Date: Tue, 2 Apr 1996 14:44:59 +0930 (CST) From: Michael Smith <msmith@atrad.adelaide.edu.au> To: koshy@india.hp.com (A JOSEPH KOSHY) Cc: msmith@atrad.adelaide.edu.au, hackers@freebsd.org Subject: Re: HDD cpu usage (IDE vs. SCSI). Message-ID: <199604020515.OAA11178@genesis.atrad.adelaide.edu.au> In-Reply-To: <199604020445.AA210060355@fakir.india.hp.com> from "A JOSEPH KOSHY" at Apr 2, 96 10:15:54 am
next in thread | previous in thread | raw e-mail | index | archive | help
A JOSEPH KOSHY stands accused of saying: > ms> No, you're not understanding. For a given CPU, IDE will _always_ use more > ms> CPU time than SCSI. Period. > > I'm afraid I don't understand too; I recently had the oppurtunity to examine > a Future Domain TMC-1680 card. From what I could see this was an ISA card > with no bus-mastering capability. After the card had read in data from the > scsi bus, it would interrupt and the CPU had to use PIO to copy data from > the card to the system buffers. Pedant 8) I consider non-busmaster SCSI controllers to be at least as bad as IDE, if not worse. > The issue really is how much performance you are getting for your rupee. > The last time I checked here, a 1-disk SCSI sub-system cost around twice as > much as an equivalent IDE 1-disk sub-system. This doesn't hold for larger disk capacities. How much would you pay for a 7200rpm 4GB IDE disk? You're basically making the same point that I am - if performance is an issue, then SCSI is the animal of choice, cost permitting. > Koshy -- ]] Mike Smith, Software Engineer msmith@atrad.adelaide.edu.au [[ ]] Genesis Software genesis@atrad.adelaide.edu.au [[ ]] High-speed data acquisition and (GSM mobile) 0411-222-496 [[ ]] realtime instrument control (ph/fax) +61-8-267-3039 [[ ]] Collector of old Unix hardware. "Where are your PEZ?" The Tick [[
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199604020515.OAA11178>