Thank Goodness for well-behaved applications, right? ( Misbehaving TCP stacks and UDP-based apps don't obey these back off rules. ) I remember Van Jacobson gave a presentation back in 1997 that spoke about the problems with applications that didn't exhibit these characteristics: http://www.academ.com/nanog/october1997/
It would be interesting to see some recent verification that well-behaved TCP-apps are the norm on the Internet...any data out there in this regard?
Bill
Thank Goodness for well-behaved applications, right?
( Misbehaving TCP
stacks and UDP-based apps don't obey these back off
rules. )
You can see lot of intiatives to make things more
TCP friendly to avoid hogging of bandwidth by some
selected applications( mostly multimedia based.) More
details on the intiative can be obtained from
http://www.psc.edu/networking/tcp_friendly.html.
Equation based congestion control and DCCP are some of
the options for such applications which doesnt obey
back off rules.
It would be interesting to see some recent
verification that well-behaved
TCP-apps are the norm on the Internet...any data out
there in this regard?
You can see a clear demarkation in the UDP Vs TCP
study by WPI
(ftp://ftp.cs.wpi.edu/pub/techreports/pdf/02-17.pdf)…Particularly
figure 6. Also, the analysis of mice Vs elephants is
important in addtion to mis-behaving flows.
Also, Sally floyd maintains a page on recent
measurement studies on TCP-friendly application.
(http://www.icir.org/floyd/tcp_unfriendly.html)