The IP over ATM Mailing List Archive by date

[Sam Wilson <ercm20@tattoo.ed.ac.uk>]

> > I wouldn't want to get into an argument about the potential performance
> > of future cell switches vs future packet switches.  On our network, at
> > the moment, with the kit we have, each router hop adds considerable
> > latency and may introduce capacity bottlenecks.  To avoid it requires
> > either NHRP (non-scaling according to Ohta-san) or some mangling of the
> > routing model.
> 
> To avoid what?

Latency or bottlenecks due to hopping in and out of routers on sticks.

[ Rest of comments deleted with no disagreement ]

> > [ discription of interconnected MANs and campuses deleted ]
> 
> > Now, Ohta-san - is that large? It is not large in the sense of number of
> > connected entities (I'd guess 30-40K attached hosts in the catenet) nor
> > in complexity of routing.
> 
> It is large. Considering that it should be a part of the Internet,
> it is as large as the Internet.
> 
> But, something constructed with the catenet is not a cloud.

I was using 'catenet' in a general sense, not to mean a linear
arrangement.  All the hosts with ATM connections could see the connected
networks as a cloud, certainly within Scotland the aim to to make the
ATM cloud UK-wide, at least within the academic community.  The scope of
my problem in the short term is NOT the whole Internet, just the
Scottish Academic part of it. 

> > [ logical meshes on top of physical stars or vice versa ]
> 
> Making something logical only add unnecessary management burden with
> no real benefit.

In general I disagree, but I won't argue. 

Sam Wilson
Network Services Division
Computing Services, The University of Edinburgh
Edinburgh, Scotland, UK