Kent W. England writes:
Here are some examples:
> 2. Identify which % of traffic, if any, has regional locality.
> For pure Internet traffic, the probability that the source and
> destinatino of traffic are within the same metropolitan area
> tends to be low (10% or lower for metros within the US).
This is true only so long as the density of the Internet is low. This is so
because so long as the density is low, few of your neighbors will be on the
Internet and therefore local issues are irrelevant. However, at some point,
the density of the Internet gets to a critical point, say 30% to 40%. At
that point a pizza parlor owner says to himself "two out of every five of
my customers are on the Internet. Perhaps I need a web page." And,
suddenly, pizza on the Net makes a lot of sense and the traffic patterns
shift. As the density grows to 90%, local traffic becomes dominant over
distant traffic.
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.
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.
So, by all means, do your traffic studies, but be prepared to throw them
out or re-write them when the environment changes. Then throw bandwidth
where it will do the most good. 
No debate here.
--Kent
--pushpendra
Pushpendra Mohta pushp@cerf.net +1 619 812 3908
TCG CERFnet http://www.cerf.net +1 619 812 3995 (FAX)
I'm not at all convinced that 'local' traffic stays 'local', in fact,
I'd suspect that the latter case which you mention is already true.
I'd very much like to see the ration of traffic which is 'pushed' to
that which is 'pulled' from the local exchange, especially at smaller
exchanges (e.g. Tucson, Packet Clearing House) to verify these
assumptions. Not sure enough solid data can be correlated at the
larger exchange points to provide a conclusion.
- paul
well if I may stick my two cents in from a rainy russian sankt
peterburg, I disagree. Sure the majority of my traffic is not local and I
do business with my newsletter all over the world/ But I will not be
entirely happy with the internet until i have a locally usable conncetion
to my township city hall where I and my fellow citizens can debate local
politics. I want the same connection to my local school board and internet
using teachers. the same to my county commissioners and my state
legislature. I want email to the local library and use of its web site.
I want access to local transportation schedules and local businesses and
restaurant menus. and yes maybe even to the local pizza parlor. as long
as we live in **physical places** and pay taxes to local governments, the
internet will not make local geography entirely irrelevant.
I cannot predict exact percentages but I know with certainty there is a
LOT of local communication the *I* would like to do that I cannot.
Given an increase in the density of local users local traffic will surely
increase.
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.
Cheers.
--Kent
Gordon, you're the exception that proves every rule. Cheers. --Kent