Relay-Version: version B 2.10 5/3/83; site utzoo.UUCP
Path: utzoo!mnetor!seismo!lll-crg!lll-lcc!rro
From: rro@lll-lcc.UUCP (Rodney Oldehoeft)
Newsgroups: net.arch
Subject: Re: Very large memories
Message-ID: <395@lll-lcc.UUCP>
Date: Tue, 2-Sep-86 22:54:44 EDT
Article-I.D.: lll-lcc.395
Posted: Tue Sep  2 22:54:44 1986
Date-Received: Wed, 3-Sep-86 02:13:15 EDT
Distribution: na
Lines: 17
Keywords: memory, disk speed, memory cost

Sacrifice line.

At an ARO workshop last spring in South Carolina, I got the drift
of a conversation among architects (names not noted) that went
something like this:

"Memory costs are getting cheaper faster than disks are getting
faster.  So large memories are advantageous.  However, since large
memories with fixed page size result in large page tables, larger page
size is a win."

This is a faintly heretical conclusion, what with recent trends in page
size, and the notion that a set of small pages more nearly
approximates the actual working set of a process.

Maybe the ``approximate constant'' being sought is the fraction of
virtual space embodied in a single page.