Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!csd4.csd.uwm.edu!cs.utexas.edu!uunet!loft386!dpi
From: dpi@loft386.UUCP (Doug Ingraham)
Newsgroups: comp.os.minix
Subject: Re: minix on the macintosh
Summary: IBM's don't DMA to the hard disk
Message-ID: <511@loft386.UUCP>
Date: 9 Sep 89 16:17:36 GMT
References: <334@crash.cts.com>
Organization: Lofty Pursuits, Rapid City, SD USA
Lines: 30

In article <334@crash.cts.com>, jca@pnet01.cts.com (John C. Archambeau) writes:
> Minix on a Mac would be a very lousy platform.  Reason being that Macs don't
> have a notion what DMA is.  Run Minix on a Mac Plus and I guarrantee you it
> will perform worse than a 4.77 XT with a Western Digital controller w/DMA. 

IBM AT's and AT clones don't as a rule use DMA on the Hard Disk.  They do use
it on the floppy.  The reason this approach was chosen was in fact speed.
The data is transfered using the REP INPSW and REP OUTSW instructions which
of course tie up the CPU, but under DOS there is no multi tasking and the
transfer took less physical time than using DMA.  For a 512 byte transfer
(the sector size) it takes only 1549 clocks (194us @ 8mhz) for input and
1292 clocks (162us @ 8mhz) for output (assuming no wait states).  An
equivalent DMA would take a minimum of 320us excluding wait states and
bus transfer time.  Under a multi tasking system DMA would be preferable,
but as we know from experience not essential.
 
> Without DMA support in hardware, porting Minix to a Mac would be pointless. 
> But one thing that does come to mind.  If the Radius Accelerators support DMA
> with hard drive I/O, then the platform to a Mac with a Radius Accelerator
> would be worthwhile.

I have heard that Apple sells Unix for the MAC.  If it doesn't work then
who would buy it?

I am not a MAC fan, but this is not one of the reasons I wouldn't buy one.

-- 
Doug Ingraham (SysAdmin)
Lofty Pursuits (Public Access for Rapid City SD USA)
uunet!loft386!dpi