Xref: utzoo comp.periphs:3451 comp.sys.sgi:8194 comp.periphs.scsi:1857 Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!usc!samsung!munnari.oz.au!yoyo.aarnet.edu.au!sirius.ucs.adelaide.edu.au!sirius!jeremy From: jeremy@cs.adelaide.edu.au (Jeremy Webber) Newsgroups: comp.periphs,comp.sys.sgi,comp.periphs.scsi Subject: Re: exabyte record size limit Message-ID: Date: 10 Feb 91 05:44:01 GMT References: <1991Feb8.154740.11155@helios.physics.utoronto.ca> Sender: news@ucs.adelaide.edu.au Followup-To: comp.periphs Organization: Digital Arts Film and Television Lines: 20 Nntp-Posting-Host: chook.ua.oz.au In-reply-to: sysmark@physics.utoronto.ca's message of 8 Feb 91 20:47:40 GMT Hi all, FYI, I did some performance tests on an Exabyte connected to a Sun 4/280 some years ago, and found that transfer rate was maximized for transfers of 64K. That is, transfers below that block size were substantially slower, and transfers above that block size showed no noticable gain. Very small transfers also seemed to use more *tape* than larger transfers. I'm not sure why. 1K blocks got less than half the storage on the tape that 64K blocks did. All block sizes were multiples of 1K. -jeremy -- -- Jeremy Webber ACSnet: jeremy@chook.ua.oz Digital Arts Film and Television, Internet: jeremy@chook.ua.oz.au 3 Milner St, Hindmarsh, SA 5007, Voicenet: +61 8 346 4534 Australia Papernet: +61 8 346 4537 (FAX)