From owner-freebsd-hackers  Thu Feb 21  0:57:19 2002
Delivered-To: freebsd-hackers@freebsd.org
Received: from freebsd.dk (fw-rl0.freebsd.dk [212.242.86.114])
	by hub.freebsd.org (Postfix) with ESMTP
	id D878F37B405; Thu, 21 Feb 2002 00:57:15 -0800 (PST)
Received: (from sos@localhost)
	by freebsd.dk (8.11.6/8.11.6) id g1L8v2E70980;
	Thu, 21 Feb 2002 09:57:02 +0100 (CET)
	(envelope-from sos)
From: Søren Schmidt <sos@freebsd.dk>
Message-Id: <200202210857.g1L8v2E70980@freebsd.dk>
Subject: Re: ATA Controller choices
In-Reply-To: <000001c1ba67$b66429e0$fc5807ca@mosm1>
To: Jan Mikkelsen <janm@transactionware.com>
Date: Thu, 21 Feb 2002 09:57:02 +0100 (CET)
Cc: sos@FreeBSD.ORG, freebsd-hackers@FreeBSD.ORG
Reply-To: sos@freebsd.dk
X-Mailer: ELM [version 2.4ME+ PL94b (25)]
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain; charset=ISO-8859-1
Sender: owner-freebsd-hackers@FreeBSD.ORG
Precedence: bulk
List-ID: <freebsd-hackers.FreeBSD.ORG>
List-Archive: <http://docs.freebsd.org/mail/> (Web Archive)
List-Help: <mailto:majordomo@FreeBSD.ORG?subject=help> (List Instructions)
List-Subscribe: <mailto:majordomo@FreeBSD.ORG?subject=subscribe%20freebsd-hackers>
List-Unsubscribe: <mailto:majordomo@FreeBSD.ORG?subject=unsubscribe%20freebsd-hackers>
X-Loop: FreeBSD.ORG

It seems Jan Mikkelsen wrote:
> Søren Schmidt wrote:
> > ... However the Serverworks ROSB4 chips is not one I 
> > would recommend using, if you need serious ATA support on 
> > such a board, install a Promise TX2 or later or a HPT370 or later ...
> 
> I think I've also seen you post that the Highpoint is better than the
> Promise.

That was before Promise made the TX2 line, they are pretty good, but
the new HPT374 also has potential.

> What is the "quality heirarchy" of ATA chips?  Eg. I know the VIA chips
> have issues.  Where does the CMD 649 fit in that heirarchy?

There are two different kinds, those that are part of a southbridge
chip (eg the VIA, SiS, Intel etc) and those that are meant for addon
PCI cards (eg Promise, Highpoint).
For the first type you only have part of a choice, since you cannot
always decide what kind you want for a given platform, but you
can always disable it and use something else.

Now for PCI based controllers the low end is the CMD chips, they are
horrible performers, and the older versions has all kinds of "nits"
that needs workarounds (I chose not to support them instead).
Then there isn't really much to think about, only if it needs to be
Promise or HighPoint :)

> Such a list (or even a list of known issues with particular chips) would
> be useful for specifying new machines.

Hmm, I have such a list on various pieces of paper here and lots of
loose notes, but nothing that could be easily posted. However it a
good idea and I'll get it into shape *sometime*

-Søren

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