From owner-freebsd-chat  Thu Nov  6 17:56:05 1997
Return-Path: <owner-freebsd-chat>
Received: (from root@localhost)
          by hub.freebsd.org (8.8.7/8.8.7) id RAA29636
          for chat-outgoing; Thu, 6 Nov 1997 17:56:05 -0800 (PST)
          (envelope-from owner-freebsd-chat)
Received: from word.smith.net.au (word.smith.net.au [202.0.75.3])
          by hub.freebsd.org (8.8.7/8.8.7) with ESMTP id RAA29586
          for <freebsd-chat@FreeBSD.ORG>; Thu, 6 Nov 1997 17:54:56 -0800 (PST)
          (envelope-from mike@word.smith.net.au)
Received: from word.smith.net.au (localhost.smith.net.au [127.0.0.1])
	by word.smith.net.au (8.8.7/8.8.5) with ESMTP id MAA00407;
	Fri, 7 Nov 1997 12:20:31 +1030 (CST)
Message-Id: <199711070150.MAA00407@word.smith.net.au>
X-Mailer: exmh version 2.0zeta 7/24/97
To: chris@netmonger.net (Christopher Masto)
cc: freebsd-chat@FreeBSD.ORG
Subject: Re: hardware 
In-reply-to: Your message of "06 Nov 1997 18:22:56 GMT."
             <63t1u0$fbd$1@schenectady.netmonger.net> 
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Fri, 07 Nov 1997 12:20:30 +1030
From: Mike Smith <mike@smith.net.au>
Sender: owner-freebsd-chat@FreeBSD.ORG
X-Loop: FreeBSD.org
Precedence: bulk

> > Perhaps I should have posted over my other signature, the one that says 
> > "high-speed data acquisition and realtime instrument control"?  I *do* 
> > try to keep a reasonable eye on things that impact on storage.  8)
> 
> Oh, I see.  You're more qualified to post your opinion than I am.

Damn right, as you have just admitted.

> The
> fact is that I do a lot of work on machines with IDE and SCSI and I
> decided to share my experience.  I hear this "IDE is just as good as
> SCSI if you have only one drive" argument constantly, and frankly, I
> don't believe it.

... and my point is that I *do*, having converted from your point of 
view some time back.  Please note that I have a moderately broad 
collection of SCSI and IDE peripherals and adapters, and as I 
previously mentioned my current employer depends upon single-disk 
performance across a wide variety of file sizes (a few bytes to many 
hundreds of megabytes) on heavily loaded realtime systems.

>  I suspect it has a lot more to do with scattered
> small files than sustained performance.

"Huh"?  What does "scattered small files" have to do with anything?  We 
are talking basic disk performance vs. cost.

> ...  I can report that on the news machine (which has an IDE boot
> and /tmp drive), heavy access on the IDE drive causes a lot more
> CPU load than heavy SCSI access (Adaptec 3940UW).

And I will observe that you are probably running with the IDE disk in 
compatability mode (flags 0) rather than taking advantage of any of the 
minor improvements in the 2.2 driver (flags 0x80ff), let alone the 
busmaster DMA in the 3.x driver (flag 0xa000).

This is like talking about a 5MHz async SCSI 1 peripheral.  Like I 
said, apples with apples.

> Then that doesn't explain the difference, and my theory is wrong.
> I'll have to read the specs at some point. 

I'll stop here.  You do that.  Then we can talk.  Until then, for 
crying out loud, consider listening to people that _have_.  If you 
don't trust me, try Soren (who has one of the faster worldbuilders 
running on IDE disks), or John Dyson (who had six IDE disks in a system 
at one stage, running ~10MB/sec sustained), or John Hood (who did the 
DMA work).

None of us are complete idiots, thanks very much.

mike