diff mbox

[08/16] cpufreq: governors: Calculate iowait time only when necessary

Message ID caeb0f608292de57598d000b92023e265ce0146b.1368696171.git.viresh.kumar@linaro.org
State Accepted
Headers show

Commit Message

Viresh Kumar May 16, 2013, 9:28 a.m. UTC 
From: Stratos Karafotis <stratosk@semaphore.gr>

Currently we always calculate the CPU iowait time and add it to idle time.
If we are in ondemand and we use io_is_busy, we re-calculate iowait time
and we subtract it from idle time.

With this patch iowait time is calculated only when necessary avoiding
the double call to get_cpu_iowait_time_us. We use a parameter in
function get_cpu_idle_time to distinguish when the iowait time will be
added to idle time or not, without the need of keeping the prev_io_wait.

Signed-off-by: Stratos Karafotis <stratosk@semaphore.gr>
Acked-by: Viresh Kumar <viresh.kumar@linaro.,org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq_conservative.c |  2 +-
 drivers/cpufreq/cpufreq_governor.c     | 48 +++++++++++++---------------------
 drivers/cpufreq/cpufreq_governor.h     |  3 +--
 drivers/cpufreq/cpufreq_ondemand.c     | 11 +++++++-
 4 files changed, 30 insertions(+), 34 deletions(-)
diff mbox

Patch

diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index 98b4946..2465e63 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -238,7 +238,7 @@  static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 		struct cs_cpu_dbs_info_s *dbs_info;
 		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
 		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-						&dbs_info->cdbs.prev_cpu_wall);
+					&dbs_info->cdbs.prev_cpu_wall, 0);
 		if (cs_tuners->ignore_nice)
 			dbs_info->cdbs.prev_cpu_nice =
 				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index 38f959b..13ca17a 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -67,13 +67,13 @@  static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 	return cputime_to_usecs(idle_time);
 }
 
-u64 get_cpu_idle_time(unsigned int cpu, u64 *wall)
+u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 {
-	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+	u64 idle_time = get_cpu_idle_time_us(cpu, io_busy ? wall : NULL);
 
 	if (idle_time == -1ULL)
 		return get_cpu_idle_time_jiffy(cpu, wall);
-	else
+	else if (!io_busy)
 		idle_time += get_cpu_iowait_time_us(cpu, wall);
 
 	return idle_time;
@@ -100,13 +100,22 @@  void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 	/* Get Absolute Load (in terms of freq for ondemand gov) */
 	for_each_cpu(j, policy->cpus) {
 		struct cpu_dbs_common_info *j_cdbs;
-		u64 cur_wall_time, cur_idle_time, cur_iowait_time;
-		unsigned int idle_time, wall_time, iowait_time;
+		u64 cur_wall_time, cur_idle_time;
+		unsigned int idle_time, wall_time;
 		unsigned int load;
+		int io_busy = 0;
 
 		j_cdbs = dbs_data->cdata->get_cpu_cdbs(j);
 
-		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
+		/*
+		 * For the purpose of ondemand, waiting for disk IO is
+		 * an indication that you're performance critical, and
+		 * not that the system is actually idle. So do not add
+		 * the iowait time to the cpu idle time.
+		 */
+		if (dbs_data->cdata->governor == GOV_ONDEMAND)
+			io_busy = od_tuners->io_is_busy;
+		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time, io_busy);
 
 		wall_time = (unsigned int)
 			(cur_wall_time - j_cdbs->prev_cpu_wall);
@@ -134,29 +143,6 @@  void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 			idle_time += jiffies_to_usecs(cur_nice_jiffies);
 		}
 
-		if (dbs_data->cdata->governor == GOV_ONDEMAND) {
-			struct od_cpu_dbs_info_s *od_j_dbs_info =
-				dbs_data->cdata->get_cpu_dbs_info_s(cpu);
-
-			cur_iowait_time = get_cpu_iowait_time_us(j,
-					&cur_wall_time);
-			if (cur_iowait_time == -1ULL)
-				cur_iowait_time = 0;
-
-			iowait_time = (unsigned int) (cur_iowait_time -
-					od_j_dbs_info->prev_cpu_iowait);
-			od_j_dbs_info->prev_cpu_iowait = cur_iowait_time;
-
-			/*
-			 * For the purpose of ondemand, waiting for disk IO is
-			 * an indication that you're performance critical, and
-			 * not that the system is actually idle. So subtract the
-			 * iowait time from the cpu idle time.
-			 */
-			if (od_tuners->io_is_busy && idle_time >= iowait_time)
-				idle_time -= iowait_time;
-		}
-
 		if (unlikely(!wall_time || wall_time < idle_time))
 			continue;
 
@@ -236,6 +222,7 @@  int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	struct cs_dbs_tuners *cs_tuners = NULL;
 	struct cpu_dbs_common_info *cpu_cdbs;
 	unsigned int sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
+	int io_busy = 0;
 	int rc;
 
 	if (have_governor_per_policy())
@@ -338,6 +325,7 @@  int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		sampling_rate = od_tuners->sampling_rate;
 		ignore_nice = od_tuners->ignore_nice;
 		od_ops = dbs_data->cdata->gov_ops;
+		io_busy = od_tuners->io_is_busy;
 	}
 
 	switch (event) {
@@ -354,7 +342,7 @@  int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			j_cdbs->cpu = j;
 			j_cdbs->cur_policy = policy;
 			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
-					&j_cdbs->prev_cpu_wall);
+					       &j_cdbs->prev_cpu_wall, io_busy);
 			if (ignore_nice)
 				j_cdbs->prev_cpu_nice =
 					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
index 8998d3d..eae3163 100644
--- a/drivers/cpufreq/cpufreq_governor.h
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -148,7 +148,6 @@  struct cpu_dbs_common_info {
 
 struct od_cpu_dbs_info_s {
 	struct cpu_dbs_common_info cdbs;
-	u64 prev_cpu_iowait;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int freq_lo;
 	unsigned int freq_lo_jiffies;
@@ -257,7 +256,7 @@  static ssize_t show_sampling_rate_min_gov_pol				\
 	return sprintf(buf, "%u\n", dbs_data->min_sampling_rate);	\
 }
 
-u64 get_cpu_idle_time(unsigned int cpu, u64 *wall);
+u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
 void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
 bool need_load_eval(struct cpu_dbs_common_info *cdbs,
 		unsigned int sampling_rate);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 15e80ee..8500147 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -339,11 +339,20 @@  static ssize_t store_io_is_busy(struct dbs_data *dbs_data, const char *buf,
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 	unsigned int input;
 	int ret;
+	unsigned int j;
 
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
 	od_tuners->io_is_busy = !!input;
+
+	/* we need to re-evaluate prev_cpu_idle */
+	for_each_online_cpu(j) {
+		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
+									j);
+		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
+			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
+	}
 	return count;
 }
 
@@ -414,7 +423,7 @@  static ssize_t store_ignore_nice(struct dbs_data *dbs_data, const char *buf,
 		struct od_cpu_dbs_info_s *dbs_info;
 		dbs_info = &per_cpu(od_cpu_dbs_info, j);
 		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
-						&dbs_info->cdbs.prev_cpu_wall);
+			&dbs_info->cdbs.prev_cpu_wall, od_tuners->io_is_busy);
 		if (od_tuners->ignore_nice)
 			dbs_info->cdbs.prev_cpu_nice =
 				kcpustat_cpu(j).cpustat[CPUTIME_NICE];