Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!watmath!clyde!rutgers!ames!ucbcad!ucbvax!ted@cgl.ucsf.edu@blia.UUCP
From: ted@cgl.ucsf.edu@blia.UUCP
Newsgroups: mod.computers.vax
Subject: Re: Local-Area VAXclusters
Message-ID: <8702091655.AA09286@blia.BLI>
Date: Mon, 9-Feb-87 11:55:30 EST
Article-I.D.: blia.8702091655.AA09286
Posted: Mon Feb  9 11:55:30 1987
Date-Received: Wed, 11-Feb-87 07:14:42 EST
References: <8702070804.AA18314@ucbvax.Berkeley.EDU>
Sender: daemon@ucbvax.BERKELEY.EDU
Organization: The ARPA Internet
Lines: 28
Approved: info-vax@sri-kl.arpa

In article <8702070804.AA18314@ucbvax.Berkeley.EDU>, oberman%icaen.DECnet@LLL-ICDC.ARPA ("ICAEN::OBERMAN") writes:
> >I wonder if anyone could answer these queries:
> > 
> >(1) Do you HAVE to run all the LAVC nodes off a common system disc at the
> >    boot node, or can you run a system disc local to the node and use
> >    cluster functionality simply to allow a set of user discs to be accessed
> >    efficiently and identically from any node? (I know that this inhomogeneous
> >    arrangement is possible with ordinary CI clusters)
> No. The LAVC is based on the requirement that all boots be from one system.

At the last Fall DECUS Symposium, I stood up and asked if I could configure
multiple, independent systems into a LAVC. The speaker (from DEC) said that
it should work but that they would not support such a configuration (at least
for now). This may have changed, but I suspect not.

===============================================================================
            Ted Marshall
            Britton Lee, Inc.
p-mail:     14600 Winchester Blvd, Los Gatos, Ca 95030
voice:      (408)378-7000
uucp:       ...!ucbvax!mtxinu!blia!ted
ARPA:       mtxinu!blia!ted@Berkeley.EDU
disclaimer: These opinions are my own and may not reflect those of my employer;
            I leave them alone and they leave me alone.
fortune for today:
First Law of Bicycling:
	No matter which way you ride, it's uphill and against the
	wind.