From owner-freebsd-stable Mon Mar 12 22:39:51 2001 Delivered-To: freebsd-stable@freebsd.org Received: from ns1.venon.com (ns1.venon.com [64.7.7.83]) by hub.freebsd.org (Postfix) with ESMTP id 44EEF37B728; Mon, 12 Mar 2001 22:39:38 -0800 (PST) (envelope-from all@biosys.net) Received: from megalomaniac.biosys.net (megalomaniac.venon.com [64.7.7.82]) by ns1.venon.com (Postfix) with ESMTP id 5BB15D1613; Tue, 13 Mar 2001 01:37:42 -0500 (EST) Message-Id: <4.3.2.7.2.20010313013018.00c49fd0@64.7.7.83> X-Sender: (Unverified) X-Mailer: QUALCOMM Windows Eudora Version 4.3.2 Date: Tue, 13 Mar 2001 01:39:26 -0500 To: Jean-Marc Zucconi , freebsd-stable@FreeBSD.ORG From: Allen Landsidel Subject: Re: UDMA 33/UDMA 100 perfs In-Reply-To: <4.3.2.20010313002151.02d94c70@207.227.119.2> References: <200103130329.f2D3TXN73556@freefall.freebsd.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG At 00:24 3/13/2001 -0600, Jeffrey J. Mountin wrote: >At 07:29 PM 3/12/01 -0800, Jean-Marc Zucconi wrote: >>Is this the normal behavior expected? >> >>1) >>ata0-master: DMA limited to UDMA33, non-ATA66 compliant cable >>ad0: 19092MB [38792/16/63] at ata0-master using UDMA33 >># dd if=/dev/ad0e of=/dev/null bs=1m count=1000 >>1048576000 bytes transferred in 49.445390 secs (21206750 bytes/sec) >> >>2) >>ad0: 19092MB [38792/16/63] at ata0-master UDMA100 >># dd if=/dev/ad0e of=/dev/null bs=1m count=1000 >>1048576000 bytes transferred in 49.337278 secs (21253220 bytes/sec) >> >>I get the same performance in both cases. This is with a 4.3-BETA >>kernel. I have only one drive on the IDE bus. > >Just because the speed limit goes up doesn't mean your car will go faster. > >To wit there are few drives that can exceed what UDMA33 can handle and >only then would the higher "speed limit" help. It should be pointed out that people are really expecting something that systems really aren't designed to deliver when they have "problems" like this. The point of a higher bus speed is not to get higher transfer rates from a single drive, but to avoid saturating the bus when you have multiple drives on a single channel of a controller. This is true of both IDE and SCSI. The above mentioned drive is a Western Digital "Protoge", their lowest-end drive family. It may be ATA-100, but it's also 5400RPM. Their site tells us this drive has minimum to-media transfer rate of 24MB/s, and a maximum transfer rate of 40MB/s. What rate you get will dependant upon where your data is located on the disk. The closer to the outside of the disk, the faster your transfer rates will be. It looks to me like Mr. Zucconi is getting exactly the performace he should expect out of that drive. If you want better performance, you have a few options. All of them, unfortunately, involve buying more hardware. 1. Buy a drive with faster to and from media characteristics. Higher drive rpm, and higher data density will contribute to this to a degree. 2. Set up a RAID, either through outlay of some $$ for a hardware controller, or by using vinum. -------signature file------- PGP Key Fingerprint: 446B 7718 B219 9F1E 43DD 8E4A 6BE9 D739 CCC5 7FD7 "I don't think [Linux] will be very successful in the long run." "My experience and some of my friends' experience is that Linux is quite unreliable. Microsoft is really unreliable but Linux is worse." -Ken Thompson, Interview May 1999. http://www.freebsd.org FreeBSD - The Power to Serve http://www.rfnj.org Radio Free New Jersey - 375 streams - 96kbps @ 44.1khz http://namespace.org -- http://name.space Resist the ICANN! Support name.space! To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message