diff options
author | Nikhil Rao <ncrao@google.com> | 2011-05-18 10:09:39 -0700 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2011-05-20 14:16:50 +0200 |
commit | 1399fa7807a1a5998bbf147e80668e9950661dfa (patch) | |
tree | dc4e1a97f50b8e7297c82f63e1ad2b15430b33d9 /kernel/sched.c | |
parent | f05998d4b80632f2cc00f108da503066ef5d38d5 (diff) | |
download | op-kernel-dev-1399fa7807a1a5998bbf147e80668e9950661dfa.zip op-kernel-dev-1399fa7807a1a5998bbf147e80668e9950661dfa.tar.gz |
sched: Introduce SCHED_POWER_SCALE to scale cpu_power calculations
SCHED_LOAD_SCALE is used to increase nice resolution and to
scale cpu_power calculations in the scheduler. This patch
introduces SCHED_POWER_SCALE and converts all uses of
SCHED_LOAD_SCALE for scaling cpu_power to use SCHED_POWER_SCALE
instead.
This is a preparatory patch for increasing the resolution of
SCHED_LOAD_SCALE, and there is no need to increase resolution
for cpu_power calculations.
Signed-off-by: Nikhil Rao <ncrao@google.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Stephan Barwolf <stephan.baerwolf@tu-ilmenau.de>
Cc: Mike Galbraith <efault@gmx.de>
Link: http://lkml.kernel.org/r/1305738580-9924-3-git-send-email-ncrao@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/sched.c')
-rw-r--r-- | kernel/sched.c | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/kernel/sched.c b/kernel/sched.c index d036048..375e9c6 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6530,7 +6530,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->cpu_power != SCHED_LOAD_SCALE) { + if (group->cpu_power != SCHED_POWER_SCALE) { printk(KERN_CONT " (cpu_power = %d)", group->cpu_power); } @@ -7905,7 +7905,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_power = SCHED_LOAD_SCALE; + rq->cpu_power = SCHED_POWER_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; |