Subject: Re: compressed virtual memory - interested?
To: None <tech-kern@NetBSD.ORG>
From: VaX#n8 <firstname.lastname@example.org>
Date: 05/31/1995 16:36:30
While really really bored, Ignatios Souvatzis wrote:
> You're sure you want to trade yet more cpu cycles against swap space?
> Then again, you would save on the paging i/o operations. Hm... I guess
> there are other things to do in NetBSD, but if you insist (and get
> credits for it at your university), it might be worth a try. At least
> for fast CPU's like i486 or Pentium or 68040/60 above 50 MHz.
Since there are ~ three orders of magnitude difference in memory versus
swap access, it's okay as long as you have a fast algorithm. But this is
all academic - if the tradeoff of CPU cycles versus disk accesses were not
beneficial, NetBSD wouldn't do disk caching.
Anyway, I assume it's a pretty good performance win but I don't have numbers
to back my assumptions. It's also quite good for laptops where disk access can
require spinup latency. Whatever the case, I was asking if there's interest,
given the assumption that it's going to be a performance win. If it isn't,
I don't expect anyone to be interested.
I just subscribed to tech-kern - although now I'll get -more- mail to read :(
VaX#n8 (vak-sa-nate) - n, CS senior++ and Unix junkie - email@example.com
Deal with evil through strength, yet encourage good through trust. - PGP me