Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!usc!rpi!crdgw1!crdos1!davidsen
From: davidsen@crdos1.crd.ge.COM (Wm E Davidsen Jr)
Newsgroups: comp.arch
Subject: Re: Optical Tape
Message-ID: <3318@crdos1.crd.ge.COM>
Date: 8 Apr 91 15:39:36 GMT
References: <3306@crdos1.crd.ge.COM> <1991Apr2.163914.7948@snitor.uucp> <12608@pt.cs.cmu.edu>
Reply-To: davidsen@crdos1.crd.ge.com (bill davidsen)
Organization: GE Corp R&D Center, Schenectady NY
Lines: 19

In article <12608@pt.cs.cmu.edu> lindsay@gandalf.cs.cmu.edu (Donald Lindsay) writes:

|                                                            I assume
| (well, hope) that the 3 MB/s SCSI interface was a marketing decision,
| not a technological limit.

  Well, a usefully high one. If you assume a fair sized file server
might have a backup volume of 80GB per day, then 80GB/3MB is 26667 sec,
or 7.4 hours. That's about right for an eight hour shift, and not having
to pay an operator to hang tapes all night long would pay for the drive.

  Now the question is, how much is the media, and can you find a given
place on it in a reasonable time? You could break the disk into small
(200MB or so) filesystems in many cases, if you could write a filemark
after each one and scan quickly through them.
-- 
bill davidsen	(davidsen@crdos1.crd.GE.COM -or- uunet!crdgw1!crdos1!davidsen)
        "Most of the VAX instructions are in microcode,
         but halt and no-op are in hardware for efficiency"