OT - Vint Cerf joins Google

Marshall Eubanks tme at multicasttech.com
Mon Sep 12 12:42:53 UTC 2005


On Mon, 12 Sep 2005 05:06:36 +0000 (GMT)
 "Christopher L. Morrow" <christopher.morrow at mci.com> wrote:
> 
> On Sun, 11 Sep 2005, JORDI PALET MARTINEZ wrote:
> 
> >
> > I recall last month in our web servers was something like 8% with IPv6
> > (average), but in my opinion most of the IPv6 traffic is peer-to-peer so not
> 
> 8% seems high to me as well, I don't think I've ever seen my v6 traffic
> over 1% honestly :( Why do you think it's mostly P2P traffic? Are there
> P2P applications that prefer v6 over v4? or only work on v6? If a host has
> v6 capabilities, in my experience, it'll use them atleast as often as v4
> when given the chance.

These estimates seem way high and need support. Here is a counter-example.

Netflow on Internet 2 for last week 

http://netflow.internet2.edu/weekly/20050829/

has 6.299 Gigabytes being sent by IPv6, out of a total 383.2 Terabytes, or 0.0016%
This is backbone traffic, and would not catch intra-Campus traffic, nor would it catch
tunnel or VPN traffic, but it is suggestive.

By contrast, (IPv4) UDP is 12 % of the data sent, and (IPv4 ASM) Multicast is  1.76%, so
IPv6 trafic is just about  10^-3 of the Multicast (before any  fan-out).

According to the graph

http://netflow.internet2.edu/weekly/longit/perc-protocols41-octets.png

the most I2 IPv6 traffic was in  2002, when it was almost 0.6% of the total. 

It is hard for me to imagine that the situation for commerical US traffic is much
different.

There may be similar statistics for Geant - I would be interested to see them.

Regards
Marshall Eubanks

> 
> I think the last v6 traffic study I saw still said +90% of the v6 traffic
> was still ping/traceroute :(
> 
> 
> 




More information about the NANOG mailing list