sched: remove stat_gran

remove the stat_gran code - it was disabled by default and it causes
unnecessary overhead.

Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 15 insertions, 47 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index ae1544f0a20..d4dabfcc776 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -829,7 +829,7 @@ static void update_curr_load(struct rq *rq)
 	 * Stagger updates to ls->delta_fair. Very frequent updates
 	 * can be expensive.
 	 */
-	if (ls->delta_stat >= sysctl_sched_stat_granularity)
+	if (ls->delta_stat)
 		__update_curr_load(rq, ls);
 }
 
@@ -1588,9 +1588,6 @@ static void __sched_fork(struct task_struct *p)
 	p->se.exec_start		= 0;
 	p->se.sum_exec_runtime		= 0;
 	p->se.prev_sum_exec_runtime	= 0;
-	p->se.delta_exec		= 0;
-	p->se.delta_fair_run		= 0;
-	p->se.delta_fair_sleep		= 0;
 	p->se.wait_runtime		= 0;
 	p->se.sleep_start_fair		= 0;
 
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 2e84aaffe42..2138c40f483 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -85,8 +85,6 @@ const_debug unsigned int sysctl_sched_batch_wakeup_granularity = 25000000UL;
  */
 const_debug unsigned int sysctl_sched_wakeup_granularity = 1000000UL;
 
-const_debug unsigned int sysctl_sched_stat_granularity;
-
 unsigned int sysctl_sched_runtime_limit __read_mostly;
 
 /*
@@ -360,13 +358,13 @@ add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
  * are not in our scheduling class.
  */
 static inline void
-__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
+	      unsigned long delta_exec)
 {
-	unsigned long delta, delta_exec, delta_fair, delta_mine;
+	unsigned long delta, delta_fair, delta_mine;
 	struct load_weight *lw = &cfs_rq->load;
 	unsigned long load = lw->weight;
 
-	delta_exec = curr->delta_exec;
 	schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
 
 	curr->sum_exec_runtime += delta_exec;
@@ -400,6 +398,7 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 static void update_curr(struct cfs_rq *cfs_rq)
 {
 	struct sched_entity *curr = cfs_rq_curr(cfs_rq);
+	u64 now = rq_of(cfs_rq)->clock;
 	unsigned long delta_exec;
 
 	if (unlikely(!curr))
@@ -410,15 +409,10 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	 * since the last time we changed load (this cannot
 	 * overflow on 32 bits):
 	 */
-	delta_exec = (unsigned long)(rq_of(cfs_rq)->clock - curr->exec_start);
-
-	curr->delta_exec += delta_exec;
+	delta_exec = (unsigned long)(now - curr->exec_start);
 
-	if (unlikely(curr->delta_exec > sysctl_sched_stat_granularity)) {
-		__update_curr(cfs_rq, curr);
-		curr->delta_exec = 0;
-	}
-	curr->exec_start = rq_of(cfs_rq)->clock;
+	__update_curr(cfs_rq, curr, delta_exec);
+	curr->exec_start = now;
 }
 
 static inline void
@@ -494,10 +488,9 @@ static void update_stats_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Note: must be called with a freshly updated rq->fair_clock.
  */
 static inline void
-__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
+__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			unsigned long delta_fair)
 {
-	unsigned long delta_fair = se->delta_fair_run;
-
 	schedstat_set(se->wait_max, max(se->wait_max,
 			rq_of(cfs_rq)->clock - se->wait_start));
 
@@ -519,12 +512,7 @@ update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
 			(u64)(cfs_rq->fair_clock - se->wait_start_fair));
 
-	se->delta_fair_run += delta_fair;
-	if (unlikely(abs(se->delta_fair_run) >=
-				sysctl_sched_stat_granularity)) {
-		__update_stats_wait_end(cfs_rq, se);
-		se->delta_fair_run = 0;
-	}
+	__update_stats_wait_end(cfs_rq, se, delta_fair);
 
 	se->wait_start_fair = 0;
 	schedstat_set(se->wait_start, 0);
@@ -567,9 +555,10 @@ update_stats_curr_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
  * Scheduling class queueing methods:
  */
 
-static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se,
+			      unsigned long delta_fair)
 {
-	unsigned long load = cfs_rq->load.weight, delta_fair;
+	unsigned long load = cfs_rq->load.weight;
 	long prev_runtime;
 
 	/*
@@ -582,8 +571,6 @@ static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	if (sysctl_sched_features & SCHED_FEAT_SLEEPER_LOAD_AVG)
 		load = rq_of(cfs_rq)->cpu_load[2];
 
-	delta_fair = se->delta_fair_sleep;
-
 	/*
 	 * Fix up delta_fair with the effect of us running
 	 * during the whole sleep period:
@@ -618,12 +605,7 @@ static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
 		(u64)(cfs_rq->fair_clock - se->sleep_start_fair));
 
-	se->delta_fair_sleep += delta_fair;
-	if (unlikely(abs(se->delta_fair_sleep) >=
-				sysctl_sched_stat_granularity)) {
-		__enqueue_sleeper(cfs_rq, se);
-		se->delta_fair_sleep = 0;
-	}
+	__enqueue_sleeper(cfs_rq, se, delta_fair);
 
 	se->sleep_start_fair = 0;
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 6c97259e863..9b1b0d4ff96 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -266,17 +266,6 @@ static ctl_table kern_table[] = {
 	},
 	{
 		.ctl_name	= CTL_UNNUMBERED,
-		.procname	= "sched_stat_granularity_ns",
-		.data		= &sysctl_sched_stat_granularity,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= &min_wakeup_granularity_ns,
-		.extra2		= &max_wakeup_granularity_ns,
-	},
-	{
-		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "sched_runtime_limit_ns",
 		.data		= &sysctl_sched_runtime_limit,
 		.maxlen		= sizeof(unsigned int),