From riel@nl.linux.org Wed Feb 16 16:10:27 2000
Date: Wed, 9 Feb 2000 19:33:40 +0100 (CET)
From: Rik van Riel <riel@nl.linux.org>
To: Andreas Schuldei <schuldei@uni-bremen.de>
Cc: spindler@unix-ag.uni-kl.de
Subject: Re: kernel talk at linuxtag

On Wed, 9 Feb 2000, Andreas Schuldei wrote:

> I wanted to ask you to mail an assey to spindler@unix-ag.uni-kl.de
> with a short outline of your talk.
> 
> I think it would be best to not go into tomuck technicak detail in
> the talk, because you might be losing a majot part of the
> audience. But I guess you would be flexible and if smart questions
> came you would answer even smarter. :-)

Here's a quick abstract. I hope you'll like it...
Just tell me if it is too long, short, detailed,
etc.

---------------------------------------------------

"Too little, too slow; an introduction to memory management"

--

I'll give an introduction to memory management, a fairly
basic overview on a conceptual level. No source code or
complex calculations will be involved. We start out with
looking at the size and speed differences between CPU,
cache, memory and hard disks, the so called "memory
hierarchy".

The speed difference between CPU and memory (25 to 100
times as slow) and memory and hard disk (>100.000 times
as slow) is quite big. Because of this the memory
hierarchy poses some "interesting" performance problems
that the operating system has to deal with.

The speed difference between CPU and memory is mainly
masked by "cache"; cache is very fast memory and using
it does not need support from the Operating System or
application. However, there are some tricks the OS can
perform to make it easier for the cache to do its job
well and to raise system performance.

The speed difference between memory and hard disk is
truly enormous. Furthermore, data on disk will be saved
permanently so we need to store some of it in a way that
we can find it back after the computer is rebooted.

This means that we have to store the data in a "filesystem".
I won't talk about how a filesystem works. The important
part is that a filesystem works like an index where you
have to look up where the data is.

The extra lookup means that the disk would be even slower,
more than a million times as slow as the processor!  The
only reason that the system still runs reasonably fast is
because of some memory management and filesystem tricks.

In this talk I will focus on the behaviour of programs
and the tricks we can be done in hardware and software
to keep performance good in spite of the large speed
differences. No previous knowledge about the subject
is required.

--

Keywords: cache, read ahead, virtual memory, filesystem,
memory management, scheduling, memory hierarchy, performance.

----------------------------

regards,

Rik
--
The Internet is not a network of computers. It is a network
of people. That is its real strength.

