Path: utzoo!attcan!uunet!mcsun!ukc!strath-cs!jim
From: jim@cs.strath.ac.uk (Jim Reid)
Newsgroups: comp.arch
Subject: Re: Memory utilization & inter-process contention
Message-ID: <278@baird.cs.strath.ac.uk>
Date: 4 Sep 89 12:56:43 GMT
References: <1114@aber-cs.UUCP>
Sender: news@cs.strath.ac.uk
Reply-To: jim@cs.strath.ac.uk
Organization: Comp. Sci. Dept., Strathclyde Univ., Scotland.
Lines: 27

In article <1114@aber-cs.UUCP> pcg@cs.aber.ac.uk (Piercarlo Grandi) writes:
>I hope that system V.4 has a better pager and swapper. It is not true
>like many people assume that memory is infinite and all machines are
>single user, so paging essentially never occurs and swapping should
>never occur.  On top of that, the SUN vm architecture is not the most
>smooth around; it was designed with the SUN hacker's principle in mind,
>"as long as it performs/works in some frequent enough cases, people
>will buy it".

It's hard to see how System V.4 will dramatically improve the VM system.
System V.4 is being touted as the ultimate all-singing, all-dancing UNIX
version. This is supposed to run on most hardware platforms: humble
machines with maybe only 0.5 or 1 Mbyte of RAM (the Sun kernel people
will soon show those users the error of their ways) to monster multi-user
systems with many tens of Megabytes of memory. On top of that are the
architectural considerations: what's best for a multiprocessor box or a
RISC? What about the interaction of page tables with the MMU? How can
that code be written in a generic way for different computers? Then there
will be the variety of job mixes to consider: window managers, lisp
processes, database packages, simulators and so on. Then consider "new"
ideas like paging through the file system and lightweight processes. Some
of these are bound to surface in System V.4

A VM system general enough to perform well for most potential users and
their applications on most potential hardware platforms is asking a lot.

		Jim