From owner-freebsd-hackers Fri Feb 23 12:17:39 2001 Delivered-To: freebsd-hackers@freebsd.org Received: from smtpproxy1.mitre.org (mb-20-100.mitre.org [129.83.20.100]) by hub.freebsd.org (Postfix) with ESMTP id 6365937B67D for ; Fri, 23 Feb 2001 12:17:33 -0800 (PST) (envelope-from jandrese@mitre.org) Received: from avsrv1.mitre.org (avsrv1.mitre.org [129.83.20.58]) by smtpproxy1.mitre.org (8.9.3/8.9.3) with ESMTP id PAA06048 for ; Fri, 23 Feb 2001 15:17:31 -0500 (EST) Received: from mailsrv2.mitre.org (mailsrv2.mitre.org [129.83.221.17]) by smtpsrv1.mitre.org (8.9.3/8.9.3) with ESMTP id PAA24639 for ; Fri, 23 Feb 2001 15:17:30 -0500 (EST) Received: from mitre.org ([128.29.145.140]) by mailsrv2.mitre.org (Netscape Messaging Server 4.15) with ESMTP id G988D500.T40; Fri, 23 Feb 2001 15:17:29 -0500 Message-ID: <3A96C577.C0FC12C1@mitre.org> Date: Fri, 23 Feb 2001 15:17:59 -0500 From: "Andresen,Jason R." X-Mailer: Mozilla 4.75 [en]C-20000818M (Win98; U) X-Accept-Language: en MIME-Version: 1.0 To: Torbjorn Kristoffersen Cc: FreeBSD-Hackers Subject: Re: IOmega ZIP problem References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Torbjorn Kristoffersen wrote: > > On Fri, 23 Feb 2001, Peter Pentchev wrote: > > > On Thu, Feb 22, 2001 at 01:19:33PM -0600, Michael C . Wu wrote: > > > On Thu, Feb 22, 2001 at 07:40:16PM +0100, Torbjorn Kristoffersen scribbled: > > > | Hi I'm using 4.2-RELEASE, with a parallel port ZIP drive (100M). > > > | Whenever I copy a large file from the zip drive (for example /dev/da0s1), > > > | the "cp" process eats 98% of the system resources. What's behind all this? > > > | Is there a way to fix it? > > > | > > > | 711 root 54 0 280K 168K RUN 0:45 93.87% 93.21% cp > > > | > > > | A 'renice' won't help. > > > > > > > > > That's natural with "parallel". No way around it. > > > > To clarify a bit, parallel port hardware depends on the system processor > > doing all the data transfers, every single byte, and spending even more > > time checking if it's time for the next byte to go. There's no DMA, there's > > not even a controller you can tell 'here's a 512-byte block, let it fly'. > > > > There's no way around it indeed. > > > > G'luck, > > Peter > > So there doesn't exists any controllers (ISA/PCI) that can do the > serialization of parallel data, and pass it to a serial interface (or > UART), so we can use DMA and move Serial Data Units instead of > single bytes? Not that I'm aware of, although someone could build one fairly easily. Of course if you are going to go to all the trouble to build a specialty card, you might as well just go out and buy a zip drive with a interface. Granted zip drives tend to only use the most minimal subset of whatever protocol they're speaking (ATAPI-floppy device and SCSI-I), but they do work, and are reasonably fast (for zip drives). -- _ _ _ ___ ____ ___ ______________________________________ / \/ \ | ||_ _|| _ \|___| | Jason Andresen -- jandrese@mitre.org / /\/\ \ | | | | | |/ /|_|_ | Views expressed may not reflect those /_/ \_\|_| |_| |_|\_\|___| | of the Mitre Corporation. To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message