Path: utzoo!utgpu!news-server.csri.toronto.edu!rutgers!cs.utexas.edu!samsung!munnari.oz.au!uniwa!DIALix!bernie
From: bernie@DIALix.UUCP (Bernd Felsche)
Newsgroups: comp.sys.amiga.tech
Subject: Re: GVP Trade-in
Summary: Filesystem Speeds
Keywords: SCSI, GVP
Message-ID: <559@DIALix.UUCP>
Date: 2 Sep 90 11:27:33 GMT
References: <14069@cbmvax.commodore.com>
Followup-To: comp.sys.amiga.hardware
Organization: DIALix Services, Perth Western Australia
Lines: 47
X-why: Mail failed

In article <14069@cbmvax.commodore.com> jesup@cbmvax (Randell Jesup) writes:
>In article <552@DIALix.UUCP> bernie@DIALix.oz.au (Bernd Felsche) writes:
[..quote about AmigaDOS FS deleted..]
>
>      Actually, it does far better at things like that than say, Unix, does.

I presume that you're talking about System V.x here.  Berkeley FFS
does heaps better, (than SYS V) as does SunOS, which caches block 
disk I/O into all available RAM.

>There's been quite a bit of discussion at times in comp.arch about filesystem
(I read that newsgroup as well.)
>speeds, and even a 68000 amiga with a DMA controller can keep up there with
>pretty high-power Unix boxes.  One of the reasons is that FFS allows us to do
>direct transfers to the end destination, instead of having to xfer to a buffer
>pool and then cpu copy to destination (like most unix implementations).

Direct transfer is a most efficient approach, and UNIX does allow 
this approach in limited circumstances (raw device i/o).  It is used
almost exculsively by high performance databases, not only for
speed, but also for integrity, as UNIX 'blocking i/o' is write-delayed,
and the application could never be sure if i/o was successful, and
when it actually happened.

>      If you want to see what they can do, check out floppies under 2.0
>trackdisk and FFS.  I've seen >20K/sec reads.  Note that the theoretical
>maximum is ~24K/sec, not including seek and settle times or any other overhead.
>Trackdisk does 22K/sec via the device interface (including seek/settle) under
>2.0.
How about hard disks?  CPU time will be a larger proportion of total
time, so it will be more significant.
>
>      Even on a 68000, sustained transfer speed is limited by disk speed
>in most cases, not processor handling of the data.  A 680{2,3}0 will improve
>rates, but not immensely.

Can you give some statistics on disk i/o for the A3000 running
AmigaDOS vs A3000 running UNIX V.4?  I'd prefer to compare apples
(ooops) I mean Amigas with Amigas.

Also, I'd be interested in how a well-worn filesystem performs; one
that has quite a lot of fragmentation (>10%), for both DOS and
UNIX.  Which UNIX filesystem does AMIX(?) use?

[...deleted stuff...]

bernie