Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.1 6/24/83; site eosp1.UUCP
Path: utzoo!watmath!clyde!burl!ulysses!allegra!princeton!astrovax!fisher!eosp1!lincoln
From: lincoln@eosp1.UUCP (Dick Lincoln)
Newsgroups: net.micro,net.college
Subject: Re: Overloaded Computing Systems
Message-ID: <1312@eosp1.UUCP>
Date: Fri, 21-Dec-84 10:44:36 EST
Article-I.D.: eosp1.1312
Posted: Fri Dec 21 10:44:36 1984
Date-Received: Sat, 22-Dec-84 02:21:07 EST
References: <773@amdahl.UUCP> <10468@watmath.UUCP>
Organization: Exxon Office Systems, Princeton, NJ
Lines: 22
Xref: watmath net.micro:8958 net.college:566

> There is no problem keeping my brain fully utilized.  One instance
> when my brain is clearly underutilized is during those times when
> courses require that I work with the computer, and the computer
> is so overloaded as to waste a great deal of my time.  (Ever typed
> 80 characters, stopped, and watched all 80 of them appear on the
> screen, one at a time?)  To this I object strongly, and it has the
> side effect of turning a potentially useful exercise into something
> to get quickly out of the way.

One simple way to eliminate a significant amount of mainframe cycle
usage of the kind you cite is to eliminate "full duplex" (UNIX "raw"
mode) terminal drive.  Sure, full duplex is convenient, but to cause a
full user task context switch just to echo back a keystroke, as is the
case for Berkeley "vi", is close to as wasteful as you can be.  Large
time sharing systems worked for years with IBM 3270 protocol and the
like, and supported a full range of applications including text editing
and word processing.  You need a little more down-loaded intelligence in
your terminals to cut down on trivial traffic to your central cpu.

While full duplex is no doubt needed for many research projects, mass
student text processing, programming and number crunching can
certainly be conducted without it.