[PATCHv2 2/7] sched/fair: Add group_misfit_task load-balance type

From: Morten Rasmussen
Date: Thu Mar 15 2018 - 10:49:16 EST


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@xxxxxxxxxx>
cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>

Signed-off-by: Morten Rasmussen <morten.rasmussen@xxxxxxx>
---
kernel/sched/fair.c | 57 +++++++++++++++++++++++++++++++++++++++++++---------
kernel/sched/sched.h | 2 ++
2 files changed, 50 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e4ce572113a9..1e06c722bc2e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -697,6 +697,7 @@ 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)
@@ -1407,7 +1408,6 @@ 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 {
@@ -3873,6 +3873,30 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq)

static int idle_balance(struct rq *this_rq, struct rq_flags *rf);

+static inline unsigned long task_util(struct task_struct *p);
+static inline int task_fits_capacity(struct task_struct *p, long capacity)
+{
+ return capacity * 1024 > task_util(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 */

static inline int
@@ -3902,6 +3926,8 @@ static inline int idle_balance(struct rq *rq, struct rq_flags *rf)
return 0;
}

+static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
+
#endif /* CONFIG_SMP */

static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -5835,7 +5861,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
return target;
}

-static inline unsigned long task_util(struct task_struct *p);
static unsigned long cpu_util_wake(int cpu, struct task_struct *p);

static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
@@ -6398,7 +6423,7 @@ 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);
}

/*
@@ -6829,9 +6854,12 @@ 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);

/*
@@ -7037,6 +7065,13 @@ 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
@@ -7578,12 +7613,6 @@ 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
*/
@@ -7599,6 +7628,7 @@ struct sg_lb_stats {
unsigned int group_weight;
enum group_type group_type;
int group_no_capacity;
+ int 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;
@@ -7898,6 +7928,9 @@ 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;
}

@@ -7972,6 +8005,10 @@ 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 */
@@ -9753,6 +9790,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)

if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
+
+ update_misfit_status(curr, rq);
}

/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 017f62069e0b..22177dfc1f04 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -815,6 +815,8 @@ struct rq {

unsigned char idle_balance;

+ unsigned int misfit_task_load;
+
/* For active balancing */
int active_balance;
int push_cpu;
--
2.7.4