I just wonder, did anybody try the S. Keshav's approach to the TCP flow control in the real life:
http://blizzard.cs.uwaterloo.ca/keshav/home/Papers/data/91/thesis/ch4.pdf http://blizzard.cs.uwaterloo.ca/keshav/home/Papers/data/91/pp_sigcomm.pdf http://blizzard.cs.uwaterloo.ca/keshav/wiki/index.php/Paper-chron David Barrett wrote: > Following up on my earlier question, TCP has a bunch of “magic numbers” > whose best values vary depending upon the source you consult. I’m > curious if you have any input on: > > > > 1) _What’s a good initial value for the cwnd, whether starting > from scratch or after a RTO?_ I know RFC2581 says one thing, and 3465 > says another, and others say other things. I’m curious what you > actually use and like, and why. > > 2) _To what do you set the ssthresh in response to a RTO?_ To a > fixed-fraction of pipe (say, 50%) or some fraction of something else? > > 3) _How far do you “fall back” the cwnd in response to a RTO?_ To > a fixed value (say, 1472 bytes) or to some fraction of something else? > > 4) _To what do you set the ssthresh in response to a drop?_ To a > fixed-fraction of pipe (say, 50%) or some fraction of something else? > > 5) _How far do you “fall back” the cwnd in response to a RTO?_ To > ‘ssthresh’ or something else? > > 6) _What ALPHA value do you use for RTT smoothing?_ RFC 793 (3.7) > recommends between .8 and .9; any preference? (updatedRTT = ALPHA*oldRTT > + (1-ALPHA)*newRTT) I’m using .85 for lack of a better idea. > > 7) _What BETA value do you use for RTO calculation?_ RFC 893 > (3.6) recommends between 1.3 and 2.0; any preference? > (retransmitTimeout = BETA * rtt) I’m using 1.65, for no particular reason. > > > > Sorry for the big dump of questions; can you offer any guidance on any > of these? > > > > -david > > > ------------------------------------------------------------------------ > > _______________________________________________ > p2p-hackers mailing list > [email protected] > http://lists.zooko.com/mailman/listinfo/p2p-hackers _______________________________________________ p2p-hackers mailing list [email protected] http://lists.zooko.com/mailman/listinfo/p2p-hackers
