[PATCH v2 13/17] sched/core: Introduce a simple steal monitor

[Shrikanth Hegde]

Start with a simple steal monitor.

It is meant to look at steal time and make the decision to
reduce/increase the preferred CPUs.

It has
- work function to execute the steal time calculations and decision
  making periodically.
- temporary cpumask, which will be used in the work function. This helps
  to avoid cpumask allocation in periodic work function.
- low and high thesholds for steal time.
- sampling period to control the frequency of steal time calculations.
- cache the previous decision to avoid oscillations

Signed-off-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>
---
 kernel/sched/core.c  | 23 +++++++++++++++++++++++
 kernel/sched/sched.h | 14 ++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7a9442439eb2..8c80600ddd28 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9083,6 +9083,8 @@ void __init sched_init(void)
 
 	preempt_dynamic_init();
 
+	sched_init_steal_monitor();
+
 	scheduler_running = 1;
 }
 
@@ -11332,4 +11334,25 @@ void sched_push_current_non_preferred_cpu(struct rq *rq)
 	local_irq_restore(flags);
 }
 
+struct steal_monitor_t steal_mon;
+
+void sched_init_steal_monitor(void)
+{
+	INIT_WORK(&steal_mon.work, sched_steal_detection_work);
+	zalloc_cpumask_var(&steal_mon.tmp_mask, GFP_NOWAIT);
+	steal_mon.low_threshold       = 200;		/* 2% steal time */
+	steal_mon.high_threshold      = 500;		/* 5% steal time */
+	steal_mon.sampling_period_ms  = 1000;		/* once per second */
+}
+
+/* This is only a skeleton. Subsequent patches introduce more of it */
+void sched_steal_detection_work(struct work_struct *work)
+{
+	struct steal_monitor_t *sm = container_of(work, struct steal_monitor_t, work);
+	ktime_t now;
+
+	/* Update the prev_time for next iteration*/
+	now = ktime_get();
+	sm->prev_time = now;
+}
 #endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c1d037f11c62..c0fbfb04eda3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -4138,12 +4138,25 @@ DEFINE_CLASS_IS_UNCONDITIONAL(sched_change)
 #include "ext.h"
 
 #ifdef CONFIG_PARAVIRT
+struct steal_monitor_t {
+	struct work_struct  work;
+	cpumask_var_t tmp_mask;
+	ktime_t prev_time;
+	u64 prev_steal;
+	int previous_decision;
+	unsigned int low_threshold;
+	unsigned int high_threshold;
+	unsigned int sampling_period_ms;
+};
+
 static inline bool task_can_run_on_preferred_cpu(struct task_struct *p)
 {
 	return cpumask_intersects(p->cpus_ptr, cpu_preferred_mask);
 }
 
 void sched_push_current_non_preferred_cpu(struct rq *rq);
+void sched_init_steal_monitor(void);
+void sched_steal_detection_work(struct work_struct *work);
 #else
 static inline bool task_can_run_on_preferred_cpu(struct task_struct *p)
 {
@@ -4151,6 +4164,7 @@ static inline bool task_can_run_on_preferred_cpu(struct task_struct *p)
 }
 
 static inline void sched_push_current_non_preferred_cpu(struct rq *rq) { }
+static inline void sched_init_steal_monitor(void) { }
 #endif
 
 #endif /* _KERNEL_SCHED_SCHED_H */
-- 
2.47.3