> about handling workloads that exceed the processing capacity
> of a single node -- even if that node has 100x the capacity
> of today's high end Sun boxes.

One side to this could be that in other hand some company could build single
node that is capable to handle the load they have.

Most of the companies just don't have the money to do that. It could be much
cheaper to have cloud of, more than less, standard PC's and add those to the
Cloud as they need/can. (not 100% if this the goal, but at least in my eyes
it seems that it definetly could/should)

-TP-

Ps. Very interesting to follow this dicussion...