[Nanog] Lies, Damned Lies, and Statistics [Was: Re: ATT VP: Internet to hit capacity by 2010]

Christopher Morrow christopher.morrow at gmail.com
Wed Apr 23 09:47:18 CDT 2008


On Tue, Apr 22, 2008 at 10:48 AM, Laird Popkin <laird at pando.com> wrote:
> This raises an interesting issue - should optimization of p2p traffic (P4P) be based on "static" network information, or "dynamic" network information. It's certainly easier for ISP's to provide a simple network map that real-time network condition data, but the real-time data might be much more effective. Or even if it's not real-time, perhaps there could be "static" network maps reflecting conditions at different times of day?
>

100% solution + 100% more complexity vs 80% solution ?

It strikes me that often just doing a reverse lookup on the peer
address would be 'good enough' to keep things more 'local' in a
network sense. Something like:

1) prefer peers with PTR's like mine (perhaps get address from a
public-ish server - myipaddress.com/ipchicken.com/dshield.org)
2) prefer peers within my /24->/16 ?

This does depend on what you define as 'local' as well, 'stay off my
transit links' or 'stay off my last-mile' or 'stay off that godawful
expensive VZ link from CHI to NYC in my backhaul network...

P4P is an interesting move by Verizon, tin-hat-ness makes me think
it's a method to raise costs on the direct competitors to VZ (increase
usage on access-links where competitors mostly have shared
access-links) but I agree with Harrowell that it's sure nice to see VZ
participating in Internet things in a good way for the community.
(though see tin-hat perhaps it's short-term good and long-term
bad.../me puts away hat now)

-Chris




More information about the NANOG mailing list