs like Pooch 
(http://daugerresearch.com/pooch/). 

Is that what you are thinking of Bob? A "pooch" 
for linux, or maybe a cross platform "puppie"? I'd 
like that...

>>> chrome at real-time.com 03/19/02 11:51AM >>>
On Tue, Mar 19, 2002 at 12:45:18AM -0600, Bob Tanner wrote:
> I'm talking about distributing the compile of the kernel across idle boxes on
> your network.
	it's possible that just building a beowulf cluster (which is what
you're looking for) and substituting 'pmake' for 'make' will do the job for
some problems.
...<snip>...
> Something ala pvm. NOT like a cluster.
	pvm is what beowulf clustering uses (tho it could be that I'm
equivocating here). you're probably thinking of other types of clustering;
for redundancy or network load-balancing, which most certainly aren't
appropriate here.