Nobody Actually Knows Precise P2P Traffic Stats - Maybe we should before we continue fighting about it....
Links: home · search · speed test · login · more ·

Nobody Actually Knows Precise P2P Traffic Stats
Maybe we should before we continue fighting about it....
(old news - 09:13AM Wednesday May 07 2008)
tags: Fileswapping · business · bandwidth · stats · networking
Wired News discusses how encryption and the use of random ports makes actually tracking which protocols eat up network traffic a virtually impossible task. While independent research firms issue reports all over the map (P2P is either a raging menace or easily manageable depending who you ask), the only people who really know are the ISPs and middle-carriers, who don't share raw data. Wired's Ryan Singel wonders if we should have better data before making landmark decisions on network neutrality, caps or throttling.
We would love to know if good measurements of P2P traffic are out there or if, indeed, the debate over net neutrality is taking place without the slightest bit of verifiable data.
No worries, ignoring science and data is the new black; the FCC has been shaping broadband policy for years now without actually knowing anything about the broadband networks they regulate.

Related:
  1. Sandvine Jumps On 'Protocol Agnostic' Bandwagon
  2. Comcast Begins Testing 'Protocol Agnostic' Network Management
  3. Sandvine: 44% of Internet Traffic P2P
  4. Comcast, Cox, Trot Out Their Worst 'Bandwidth Hogs'
  5. Beating Comcast's Sandvine On Linux With Iptables
  6. Bypass Bell Canada's Throttling
  7. Monday Evening Links
  8. Friday Morning Links
Links: New Topic
Forums »

nasadude @ 7th May 11:06AM:
what's data got to do with it?

the FCC don't need no stinkin' data; they rely on what their industry buddies tell them to do.
reply
anon @ 7th May 11:10AM:
Random ports?

Random ports don't affect Sandvine or other DPI boxes. They see the headers in the packet, they know it's P2P no matter what port it is on.

Encryption on the other hand can be hard to track, but that all depends on the setup of the session and if it can be tracked accurately through a signature.

But I do know that encrypted NNTP just shows up as SSL to DPI, no way to know it's NNTP in there.
reply
nanook @ 7th May 11:29AM:
Re "they aren't telling"

said by TFA :
How much of the traffic on the internet is peer-to-peer file trading? Everyone seems to agree it represents a lot of the traffic, but the truth is no one knows (with the possible exception of the ISPs and backbone providers in the middle, and they aren't telling or sharing raw data).
Of course they are not telling. If they did then their argument for throttling P2P would collapse. Now that would be very "telling" ;)

And BTW guess who owns a stake in Ellacoya? »www.ellacoya.com/news/pdf/2005/E···ding.pdf
reply
jc100 @ 7th May 02:53PM:
Re: what's data got to do with it?

99 percent of facts are made up is what I always say.
reply
espaeth @ 7th May 03:54PM:
Re: Random ports?

said by skuv :

Encryption on the other hand can be hard to track, but that all depends on the setup of the session and if it can be tracked accurately through a signature.
It can be heuristically tracked in aggregate by looking at the connection stats. P2P traffic is easy to spot if you look at active TCP session number stats per IP address.
reply

Thank you for using lo-fi dslreports.com - report bugs
© 99-2008 silver matrix LLC