Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Posting-Version: version B 2.10.2 9/5/84; site mcc-db2.UUCP
Path: utzoo!watmath!clyde!cbosgd!gatech!ut-sally!mcc-db2!patrick
From: patrick@mcc-db2.UUCP (Patrick McGehearty)
Newsgroups: net.arch
Subject: Re: Re: IOCALL results and problems
Message-ID: <368@mcc-db2.UUCP>
Date: Wed, 8-Jan-86 09:52:19 EST
Article-I.D.: mcc-db2.368
Posted: Wed Jan  8 09:52:19 1986
Date-Received: Thu, 9-Jan-86 03:08:02 EST
References: <380@ncr-sd.UUCP> <835@bu-cs.UUCP>
Organization: MCC (Austin, TX)
Lines: 23

> Re: measuring multi-user system performance
> 
> The only sane thing I have heard in years is what DEC is doing with
> ULTRIX (they say the method originated at AT&T) called Remote Terminal
> Emulation (RTE.)
> 
> Does anyone know of or have the ATT references (I assume there are
> Bell Lab TMs about this.)
> 
- actually, RTE has been around for a long time.  The earliest
reference I used in my thesis work was:
Lassettre, E.R., and A.L. Scherr.
"Modeling and Performance of the OS/360 Time-Sharing Option (TSO)"
Academic Press, 1967, pages 57-72.
DEC has been used RTE since before 1974 to my knowledge.
I consider RTEs the best way (from the point of view of data quality)
to evaluate the performance of time-sharing environments.
The major drawback is the cost of developing a flexible RTE system.
For an extensive discussion of related issues, see
"Guidelines for the Measurement of Interactive Computer Service
Throughput, Turnaround Time, and Response Time." by M.D. Abrams,
Technical Report, Federal Information Processing Standards
Publication, 1979.