Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!lll-lcc!ames!ucbcad!ucbvax!nosc.ARPA!dennis%cod
From: dennis%cod@nosc.ARPA (Dennis Cottel)
Newsgroups: mod.computers.apollo
Subject: Re:  tape I/O hogging nodes
Message-ID: <8701211908.AA13712@cod.ARPA>
Date: Wed, 21-Jan-87 14:08:03 EST
Article-I.D.: cod.8701211908.AA13712
Posted: Wed Jan 21 14:08:03 1987
Date-Received: Thu, 22-Jan-87 02:08:24 EST
Sender: daemon@ucbvax.BERKELEY.EDU
Organization: The ARPA Internet
Lines: 9
Approved: apollo@yale-comix.arpa

I can understand that tape I/O might slow the node down some, but you
don't expect the display manager to go dormant.  Regardless of what else
is going on, I would think that the display manager should have high
enough priority to keep the cursor moving, accept and display keystrokes,
and the like.  The explanation of a single lock for both disk and tape
(on the DN3000) doesn't seem to explain why the DM can't keep up.

	Dennis Cottel  Naval Ocean Systems Center, San Diego, CA  92152
	(619) 225-2406     dennis@NOSC.MIL      sdcsvax!noscvax!dennis