Jean-Christian,
On Thu, Mar 25, 2010 at 09:59:44PM +0100, Jean-Christian Goussard wrote:
> Le 25/03/2010 18:44, Dominik Brodowski a écrit :
> > Subject: [PATCH] cpufreq: use average load in conservative governor
> >
> > Instead of using the load of the last CPU in a package, use the
> > average of all CPUs in a package.
>
> Don't we want to check the max load rather than the average, for a user
> running a single threaded job wants the CPU to jump to max speed?
You're right -- that's what I implemented first (that's why there was a
max_load variable). Then I was mis-lead to believe averaging out (e.g. on
two 50%-jobs) would be a better idea. But that's the scheduler's task, not
the governor's.
Thanks,
Dominik
From: Dominik Brodowski <linux@xxxxxxxxxxxxxxxxxxxx>
Date: Fri, 26 Mar 2010 10:00:20 +0100
Subject: [PATCH] cpufreq: use max load in conservative governor
Instead of using the load of the last CPU in a package, use the
maximum load of all CPUs in a package.
Reported-by: Jean-Christian Goussard <jeanchristian.goussard@xxxxxx>
Signed-off-by: Dominik Brodowski <linux@xxxxxxxxxxxxxxxxxxxx>
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 599a40b..3a14787 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -444,6 +444,7 @@ static struct attribute_group dbs_attr_group_old = {
static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
{
unsigned int load = 0;
+ unsigned int max_load = 0;
unsigned int freq_target;
struct cpufreq_policy *policy;
@@ -501,6 +502,9 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
continue;
load = 100 * (wall_time - idle_time) / wall_time;
+
+ if (load > max_load)
+ max_load = load;
}
/*
@@ -511,7 +515,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
return;
/* Check for frequency increase */
- if (load > dbs_tuners_ins.up_threshold) {
+ if (max_load > dbs_tuners_ins.up_threshold) {
this_dbs_info->down_skip = 0;
/* if we are already at full speed then break out early */
@@ -538,7 +542,7 @@ static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
* can support the current CPU usage without triggering the up
* policy. To be safe, we focus 10 points under the threshold.
*/
- if (load < (dbs_tuners_ins.down_threshold - 10)) {
+ if (max_load < (dbs_tuners_ins.down_threshold - 10)) {
freq_target = (dbs_tuners_ins.freq_step * policy->max) / 100;
this_dbs_info->requested_freq -= freq_target;
--
To unsubscribe from this list: send the line "unsubscribe cpufreq" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
