Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!wuarchive!rice!rice!sun-spots-request
From: henry@zoo.toronto.edu
Newsgroups: comp.sys.sun
Subject: Re: Process taking over system
Keywords: Miscellaneous
Message-ID: <1990Oct7.223305.27540@rice.edu>
Date: 7 Oct 90 21:30:00 GMT
Sender: sun-spots-request@rice.edu
Organization: Sun-Spots
Lines: 13
Approved: Sun-Spots@rice.edu
Originator: spots@walhalla.rice.edu
X-Sun-Spots-Digest: Volume 9, Issue 321, message 4
X-Refs:  Original: v9n314

>The problem:  When a compute-intensive process starts running and the
>3/260 server, the NFS response to the clients drops to the point of being
>unusable...

I'm not up on 4.0.1's peculiarities, but for a guess, what you have here
is Sun's well-known AWW (All the World's a Workstation) syndrome.  Since
all Suns are single-user workstations :-), when a big compute-intensive
process starts running, clearly it is *meant* to have the whole machine to
itself, and NFS service to interlopers from other CPUs is second priority.
AWW assumptions like this were all over SunOS 3.n, and I wouldn't be at
all surprised if they'd persisted.

                                          henry@zoo.toronto.edu   utzoo!henry