[e2e] TCP un-friendly congestion control

[Jon Crowcroft]

yes, it is a pain

but for the right way to do it see
http://www-lce.eng.cam.ac.uk/~ctk21/
:-)

In missive <Pine.GSO.4.50.0306052354270.2296-100000 at artemis.ee.surrey.ac.uk>, L
loyd Wood typed:

 >>[The title of this thread is misleading at best, and a bad pun at
 >>worst.]
 >>
 >>http://news.google.com/news?q=FAST+Caltech
 >>
 >>Oh, great.
 >>
 >>For the past couple of months, whenever someone has bounced up and
 >>down extolling the virtues of Katabi's et al.'s XCP and saying
 >>something should be done about it, I'd say something like 'gee, that's
 >>not the only new(ish) kid on the block. What about, oh, Caltech's FAST
 >>work? Which doesn't require the same degree of midpoint modification?
 >>And has actual not-just-in-ns implementations? No. N-S.'
 >>
 >>Now FAST's getting all the news after another PR offensive, so in the
 >>next couple of months, when people start bouncing up and down saying
 >>something should be done about FAST, I'll likely end up saying
 >>something like 'gee, that's not the only new(ish) kid on the block.
 >>What about, oh, Katabi's XCP? Which doesn't require changing TCP? And,
 >>has SIGCOMM papers and simulations to back it up? No. S-I-G.'
 >>
 >>I'd be happier about either of these things if I actually understood
 >>the maths behind them, and what that proved. Then maybe I'd be
 >>bouncing up and down too.
 >>
 >>L.
 >>
 >>I'm really not a fan of new kids on the block.
 >>http://www.legacyrecordings.com/nkotb/
 >>I'm really not bouncing up and down here.
 >>
 >><http://www.ee.surrey.ac.uk/Personal/L.Wood/><L.Wood at ee.surrey.ac.uk>
 >>

 cheers

   jon