Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sun-barr!newstop!exodus!frisbee.Eng.Sun.COM!jcb
From: jcb@frisbee.Eng.Sun.COM (Jim Becker)
Newsgroups: comp.sys.amiga.advocacy
Subject: Re: Commodore Research and Development.
Message-ID: <5995@exodus.Eng.Sun.COM>
Date: 16 Jan 91 00:54:23 GMT
References: <187e4f65.ARN097c@easy.hiam> <1991Jan09.153108.17485@convex.com> <17561@cbmvax.commodore.com> <242^HH|@rpi.edu> <17616@cbmvax.commodore.com>
Sender: news@exodus.Eng.Sun.COM
Lines: 21

daveh@cbmvax.commodore.com (Dave Haynie) writes:

    Actually, the same kind of thing seems to be true of Sun SPARC
    machines.  Though the SPARCs seems to have kind of a plateau
    effect -- they drop off linearly for CPU hog tasks 1..N, then all
    of a sudden take a nose dive.  I don't know if this is a Sun 4
    implementation detail, or an expected effect of the SPARC
    architecture, though.

There was a problem with PMEG allocation scheme that caused this  sort
of  problem.  It has been fixed for new software releases. The problem
occurs when virtual memory goes over 16meg and the Page  Mapping  info
isn't cached.

-Jim Becker

--
--    
	 Jim Becker / jcb%frisbee@sun.com  / Sun Microsystems

		     (kinder & gentler) != WW[3]