NAME

DESCRIPTION

The congestion window is increased as a function of the time elapsed since the last congestion event. The window increase algorithm operates like NewReno for the first second after a congestion event, and then switches to a high-speed mode based on a quadratic increase function.

The implementation was done in a clean-room fashion, and is based on the Internet Draft and other documents referenced in the SEE ALSO section below.

MIB Variables

adaptive_backoff

Controls use of the adaptive backoff algorithm, which is designed to keep network queues non-empty during congestion recovery episodes. Default is 0 (disabled).

rtt_scaling

Controls use of the RTT scaling algorithm, which is designed to make congestion window increase during congestion avoidance mode invariant with respect to RTT. Default is 0 (disabled).

SEE ALSO

D. Leith and R. Shorten, H-TCP: TCP Congestion Control for High Bandwidth-Delay Product Paths, http://tools.ietf.org/id/draft-leith-tcp-htcp-06.txt.

D. Leith, R. Shorten, and T. Yee, H-TCP: A framework for congestion control in high-speed and long-distance networks, Proc. PFLDnet, 2005.

G. Armitage, L. Stewart, M. Welzl, and J. Healy, An independent H-TCP implementation under FreeBSD 7.0: description and observed behaviour, SIGCOMM Comput. Commun. Rev., 3, 38, 27-38, July 2008.

ACKNOWLEDGEMENTS

HISTORY

The module was first released in 2007 by James Healy and Lawrence Stewart whilst working on the NewTCP research project at Swinburne University of Technology's Centre for Advanced Internet Architectures, Melbourne, Australia, which was made possible in part by a grant from the Cisco University Research Program Fund at Community Foundation Silicon Valley. More details are available at:

http://caia.swin.edu.au/urp/newtcp/

AUTHORS

This manual page was written by Lawrence Stewart <lstewart@FreeBSD.org> and David Hayes <david.hayes@ieee.org>.