*BSD News Article 74556


Return to BSD News archive

Path: euryale.cc.adfa.oz.au!newshost.anu.edu.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!news.mel.connect.com.au!news.mira.net.au!inquo!in-news.erinet.com!imci5!pull-feed.internetmci.com!news.internetMCI.com!newsfeed.internetmci.com!hunter.premier.net!news.cais.net!rtd.com!dgy
From: dgy@rtd.com (Don Yuniskis)
Newsgroups: comp.unix.bsd.freebsd.misc,comp.os.linux.hardware
Subject: Re: Does cache memory size 512K over 256K matter?
Date: 24 Jul 1996 07:51:07 GMT
Organization: CICDO
Lines: 23
Message-ID: <4t4klb$q7m@baygull.rtd.com>
References: <Pine.A32.3.93.960716180913.29739A-100000@r2d3.sbac.edu> <31F17B64.EDF@www.play-hookey.com> <4t2pe4$9o@anorak.coverform.lan>
NNTP-Posting-Host: seagull.rtd.com
Xref: euryale.cc.adfa.oz.au comp.unix.bsd.freebsd.misc:24289 comp.os.linux.hardware:45400

In article <4t2pe4$9o@anorak.coverform.lan>,
Brian Somers <brian@awfulhak.demon.co.uk> wrote:
>Ken Bigelow (kbigelow@www.play-hookey.com) wrote:
>[relevent stuff deleted]
>: I doubt if size will make too much difference, but speed very definitely 
>: will.
>[The rest of the relevent stuff delted]
>
>I wouldn't let your partner hear that ! ;-)

(grin)

Seriously, I think you're getting to the point of diminishing returns
when cache size gets up there.  I don't *think* (OK, flame me *here* :>)
that any of these OS's particularly try to load the kernel and lock
the cache (etc.) or other similar *potential* optimizations (it's
doubtful whether any such broad-brush optimization would be the most
efficient use of the cache, anyway).  It would be possible to
make such refinements for a particular "kernel" in a particular
set of circumstances, etc.

Of course, if money is no object (email and I'll send you the address
of my PO Box!  :>), more is "always" better...