Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 08f5e5b5 authored by Joonwoo Park's avatar Joonwoo Park
Browse files

sched: eliminate sched_account_wait_time knob 



Kill unused scheduler knob sched_account_wait_time. With this change
scheduler always accounts task's wait time into demand.

Change-Id: Ifa4bcb5685798f48fd020f3d0c9853220b3f5fdc
Signed-off-by: default avatarJoonwoo Park <joonwoop@codeaurora.org>
parent fa709963

Documentation/scheduler/sched-zone.txt

+17 −27
Original line number Diff line number Diff line
@@ -1113,16 +1113,7 @@ tracking mechanism maintains per task. If default values are used for 
both this and sched_ravg_window then a total of 50ms of task history

would be maintained in 5 10ms windows.



*** 7.11 sched_account_wait_time



Appears at: /proc/sys/kernel/sched_account_wait_time



Default value: 1



This controls whether a task's wait time is accounted as its demand for cpu

and thus the values found in its sum, sum_history[] and demand attributes.



*** 7.12 sched_freq_account_wait_time

*** 7.11 sched_freq_account_wait_time



Appears at: /proc/sys/kernel/sched_freq_account_wait_time
@@ -1132,7 +1123,7 @@ This controls whether a task's wait time is accounted in its curr_window and 
prev_window attributes and thus in a cpu's curr_runnable_sum and

prev_runnable_sum counters.



*** 7.13 sched_migration_fixup

*** 7.12 sched_migration_fixup



Appears at: /proc/sys/kernel/sched_migration_fixup
@@ -1141,7 +1132,7 @@ Default value: 1 
This controls whether a cpu's busy time counters are adjusted during task

migration.



*** 7.14 sched_freq_inc_notify

*** 7.13 sched_freq_inc_notify



Appears at: /proc/sys/kernel/sched_freq_inc_notify
@@ -1153,7 +1144,7 @@ exceeds sched_freq_inc_notify, where freq_required is the frequency calculated 
by scheduler to meet current task demand. Note that sched_freq_inc_notify is

specified in kHz units.



*** 7.15 sched_freq_dec_notify

*** 7.14 sched_freq_dec_notify



Appears at: /proc/sys/kernel/sched_freq_dec_notify
@@ -1166,7 +1157,7 @@ exceeds sched_freq_dec_notify, where freq_required is the frequency calculated 
by scheduler to meet current task demand. Note that sched_freq_dec_notify is

specified in kHz units.



** 7.16 sched_heavy_task

** 7.15 sched_heavy_task



Appears at: /proc/sys/kernel/sched_heavy_task
@@ -1178,7 +1169,7 @@ comparison. Scheduler will request a raise in cpu frequency when heavy tasks 
wakeup after at least one window of sleep, where window size is defined by

sched_ravg_window. Value 0 will disable this feature.



*** 7.17 sched_cpu_high_irqload

*** 7.16 sched_cpu_high_irqload



Appears at: /proc/sys/kernel/sched_cpu_high_irqload
@@ -1196,7 +1187,7 @@ longer eligible for placement. This will affect the task placement logic 
described above, causing the scheduler to try and steer tasks away from

the CPU.



** 7.18 cpu.upmigrate_discourage

** 7.17 cpu.upmigrate_discourage



Default value : 0
@@ -1212,7 +1203,7 @@ overcommitted scenario. See notes on sched_spill_nr_run and sched_spill_load for 
how overcommitment threshold is defined and also notes on

'sched_upmigrate_min_nice' tunable.



*** 7.19 sched_static_cpu_pwr_cost

*** 7.18 sched_static_cpu_pwr_cost



Default value: 0
@@ -1227,7 +1218,7 @@ within a cluster and possibly have differing value between clusters as 
needed.





*** 7.20 sched_static_cluster_pwr_cost

*** 7.19 sched_static_cluster_pwr_cost



Default value: 0
@@ -1238,7 +1229,7 @@ power mode. It ignores the actual D-state that a cluster may be in and assumes 
the worst case power cost of the highest D-state. It is means of biasing task

placement away from idle clusters when necessary.



***7.23 sched_early_detection_duration

*** 7.20 sched_early_detection_duration



Default value: 9500000
@@ -1249,7 +1240,7 @@ tick for it to be eligible for the scheduler's early detection feature 
under scheduler boost. For more information on the feature itself please

refer to section 5.2.1.



*** 7.24 sched_restrict_cluster_spill

*** 7.21 sched_restrict_cluster_spill



Default value: 0
@@ -1268,7 +1259,7 @@ CPU across all clusters. When this tunable is enabled, the RT tasks are 
restricted to the lowest possible power cluster.





*** 7.25 sched_downmigrate

*** 7.22 sched_downmigrate



Appears at: /proc/sys/kernel/sched_downmigrate
@@ -1281,7 +1272,7 @@ its demand *in reference to the power-efficient cpu* drops less than 60% 
(sched_downmigrate).





*** 7.26 sched_small_wakee_task_load

*** 7.23 sched_small_wakee_task_load



Appears at: /proc/sys/kernel/sched_small_wakee_task_load
@@ -1293,7 +1284,7 @@ categorized as small wakee tasks. Scheduler places small wakee tasks on the 
waker's cluster.





*** 7.27 sched_big_waker_task_load

*** 7.24 sched_big_waker_task_load



Appears at: /proc/sys/kernel/sched_big_waker_task_load
@@ -1303,7 +1294,7 @@ This tunable is a percentage. Configure the minimum demand of big sync waker 
task.  Scheduler places small wakee tasks woken up by big sync waker on the

waker's cluster.



*** 7.28 sched_prefer_sync_wakee_to_waker

*** 7.25 sched_prefer_sync_wakee_to_waker



Appears at: /proc/sys/kernel/sched_prefer_sync_wakee_to_waker
@@ -1467,10 +1458,9 @@ cpus are being reset. Changes to below attributes result in such a reset: 


* sched_ravg_window (See Sec 2)

* sched_window_stats_policy (See Sec 2.4)

* sched_account_wait_time (See Sec 7.15)

* sched_ravg_hist_size (See Sec 7.11)

* sched_migration_fixup (See Sec 7.17)

* sched_freq_account_wait_time (See Sec 7.16)

* sched_migration_fixup (See Sec 7.12)

* sched_freq_account_wait_time (See Sec 7.11)



<task>-0     [004] d.h4 12700.711489: sched_reset_all_windows_stats: time_taken 1123 window_start 0 window_size 0 reason POLICY_CHANGE old_val 0 new_val 1

include/linux/sched/sysctl.h

+1 −1
Original line number Diff line number Diff line
@@ -42,7 +42,6 @@ extern unsigned int sysctl_sched_child_runs_first; 
extern unsigned int sysctl_sched_wake_to_idle;

extern unsigned int sysctl_sched_wakeup_load_threshold;

extern unsigned int sysctl_sched_window_stats_policy;

extern unsigned int sysctl_sched_account_wait_time;

extern unsigned int sysctl_sched_ravg_hist_size;

extern unsigned int sysctl_sched_cpu_high_irqload;

extern unsigned int sysctl_sched_freq_account_wait_time;
@@ -75,6 +74,7 @@ extern unsigned int sysctl_sched_prefer_sync_wakee_to_waker; 
extern unsigned int sysctl_sched_min_runtime;

extern unsigned int sysctl_sched_small_task_pct;

extern unsigned int sysctl_sched_restrict_tasks_spread;

extern unsigned int sysctl_sched_account_wait_time;

#else

extern unsigned int sysctl_sched_select_prev_cpu_us;

extern unsigned int sysctl_sched_enable_colocation;

kernel/sched/core.c

+3 −11
Original line number Diff line number Diff line
@@ -1684,7 +1684,7 @@ struct cpu_cycle { 
#if defined(CONFIG_SCHED_HMP)



/*

 * sched_window_stats_policy, sched_account_wait_time, sched_ravg_hist_size,

 * sched_window_stats_policy, sched_ravg_hist_size,

 * sched_migration_fixup, sched_freq_account_wait_time have a 'sysctl' copy

 * associated with them. This is required for atomic update of those variables

 * when being modifed via sysctl interface.
@@ -1707,8 +1707,7 @@ static __read_mostly unsigned int sched_window_stats_policy = 
__read_mostly unsigned int sysctl_sched_window_stats_policy =

	WINDOW_STATS_MAX_RECENT_AVG;



static __read_mostly unsigned int sched_account_wait_time = 1;

__read_mostly unsigned int sysctl_sched_account_wait_time = 1;

#define SCHED_ACCOUNT_WAIT_TIME 1



__read_mostly unsigned int sysctl_sched_cpu_high_irqload = (10 * NSEC_PER_MSEC);
@@ -2811,7 +2810,7 @@ static int account_busy_for_task_demand(struct task_struct *p, int event) 
	 * time. Likewise, if wait time is not treated as busy time, then

	 * when a task begins to run or is migrated, it is not running and

	 * is completing a segment of non-busy time. */

	if (event == TASK_WAKE || (!sched_account_wait_time &&

	if (event == TASK_WAKE || (!SCHED_ACCOUNT_WAIT_TIME &&

			 (event == PICK_NEXT_TASK || event == TASK_MIGRATE)))

		return 0;
@@ -3203,7 +3202,6 @@ static void enable_window_stats(void) 
enum reset_reason_code {

	WINDOW_CHANGE,

	POLICY_CHANGE,

	ACCOUNT_WAIT_TIME_CHANGE,

	HIST_SIZE_CHANGE,

	MIGRATION_FIXUP_CHANGE,

	FREQ_ACCOUNT_WAIT_TIME_CHANGE,
@@ -3213,7 +3211,6 @@ enum reset_reason_code { 
const char *sched_window_reset_reasons[] = {

	"WINDOW_CHANGE",

	"POLICY_CHANGE",

	"ACCOUNT_WAIT_TIME_CHANGE",

	"HIST_SIZE_CHANGE",

	"MIGRATION_FIXUP_CHANGE",

	"FREQ_ACCOUNT_WAIT_TIME_CHANGE"};
@@ -3278,11 +3275,6 @@ void reset_all_window_stats(u64 window_start, unsigned int window_size) 
		old = sched_window_stats_policy;

		new = sysctl_sched_window_stats_policy;

		sched_window_stats_policy = sysctl_sched_window_stats_policy;

	} else if (sched_account_wait_time != sysctl_sched_account_wait_time) {

		reason = ACCOUNT_WAIT_TIME_CHANGE;

		old = sched_account_wait_time;

		new = sysctl_sched_account_wait_time;

		sched_account_wait_time = sysctl_sched_account_wait_time;

	} else if (sched_ravg_hist_size != sysctl_sched_ravg_hist_size) {

		reason = HIST_SIZE_CHANGE;

		old = sched_ravg_hist_size;

kernel/sched/fair.c

+1 −5
Original line number Diff line number Diff line
@@ -3843,16 +3843,12 @@ static inline int invalid_value(unsigned int *data) 
	if (data == &sysctl_sched_window_stats_policy)

		return val >= WINDOW_STATS_INVALID_POLICY;



	if (data == &sysctl_sched_account_wait_time)

		return !(val == 0 || val == 1);



	return invalid_value_freq_input(data);

}



/*

 * Handle "atomic" update of sysctl_sched_window_stats_policy,

 * sysctl_sched_ravg_hist_size, sysctl_sched_account_wait_time and

 * sched_freq_legacy_mode variables.

 * sysctl_sched_ravg_hist_size and sched_freq_legacy_mode variables.

 */

int sched_window_update_handler(struct ctl_table *table, int write,

		void __user *buffer, size_t *lenp,

kernel/sysctl.c

+7 −7
Original line number Diff line number Diff line
@@ -340,13 +340,6 @@ static struct ctl_table kern_table[] = { 
	},

#endif

#ifdef CONFIG_SCHED_HMP

	{

		.procname       = "sched_account_wait_time",

		.data           = &sysctl_sched_account_wait_time,

		.maxlen         = sizeof(unsigned int),

		.mode           = 0644,

		.proc_handler   = sched_window_update_handler,

	},

	{

		.procname       = "sched_cpu_high_irqload",

		.data           = &sysctl_sched_cpu_high_irqload,
@@ -392,6 +385,13 @@ static struct ctl_table kern_table[] = { 
		.extra1		= &zero,

		.extra2		= &one,

	},

	{

		.procname       = "sched_account_wait_time",

		.data           = &sysctl_sched_account_wait_time,

		.maxlen         = sizeof(unsigned int),

		.mode           = 0644,

		.proc_handler   = sched_window_update_handler,

	},

#endif

	{

		.procname	= "sched_spill_load",