Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 14 Nov 2001 17:15:10 -0500
From:      Bill Vermillion <bv@wjv.com>
To:        "Steve O'Hara-Smith" <steve@sohara.org>
Cc:        damascus@home.com, stable@FreeBSD.ORG
Subject:   Re: ATA hard drives
Message-ID:  <20011114171509.A16898@wjv.com>
In-Reply-To: <20011114230708.3ceb579d.steve@sohara.org>; from steve@sohara.org on Wed, Nov 14, 2001 at 11:07:08PM %2B0100
References:  <bulk.37366.20011114002208@hub.freebsd.org> <bulk.37366.20011114002208@hub.freebsd.org> <20011114051132.A12369@wjv.com> <5.1.0.14.2.20011114091338.03464ec0@netmail.home.com> <20011114095048.A14300@wjv.com> <20011114230708.3ceb579d.steve@sohara.org>

next in thread | previous in thread | raw e-mail | index | archive | help
On Wed, Nov 14, 2001 at 11:07:08PM +0100, Steve O'Hara-Smith thus spoke:
> On Wed, 14 Nov 2001 09:50:48 -0500
> Bill Vermillion <bv@wjv.com> wrote:

> > Not neccesarily true. About 3-4 years ago I was researching drives
> > and found the IBM 5400RPM SCSI drives were faster than the SEAGATE
> > Baracudda 7200RPM drives.  This was because the IBM's were using a
> > new head design.  Improved media can also mean that you can write

> 	So the IBMs had a higher capacity or fewer platters at higher
> density. Head design alone doesn't help unless it translates to more
> bits per inch of track or more tracks per inch or both.

That's what head design does - it give you more bits per inch.
IBM was using their GMR heads when everyone else was uing MR, both
of which IBM had a hand in developing the GMR [Giant MR] had as I
recall more of a focused gap because of insulators on both sides of
a central pole - and this gave a much narrower magnetic pole -
while the standard gap would spread this.

> 	It seems likely that the 160Gb Maxtor 5400 RPM could have a
> faster data rate than a 7200 RPM 80Gb unless the Maxtor has rather
> more platters than the typical 7200 RPM 80Gb. Disc performance is
> a complex thing depending on rotational speed, linear bit density,
> track density, head movement speed, head settling time, soft error
> rate, pattern of use and probably a few other things.

As I recall there is not a wealth of technical data on the Maxtor
EIDE drives, but there is on their SCSI drivers.  You are correct
that disk performance is complex.   One of the very important other
things you left out is the platter material.  With the extremely
high track density - last I recall on the big ones was 35,000
tracks/inch you don't have to far to move either.  The lightness of
the stalks/heads also make things much faster.  I've been around
magnetic media almost all my life and have become [at times] more
familiar with it than I had planned.


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




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20011114171509.A16898>