[Iccrg] Re: Easter egg in my flow Isolation (non) talk
Matt Mathis
matt.mathis at gmail.com
Mon Mar 29 04:05:13 BST 2010
Oops, this message seems to have been truncated.....
On Wed, Mar 24, 2010 at 2:42 PM, Matt Mathis <matt.mathis at gmail.com> wrote:
> 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....
>
My talk is on the meeting materials page or
http://staff.psc.edu/mathis/papers/FlowIsolation20100323.pdf
Thanks,
--MM--
-------------------------------------------
Matt Mathis http://staff.psc.edu/mathis
Work:412.268.3319 Home/Cell:412.654.7529
-------------------------------------------
Evil is defined by mortals who think they know
"The Truth" and use force to apply it to others.
More information about the Iccrg
mailing list