nanog mailing list archives
Re: That MIT paper
From: Niels Bakker <niels=nanog () bakker net>
Date: Thu, 12 Aug 2004 13:35:36 +0200
David, * dga () lcs mit edu (David G. Andersen) [Thu 12 Aug 2004, 02:55 CEST]:
Global impact is greatest when the resulting load changes are concentrated in one place. The most clear example of that is changes that impact the root servers. When a 1% increase in total traffic is instead spread among hundreds of thousands of different, relatively unloaded DNS servers, the impact on any one DNS server is minimal. And since we're talking about a protocol that variously occupies less than 3% of all Internet traffic, the packet count / byte count impact is negligible (unless it's concentrated, as happens at root and gtld servers).
This doesn't make sense to me. You're saying here that a 1% increase in average traffic is a 1% average increase in traffic. What's your point? if a load change is concentrated in one place how can the impact be global? How can a 1% load increase in one specific place have anything but minimal impact? At root and gTLD servers I assume DNS traffic occupies significantly more than 3% of all traffic there. Still, a 1% increase remains 1%. -- Niels.
Current thread:
- Re: That MIT paper Joe Shen (Aug 10)
- Re: That MIT paper Siegbert Marschall (Aug 10)
- Re: That MIT paper Paul Vixie (Aug 11)
- Re: That MIT paper David G. Andersen (Aug 11)
- Re: That MIT paper Randy Bush (Aug 11)
- Re: That MIT paper Niels Bakker (Aug 12)
- Re: That MIT paper David G. Andersen (Aug 12)
- Re: That MIT paper Paul Vixie (Aug 12)
- Re: That MIT paper Randy Bush (Aug 12)
- Re: That MIT paper David G. Andersen (Aug 11)
- Re: That MIT paper William Allen Simpson (Aug 12)
- ttl for ns William Allen Simpson (Aug 12)
- Re: ttl for ns Stephen J. Wilcox (Aug 13)
- Re: ttl for ns William Allen Simpson (Aug 13)
- Re: ttl for ns William Allen Simpson (Aug 13)
- Re: ttl for ns John Payne (Aug 13)