public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Con Kolivas <kernel@kolivas.org>
To: linux kernel mailing list <linux-kernel@vger.kernel.org>
Subject: 2.4.20-ck7
Date: Mon, 26 May 2003 16:48:54 +1000	[thread overview]
Message-ID: <200305261649.02132.kernel@kolivas.org> (raw)

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Here's an update to my patchset

http://kernel.kolivas.org

Includes:
O(1) scheduler with batch scheduling
Preemptible
Low Latency
Read Latency2
Autoregulated VM
Variable Hz
Scheduler Tunables
Desktop Tuning
Supermount NG
XFS 1.2
ACPI
CPU Frequency Scaling
NForce2 update
Packet writing
GCC 3.3 fixes

Optional extras not included in full patch but available:
2.5 Interactivity update
Swap prefetching
Lowest Latency Disk Hack
AA VM addons
RMAP
Compressed Caching.

Changes:
Patch restructure to allow easy selection and applying of split out patches.
Major change is my VM hacks that are now the default. These use the default VM 
with changes based on the system and memory stress the kernel senses to 
create a VM that's cachier with free memory and aggressive at avoiding swap. 
It builds on the lean nature of the default VM without adding noticeable 
overhead. See my website for a lengthier description or the patch itself for 
documented code.
The desktop tuning is now 10/40 ms for min/max timeslice, and further tuning 
to avoid that nasty nasty i/o elevator pause problem. MCP and I are working 
hard on trying to find a useful fix since noone else is interested any more. 
See http://kernel.kolivas.org/elevator.html for more info.
Supermount has been revamped to the new supermount-ng code 
(http://supermount-ng.sf.net)
Nforce2 update and GCC3.3 fixes.
Optional:
I've implemented some simple (read braindead) but effective swap prefetching 
code which slowly trickles in pages from swap when the machine is idle and 
there is free ram.
For the most resistant cases of i/o induced pauses I have the nasty lowest 
latency disk hack I made which drops throughput significantly but will remove 
them entirely.
The AA VM addons are now optional instead of the default as I've moved to my 
VM addons, and will rip out my changes (as is the case with rmap).
Compressed caching adds to my VM addons instead of AA.

Feel free to send me queries, comments, suggestions, patches etc.

Regards,
Con Kolivas
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.1 (GNU/Linux)

iD8DBQE+0bjWF6dfvkL3i1gRAqeMAJ9MnPdAn1wg94vi+V5MHl49SfyTMgCfYAiN
FO4NBqHV68whBUxOmcUyils=
=9+SU
-----END PGP SIGNATURE-----


             reply	other threads:[~2003-05-26  6:34 UTC|newest]

Thread overview: 2+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-05-26  6:48 Con Kolivas [this message]
2003-05-26 19:03 ` 2.4.20-ck7 Josh McKinney

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=200305261649.02132.kernel@kolivas.org \
    --to=kernel@kolivas.org \
    --cc=linux-kernel@vger.kernel.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