[Iccrg] Easter egg in my flow Isolation (non) talk

[Matt Mathis]

Due to constraints on the meeting time and the extension for the IW
discussion, my presentation on Flow Isolation fell off the agenda.

I would like to point out an unrelated mini-talk attached to the end
of my flow isolation slides, titled "TCP is still lame" (slides
30-35).   It outlines a complete restructuring of the current
congestion control algorithms.  My proposal does not change any of the
principles behind any of the current algorithms, but would completely
change their implementations to make them far simpler and TCP's
behavior easier to model.  Furthermore many of the existing algorithms
become implicit:  sshthresh disappears completely, and the initial
slowstart happens as a side effect of setting cwnd=MAXWIN

I'm guessing the new algorithms would be about 10% of the current code....