From: venkatesh.pallipadi@intel.com
To: cpufreq@www.linux.org.uk
Cc: davej@redhat.com
Subject: [patch 6/6] cpufreq: Add idle microaccounting in ondemand governor
Date: Thu, 17 Jul 2008 13:56:00 -0700 [thread overview]
Message-ID: <20080717205616.663052000@intel.com> (raw)
In-Reply-To: 20080717205554.214645000@intel.com
[-- Attachment #1: intro_idle_microaccounting.patch --]
[-- Type: text/plain, Size: 3542 bytes --]
Use get_cpu_idle_time_us() to get micro-accounted idle information.
This enables ondemand to get more accurate idle and busy timings
than the jiffy based calculation. As a result, we can decrease
the ondemand safety gaurd band from 80-10 to 95-3.
Results in more aggressive power savings.
Signed-off-by: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
---
drivers/cpufreq/cpufreq_ondemand.c | 46 ++++++++++++++++++++++++++++++++++++-
1 file changed, 45 insertions(+), 1 deletion(-)
Index: linux-2.6/drivers/cpufreq/cpufreq_ondemand.c
===================================================================
--- linux-2.6.orig/drivers/cpufreq/cpufreq_ondemand.c 2008-07-17 13:19:08.000000000 -0700
+++ linux-2.6/drivers/cpufreq/cpufreq_ondemand.c 2008-07-17 13:27:33.000000000 -0700
@@ -18,6 +18,9 @@
#include <linux/jiffies.h>
#include <linux/kernel_stat.h>
#include <linux/mutex.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/ktime.h>
/*
* dbs is used in this file as a shortform for demandbased switching
@@ -26,6 +29,8 @@
#define DEF_FREQUENCY_DOWN_DIFFERENTIAL (10)
#define DEF_FREQUENCY_UP_THRESHOLD (80)
+#define MICRO_FREQUENCY_DOWN_DIFFERENTIAL (3)
+#define MICRO_FREQUENCY_UP_THRESHOLD (95)
#define MIN_FREQUENCY_UP_THRESHOLD (11)
#define MAX_FREQUENCY_UP_THRESHOLD (100)
@@ -58,6 +63,7 @@ enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE}
struct cpu_dbs_info_s {
cputime64_t prev_cpu_idle;
cputime64_t prev_cpu_wall;
+ cputime64_t prev_cpu_nice;
struct cpufreq_policy *cur_policy;
struct delayed_work work;
struct cpufreq_frequency_table *freq_table;
@@ -97,7 +103,8 @@ static struct dbs_tuners {
.powersave_bias = 0,
};
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
+static inline cputime64_t get_cpu_idle_time_jiffy(unsigned int cpu,
+ cputime64_t *wall)
{
cputime64_t idle_time;
cputime64_t cur_wall_time;
@@ -123,6 +130,33 @@ static inline cputime64_t get_cpu_idle_t
return idle_time;
}
+static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
+{
+ u64 idle_time = get_cpu_idle_time_us(cpu, wall);
+
+ if (idle_time == -1ULL)
+ return get_cpu_idle_time_jiffy(cpu, wall);
+
+ if (dbs_tuners_ins.ignore_nice) {
+ cputime64_t cur_nice;
+ unsigned long cur_nice_jiffies;
+ struct cpu_dbs_info_s *dbs_info;
+
+ dbs_info = &per_cpu(cpu_dbs_info, cpu);
+ cur_nice = cputime64_sub(kstat_cpu(cpu).cpustat.nice,
+ dbs_info->prev_cpu_nice);
+ /*
+ * Assumption: nice time between sampling periods will be
+ * less than 2^32 jiffies for 32 bit sys
+ */
+ cur_nice_jiffies = (unsigned long)
+ cputime64_to_jiffies64(cur_nice);
+ dbs_info->prev_cpu_nice = kstat_cpu(cpu).cpustat.nice;
+ return idle_time + jiffies_to_usecs(cur_nice_jiffies);
+ }
+ return idle_time;
+}
+
/*
* Find right freq to be set now with powersave_bias on.
* Returns the freq_hi to be used right now and will set freq_hi_jiffies,
@@ -602,6 +636,16 @@ EXPORT_SYMBOL(cpufreq_gov_ondemand);
static int __init cpufreq_gov_dbs_init(void)
{
+ cputime64_t wall;
+ u64 idle_time = get_cpu_idle_time_us(smp_processor_id(), &wall);
+
+ if (idle_time != -1ULL) {
+ /* Idle micro accounting is supported. Use finer thresholds */
+ dbs_tuners_ins.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
+ dbs_tuners_ins.down_differential =
+ MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
+ }
+
kondemand_wq = create_workqueue("kondemand");
if (!kondemand_wq) {
printk(KERN_ERR "Creation of kondemand failed\n");
--
next prev parent reply other threads:[~2008-07-17 20:56 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-17 20:55 [patch 0/6] cpufreq: Use idle micro-accounting information in ondemand governor venkatesh.pallipadi
2008-07-17 20:55 ` [patch 1/6] cpufreq: Add cpu number parameter to __cpufreq_driver_getavg() venkatesh.pallipadi
2008-07-17 20:55 ` [patch 2/6] cpufreq: Change load calculation in ondemand for software coordination venkatesh.pallipadi
2008-07-17 20:55 ` [patch 3/6] cpufreq: get_cpu_idle_time() changes in ondemand to suit idle-microaccounting venkatesh.pallipadi
2008-07-17 20:55 ` [patch 4/6] cpufreq_ondemand: Parameterize down differential venkatesh.pallipadi
2008-07-17 20:55 ` [patch 5/6] cpufreq: Changes to get_cpu_idle_time_us(), to be used in ondemand governor venkatesh.pallipadi
2008-07-17 20:56 ` venkatesh.pallipadi [this message]
2008-07-30 16:56 ` [patch 0/6] cpufreq: Use idle micro-accounting information " Dave Jones
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=20080717205616.663052000@intel.com \
--to=venkatesh.pallipadi@intel.com \
--cc=cpufreq@www.linux.org.uk \
--cc=davej@redhat.com \
/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 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).