The IP Over NBMA (ION) Archive

Cell Relay Retreat>ION Archive>month:1996-Nov> msg00138



[Date Prev][Date Next][Thread Prev][Thread Next]  
  [Date Index][Thread Index][Author Index][Subject Index]

Annoying inscalable proposals

  • From: Masataka Ohta <mohta@necom830.hpcl.titech.ac.jp>
  • Date: Tue, 19 Nov 96 11:51:07 JST
  • Cc: mohta@necom830.hpcl.titech.ac.jp, jlawrenc@cisco.com, egret@nh.ultranet.com, tagswitch@cisco.com, ion@nexen.com, colip-atm@necom830.hpcl.titech.ac.jp

> > With certain routing protocol such as OSPF, it is possible to know not
> > only the next but also the second, the third or even the forth next
> > hop router. Thus, by establishing "steps" from the current to the N-th
> > next hop router, it is possible to reduce the average number of IP
> > header processing by 1/N.

> AIRS, IFMP, or TAG seems to be able to accomplish at least the same.

Any ATM switch can accomplish the "step" operation, of course.

> In
> case of AIRS, which allows you to "step" though N hops

Unless N is bouded to be a small number, it's a "jump" and
doesn't scale.

With N ingress and N egress routers, the number of VCs is N^2,
which is the problem.

							Masataka Ohta