From: yodaiken@fsmlabs.com
To: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@osdl.org>, Larry McVoy <lm@bitmover.com>,
Andrea Arcangeli <andrea@suse.de>,
andrea@kernel.org,
Kernel Mailing List <linux-kernel@vger.kernel.org>,
Matthew Wilcox <willy@debian.org>,
Marcelo Tosatti <marcelo.tosatti@cyclades.com.br>
Subject: Re: log-buf-len dynamic
Date: Wed, 24 Sep 2003 15:11:05 -0600 [thread overview]
Message-ID: <20030924211105.GA18149@hq.fsmlabs.com> (raw)
In-Reply-To: <Pine.LNX.4.44.0309240007040.17335-100000@chimarrao.boston.redhat.com>
If people would just wake up to the lossy memory compression algorithms that
Steve Tweedie invented, the whole problem could be solved in a moment.
On Wed, Sep 24, 2003 at 12:12:51AM -0400, Rik van Riel wrote:
> On Tue, 23 Sep 2003, Linus Torvalds wrote:
>
> > Yeah, SunOS was nice. But I really think it's the access patterns that
> > changed.
>
> Absolutely. Garbage collection and object orientation have
> obsoleted LRU and related algorithms.
>
> Huge memory sizes also have done their share to obsolete
> recency based replacement algorithms.
>
> I suspect we'll want something closer to a frequency based
> replacement scheme in the future. Possibly something like
> LIRS or ARC, but adapted to work in a general purpose OS in
> a very light weight way.
>
> The argument that because we have more memory replacement
> is no longer as important doesn't quite hold because the
> cost of page replacement, measured in cpu cycles, has gone
> completely through the roof in the last decades.
>
> Then there's the whole different bag of cookies that is the
> caching of filesystem metadata, like our inode and dentry
> caches. I'm not sure what would be a good replacement
> strategy for those, but I do know that we'll want a good
> algorithm here because hard disks (and the number of files
> on them) are growing so much faster than anything else in
> our computers...
>
> --
> "Debugging is twice as hard as writing the code in the first place.
> Therefore, if you write the code as cleverly as possible, you are,
> by definition, not smart enough to debug it." - Brian W. Kernighan
>
> -
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at http://www.tux.org/lkml/
--
---------------------------------------------------------
Victor Yodaiken
Finite State Machine Labs: The RTLinux Company.
www.fsmlabs.com www.rtlinux.com
1+ 505 838 9109
next prev parent reply other threads:[~2003-09-24 21:19 UTC|newest]
Thread overview: 97+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20030923142706.54b2428a.davem@redhat.com>
2003-09-23 21:53 ` log-buf-len dynamic Linus Torvalds
2003-09-23 22:15 ` Andrea Arcangeli
2003-09-23 22:54 ` Linus Torvalds
2003-09-24 0:36 ` Andrea Arcangeli
2003-09-24 1:19 ` Larry McVoy
2003-09-24 2:04 ` andrea
2003-09-24 2:29 ` Larry McVoy
2003-09-24 2:39 ` Andrea Arcangeli
2003-09-24 3:16 ` Larry McVoy
2003-09-24 3:31 ` Rik van Riel
2003-09-24 3:45 ` Larry McVoy
2003-09-24 3:54 ` Linus Torvalds
2003-09-24 4:12 ` Rik van Riel
2003-09-24 21:11 ` yodaiken [this message]
2003-09-24 13:09 ` Alan Cox
2003-09-24 18:56 ` Jörn Engel
2003-09-24 3:46 ` Andrea Arcangeli
2003-09-24 4:02 ` Larry McVoy
2003-09-24 4:06 ` Rik van Riel
2003-09-24 2:36 ` Linus Torvalds
2003-09-24 2:48 ` Andrea Arcangeli
2003-09-24 3:06 ` Linus Torvalds
2003-09-24 3:28 ` Andrea Arcangeli
2003-09-24 3:38 ` Linus Torvalds
2003-09-24 3:56 ` Andrea Arcangeli
2003-09-24 4:26 ` viro
2003-09-24 3:42 ` Rik van Riel
2003-09-24 3:11 ` David S. Miller
2003-09-24 14:43 ` Roman Zippel
2003-09-25 4:08 ` Miles Bader
2003-09-25 4:20 ` Nick Piggin
2003-09-25 17:15 ` Eric W. Biederman
2003-09-25 17:30 ` Linus Torvalds
2003-09-25 17:57 ` Jeff Garzik
2003-09-25 18:22 ` Jörn Engel
2003-09-25 18:33 ` Randy.Dunlap
2003-09-25 18:36 ` Larry McVoy
2003-09-25 19:02 ` Jörn Engel
2003-09-25 19:41 ` OT go to gnu-arch-users for these matters (Re: log-buf-len dynamic) Andrea Arcangeli
2003-09-25 18:28 ` log-buf-len dynamic Charles Cazabon
2003-09-25 18:29 ` Larry McVoy
2003-09-25 20:15 ` David Lang
2003-09-25 20:27 ` Larry McVoy
2003-09-29 8:56 ` Rob Landley
2003-09-29 11:24 ` John Bradford
2003-09-29 12:30 ` Rob Landley
2003-09-29 15:22 ` John Bradford
2003-09-29 13:20 ` Rik van Riel
2003-09-29 13:23 ` Valdis.Kletnieks
2003-09-29 15:03 ` Larry McVoy
2003-09-29 18:21 ` Hua Zhong
2003-09-29 15:07 ` Larry McVoy
2003-09-25 19:23 ` Eric W. Biederman
2003-09-25 17:31 ` Christoph Hellwig
2003-09-25 19:28 ` Erik Andersen
2003-09-25 17:36 ` Dave Jones
2003-09-25 18:34 ` Larry McVoy
2003-09-25 18:35 ` Eric W. Biederman
2003-09-25 18:49 ` Larry McVoy
2003-09-25 20:02 ` Eric W. Biederman
2003-09-25 23:36 ` Pau Aliagas
2003-09-26 2:25 ` Miles Bader
2003-09-26 4:38 ` Davide Libenzi
2003-09-26 17:09 ` John Goerzen
2003-09-24 7:56 ` Pau Aliagas
2003-09-26 13:24 Samium Gromoff
2003-09-26 14:49 ` viro
-- strict thread matches above, loose matches on Subject: below --
2003-09-25 19:43 Mudama, Eric
2003-09-24 17:39 Ken Ryan
2003-09-22 19:48 Andrea Arcangeli
2003-09-23 1:51 ` Matthew Wilcox
2003-09-23 21:08 ` Andrea Arcangeli
2003-09-23 4:28 ` Willy Tarreau
2003-09-23 12:49 ` Andrea Arcangeli
2003-09-23 14:06 ` Willy Tarreau
2003-09-23 14:44 ` Andrea Arcangeli
2003-09-23 15:01 ` Jan Evert van Grootheest
2003-09-23 15:41 ` Andrea Arcangeli
2003-09-23 16:09 ` Willy Tarreau
2003-09-23 16:26 ` Andrea Arcangeli
2003-09-23 16:56 ` Ruth Ivimey-Cook
2003-09-23 17:40 ` Tom Zanussi
2003-09-23 17:53 ` Andrea Arcangeli
2003-09-23 21:37 ` Andrew Morton
2003-09-23 22:22 ` Andrea Arcangeli
2003-09-24 0:15 ` Andrew Morton
2003-09-24 0:38 ` Andrea Arcangeli
2003-09-23 16:06 ` Willy Tarreau
2003-09-23 16:23 ` Andrea Arcangeli
2003-09-23 19:02 ` Willy Tarreau
2003-09-23 22:34 ` Andrea Arcangeli
2003-09-23 23:29 ` Willy Tarreau
2003-09-23 23:48 ` Andrea Arcangeli
2003-09-23 23:50 ` Willy Tarreau
2003-09-23 12:46 ` Daniel Jacobowitz
2003-09-25 13:40 ` marcelo
2003-09-26 20:26 ` Andrea Arcangeli
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20030924211105.GA18149@hq.fsmlabs.com \
--to=yodaiken@fsmlabs.com \
--cc=andrea@kernel.org \
--cc=andrea@suse.de \
--cc=linux-kernel@vger.kernel.org \
--cc=lm@bitmover.com \
--cc=marcelo.tosatti@cyclades.com.br \
--cc=riel@redhat.com \
--cc=torvalds@osdl.org \
--cc=willy@debian.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox