Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 17 Jan 2001 17:00:07 +0100 (CET)
From:      Soren Schmidt <sos@freebsd.dk>
To:        martin@svenskabutiker.se (Martin Nilsson)
Cc:        sos@FreeBSD.org (=?ISO-8859-1?Q?S=F8ren?= Schmidt), questions@FreeBSD.org
Subject:   Re: cvs commit: src/sys/dev/ata ata-all.c ata-dma.c
Message-ID:  <200101171600.RAA73362@freebsd.dk>
In-Reply-To: <3A65B768.235894B9@svenskabutiker.se> from Martin Nilsson at "Jan 17, 2001 04:16:56 pm"

next in thread | previous in thread | raw e-mail | index | archive | help
It seems Martin Nilsson wrote:
> "Søren Schmidt" wrote:
> > 
> > sos         2001/01/17 01:22:13 PST
> > 
> >   Modified files:
> >     sys/dev/ata          ata-all.c ata-dma.c
> >   Log:
> >   Add first cut support for the ATA100 capable VIA82c686b.
> > 
> 
> Are the any differences in quality/functions between this chip and a HPT370?
> What I want to know is if there is any reason to buy a 686b equipped board 
> with an additional HPT370 controller on it or not. 
> I don't care about the "RAID" and won't have any need for more than 4 ata 
> devices. I will use it with a IBM 75GXP disk.

Well, if you ask me the HPT370 is about the best ATA chip you can get
currently, it has the lowest overhead of them all. I can get slightly
faster write transfer rate (we are talking controller to disk buffer
here) on the Promise ATA100 controller, but they are both very close
to whats possible...

However stay clear of CMD ATA chips they suck bigtime even the new ones...

So you only really need to have a board with extra ATA channels on it
(be it HPT or Promise) if you need the extra connections it gives 
you (remember that for best performance you would only put one disk
on each channel).


-Søren


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




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200101171600.RAA73362>