[tcpm] Running code: Laminar TCP

Matt Mathis <mattmathis@google.com> Thu, 19 July 2012 22:25 UTC

MIME-Version: 1.0
Date: Thu, 19 Jul 2012 15:26:50 -0700
Message-ID: <CAH56bmCE2Zxgu=4FztUkSKwOH9o_f5YVwOxi0P0MgjBz=dao2Q@mail.gmail.com>
From: Matt Mathis <mattmathis@google.com>
To: TCP Maintenance and Minor Extensions WG <tcpm@ietf.org>
Content-Type: text/plain; charset="ISO-8859-1"
Subject: [tcpm] Running code: Laminar TCP
Precedence: list

BTW, if you want to play with Laminar TCP, try the experimental patch
at https://developers.google.com/speed/protocols/tcp-laminar

It replaces nearly all of congestion control code in Linux 3.5....  YMMV

Thanks,
--MM--
The best way to predict the future is to create it.  - Alan Kay

---------- Forwarded message ----------
From: <internet-drafts@ietf.org>
Date: Mon, Jul 16, 2012 at 2:52 PM
Subject: New Version Notification for draft-mathis-tcpm-tcp-laminar-01.txt
To: mattmathis@google.com



A new version of I-D, draft-mathis-tcpm-tcp-laminar-01.txt
has been successfully submitted by Matt Mathis and posted to the
IETF repository.

Filename:        draft-mathis-tcpm-tcp-laminar
Revision:        01
Title:           Laminar TCP and the case for refactoring TCP congestion control
Creation date:   2012-07-15
WG ID:           Individual Submission
Number of pages: 15
URL:
http://www.ietf.org/internet-drafts/draft-mathis-tcpm-tcp-laminar-01.txt
Status:          http://datatracker.ietf.org/doc/draft-mathis-tcpm-tcp-laminar
Htmlized:        http://tools.ietf.org/html/draft-mathis-tcpm-tcp-laminar-01
Diff:
http://tools.ietf.org/rfcdiff?url2=draft-mathis-tcpm-tcp-laminar-01

Abstract:
   The primary state variables used by all TCP congestion control
   algorithms, cwnd and ssthresh, are heavily overloaded, carrying
   different semantics in different states.  This leads to excess
   implementation complexity and poorly defined behaviors under some
   combinations of events, such as application stalls during loss
   recovery.  We propose a new framework for TCP congestion control, and
   to recast current standard algorithms to use new state variables.
   This new framework will not generally change the behavior of any of
   the primary congestion control algorithms when they are invoked in
   isolation.  It will permit new algorithms with better behaviors in
   many corner cases, such as when two distinct primary algorithms are
   invoked concurrently.  It will also foster the creation of new
   algorithms to address some events that are poorly treated by today's
   standards.  For the vast majority of traditional algorithms the
   transformation to the new state variables is completely
   straightforward.  However, the resulting implementation is likely to
   technically be in violation of existing TCP standards, even if it is
   fully compliant with their principles and intent.




The IETF Secretariat

[tcpm] Running code: Laminar TCP Matt Mathis