*BSD News Article 81258


Return to BSD News archive

#! rnews 1600 bsd
Newsgroups: comp.os.linux.development.system,comp.unix.bsd.freebsd.misc
Path: euryale.cc.adfa.oz.au!newshost.carno.net.au!harbinger.cc.monash.edu.au!munnari.OZ.AU!metro!metro!asstdc.scgt.oz.au!nsw.news.telstra.net!act.news.telstra.net!psgrain!usenet.eel.ufl.edu!news.mathworks.com!howland.erols.net!EU.net!Norway.EU.net!sn.no!nntp.uio.no!nntp.zit.th-darmstadt.de!fu-berlin.de!zrz.TU-Berlin.DE!news.dfn.de!news.dkrz.de!news.rrz.uni-hamburg.de!news.Hanse.DE!wavehh.hanse.de!cracauer
From: cracauer@wavehh.hanse.de (Martin Cracauer)
Subject: Re: Linux vs FreeBSD disk io performance
Message-ID: <1996Oct21.131053.14924@wavehh.hanse.de>
Organization: BSD User Group Hamburg
References: <86g23ey1uc.fsf@romulus.ihosteng.priv.no> <544o8g$rlu@newsbr.eunet.fr>
Date: Mon, 21 Oct 96 13:10:53 GMT
Lines: 20
Xref: euryale.cc.adfa.oz.au comp.os.linux.development.system:33854 comp.unix.bsd.freebsd.misc:29713

Frederic.Marand@osinet.fr (Frederic MARAND) writes:

>Ivar Hosteng <ivarh@romulus.ihosteng.priv.no> wrote:
>>Can someone explain this different behaviour?

>There's one silly thing I noticed years ago on HP-UX : the code for
>the /dev/null driver is less efficient than the one for disk I/O. 

>Unbelievable as it seemed to us at the time, we got much better
[...]

I did some benchmarks on /dev/null a few years ago on several
systems. They are *very* different and it is totally bogus to
benchmark other things and use /dev/null as a target device.

Martin

-- 
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
Martin Cracauer <cracauer@wavehh.hanse.de>  http://cracauer.cons.org