LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
To: LKML <linux-kernel@vger.kernel.org>, Ingo Molnar <mingo@elte.hu>
Cc: Dmitry Adamushko <dmitry.adamushko@gmail.com>,
	Mike Galbraith <efault@gmx.de>,
	Dhaval Giani <dhaval@linux.vnet.ibm.com>,
	Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>
Subject: [RFC/PATCH 17/17] sched: fair: optimize the elegebility test
Date: Sun, 09 Mar 2008 18:09:07 +0100	[thread overview]
Message-ID: <20080309170929.883491000@chello.nl> (raw)
In-Reply-To: <20080309170850.256853000@chello.nl>

[-- Attachment #1: sched-fair-avg_runtime-opt.patch --]
[-- Type: text/plain, Size: 1361 bytes --]

Suggested by Dmitry Adamushko; trade a div for a mult.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 kernel/sched_fair.c |   13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

Index: linux-2.6-2/kernel/sched_fair.c
===================================================================
--- linux-2.6-2.orig/kernel/sched_fair.c
+++ linux-2.6-2/kernel/sched_fair.c
@@ -339,6 +339,12 @@ s64 avg_vruntime(struct cfs_root_rq *cfs
 }
 
 static inline
+int avg_vruntime_cmp(struct cfs_root_rq *cfs_r_rq, s64 vruntime)
+{
+	return (vruntime * cfs_r_rq->nr_queued) <= cfs_r_rq->avg_vruntime;
+}
+
+static inline
 s64 entity_deadline_key(struct cfs_root_rq *cfs_r_rq, struct sched_entity *se)
 {
 	return se->vruntime + se->vperiod - cfs_r_rq->min_vruntime;
@@ -430,11 +436,10 @@ static struct sched_entity *__pick_next_
  */
 static struct sched_entity *__pick_next_entity(struct cfs_root_rq *cfs_r_rq)
 {
-	struct sched_entity *next_deadline;
-	s64 avg = avg_vruntime(cfs_r_rq);
+	struct sched_entity *next_deadline = __pick_next_deadline(cfs_r_rq);
+	s64 vruntime = entity_timeline_key(cfs_r_rq, next_deadline);
 
-	next_deadline = __pick_next_deadline(cfs_r_rq);
-	if (entity_timeline_key(cfs_r_rq, next_deadline) <= avg)
+	if (avg_vruntime_cmp(cfs_r_rq, vruntime))
 		return next_deadline;
 
 	return __pick_next_timeline(cfs_r_rq);

--


      parent reply	other threads:[~2008-03-09 17:12 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-03-09 17:08 [RFC/PATCH 00/17] Current sched patch stack Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 01/17] sched: mix tasks and groups Peter Zijlstra
2008-04-01 12:12   ` Srivatsa Vaddagiri
2008-04-01 12:05     ` Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 02/17] sched: allow the CFS group scheduler to have multiple levels Peter Zijlstra
2008-03-12 14:47   ` Dhaval Giani
2008-03-09 17:08 ` [RFC/PATCH 03/17] sched: rt-group: full hierarchy support for the rt groups Peter Zijlstra
2008-03-12  8:25   ` Dhaval Giani
     [not found]     ` <661de9470803120129l66497656o948c13c6c0c26766@mail.gmail.com>
2008-03-12  9:29       ` Peter Zijlstra
2008-03-12 13:34         ` Balbir Singh
2008-03-12 13:39           ` Dhaval Giani
2008-03-12 14:08         ` Balbir Singh
2008-03-09 17:08 ` [RFC/PATCH 04/17] sched: fair-group: SMP-nice for group scheduling Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 05/17] sched: rt-group: optimize dequeue_rt_stack Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 06/17] sched: fair-group scheduling vs latency Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 07/17] sched: fair-group: de-couple load-balancing from the rb-trees Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 08/17] sched: fair-group: single RQ approach Peter Zijlstra
2008-03-09 17:08 ` [RFC/PATCH 09/17] sched: fair: remove moved_group() Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 10/17] sched: remove sysctl_sched_batch_wakeup_granularity Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 11/17] sched: fair: optimize sched_slice() Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 12/17] sched: fair: cfs_root_rq Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 13/17] sched: fair: calc_delta_weight() Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 14/17] sched: fair: avg_vruntime Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 15/17] sched: fair-group: EEVDF scheduling Peter Zijlstra
2008-03-09 17:09 ` [RFC/PATCH 16/17] sched: fair: bound tardiness Peter Zijlstra
2008-03-09 17:09 ` Peter Zijlstra [this message]

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=20080309170929.883491000@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=dhaval@linux.vnet.ibm.com \
    --cc=dmitry.adamushko@gmail.com \
    --cc=efault@gmx.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@elte.hu \
    --cc=vatsa@linux.vnet.ibm.com \
    --subject='Re: [RFC/PATCH 17/17] sched: fair: optimize the elegebility test' \
    /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

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).