[17311] in North American Network Operators' Group
Re: PC Bozo's World bites again (CNN, too)
daemon@ATHENA.MIT.EDU (Vern Paxson)
Fri May 29 03:14:29 1998
To: "Forrest W. Christian" <forrestc@iMach.com>
Cc: nanog@merit.edu
In-reply-to: Your message of Thu, 28 May 1998 22:58:26 PDT.
Date: Fri, 29 May 1998 00:01:57 PDT
From: Vern Paxson <vern@ee.lbl.gov>
> Has anyone done an analysis of how having a smaller MTU affects
> slow-start? It seems to me that a TCP session would come up to speed
> about 3 times faster with a mtu of ~500 vs a mtu of ~1500.
It doesn't, because the smaller MTU doesn't mean you get more acks per unit
time, just that you get more acks overall. So you still get the same slow
start increase pattern, only your segments are 1/3 the size they could be,
so your data rate is 1/3 what it could otherwise be (until cwnd is big enough
to consume the available bandwidth).
The improved-performance-with-low-MTU is a puzzle I'd certainly like to
understand better. It seems step 1 is to eliminate the possibility that
the 1500 MTU is leading to fragmentation.
Vern
