Re: TCP (and SCTP) sucks on high speed networks

[Thomas Skibo <skibo@juniper.net>]

Mea Culpa.

Somebody pointed out to me that the congestion window is only increased one
segment per *window* instead of one segment per ACK.  I blew it.  I apologize.
As that lady on Saturday Night Live used to say:  "nevermind."



> 
> > Once new ACKs start coming back, you'll increase the congestion
> > window by a segment size for each ACK.
> 
> No.  You want to increase cwnd by something on the order of 1/cwnd
> for each ACK that arrives during congestion avoidance.  Increasing
> the cwnd by a segment for each ACK results in exponential cwnd
> growth (ala slow start) rather than linear growth.  See RFC 2581.
> 
> (BTW, If there really are implementations that do what you describe,
> I'd be quite interested in an example trace!)
> 
> allman
> 
> 
> ---
> http://roland.grc.nasa.gov/~mallman/
> 

-- 
Thomas Skibo		Juniper Networks, Inc.		skibo@juniper.net