[e2e] Cannara's views
J. Noel Chiappa
jnc at ginger.lcs.mit.edu
Fri Apr 13 10:30:23 PDT 2001
> From: "David P. Reed" <dpreed at reed.com>
> try to build a net that can support commercial applications and
> services of this scale and diversity on the X.25 networks or the ATM
> SVC networks.
> if congestion turns out to be better controlled by deploying twice as
> much fiber as needed, that seems to me to be both theoretically and
> practically sound.
This is an approach that computer science has taken again and again. I often
use the example of virtual memory paging algorithms - how much time and
energy was spent on those in the late 60's and early 70's!
Now we just walk down to the local Office Max equivalent and fork over US$50
for another 64MB (or whatever the going rate is these days, it's been a
couple of months since I last bought any :-).
> Hardware is now a commodity that is easily spent, something that
> theoreticians have not come to understand in their framing of
> "optimization" problems. The boundary conditions of any attempt to
> optimize should incorporate the tradeoff between adding resources and
> adding control complexity.
Well, there are other axes too - like the one I pointed out in a previous
message, which is that designer/developer/support time/energy/etc is a
relatively finite and basically fungible commodity. So a true systemic
optimization has to consider the various places in the architecture one can
spend this limited resource.
Resources spent developing/deploying solutions to problem A might provide the
community as a whole with better service if spent instead on problem B, if B
is more severe than A.
More information about the end2end-interest