All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@digeo.com>
To: Robert Love <rml@tech9.net>
Cc: Con Kolivas <conman@kolivas.net>,
	linux kernel mailing list <linux-kernel@vger.kernel.org>
Subject: Re: [BENCHMARK] scheduler tunables with contest - prio_bonus_ratio
Date: Thu, 19 Dec 2002 15:18:49 -0800	[thread overview]
Message-ID: <3E0253D9.94961FB@digeo.com> (raw)
In-Reply-To: 1040337982.2519.45.camel@phantasy

Robert Love wrote:
> 
> ...
> Not too sure what to make of it.  It shows the interactivity estimator
> does indeed help... but only if what you consider "important" is what is
> considered "interactive" by the estimator.  Andrew will say that is too
> often not the case.
> 

That is too often not the case.

I can get the desktop machine working about as comfortably
as 2.4.19 with:

# echo 10 > max_timeslice 
# echo 0 > prio_bonus_ratio 

ie: disabling all the fancy new scheduler features :(

Dropping max_timeslice fixes the enormous stalls which happen
when an interactive process gets incorrectly identified as a
cpu hog.  (OK, that's expected)

But when switching virtual desktops some windows still take a
large fraction of a second to redraw themselves.  Disabling the
interactivity estimator fixes that up too.  (Not OK.  That's bad)

hm.  It's actually quite nice.  I'd be prepared to throw away
a few cycles for this.

I don't expect the interactivity/cpuhog estimator will ever work
properly on the desktop, frankly.  There will always be failure
cases when a sudden swing in load causes it to make the wrong
decision.

So it appears that to stem my stream of complaints we need to
merge scheduler_tunables.patch and edit my /etc/rc.local.

  reply	other threads:[~2002-12-19 23:11 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2002-12-19 21:50 [BENCHMARK] scheduler tunables with contest - prio_bonus_ratio Con Kolivas
2002-12-19 22:46 ` Robert Love
2002-12-19 23:18   ` Andrew Morton [this message]
2002-12-19 23:41     ` Robert Love
2002-12-20  0:02       ` Andrew Morton
2002-12-20  0:15         ` Robert Love
2002-12-20  0:22           ` Con Kolivas
2002-12-20  0:29             ` Robert Love
2002-12-20  0:27       ` Andrew Morton
2002-12-20  2:42         ` Robert Love
2002-12-20  2:48           ` Andrew Morton
2002-12-24 22:26       ` scott thomason
2002-12-25  7:29         ` Con Kolivas
2002-12-25 16:17           ` scott thomason
2002-12-26 15:01             ` scott thomason
2003-01-01  0:31       ` Impact of scheduler tunables on interactive response (was Re: [BENCHMARK] scheduler tunables with contest - prio_bonus_ratio) scott thomason
2003-01-01 16:05         ` Bill Davidsen
2003-01-01 17:15           ` scott thomason
2002-12-19 23:42     ` [BENCHMARK] scheduler tunables with contest - prio_bonus_ratio Con Kolivas
2002-12-19 23:53       ` Robert Love
2002-12-20  0:04         ` Con Kolivas
2002-12-20  0:16           ` Robert Love
2002-12-20 11:17         ` Marc-Christian Petersen
2002-12-20 17:54           ` Robert Love

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=3E0253D9.94961FB@digeo.com \
    --to=akpm@digeo.com \
    --cc=conman@kolivas.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rml@tech9.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.