From owner-freebsd-qa  Sun Oct 29 20: 6: 4 2000
Delivered-To: freebsd-qa@freebsd.org
Received: from spoon.beta.com (064-184-210-067.inaddr.vitts.com [64.184.210.67])
	by hub.freebsd.org (Postfix) with ESMTP
	id 1769037B4C5; Sun, 29 Oct 2000 20:06:01 -0800 (PST)
Received: from spoon.beta.com (localhost [127.0.0.1])
	by spoon.beta.com (8.11.0/8.11.0) with ESMTP id e9U45wu75483;
	Sun, 29 Oct 2000 23:05:59 -0500 (EST)
	(envelope-from mcgovern@spoon.beta.com)
Message-Id: <200010300405.e9U45wu75483@spoon.beta.com>
To: qa@freebsd.org
Cc: hackers@freebsd.org
Subject: DMA/66 not available for secondary IDE bus?
Date: Sun, 29 Oct 2000 23:05:58 -0500
From: Brian McGovern <mcgovern@spoon.beta.com>
Sender: owner-freebsd-qa@FreeBSD.ORG
Precedence: bulk
X-Loop: FreeBSD.ORG

This may be intentional, but I've noticed that if you have a non-UDMA66 device
on the primary IDE bus, FreeBSD 4.x does not allow you to have UDMA66 on
the secondary bus.

To wit, if you had a configuration similar to:


Primary bus
Older (UDMA33 or earlier) IDE boot disk
CD ROM

Secondary bus
15GB UDMA 66 disk
15GB UDMA 66 disk

then even your 16GB drives can not be UDMA 66, and are limited to the UDMA (or
less!) speed provided on the primary bus.

This is particularly troubling if one were to use vinum to try to do a mirror,
as you will not get optimum performance from the drives.

One could argue that shuffling devices around and upgrading the boot drive 
would solve the problem on one of the 15GB disks, but its still not really
an optimal solution, as you'd have to move your CD rom on to the secondary bus,
which would kill the other 15GB drive.

Any possibility that we could 'unhook' the two PCI buses, and allow the 
secondary to go to UDMA66 if the first is down at UDMA 33 or slower?

	-Brian



To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-qa" in the body of the message