*BSD News Article 20864


Return to BSD News archive

Xref: sserve comp.unix.misc:9096 comp.os.linux:54722 comp.os.386bsd.misc:984
Path: sserve!newshost.anu.edu.au!munnari.oz.au!constellation!aardvark.ucs.uoknor.edu!ns1.nodak.edu!netnews.nwnet.net!ogicse!uwm.edu!cs.utexas.edu!uunet!wyvern!taylor.wyvern.com!mark
Newsgroups: comp.unix.misc,comp.os.linux,comp.os.386bsd.misc
Subject: Re: What are the various PC bassed Unix box OS?
Message-ID: <1993Sep13.121546.19533@taylor.uucp>
From: mark@taylor.uucp (Mark A. Davis)
Date: 13 Sep 93 12:15:46 GMT
References: <1993Sep02.184251.23903@engr.engr.uark.edu> 
 <2C8E9252.3016@news.service.uci.edu> 
 <michaelv.747547179@ponderous.cc.iastate.edu> <1993Sep12.235912.32501@unixland.ci.net> <1993Sep13.084852.1164@black.ox.ac.uk>
Organization: Lake Taylor Hospital Computer Services
Keywords: pc,unix
Article-I.D.: taylor.1993Sep13.121546.19533
Lines: 32

mbeattie@black.ox.ac.uk (Malcolm Beattie) writes:

>In article <1993Sep12.235912.32501@unixland.ci.net> bill@unixland.ci.net (Bill Heiser) writes:
>>In article <michaelv.747547179@ponderous.cc.iastate.edu> michaelv@iastate.edu (Michael L. VanLoon) writes:
>>>>>iiitac@swan.pyr (Alan Cox) writes:
>>>>>>In article <chmae.747045462@guug.de> chmae@guug.de (Christoph Maethner) writes:
>>>>>>>I don't think I will ever need a 486 , I would perfer more RAM.
>>>>Wouldn't this, however, be an argument *for* getting a 486?  I am just
>>>>wondering, as I have heard that UNIX on a 486 should conceivably run
>>>>better because the 486's hardware, especially if it has a local bus,
>>>No matter how fast the drive and controller, RAM will always be
>>>faster.
>>
>>I ran a Unix SVR3 on a 386/25.  I then upgraded the machine to a
>>486/33.  Overall system performance was *twice* as fast (using the
>>same peripherals) with the 486 machine than on the 386.

>That's because of the difference in clock speeds. A rule of
>thumb is that at a given clock speed a 486 is about 1/3 faster
>than a 386, and that performance increases roughly linearly
>(very, very roughly) in this range of clock speeds.
>Comparing your 386/25 with your 486/33 you can see where the
>factor of two comes from. The usual "386 v 486" question
>centres on the comparison of a 386/40 with a 486/33.

You also forgot that his 386 had no math processor and the 486 does.

-- 
  /--------------------------------------------------------------------------\
  | Mark A. Davis    | Lake Taylor Hospital | Norfolk, VA (804)-461-5001x431 |
  | Sys.Administrator|  Computer Services   | mark@taylor.wyvern.com   .uucp |
  \--------------------------------------------------------------------------/