sched: Scale down cpu_power due to RT tasks

Keep an average on the amount of time spend on RT tasks and use
that fraction to scale down the cpu_power for regular tasks.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Tested-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Andreas Herrmann <andreas.herrmann3@amd.com>
Acked-by: Gautham R Shenoy <ego@in.ibm.com>
Cc: Balbir Singh <balbir@in.ibm.com>
LKML-Reference: <20090901083826.287778431@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

3 files changed, 71 insertions, 7 deletions

diff --git a/kernel/sched.c b/kernel/sched.c
index 036600fd70bb..ab532b5de40e 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -627,6 +627,9 @@ struct rq {
 
         struct task_struct *migration_thread;
         struct list_head migration_queue;
+
+        u64 rt_avg;
+        u64 age_stamp;
 #endif
 
         /* calc_load related fields */
@@ -863,6 +866,14 @@ unsigned int sysctl_sched_shares_ratelimit = 250000;
 unsigned int sysctl_sched_shares_thresh = 4;
 
 /*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
  * period over which we measure -rt task cpu usage in us.
  * default: 1s
  */
@@ -1280,12 +1291,37 @@ void wake_up_idle_cpu(int cpu)
 }
 #endif /* CONFIG_NO_HZ */
 
+static u64 sched_avg_period(void)
+{
+        return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
+}
+
+static void sched_avg_update(struct rq *rq)
+{
+        s64 period = sched_avg_period();
+
+        while ((s64)(rq->clock - rq->age_stamp) > period) {
+                rq->age_stamp += period;
+                rq->rt_avg /= 2;
+        }
+}
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+        rq->rt_avg += rt_delta;
+        sched_avg_update(rq);
+}
+
 #else /* !CONFIG_SMP */
 static void resched_task(struct task_struct *p)
 {
         assert_spin_locked(&task_rq(p)->lock);
         set_tsk_need_resched(p);
 }
+
+static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -3699,7 +3735,7 @@ static inline int check_power_save_busiest_group(struct sd_lb_stats *sds,
 }
 #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
 
-unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
+unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu)
 {
         unsigned long weight = cpumask_weight(sched_domain_span(sd));
         unsigned long smt_gain = sd->smt_gain;
@@ -3709,6 +3745,24 @@ unsigned long __weak arch_smt_gain(struct sched_domain *sd, int cpu)
         return smt_gain;
 }
 
+unsigned long scale_rt_power(int cpu)
+{
+        struct rq *rq = cpu_rq(cpu);
+        u64 total, available;
+
+        sched_avg_update(rq);
+
+        total = sched_avg_period() + (rq->clock - rq->age_stamp);
+        available = total - rq->rt_avg;
+
+        if (unlikely((s64)total < SCHED_LOAD_SCALE))
+                total = SCHED_LOAD_SCALE;
+
+        total >>= SCHED_LOAD_SHIFT;
+
+        return div_u64(available, total);
+}
+
 static void update_cpu_power(struct sched_domain *sd, int cpu)
 {
         unsigned long weight = cpumask_weight(sched_domain_span(sd));
@@ -3719,11 +3773,15 @@ static void update_cpu_power(struct sched_domain *sd, int cpu)
         /* here we could scale based on cpufreq */
 
         if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) {
-                power *= arch_smt_gain(sd, cpu);
+                power *= arch_scale_smt_power(sd, cpu);
                 power >>= SCHED_LOAD_SHIFT;
         }
 
-        /* here we could scale based on RT time */
+        power *= scale_rt_power(cpu);
+        power >>= SCHED_LOAD_SHIFT;
+
+        if (!power)
+                power = 1;
 
         if (power != old) {
                 sdg->__cpu_power = power;
diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c
index 3d4020a9ba1b..2eb4bd6a526c 100644
--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -615,6 +615,8 @@ static void update_curr_rt(struct rq *rq)
         curr->se.exec_start = rq->clock;
         cpuacct_charge(curr, delta_exec);
 
+        sched_rt_avg_update(rq, delta_exec);
+
         if (!rt_bandwidth_enabled())
                 return;
 
@@ -887,8 +889,6 @@ static void enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup)
 
         if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1)
                 enqueue_pushable_task(rq, p);
-
-        inc_cpu_load(rq, p->se.load.weight);
 }
 
 static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
@@ -899,8 +899,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep)
         dequeue_rt_entity(rt_se);
 
         dequeue_pushable_task(rq, p);
-
-        dec_cpu_load(rq, p->se.load.weight);
 }
 
 /*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 58be76017fd0..6c9836ef4b47 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -332,6 +332,14 @@ static struct ctl_table kern_table[] = {
         },
         {
                 .ctl_name       = CTL_UNNUMBERED,
+                .procname       = "sched_time_avg",
+                .data           = &sysctl_sched_time_avg,
+                .maxlen         = sizeof(unsigned int),
+                .mode           = 0644,
+                .proc_handler   = &proc_dointvec,
+        },
+        {
+                .ctl_name       = CTL_UNNUMBERED,
                 .procname       = "timer_migration",
                 .data           = &sysctl_timer_migration,
                 .maxlen         = sizeof(unsigned int),