Upper bound on numbers of users

John Campbell jdc at naucse.cse.nau.edu
Thu Mar 14 03:20:13 AEST 1991


Help!

I'm trying to compile a table for use here at the University that
summarizes, to some extent, different computer platforms.  I have
a little bit of information about machine performance--although
I've found getting something like SPECmarks on non-unix platforms
fairly difficult.

The "other" side of the issue is numbers of users a machine can
handle.  

What I'd like, is to hear from other sites and try to get an
idea on the number of users actually using different machines 
concurrently.  In other words, what machines are you running 
and what's an "average" number of users?  I'm particularly
interested in any sites that run "large" (>5) numbers of users
on Workstations (we don't).

Here's a synopsis, by the way, of our site:

Computer        Memory     Disk    #accts   Avg # users    (Mips)    O.S.
IBM ES9000-210   128Mb    10000Mb   1020        200         (14?)    MVS
VAX 6310          32Mb     1800Mb    630         30         (10?)    VMS
IBM 9375          16Mb     1600Mb    470         40         ( 7?)    CMS
MicroVax-3500     16Mb     1400Mb    110         10         ( 6?)    Ultrix
MicroVax-II       11Mb      113Mb    160         10         ( 4?)    Ultrix  

Type of use:
IBM ES9000-210  mostly on-line transactions, production programming (cobol)
VAX 6310        academic research and instruction
IBM 9375        email (PROFS) and instruction
MVAX-3500       academic research and instruction
MVAX-II         instruction

We have, as you might expect, other machines (DECStation 3100, Apollo
DN1000, IRIS 4D25G) but they are typically running with very few (<3)
users at a time.  Where do most sites put most of their users?  (And
why?)   ((Is there any reason--providing unlimited licensing is available--
not to run lots of users on workstations?))

If there is any interest in this I'll summarize.

Thanks!   John Campbell   CAMPBELL at NAUVAX.UCC.NAU.EDU
-- 
	John Campbell               jdc at naucse.cse.nau.edu
                                    CAMPBELL at NAUVAX.bitnet
	unix?  Sure send me a dozen, all different colors.



More information about the Comp.unix.misc mailing list