From owner-freebsd-stable@FreeBSD.ORG Thu Jan 20 19:00:48 2005 Return-Path: Delivered-To: freebsd-stable@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 59F5C16A54D for ; Thu, 20 Jan 2005 19:00:48 +0000 (GMT) Received: from mail.gmx.net (imap.gmx.net [213.165.64.20]) by mx1.FreeBSD.org (Postfix) with SMTP id 2C3D943D1F for ; Thu, 20 Jan 2005 19:00:47 +0000 (GMT) (envelope-from emanuel.strobl@gmx.net) Received: (qmail invoked by alias); 20 Jan 2005 19:00:46 -0000 Received: from flb.schmalzbauer.de (EHLO cale.flintsbach.schmalzbauer.de) (62.245.232.135) by mail.gmx.net (mp007) with SMTP; 20 Jan 2005 20:00:46 +0100 X-Authenticated: #301138 From: Emanuel Strobl To: freebsd-stable@freebsd.org Date: Thu, 20 Jan 2005 20:00:39 +0100 User-Agent: KMail/1.7.2 References: <200501201948.42707.emanuel.strobl@gmx.net> In-Reply-To: <200501201948.42707.emanuel.strobl@gmx.net> X-Birthday: 10/06/72 X-CelPhone: +49 173 9967781 X-Tel: +49 89 18947781 X-Country: Germany X-Address: Munich, 80686 X-OS: FreeBSD MIME-Version: 1.0 Content-Type: multipart/signed; boundary="nextPart1646911.PjIfmrZUXT"; protocol="application/pgp-signature"; micalg=pgp-sha1 Content-Transfer-Encoding: 7bit Message-Id: <200501202000.43688.emanuel.strobl@gmx.net> X-Y-GMX-Trusted: 0 Subject: Re: Higher ATA-Mode -> lower speed X-BeenThere: freebsd-stable@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Production branch of FreeBSD source code List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 20 Jan 2005 19:00:48 -0000 --nextPart1646911.PjIfmrZUXT Content-Type: text/plain; charset="iso-8859-15" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Am Donnerstag, 20. Januar 2005 19:48 schrieb Emanuel Strobl: > Dear ata interested guys, > > I observed a strange behaviour which seems to explain my often noticed > "16MB/s hard-limit" > > I have a UDMA133 drive (MAXTOR 6L060J3) which saturates at 16MB/s when I > dump anything to it, regardless of the block size. This transfer rate is > reached with bs=3D4k and doesn't increase any more even not with bs=3D64k. > > Now, when I set the mode to UDMA100 I get well over 40MB/s!!!! > > Can anybody confirm that for different hw? Especially people like fandino > who already discussed poor ata performance on -current (~16 Oct. 04). I can confirm that for my workstation here. i815 chipset and seagate=20 ST380011A. When set to UDMA100 (the maximum) the following dump gives 16MB/s 'dd=20 if=3D/dev/zero of=3D/usr/testfile bs=3D16k count=3D2000). When I limit the mode to UDMA66 I get 53MB/s !!!!!!!!!!!!!!!! It seems that's independent of UDMA133 instead it's when mode is set to the= =20 maximum the chipset can handle! This really hurts! But it's _the_ eplanation for all the "poor ata=20 performance" reports. =2DHarry > > Why does UDMA133 mode limit the transfer speed so badly? And why do I get > significantly slower transfer rates (32MB/s insted of 42MB/s) when I set > the mode to UDMA66 (compared to UDMA100 but twice the speed of UDMA133)? > There's only one device on the channel, so UDMA66 should be fine for > 42MB/s. The controller is a HPT372. > > Best regards, > > -Harry --nextPart1646911.PjIfmrZUXT Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.0 (FreeBSD) iD8DBQBB7//bBylq0S4AzzwRArKYAJ4mtS4/I7cpUnqvIrLzgO/MpWIe6gCff7WP pHaAdinpIqJ34qpEI25zd/U= =rO5Y -----END PGP SIGNATURE----- --nextPart1646911.PjIfmrZUXT--