sched: Add sched_avg::utilization_avg_contrib

Add new statistics which reflect the average time a task is running on the CPU
and the sum of these running time of the tasks on a runqueue. The latter is
named utilization_load_avg.

This patch is based on the usage metric that was proposed in the 1st
versions of the per-entity load tracking patchset by Paul Turner
<pjt@google.com> but that has be removed afterwards. This version differs from
the original one in the sense that it's not linked to task_group.

The rq's utilization_load_avg will be used to check if a rq is overloaded or
not instead of trying to compute how many tasks a group of CPUs can handle.

Rename runnable_avg_period into avg_period as it is now used with both
runnable_avg_sum and running_avg_sum.

Add some descriptions of the variables to explain their differences.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d77432..fdca05c 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1115,15 +1115,28 @@ struct load_weight {
 };
 
 struct sched_avg {
+       u64 last_runnable_update;
+       s64 decay_count;
+       /*
+        * utilization_avg_contrib describes the amount of time that a
+        * sched_entity is running on a CPU. It is based on running_avg_sum
+        * and is scaled in the range [0..SCHED_LOAD_SCALE].
+        * load_avg_contrib described the amount of time that a sched_entity
+        * is runnable on a rq. It is based on both runnable_avg_sum and the
+        * weight of the task.
+        */
+       unsigned long load_avg_contrib, utilization_avg_contrib;
        /*
         * These sums represent an infinite geometric series and so are bound
         * above by 1024/(1-y).  Thus we only need a u32 to store them for all
         * choices of y < 1-2^(-32)*1024.
+        * running_avg_sum reflects the time that the sched_entity is
+        * effectively running on the CPU.
+        * runnable_avg_sum represents the amount of time a sched_entity is on
+        * a runqueue which includes the running time that is monitored by
+        * running_avg_sum.
         */
-       u32 runnable_avg_sum, runnable_avg_period;
-       u64 last_runnable_update;
-       s64 decay_count;
-       unsigned long load_avg_contrib;
+       u32 runnable_avg_sum, avg_period, running_avg_sum;
 };
 
 #ifdef CONFIG_SCHEDSTATS

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 8baaf85..578ff83 100644 (file)
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -71,7 +71,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
        if (!se) {
                struct sched_avg *avg = &cpu_rq(cpu)->avg;
                P(avg->runnable_avg_sum);
-               P(avg->runnable_avg_period);
+               P(avg->avg_period);
                return;
        }
 
@@ -94,7 +94,7 @@ static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group
        P(se->load.weight);
 #ifdef CONFIG_SMP
        P(se->avg.runnable_avg_sum);
-       P(se->avg.runnable_avg_period);
+       P(se->avg.avg_period);
        P(se->avg.load_avg_contrib);
        P(se->avg.decay_count);
 #endif
@@ -214,6 +214,8 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
                        cfs_rq->runnable_load_avg);
        SEQ_printf(m, "  .%-30s: %ld\n", "blocked_load_avg",
                        cfs_rq->blocked_load_avg);
+       SEQ_printf(m, "  .%-30s: %ld\n", "utilization_load_avg",
+                       cfs_rq->utilization_load_avg);
 #ifdef CONFIG_FAIR_GROUP_SCHED
        SEQ_printf(m, "  .%-30s: %ld\n", "tg_load_contrib",
                        cfs_rq->tg_load_contrib);
@@ -636,8 +638,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m)
        P(se.load.weight);
 #ifdef CONFIG_SMP
        P(se.avg.runnable_avg_sum);
-       P(se.avg.runnable_avg_period);
+       P(se.avg.running_avg_sum);
+       P(se.avg.avg_period);
        P(se.avg.load_avg_contrib);
+       P(se.avg.utilization_avg_contrib);
        P(se.avg.decay_count);
 #endif
        P(policy);

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ee595ef..414408d 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -670,6 +670,7 @@ static int select_idle_sibling(struct task_struct *p, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 
 static inline void __update_task_entity_contrib(struct sched_entity *se);
+static inline void __update_task_entity_utilization(struct sched_entity *se);
 
 /* Give new task start runnable values to heavy its load in infant time */
 void init_task_runnable_average(struct task_struct *p)
@@ -677,9 +678,10 @@ void init_task_runnable_average(struct task_struct *p)
        u32 slice;
 
        slice = sched_slice(task_cfs_rq(p), &p->se) >> 10;
-       p->se.avg.runnable_avg_sum = slice;
-       p->se.avg.runnable_avg_period = slice;
+       p->se.avg.runnable_avg_sum = p->se.avg.running_avg_sum = slice;
+       p->se.avg.avg_period = slice;
        __update_task_entity_contrib(&p->se);
+       __update_task_entity_utilization(&p->se);
 }
 #else
 void init_task_runnable_average(struct task_struct *p)
@@ -1684,7 +1686,7 @@ static u64 numa_get_avg_runtime(struct task_struct *p, u64 *period)
                *period = now - p->last_task_numa_placement;
        } else {
                delta = p->se.avg.runnable_avg_sum;
-               *period = p->se.avg.runnable_avg_period;
+               *period = p->se.avg.avg_period;
        }
 
        p->last_sum_exec_runtime = runtime;
@@ -2512,7 +2514,8 @@ static u32 __compute_runnable_contrib(u64 n)
  */
 static __always_inline int __update_entity_runnable_avg(u64 now,
                                                        struct sched_avg *sa,
-                                                       int runnable)
+                                                       int runnable,
+                                                       int running)
 {
        u64 delta, periods;
        u32 runnable_contrib;
@@ -2538,7 +2541,7 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
        sa->last_runnable_update = now;
 
        /* delta_w is the amount already accumulated against our next period */
-       delta_w = sa->runnable_avg_period % 1024;
+       delta_w = sa->avg_period % 1024;
        if (delta + delta_w >= 1024) {
                /* period roll-over */
                decayed = 1;
@@ -2551,7 +2554,9 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
                delta_w = 1024 - delta_w;
                if (runnable)
                        sa->runnable_avg_sum += delta_w;
-               sa->runnable_avg_period += delta_w;
+               if (running)
+                       sa->running_avg_sum += delta_w;
+               sa->avg_period += delta_w;
 
                delta -= delta_w;
 
@@ -2561,20 +2566,26 @@ static __always_inline int __update_entity_runnable_avg(u64 now,
 
                sa->runnable_avg_sum = decay_load(sa->runnable_avg_sum,
                                                  periods + 1);
-               sa->runnable_avg_period = decay_load(sa->runnable_avg_period,
+               sa->running_avg_sum = decay_load(sa->running_avg_sum,
+                                                 periods + 1);
+               sa->avg_period = decay_load(sa->avg_period,
                                                     periods + 1);
 
                /* Efficiently calculate \sum (1..n_period) 1024*y^i */
                runnable_contrib = __compute_runnable_contrib(periods);
                if (runnable)
                        sa->runnable_avg_sum += runnable_contrib;
-               sa->runnable_avg_period += runnable_contrib;
+               if (running)
+                       sa->running_avg_sum += runnable_contrib;
+               sa->avg_period += runnable_contrib;
        }
 
        /* Remainder of delta accrued against u_0` */
        if (runnable)
                sa->runnable_avg_sum += delta;
-       sa->runnable_avg_period += delta;
+       if (running)
+               sa->running_avg_sum += delta;
+       sa->avg_period += delta;
 
        return decayed;
 }
@@ -2591,6 +2602,8 @@ static inline u64 __synchronize_entity_decay(struct sched_entity *se)
                return 0;
 
        se->avg.load_avg_contrib = decay_load(se->avg.load_avg_contrib, decays);
+       se->avg.utilization_avg_contrib =
+               decay_load(se->avg.utilization_avg_contrib, decays);
 
        return decays;
 }
@@ -2626,7 +2639,7 @@ static inline void __update_tg_runnable_avg(struct sched_avg *sa,
 
        /* The fraction of a cpu used by this cfs_rq */
        contrib = div_u64((u64)sa->runnable_avg_sum << NICE_0_SHIFT,
-                         sa->runnable_avg_period + 1);
+                         sa->avg_period + 1);
        contrib -= cfs_rq->tg_runnable_contrib;
 
        if (abs(contrib) > cfs_rq->tg_runnable_contrib / 64) {
@@ -2679,7 +2692,8 @@ static inline void __update_group_entity_contrib(struct sched_entity *se)
 
 static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
 {
-       __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable);
+       __update_entity_runnable_avg(rq_clock_task(rq), &rq->avg, runnable,
+                       runnable);
        __update_tg_runnable_avg(&rq->avg, &rq->cfs);
 }
 #else /* CONFIG_FAIR_GROUP_SCHED */
@@ -2697,7 +2711,7 @@ static inline void __update_task_entity_contrib(struct sched_entity *se)
 
        /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
        contrib = se->avg.runnable_avg_sum * scale_load_down(se->load.weight);
-       contrib /= (se->avg.runnable_avg_period + 1);
+       contrib /= (se->avg.avg_period + 1);
        se->avg.load_avg_contrib = scale_load(contrib);
 }
 
@@ -2716,6 +2730,27 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se)
        return se->avg.load_avg_contrib - old_contrib;
 }
 
+
+static inline void __update_task_entity_utilization(struct sched_entity *se)
+{
+       u32 contrib;
+
+       /* avoid overflowing a 32-bit type w/ SCHED_LOAD_SCALE */
+       contrib = se->avg.running_avg_sum * scale_load_down(SCHED_LOAD_SCALE);
+       contrib /= (se->avg.avg_period + 1);
+       se->avg.utilization_avg_contrib = scale_load(contrib);
+}
+
+static long __update_entity_utilization_avg_contrib(struct sched_entity *se)
+{
+       long old_contrib = se->avg.utilization_avg_contrib;
+
+       if (entity_is_task(se))
+               __update_task_entity_utilization(se);
+
+       return se->avg.utilization_avg_contrib - old_contrib;
+}
+
 static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
                                                 long load_contrib)
 {
@@ -2732,7 +2767,7 @@ static inline void update_entity_load_avg(struct sched_entity *se,
                                          int update_cfs_rq)
 {
        struct cfs_rq *cfs_rq = cfs_rq_of(se);
-       long contrib_delta;
+       long contrib_delta, utilization_delta;
        u64 now;
 
        /*
@@ -2744,18 +2779,22 @@ static inline void update_entity_load_avg(struct sched_entity *se,
        else
                now = cfs_rq_clock_task(group_cfs_rq(se));
 
-       if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq))
+       if (!__update_entity_runnable_avg(now, &se->avg, se->on_rq,
+                                       cfs_rq->curr == se))
                return;
 
        contrib_delta = __update_entity_load_avg_contrib(se);
+       utilization_delta = __update_entity_utilization_avg_contrib(se);
 
        if (!update_cfs_rq)
                return;
 
-       if (se->on_rq)
+       if (se->on_rq) {
                cfs_rq->runnable_load_avg += contrib_delta;
-       else
+               cfs_rq->utilization_load_avg += utilization_delta;
+       } else {
                subtract_blocked_load_contrib(cfs_rq, -contrib_delta);
+       }
 }
 
 /*
@@ -2830,6 +2869,7 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq,
        }
 
        cfs_rq->runnable_load_avg += se->avg.load_avg_contrib;
+       cfs_rq->utilization_load_avg += se->avg.utilization_avg_contrib;
        /* we force update consideration on load-balancer moves */
        update_cfs_rq_blocked_load(cfs_rq, !wakeup);
 }
@@ -2848,6 +2888,7 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq,
        update_cfs_rq_blocked_load(cfs_rq, !sleep);
 
        cfs_rq->runnable_load_avg -= se->avg.load_avg_contrib;
+       cfs_rq->utilization_load_avg -= se->avg.utilization_avg_contrib;
        if (sleep) {
                cfs_rq->blocked_load_avg += se->avg.load_avg_contrib;
                se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter);
@@ -3185,6 +3226,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
                 */
                update_stats_wait_end(cfs_rq, se);
                __dequeue_entity(cfs_rq, se);
+               update_entity_load_avg(se, 1);
        }
 
        update_stats_curr_start(cfs_rq, se);

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2c0d7b..4c95cc2 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -363,8 +363,14 @@ struct cfs_rq {
         * Under CFS, load is tracked on a per-entity basis and aggregated up.
         * This allows for the description of both thread and group usage (in
         * the FAIR_GROUP_SCHED case).
+        * runnable_load_avg is the sum of the load_avg_contrib of the
+        * sched_entities on the rq.
+        * blocked_load_avg is similar to runnable_load_avg except that its
+        * the blocked sched_entities on the rq.
+        * utilization_load_avg is the sum of the average running time of the
+        * sched_entities on the rq.
         */
-       unsigned long runnable_load_avg, blocked_load_avg;
+       unsigned long runnable_load_avg, blocked_load_avg, utilization_load_avg;
        atomic64_t decay_counter;
        u64 last_decay;
        atomic_long_t removed_load;