TCP Reno

TCP Reno builds upon TCP Tahoe's congestion control, adding the Fast Recovery mechanism described in RFC 2001. With this mechanism, isolated packet losses no longer lead to cwnd collapse and slow start. Instead, when a sender receives a single duplicate ACK, it halves the congestion window and enters the congestion avoidance phase.

Most widely used TCP implementations in today's (2006) operating systems conform to TCP Reno. As such, Reno forms the baseline for research on performance enhancements such as SACK, as well as modern congestion control mechanisms mostly intended for high-speed networks. The New Reno improvements have been implemented widely. The Vegas variants also build upon Reno, but has seen less use.

References

  • TCP Variants, Yee-Ting Li, 2003, is a nice overview comparing the Tahoe, Reno, and New Reno variants.
  • RFC 2001, TCP Slow Start, Congestion Avoidance, Fast Retransmit, and Fast Recovery Algorithms, W. Stevens, January 1997
  • TCP Congestion Control, RFC 5681, M. Allman, V. Paxson, E. Blanton, September 2009

-- SimonLeinen - 22 Nov 2006 - 05 Sep 2009

Edit | Attach | Watch | Print version | History: r3 < r2 < r1 | Backlinks | Raw View | Raw edit | More topic actions
Topic revision: r3 - 2009-09-05 - SimonLeinen
 
This site is powered by the TWiki collaboration platform Powered by PerlCopyright © 2004-2009 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.