Subject: Re: Serious longstanding problem with TCP
To: der Mouse <mouse@Collatz.McRCIM.McGill.EDU>
From: Trevor Blackwell <tlb@eecs.harvard.edu>
List: tech-net
Date: 11/22/1995 14:12:29
> > For quite some time (I observed this in the summer too, but figured
> > it would go away), -current TCP has been performing very badly for
> > short file transfers.  [...]  You'll note that the second packet
> > [from server to client] is not MTU-sized - this causes the receiver
> > to not send an ack immediately.
> 
> Isn't this what slow-start is all about?  Start with small packets and
> ramp up?

Well, slow start does the right thing by starting with a small
window. But this particular example is an unfortunate interaction
between slow start and the delayed ack mechanism.

For slow start to work correctly, you need packets to be acknowledged
immediately.

--
Trevor Blackwell         tlb@eecs.harvard.edu          (617) 495-8912