*BSD News Article 16349


Return to BSD News archive

Xref: sserve comp.os.linux:39704 comp.os.386bsd.questions:2591 comp.unix.pc-clone.32bit:2899
Newsgroups: comp.os.linux,comp.os.386bsd.questions,comp.unix.pc-clone.32bit
Path: sserve!newshost.anu.edu.au!munnari.oz.au!news.Hawaii.Edu!ames!agate!howland.reston.ans.net!noc.near.net!uunet!leviticus!richk
From: richk@grebyn.com (Richard Krehbiel)
Subject: Re: IDE vs SCSI  and performance
In-Reply-To: newton@cleese.apana.org.au's message of 19 May 1993 09:36:27 +0930
Message-ID: <C7CpK2.Gn2@grebyn.com>
Lines: 22
Sender: richk@grebyn.com (Richard Krehbiel)
Organization: Grebyn Timesharing, Inc.
References: <C72CAw.B47@sugar.NeoSoft.COM> <1tbtmk$a0b@cleese.apana.org.au>
Date: Thu, 20 May 1993 06:51:12 GMT

In article <1tbtmk$a0b@cleese.apana.org.au> newton@cleese.apana.org.au (Mark Newton) writes:

>   peter@NeoSoft.com (Peter da Silva) writes:
>   > I was talking to a fellow in a computer store the other day, and he was
>   > insisting that he was getting 2.5 MB/s on his IDE drives under AmigaOS,
>   > over twice what he got with SCSI.
>   > I found that hard to beleive... I suspected that his benchmark was being
>   > messed up by buffering.
>
>   Amiga benchmarking programs typically bypass the filesystem and
>   manipulate the raw disk device to do their speed tests.  They also
>   disable multitasking.

The most popular Amiga disk benchmark (DiskPerf) takes great pride in
going *through* the file system.  And it can't disable multi-tasking,
because the file system and device driver code are separate tasks; if
you disable multitasking, it wouldn't run.

>   In any case, the results obtained from benchmarks usually have no bearing
>   on the machine's real-life performance.

Always true.
-- 
Richard Krehbiel                                 richk@grebyn.com
OS/2 2.0 will do for me until AmigaDOS for the 386 comes along...