Re: NAP Architecture

[the Riz <riz () beast boogers sf ca us>]

Ben Kirkpatrick wrote:
>    Forgive my ignorance on these matters, but why haven't many NAPS tried
> to be L1 based, or at least provide the option of private wire/fiber
> between the larger customers in the same room.  It seems to me that this
> would significantly reduce the complexity and packet-loss we're currently
> seeing.  How long would it take to troubleshoot a cross-over FE compared
> to trouble shooting two routers connected via a oversubscribed switch.
>    Marketing types are concerned about how to bill and track these, but
> there should be some easy ways around those issues.
>
> --Ben Kirkpatrick
> Data Products, Electric Lightwave, DID=360.816.3508
> -not speaking for ELI, not even speaking-
> "Consciousness: that annoying time between naps."

This *is* becoming more popular; in the US, the main problem is that many
(most?) of the exchange points are operated by telcos, who are tariffed.
This means that any connection between separate entities is a "circuit"
that they must charge a certain minimum amount for.  As more telcos manage
to move their exchange point operations into the non-regulated portion of
their respected businesses, this may change, and exchanges are currently
being built by non-telco entities, which are allowed to have more
reasonable charges to connect cages in the same facility together.
(Disclaimer: in my other life, I work for one such facility... the PAIX in
Palo Alto)

Personally, I see this mix of "public" and "private" exchange in the same
facility as being a necessary evolution of the infrastructure of the net;
one size definitely does not fit all.

+j

-- 
Jeff Rizzo                                         http://boogers.sf.ca.us/~riz