lkml.org 
[lkml]   [2011]   [Jan]   [26]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
Date
From
Subject[tip:sched/core] sched: Use rq->clock_task instead of rq->clock for correctly maintaining load averages
Commit-ID:  05ca62c6ca17f39b88fa956d5ebc1fa6e93ad5e3
Gitweb: http://git.kernel.org/tip/05ca62c6ca17f39b88fa956d5ebc1fa6e93ad5e3
Author: Paul Turner <pjt@google.com>
AuthorDate: Fri, 21 Jan 2011 20:45:02 -0800
Committer: Ingo Molnar <mingo@elte.hu>
CommitDate: Wed, 26 Jan 2011 12:31:03 +0100

sched: Use rq->clock_task instead of rq->clock for correctly maintaining load averages

The delta in clock_task is a more fair attribution of how much time a tg has
been contributing load to the current cpu.

While not really important it also means we're more in sync (by magnitude)
with respect to periodic updates (since __update_curr deltas are clock_task
based).

Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20110122044852.007092349@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
kernel/sched_fair.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 1997383..0c26e2d 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -725,7 +725,7 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
if (cfs_rq->tg == &root_task_group)
return;

- now = rq_of(cfs_rq)->clock;
+ now = rq_of(cfs_rq)->clock_task;
delta = now - cfs_rq->load_stamp;

/* truncate load history at 4 idle periods */

\
 
 \ /
  Last update: 2011-01-26 13:13    [from the cache]
©2003-2011 Jasper Spaans