Scalable Scheduling again

Path: archiver1.google.com!news1.google.com!sn-xit-02!supernews.com!newsfeed.direct.ca!look.ca!newshub2.rdc1.sfba.home.com!news.home.com!newshub1-work.rdc1.sfba.home.com!gehenna.pell.portland.or.us!nntp-server.caltech.edu!nntp-server.caltech.edu!mail2news96
Newsgroups: mlist.linux.kernel
Date: 	Wed, 14 Nov 2001 16:06:30 -0800
From: Mike Kravetz <krav...@us.ibm.com>
X-To: Linus Torvalds <torva...@transmeta.com>, linux-ker...@vger.kernel.org
X-Cc: Alan Cox <a...@lxorguk.ukuu.org.uk>
Subject: [RFC][PATCH]Scalable Scheduling again
Message-ID: <linux.kernel.20011114160630.D1112@w-mikek2.des.beaverton.ibm.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Approved: n...@nntp-server.caltech.edu
Lines: 1799

Since everyone else is throwing out scheduler patches, here is
another copy of our Multi-Queue scheduler for 2.4.14.  This version
has the code cleaned up to eliminate most (if not all) of the
offending #ifdefs.

One important aspect of this work is that it attempts to preserve
the behavior of the current Linux scheduler.  In other words, it
tries very hard (and goes to great pains) to make the same global
scheduling decisions as the current scheduler.  This is unlike a
traditional Multi-Queue scheduler which makes local decisions and
employs a global load balancing scheme. 

If nothing else, I would like to kick off a discussion of what
direction should be taken with respect to Scalable Scheduling.
Alan has already expressed some concerns with the scheduler, and
these seem to be addressed by Ingo's latest patch.  The patch
below does a good of handling an increasing number of CPUs and
tasks.  However, I'm sure it doesn't address everyones issues or
concerns.  I would especially appreciate any comments from Linus
on future direction in the area of the scheduler.

Some benchmark results for this patch are available at,
http://lse.sourceforge.net/scheduling/2.4.14.results
A 'wordy' description of the patch is located at,
http://lse.sourceforge.net/scheduling/mq1.html

-- 
Mike


Patch

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/