sched: Track average sleep time

Similar to tracking average burst length for tasks, average sleep time
indicates how much a task sleeps on an average before waking up to run.
Very low sleep and burst lengths indicates tasks that could be
sensitive to task-wake latencies and hence should not be packed.

Change-Id: Ife68a9a9a9e596246aab5029f60e41c5bad781e4
Signed-off-by: Srivatsa Vaddagiri <vatsa@codeaurora.org>
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>

5 files changed, 19 insertions, 12 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2a885fbf542a..7b5135f04233 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1362,7 +1362,7 @@ struct ravg {
 	u32 sum_history[RAVG_HIST_SIZE_MAX];
 	u32 *curr_window_cpu, *prev_window_cpu;
 	u32 curr_window, prev_window;
-	u64 curr_burst, avg_burst;
+	u64 curr_burst, avg_burst, avg_sleep_time;
 	u16 active_windows;
 	u32 pred_demand;
 	u8 busy_buckets[NUM_BUSY_BUCKETS];
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 27c5c580acc2..c3e41f5f494c 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -135,6 +135,7 @@ TRACE_EVENT(sched_task_load,
 		__field(	u64,	latency			)
 		__field(	int,	grp_id			)
 		__field(	u64,	avg_burst		)
+		__field(	u64,	avg_sleep		)
 	),
 
 	TP_fast_assign(
@@ -152,13 +153,15 @@ TRACE_EVENT(sched_task_load,
 						      p->ravg.mark_start : 0;
 		__entry->grp_id		= p->grp ? p->grp->id : 0;
 		__entry->avg_burst	= p->ravg.avg_burst;
+		__entry->avg_sleep	= p->ravg.avg_sleep_time;
 	),
 
-	TP_printk("%d (%s): demand=%u boost=%d reason=%d sync=%d need_idle=%d flags=%x grp=%d best_cpu=%d latency=%llu avg_burst=%llu",
+	TP_printk("%d (%s): demand=%u boost=%d reason=%d sync=%d need_idle=%d flags=%x grp=%d best_cpu=%d latency=%llu avg_burst=%llu avg_sleep=%llu",
 		__entry->pid, __entry->comm, __entry->demand,
 		__entry->boost, __entry->reason, __entry->sync,
 		__entry->need_idle, __entry->flags, __entry->grp_id,
-		__entry->best_cpu, __entry->latency, __entry->avg_burst)
+		__entry->best_cpu, __entry->latency, __entry->avg_burst,
+		__entry->avg_sleep)
 );
 
 TRACE_EVENT(sched_set_preferred_cluster,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1a288e2de50d..1a48b0fc4d3f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2100,7 +2100,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		set_task_cpu(p, cpu);
 	}
 
-	set_task_last_wake(p, wallclock);
+	note_task_waking(p, wallclock);
 #endif /* CONFIG_SMP */
 	ttwu_queue(p, cpu);
 stat:
@@ -2169,7 +2169,7 @@ static void try_to_wake_up_local(struct task_struct *p)
 		update_task_ravg(rq->curr, rq, TASK_UPDATE, wallclock, 0);
 		update_task_ravg(p, rq, TASK_WAKE, wallclock, 0);
 		ttwu_activate(rq, p, ENQUEUE_WAKEUP);
-		set_task_last_wake(p, wallclock);
+		note_task_waking(p, wallclock);
 	}
 
 	ttwu_do_wakeup(rq, p, 0);
diff --git a/kernel/sched/hmp.c b/kernel/sched/hmp.c
index 95e618ee1124..158fc748873b 100644
--- a/kernel/sched/hmp.c
+++ b/kernel/sched/hmp.c
@@ -74,11 +74,6 @@ inline void clear_ed_task(struct task_struct *p, struct rq *rq)
 		rq->ed_task = NULL;
 }
 
-inline void set_task_last_wake(struct task_struct *p, u64 wallclock)
-{
-	p->last_wake_ts = wallclock;
-}
-
 inline void set_task_last_switch_out(struct task_struct *p, u64 wallclock)
 {
 	p->last_switch_out_ts = wallclock;
@@ -1567,6 +1562,7 @@ void init_new_task_load(struct task_struct *p, bool idle_task)
 	 * the avg_burst to go below the threshold.
 	 */
 	p->ravg.avg_burst = 2 * (u64)sysctl_sched_short_burst;
+	p->ravg.avg_sleep_time = 0;
 
 	p->ravg.curr_window_cpu = kcalloc(nr_cpu_ids, sizeof(u32), GFP_KERNEL);
 	p->ravg.prev_window_cpu = kcalloc(nr_cpu_ids, sizeof(u32), GFP_KERNEL);
@@ -4510,6 +4506,14 @@ void update_avg_burst(struct task_struct *p)
 	p->ravg.curr_burst = 0;
 }
 
+void note_task_waking(struct task_struct *p, u64 wallclock)
+{
+	u64 sleep_time = wallclock - p->last_switch_out_ts;
+
+	p->last_wake_ts = wallclock;
+	update_avg(&p->ravg.avg_sleep_time, sleep_time);
+}
+
 #ifdef CONFIG_CGROUP_SCHED
 u64 cpu_upmigrate_discourage_read_u64(struct cgroup_subsys_state *css,
 					  struct cftype *cft)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b9a109e5ef94..74035e1605ec 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1092,7 +1092,7 @@ extern void mark_task_starting(struct task_struct *p);
 extern void set_window_start(struct rq *rq);
 extern void migrate_sync_cpu(int cpu, int new_cpu);
 extern void update_cluster_topology(void);
-extern void set_task_last_wake(struct task_struct *p, u64 wallclock);
+extern void note_task_waking(struct task_struct *p, u64 wallclock);
 extern void set_task_last_switch_out(struct task_struct *p, u64 wallclock);
 extern void init_clusters(void);
 extern int __init set_sched_enable_hmp(char *str);
@@ -1490,7 +1490,7 @@ static inline void set_window_start(struct rq *rq) { }
 static inline void migrate_sync_cpu(int cpu, int new_cpu) {}
 static inline void init_clusters(void) {}
 static inline void update_cluster_topology(void) { }
-static inline void set_task_last_wake(struct task_struct *p, u64 wallclock) { }
+static inline void note_task_waking(struct task_struct *p, u64 wallclock) { }
 static inline void set_task_last_switch_out(struct task_struct *p,
 					    u64 wallclock) { }