Subject: Re: now modems have a low bandwidth-delay product, do they?
To: Miles Nordin <carton@Ivy.NET>
From: Matthew Fredette <fredette@MIT.EDU>
List: port-sun3
Date: 12/24/1999 22:10:07
> > my 3/60 gets its connectivity through a 33.6k modem, and the RFC
> > describes "TCP extensions to improve performance over large
> > bandwidth*delay product paths" - not what I have at all.
> Would you say my 768kb/s DSL has a high bandwidth-delay product?  Surely,
> we don't need fancy new RFC's for stupid technologies like old modems.
> but...


> Don't fool yourself.  Modems have a _huge_ bandwidth-delay product.  i
> have no idea what rfc1323 is or how it works, but if there's a problem
> with using it, it's definitely not that your modem's bandwidth-delay
> product is too small to make it worthwhile.

However, note that modems' bandwidth-delay products are small when
compared to those of sattelite links and "big fiber" - which are what
I think RFC1323 was written for.  (I've only skimmed it.)

Nonetheless, I figure that on my machine, RFC1323 *is* kicking in
because my b*d product crosses some threshold.  But then, either its
techniques hurt me rather than help me (which would make RFC1323
flawed in some way), or their implementation in NetBSD is incorrect.

I dunno which, but turning it off is easy enough and makes everything
work, and I'm not curious enough to figure out what the real deal is :).


Matt Fredette,,
"If you understood everything I said, you'd be me."  - Miles Davis