Return-Path: <TMcNerney@chipwrights.com>
Received: from pacific-carrier-annex.mit.edu by po11.mit.edu (8.9.2/4.7) id QAA15415; Fri, 21 Sep 2001 16:06:25 -0400 (EDT)
Received: from intranet.chipwrights.com (ipn2-a1131.net-resource.net [216.204.61.131])
	by pacific-carrier-annex.mit.edu (8.9.2/8.9.2) with ESMTP id QAA15345;
	Fri, 21 Sep 2001 16:06:21 -0400 (EDT)
Received: by intranet with Internet Mail Service (5.5.2650.21)
	id <SVQAX3M1>; Fri, 21 Sep 2001 16:07:00 -0400
Message-ID: <93A4BBB9515ED411AE9D00508BD955A5198C1F@intranet>
From: "McNerney, Tim" <TMcNerney@chipwrights.com>
To: "'John Hawkinson'" <jhawk@MIT.EDU>
Cc: "'sipb@mit.edu'" <sipb@MIT.EDU>
Subject: RE: Who do I talk to about e19-rtr-backbone.mit.edu lossage?
Date: Fri, 21 Sep 2001 16:06:53 -0400
MIME-Version: 1.0
X-Mailer: Internet Mail Service (5.5.2650.21)
Content-Type: text/plain;
	charset="iso-8859-1"

McNerney, Tim <TMcNerney@chipwrights.com> wrote on Fri, 21 Sep 2001
at 11:01:37 -0400 in <93A4BBB9515ED411AE9D00508BD955A5198C1A@intranet>:
...
> Here's an idea:
> 
> Maybe the time is right for some sort of low-bandwidth, low-
> latency path into MIT (without using dialups).  Is this something 
> SIPB might be interested in helping with?

   From: John Hawkinson [mailto:jhawk@MIT.EDU]
   Sent: Friday, September 21, 2001 3:30 PM

   I suppose it's conceivable. It certainly hasn't been thought much about.
   Perhaps you might flesh out what you had in mind a little better?

The basic problem I am trying to address is that low-bandwidth, 
interactive TCP sessions (e.g. ssh/telnet, X) are getting 
particularly screwed when routers drop packets on the floor, 
which, of course, is the "acceptable" way of dealing with network 
congestion.  

It feels to me that the fundamental problem is that while network
bandwidth is increasing, it is no longer being allocated in a
way that is "fair" to interactive sessions.  The problem may be
getting worse as routers get optimized for "bursty" traffic.

Right now the MIT backbone accommodates lots of different types of
traffic:  big packets, small packets, images, MP3s, streaming video, 
etc.  The extremes are file transfers that need throughput but can 
sacrifice latency, and interactive sessions that really need low 
latency but only constitute a trickle's worth of bandwidth.

What I had in mind was having two (real or virtual) networks inside
MIT, one low-bandwidth, low-latency, and one for everything else.
The point being to make it so that interactive streams don't get 
"starved" the way they are now.  

Without doing lots of research, I'm not sure I flesh this out too much 
more, but I hope you get the idea.  

   [jhawk continues]
   Off the cuff, it seems like a pretty niche service.

Don't people still use ssh and remote X servers?  That's the sort of
"niche" I am talking about.

--Tim
