Daniel Senie wrote: [many interesting hw design approaches that you can buy already deleted]
I should point out that none of this really is about scalability of the routing system of the Internet, it's all about hardware and software design to allow the present system to scale. Looking at completely different and more scalable routing would require finding a better way to do things than the present BGP approach.
I disagree. By your description there is no problem scaling the current model to much bigger numbers of prefixes and paths. Then why not simply do it??? Apparently there ain't a problem then? For routing you have to ways: The BGP (DFZ) way or the aggregation (by whatever arbitrary level/layer divider de jour) way. If you have third, different (not just a modification or merge of partial aspects of the former two) you may be eglible for a Nobel prize in mathematics in a few decades. They run behind a bit, you know... -- Andre