From owner-freebsd-hackers  Sat Feb 10 14:09:05 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.3/8.7.3) id OAA13671
          for hackers-outgoing; Sat, 10 Feb 1996 14:09:05 -0800 (PST)
Received: from labinfo.iet.unipi.it (labinfo.iet.unipi.it [131.114.9.5])
          by freefall.freebsd.org (8.7.3/8.7.3) with SMTP id OAA13665
          for <hackers@FreeBSD.ORG>; Sat, 10 Feb 1996 14:09:01 -0800 (PST)
Received: from localhost (luigi@localhost) by labinfo.iet.unipi.it (8.6.5/8.6.5) id XAA05138; Sat, 10 Feb 1996 23:10:59 +0100
From: Luigi Rizzo <luigi@labinfo.iet.unipi.it>
Message-Id: <199602102210.XAA05138@labinfo.iet.unipi.it>
Subject: Re: Compressed RAM/SWAP
To: terry@lambert.org (Terry Lambert)
Date: Sat, 10 Feb 1996 23:10:58 +0100 (MET)
Cc: hackers@FreeBSD.ORG
In-Reply-To: <199602102027.NAA16493@phaeton.artisoft.com> from "Terry Lambert" at Feb 10, 96 01:27:09 pm
X-Mailer: ELM [version 2.4 PL23]
Content-Type: text
Sender: owner-hackers@FreeBSD.ORG
Precedence: bulk

> The "RAM doubler" products are non-products.  For BSD, you might be
> able to compress swap, but this is not the same thing.
> 
> In general, it is a bad thing to compress swap, because swap contains
> only active, dirty pages (BSD is a memory overcommit architecture),
> and so it is likely that the swap will be referenced again.

> The two caveats on a VM capable system are:
> 
> 1)	It reduces the swap utilization in trade for CPU cycles;
> 	on a system where swap dynamically grows (Win95 or
> 	NeXTStep, etc.), this can be a (very very short term) win
> 	in a low-space scenario, where it's impractical or disallowed
> 	to grow the available swap.
> 
> 2)	It reduces the swap utilization in trade for CPU cycles:
> 	on a system with a fixed size swap area, this allows you to
> 	overtax the available swap of an overloaded machine to make
> 	it an even more overloaded machine.

As all tradeoffs, it might help in some cases. When you have your
CPU idle while writing/reading to disk, you might as well use your CPU
to compress pages and move them somewhere else, but still in RAM.
When your disk is very slow (or it is behind a network IF) this might
help as well.

I guess this is case #3 in your list.

> On the other hand, RAMDoubler sales have been huge.  It's probably
> sold more volume than "instant water" (a similar product), so who am
> I to rain on your parade.  8-).

I did not say I would have bought one, just wanted to investigate
if there is something good in the idea :)

	Luigi