home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.sys.sgi
- Path: sparky!uunet!stanford.edu!ames!sgi!classic.asd.sgi.com!jeremy
- From: jeremy@classic.asd.sgi.com (Jeremy Higdon)
- Subject: Re: CDC Drive Parameters
- Message-ID: <opo1shk@sgi.sgi.com>
- Sender: jeremy@classic.asd.sgi.com
- Organization: Silicon Graphics, Inc. Mountain View, CA
- References: <ooj77q8@zuni.esd.sgi.com> <1992Aug20.003115.19242@iscnvx.lmsc.lockheed.com>
- Date: Thu, 20 Aug 1992 01:48:41 GMT
- Lines: 32
-
- In article <1992Aug20.003115.19242@iscnvx.lmsc.lockheed.com>, cunning@arthur (Dave Cunningham) writes:
- > olson@anchor.esd.sgi.com (Dave Olson) writes:
- >
- > : | My in-company computer repair folks replaced my failing 380 Mb system
- > : | disk on a 4D20 with with a similar one last used on a sun. It's the
- > : | same model (CDC 94171-9) but with a different firmware rev. (0045).
- > :
- > : Stuff deleted...
- > :
- > : Error retry of 16 is strange, since that drive wants a multiple
- > : of 3. readahead enabled is something you definitely want for
- > : performance.
- >
- > Does the advice about readahead apply to drives shipped by SGI in
- > late '89 that have it disabled ? I have several 94161-9s and 94171-9s
- > that came with it turned off. (they shipped with 4D20s). Presumably
- > there was a reason for turning it off back then, but it may have been
- > an Irix software issue. Anyone remember ?
-
- On some old drives, the readahead didn't work; if you turned it on, you
- would get data corruption. By late '89, it was probably fixed, but you
- shouldn't turn it if you aren't willing to lose whatever data is on
- those disks. I.e., it's probably safe, but not at all guaranteed.
-
- > --
- > #include <standard_disclaimer.h>
- >
- > Dave Cunningham cunning@arthur.msd.lmsc.lockheed.com
- > Lockheed Missiles and Space Co. O/81-10, B/157-5E, (408)-756-1382
-
- jeremy
-
-