sched/fair: Add group_misfit_task load-balance type

To maximize throughput in systems with asymmetric cpu capacities (e.g.
ARM big.LITTLE) load-balancing has to consider task and cpu utilization
as well as per-cpu compute capacity when load-balancing in addition to
the current average load based load-balancing policy. Tasks with high
utilization that are scheduled on a lower capacity cpu need to be
identified and migrated to a higher capacity cpu if possible to maximize
throughput.

To implement this additional policy an additional group_type
(load-balance scenario) is added: group_misfit_task. This represents
scenarios where a sched_group has one or more tasks that are not
suitable for its per-cpu capacity. group_misfit_task is only considered
if the system is not overloaded or imbalanced (group_imbalanced or
group_overloaded).

Identifying misfit tasks requires the rq lock to be held. To avoid
taking remote rq locks to examine source sched_groups for misfit tasks,
each cpu is responsible for tracking misfit tasks themselves and update
the rq->misfit_task flag. This means checking task utilization when
tasks are scheduled and on sched_tick.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 50241d6ce6897d96b814562d3962eb693c30a97e..1170f902a0168800b1f7c985e79b437914f6e50f 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -693,6 +693,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
+static unsigned long capacity_of(int cpu);
 
 /* Give new sched_entity start runnable values to heavy its load in infant time */
 void init_entity_runnable_average(struct sched_entity *se)
@@ -1446,7 +1447,6 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page,
 static unsigned long weighted_cpuload(struct rq *rq);
 static unsigned long source_load(int cpu, int type);
 static unsigned long target_load(int cpu, int type);
-static unsigned long capacity_of(int cpu);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
@@ -3646,6 +3646,29 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
        WRITE_ONCE(p->se.avg.util_est, ue);
 }
 
+static inline int task_fits_capacity(struct task_struct *p, long capacity)
+{
+       return capacity * 1024 > task_util_est(p) * capacity_margin;
+}
+
+static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
+{
+       if (!static_branch_unlikely(&sched_asym_cpucapacity))
+               return;
+
+       if (!p) {
+               rq->misfit_task_load = 0;
+               return;
+       }
+
+       if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) {
+               rq->misfit_task_load = 0;
+               return;
+       }
+
+       rq->misfit_task_load = task_h_load(p);
+}
+
 #else /* CONFIG_SMP */
 
 #define UPDATE_TG      0x0
@@ -3675,6 +3698,7 @@ util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
 static inline void
 util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p,
                 bool task_sleep) {}
+static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
 
 #endif /* CONFIG_SMP */
 
@@ -6226,7 +6250,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
        /* Bring task utilization in sync with prev_cpu */
        sync_entity_load_avg(&p->se);
 
-       return min_cap * 1024 < task_util(p) * capacity_margin;
+       return !task_fits_capacity(p, min_cap);
 }
 
 /*
@@ -6836,9 +6860,12 @@ done: __maybe_unused;
        if (hrtick_enabled(rq))
                hrtick_start_fair(rq, p);
 
+       update_misfit_status(p, rq);
+
        return p;
 
 idle:
+       update_misfit_status(NULL, rq);
        new_tasks = idle_balance(rq, rf);
 
        /*
@@ -7044,6 +7071,13 @@ static unsigned long __read_mostly max_load_balance_interval = HZ/10;
 
 enum fbq_type { regular, remote, all };
 
+enum group_type {
+       group_other = 0,
+       group_misfit_task,
+       group_imbalanced,
+       group_overloaded,
+};
+
 #define LBF_ALL_PINNED 0x01
 #define LBF_NEED_BREAK 0x02
 #define LBF_DST_PINNED  0x04
@@ -7611,12 +7645,6 @@ static unsigned long task_h_load(struct task_struct *p)
 
 /********** Helpers for find_busiest_group ************************/
 
-enum group_type {
-       group_other = 0,
-       group_imbalanced,
-       group_overloaded,
-};
-
 /*
  * sg_lb_stats - stats of a sched_group required for load_balancing
  */
@@ -7632,6 +7660,7 @@ struct sg_lb_stats {
        unsigned int group_weight;
        enum group_type group_type;
        int group_no_capacity;
+       unsigned long group_misfit_task_load; /* A cpu has a task too big for its capacity */
 #ifdef CONFIG_NUMA_BALANCING
        unsigned int nr_numa_running;
        unsigned int nr_preferred_running;
@@ -7832,7 +7861,7 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
  * Something like:
  *
  *     { 0 1 2 3 } { 4 5 6 7 }
- *             *     * * *
+ *             *     * * *
  *
  * If we were to balance group-wise we'd place two tasks in the first group and
  * two tasks in the second group. Clearly this is undesired as it will overload
@@ -7924,6 +7953,9 @@ group_type group_classify(struct sched_group *group,
        if (sg_imbalanced(group))
                return group_imbalanced;
 
+       if (sgs->group_misfit_task_load)
+               return group_misfit_task;
+
        return group_other;
 }
 
@@ -8001,6 +8033,10 @@ static inline void update_sg_lb_stats(struct lb_env *env,
                 */
                if (!nr_running && idle_cpu(i))
                        sgs->idle_cpus++;
+
+               if (env->sd->flags & SD_ASYM_CPUCAPACITY &&
+                   sgs->group_misfit_task_load < rq->misfit_task_load)
+                       sgs->group_misfit_task_load = rq->misfit_task_load;
        }
 
        /* Adjust by relative CPU capacity of the group */
@@ -9792,6 +9828,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
                task_tick_numa(rq, curr);
 
        update_overutilized_status(task_rq(curr));
+       update_misfit_status(curr, rq);
 }
 
 /*

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 8553177ef23103e84093cb54b6fe1d34babdc836..f4da714986d70928bf3e71683e2cc34ea6e80d33 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -864,6 +864,8 @@ struct rq {
 
        unsigned char           idle_balance;
 
+       unsigned long           misfit_task_load;
+
        /* For active balancing */
        int                     active_balance;
        int                     push_cpu;