[IP] p2p in Wyoming...

[David Farber <dave@farber.net>]

________________________________________
From: Jim Thompson [jim@netgate.com]
Sent: Wednesday, March 12, 2008 7:10 AM
To: David P. Reed; David Farber
Subject: p2p in Wyoming...

Next time Brett Glass comes up on I-P talking about P2P users as
"bandwidth hogs", remember that  I recently
met the guy from Argonne who did the UDT FTP code. http://udt.sourceforge.net/

It goes *really* fast:

June 4, 2007: UDT reached 711Mb/s (peak 844Mb/s) disk-disk data
transfer between US and Russia. Scientists from the National Center
for Data Mining (NCDM) at the University of Illinois at Chicago and
the Geophysical Center at the Space Research Institute, Russian
Academy of Sciences, Moscow, demonstrated a new method for
distributing extremely large volumes of scientific information across
the world. They successfully moved 1.4 TeraBytes (TB) of data in about
4.5 hours over a 1 Gbps lightpath between Chicago and Moscow as part
of the Teraflow Network initiative...
November 17, 2006: UDT was used in the bandwidth challenge winning
entry "Transferring Sloan Digital Sky Survey Data using SECTOR" during
the annual Supercomputing conference in Tampa, FL. UDT enabled a disk
to disk data transfer at 9.18Gb/s peak throughput between Chicago and
Tampa.

and Comcast thought they had problems with P2P traffic that was based
on TCP.

It doesn't take a genius to figure out that someone is going to weld
this onto a P2P client and since the
congestion control is "user defined", I have to imagine that someone
is going to set it to "use all the bandwidth".

What will Mr. Glass do then?

jim

-------------------------------------------