Traffic Engineering

Kent W. England kwe at
Fri Sep 19 00:15:12 UTC 1997

At 04:23 PM 9/17/97 -0700, Pushpendra Mohta wrote:
>Even in the scenario where physical proximity automatically implied
>network proximity, I think the assumption that local traffic will
>dominate communications needs to be revisited. It is true today, only
>because that is how people live lives and conduct business _today_. The
>concept of "community" today is geographical.. the communities of
>tommorrow may not be so restricted.
True, it's an assumption, but as I said in another message, the only other
example we have of such a network is the telephone network. And, given the
choice, why wouldn't most people join a local community rather than a
far-away or abstract community?

But there is not much point in arguing about this -- let's just keep our
eyes on the traffic patterns and see what happens and adjust accordingly.
>> Another example is distributed web hosting. When distributed web hosting
>> takes off, your backbone will be heavily discounted and your peripheral
>> interconnect bandwidth will be woefully short. Web traffic will zoom as
>> performance dramatically improves, but your backbone bandwidth will drop.
>> That breaks your traffic model.
>This is true of a business model based around content distrubution only.
>Most ISPs of size will have both publishers and consumers of information
>so the backbones utilization should be balanced.

I see a lot of asymmetries today. Some service providers have a lot of
business access connections, some have mostly web hosting, and some have
mostly retail eyeballs.

Of course, CERFnet may be better able to balance than most, but I expect
you'll support whatever sells, whether it balances or not.  :-)



More information about the NANOG mailing list