From owner-freebsd-hackers  Wed Mar 22 08:25:12 1995
Return-Path: hackers-owner
Received: (from majordom@localhost) by freefall.cdrom.com (8.6.10/8.6.6) id IAA08361 for hackers-outgoing; Wed, 22 Mar 1995 08:25:12 -0800
Received: from ns.dknet.dk (root@ns.dknet.dk [193.88.44.42]) by freefall.cdrom.com (8.6.10/8.6.6) with SMTP id IAA08330; Wed, 22 Mar 1995 08:24:36 -0800
Received: from login.dknet.dk by ns.dknet.dk with SMTP id AA15268
  (5.65c8/IDA-1.4.4j); Wed, 22 Mar 1995 17:22:54 +0100
Received: by login.dknet.dk (4.1/SMI-4.1DKnet00)
	id AA16615; Wed, 22 Mar 95 17:21:19 +0100
From: sos@login.dknet.dk (S|ren Schmidt)
Message-Id: <9503221621.AA16615@login.dknet.dk>
Subject: Re: Why IDE is bad
To: bde@zeta.org.au (Bruce Evans)
Date: Wed, 22 Mar 95 17:21:18 MET
Cc: bde@zeta.org.au, faq@FreeBSD.org, hackers@FreeBSD.org, hasty@star-gate.com,
        phk@ref.tfs.com
In-Reply-To: <199503221513.BAA17998@godzilla.zeta.org.au>; from "Bruce Evans" at Mar 23, 95 1:13 am
X-Charset: ASCII
X-Char-Esc: 29
Sender: hackers-owner@FreeBSD.org
Precedence: bulk

> 
> >> >And that is the main thing on E-IDE, the drives are designed
> >> >with enough onboard cache, that coretest etc. reports transfer
> >> >rates close to the interface speed (13MB sec or so), but the
> >> >drive cannot hold this speed when it has to read from the media.
> >> 
> >> This is also good for reducing interrupt overhead.
> 
> >Hmm, most of the drives would intterupt once each sector anyway
> >even when doing DMA, so there is really nothing gained...
> 
> Interrupts don't take long (< 10 usec on a DX2/66) if the driver
> doesn't do anything.  The IDE driver does a lot.  It takes at least
> 155 usec to transfer 512 bytes at 3.3MB/sec.  Dividing `a lot' by
> (11.3/3.3) has good effects.

Hmm, yes but most motherboards can only run code off the cache
when the onboard DMA is running, limiting the usefullness of
this approach "somewhat". Besides the DOS dudes allready found out
and you will have VERY big trouble even finding a DOS DMA driver....
 
> >> I expect better IDE drives would have been avaiable if the
> >> interface had supported them.
> 
> >Actually I think not, the IDE thing is about making CHEAP disks
> >for the average PC user. It is much better advertising to have a
> >500MB drive than a 300MB drive, who cares about performance ???
> 
> "Only" half the posters in comp.sys.ibm.pc.hardware.*.  Even the
> average user needs ever increasing performance to run the latest
> bloatware.

Well the average user doesn't have net access (hell most doesn't
even know what it is), so this is a somewhat vague argument....
BUT what they understand is when the sales droid shoves in a
bigger disk for (allmost) the same price, not wondering how this
can be done without loosing something else (performance)...
The "advanced" user then tries coretest, and the "amasing" EIDE
disk shows these wonderfull high transferrates (thanks to a
carefully sized disk-intern cache), oh waw !

In the old days these guys sold (used) horses....

-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-
Soren Schmidt  (sos@FreeBSD.org | sos@login.dknet.dk)  FreeBSD Core Team
               So much code to hack -- so little time
..