summaryrefslogtreecommitdiff
path: root/kernel/sched/fair.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r--kernel/sched/fair.c425
1 files changed, 262 insertions, 163 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 241213be507c..ffeaa4105e48 100644
--- 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)
@@ -1196,9 +1198,11 @@ static void task_numa_assign(struct task_numa_env *env,
static bool load_too_imbalanced(long src_load, long dst_load,
struct task_numa_env *env)
{
- long imb, old_imb;
- long orig_src_load, orig_dst_load;
long src_capacity, dst_capacity;
+ long orig_src_load;
+ long load_a, load_b;
+ long moved_load;
+ long imb;
/*
* The load is corrected for the CPU capacity available on each node.
@@ -1211,30 +1215,39 @@ static bool load_too_imbalanced(long src_load, long dst_load,
dst_capacity = env->dst_stats.compute_capacity;
/* We care about the slope of the imbalance, not the direction. */
- if (dst_load < src_load)
- swap(dst_load, src_load);
+ load_a = dst_load;
+ load_b = src_load;
+ if (load_a < load_b)
+ swap(load_a, load_b);
/* Is the difference below the threshold? */
- imb = dst_load * src_capacity * 100 -
- src_load * dst_capacity * env->imbalance_pct;
+ imb = load_a * src_capacity * 100 -
+ load_b * dst_capacity * env->imbalance_pct;
if (imb <= 0)
return false;
/*
* The imbalance is above the allowed threshold.
- * Compare it with the old imbalance.
+ * Allow a move that brings us closer to a balanced situation,
+ * without moving things past the point of balance.
*/
orig_src_load = env->src_stats.load;
- orig_dst_load = env->dst_stats.load;
- if (orig_dst_load < orig_src_load)
- swap(orig_dst_load, orig_src_load);
-
- old_imb = orig_dst_load * src_capacity * 100 -
- orig_src_load * dst_capacity * env->imbalance_pct;
+ /*
+ * In a task swap, there will be one load moving from src to dst,
+ * and another moving back. This is the net sum of both moves.
+ * A simple task move will always have a positive value.
+ * Allow the move if it brings the system closer to a balanced
+ * situation, without crossing over the balance point.
+ */
+ moved_load = orig_src_load - src_load;
- /* Would this change make things worse? */
- return (imb > old_imb);
+ if (moved_load > 0)
+ /* Moving src -> dst. Did we overshoot balance? */
+ return src_load * dst_capacity < dst_load * src_capacity;
+ else
+ /* Moving dst -> src. Did we overshoot balance? */
+ return dst_load * src_capacity < src_load * dst_capacity;
}
/*
@@ -1675,7 +1688,7 @@ 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;
@@ -1765,6 +1778,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
}
}
/* Next round, evaluate the nodes within max_group. */
+ if (!max_faults)
+ break;
nodes = max_group;
}
return nid;
@@ -2503,13 +2518,15 @@ static u32 __compute_runnable_contrib(u64 n)
* load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
* = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
*/
-static __always_inline int __update_entity_runnable_avg(u64 now,
+static __always_inline int __update_entity_runnable_avg(u64 now, int cpu,
struct sched_avg *sa,
- int runnable)
+ int runnable,
+ int running)
{
u64 delta, periods;
u32 runnable_contrib;
int delta_w, decayed = 0;
+ unsigned long scale_freq = arch_scale_freq_capacity(NULL, cpu);
delta = now - sa->last_runnable_update;
/*
@@ -2531,7 +2548,7 @@ 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;
@@ -2544,7 +2561,10 @@ 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 * scale_freq
+ >> SCHED_CAPACITY_SHIFT;
+ sa->avg_period += delta_w;
delta -= delta_w;
@@ -2554,20 +2574,28 @@ 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 * scale_freq
+ >> SCHED_CAPACITY_SHIFT;
+ 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 * scale_freq
+ >> SCHED_CAPACITY_SHIFT;
+ sa->avg_period += delta;
return decayed;
}
@@ -2584,6 +2612,8 @@ 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;
}
@@ -2619,7 +2649,7 @@ 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) {
@@ -2672,7 +2702,8 @@ 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), cpu_of(rq), &rq->avg,
+ runnable, runnable);
__update_tg_runnable_avg(&rq->avg, &rq->cfs);
}
#else /* CONFIG_FAIR_GROUP_SCHED */
@@ -2690,7 +2721,7 @@ 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);
}
@@ -2709,6 +2740,30 @@ 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);
+ else
+ se->avg.utilization_avg_contrib =
+ group_cfs_rq(se)->utilization_load_avg;
+
+ return se->avg.utilization_avg_contrib - old_contrib;
+}
+
static inline void subtract_blocked_load_contrib(struct cfs_rq *cfs_rq,
long load_contrib)
{
@@ -2725,7 +2780,8 @@ 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;
+ int cpu = cpu_of(rq_of(cfs_rq));
u64 now;
/*
@@ -2737,18 +2793,22 @@ 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, cpu, &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);
+ }
}
/*
@@ -2823,6 +2883,7 @@ 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);
}
@@ -2841,6 +2902,7 @@ 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);
@@ -3178,6 +3240,7 @@ 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);
@@ -4304,6 +4367,11 @@ static unsigned long capacity_of(int cpu)
return cpu_rq(cpu)->cpu_capacity;
}
+static unsigned long capacity_orig_of(int cpu)
+{
+ return cpu_rq(cpu)->cpu_capacity_orig;
+}
+
static unsigned long cpu_avg_load_per_task(int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -4717,6 +4785,33 @@ next:
done:
return target;
}
+/*
+ * get_cpu_usage returns the amount of capacity of a CPU that is used by CFS
+ * tasks. The unit of the return value must be the one of capacity so we can
+ * compare the usage with the capacity of the CPU that is available for CFS
+ * task (ie cpu_capacity).
+ * cfs.utilization_load_avg is the sum of running time of runnable tasks on a
+ * CPU. It represents the amount of utilization of a CPU in the range
+ * [0..SCHED_LOAD_SCALE]. The usage of a CPU can't be higher than the full
+ * capacity of the CPU because it's about the running time on this CPU.
+ * Nevertheless, cfs.utilization_load_avg can be higher than SCHED_LOAD_SCALE
+ * because of unfortunate rounding in avg_period and running_load_avg or just
+ * after migrating tasks until the average stabilizes with the new running
+ * time. So we need to check that the usage stays into the range
+ * [0..cpu_capacity_orig] and cap if necessary.
+ * Without capping the usage, a group could be seen as overloaded (CPU0 usage
+ * at 121% + CPU1 usage at 80%) whereas CPU1 has 20% of available capacity
+ */
+static int get_cpu_usage(int cpu)
+{
+ unsigned long usage = cpu_rq(cpu)->cfs.utilization_load_avg;
+ unsigned long capacity = capacity_orig_of(cpu);
+
+ if (usage >= SCHED_LOAD_SCALE)
+ return capacity;
+
+ return (usage * capacity) >> SCHED_LOAD_SHIFT;
+}
/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
@@ -5843,12 +5938,12 @@ struct sg_lb_stats {
unsigned long sum_weighted_load; /* Weighted load of group's tasks */
unsigned long load_per_task;
unsigned long group_capacity;
+ unsigned long group_usage; /* Total usage of the group */
unsigned int sum_nr_running; /* Nr tasks running in the group */
- unsigned int group_capacity_factor;
unsigned int idle_cpus;
unsigned int group_weight;
enum group_type group_type;
- int group_has_free_capacity;
+ int group_no_capacity;
#ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
unsigned int nr_preferred_running;
@@ -5919,16 +6014,6 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
return load_idx;
}
-static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu)
-{
- return SCHED_CAPACITY_SCALE;
-}
-
-unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu)
-{
- return default_scale_capacity(sd, cpu);
-}
-
static unsigned long default_scale_cpu_capacity(struct sched_domain *sd, int cpu)
{
if ((sd->flags & SD_SHARE_CPUCAPACITY) && (sd->span_weight > 1))
@@ -5945,7 +6030,7 @@ unsigned long __weak arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
static unsigned long scale_rt_capacity(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- u64 total, available, age_stamp, avg;
+ u64 total, used, age_stamp, avg;
s64 delta;
/*
@@ -5961,19 +6046,12 @@ static unsigned long scale_rt_capacity(int cpu)
total = sched_avg_period() + delta;
- if (unlikely(total < avg)) {
- /* Ensures that capacity won't end up being negative */
- available = 0;
- } else {
- available = total - avg;
- }
+ used = div_u64(avg, total);
- if (unlikely((s64)total < SCHED_CAPACITY_SCALE))
- total = SCHED_CAPACITY_SCALE;
+ if (likely(used < SCHED_CAPACITY_SCALE))
+ return SCHED_CAPACITY_SCALE - used;
- total >>= SCHED_CAPACITY_SHIFT;
-
- return div_u64(available, total);
+ return 1;
}
static void update_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -5988,14 +6066,7 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu)
capacity >>= SCHED_CAPACITY_SHIFT;
- sdg->sgc->capacity_orig = capacity;
-
- if (sched_feat(ARCH_CAPACITY))
- capacity *= arch_scale_freq_capacity(sd, cpu);
- else
- capacity *= default_scale_capacity(sd, cpu);
-
- capacity >>= SCHED_CAPACITY_SHIFT;
+ cpu_rq(cpu)->cpu_capacity_orig = capacity;
capacity *= scale_rt_capacity(cpu);
capacity >>= SCHED_CAPACITY_SHIFT;
@@ -6011,7 +6082,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
{
struct sched_domain *child = sd->child;
struct sched_group *group, *sdg = sd->groups;
- unsigned long capacity, capacity_orig;
+ unsigned long capacity;
unsigned long interval;
interval = msecs_to_jiffies(sd->balance_interval);
@@ -6023,7 +6094,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
return;
}
- capacity_orig = capacity = 0;
+ capacity = 0;
if (child->flags & SD_OVERLAP) {
/*
@@ -6043,19 +6114,15 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
* Use capacity_of(), which is set irrespective of domains
* in update_cpu_capacity().
*
- * This avoids capacity/capacity_orig from being 0 and
+ * This avoids capacity from being 0 and
* causing divide-by-zero issues on boot.
- *
- * Runtime updates will correct capacity_orig.
*/
if (unlikely(!rq->sd)) {
- capacity_orig += capacity_of(cpu);
capacity += capacity_of(cpu);
continue;
}
sgc = rq->sd->groups->sgc;
- capacity_orig += sgc->capacity_orig;
capacity += sgc->capacity;
}
} else {
@@ -6066,39 +6133,24 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
group = child->groups;
do {
- capacity_orig += group->sgc->capacity_orig;
capacity += group->sgc->capacity;
group = group->next;
} while (group != child->groups);
}
- sdg->sgc->capacity_orig = capacity_orig;
sdg->sgc->capacity = capacity;
}
/*
- * Try and fix up capacity for tiny siblings, this is needed when
- * things like SD_ASYM_PACKING need f_b_g to select another sibling
- * which on its own isn't powerful enough.
- *
- * See update_sd_pick_busiest() and check_asym_packing().
+ * Check whether the capacity of the rq has been noticeably reduced by side
+ * activity. The imbalance_pct is used for the threshold.
+ * Return true is the capacity is reduced
*/
static inline int
-fix_small_capacity(struct sched_domain *sd, struct sched_group *group)
+check_cpu_capacity(struct rq *rq, struct sched_domain *sd)
{
- /*
- * Only siblings can have significantly less than SCHED_CAPACITY_SCALE
- */
- if (!(sd->flags & SD_SHARE_CPUCAPACITY))
- return 0;
-
- /*
- * If ~90% of the cpu_capacity is still there, we're good.
- */
- if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29)
- return 1;
-
- return 0;
+ return ((rq->cpu_capacity * sd->imbalance_pct) <
+ (rq->cpu_capacity_orig * 100));
}
/*
@@ -6136,37 +6188,56 @@ static inline int sg_imbalanced(struct sched_group *group)
}
/*
- * Compute the group capacity factor.
- *
- * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by
- * first dividing out the smt factor and computing the actual number of cores
- * and limit unit capacity with that.
+ * group_has_capacity returns true if the group has spare capacity that could
+ * be used by some tasks.
+ * We consider that a group has spare capacity if the * number of task is
+ * smaller than the number of CPUs or if the usage is lower than the available
+ * capacity for CFS tasks.
+ * For the latter, we use a threshold to stabilize the state, to take into
+ * account the variance of the tasks' load and to return true if the available
+ * capacity in meaningful for the load balancer.
+ * As an example, an available capacity of 1% can appear but it doesn't make
+ * any benefit for the load balance.
*/
-static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group)
+static inline bool
+group_has_capacity(struct lb_env *env, struct sg_lb_stats *sgs)
{
- unsigned int capacity_factor, smt, cpus;
- unsigned int capacity, capacity_orig;
+ if (sgs->sum_nr_running < sgs->group_weight)
+ return true;
- capacity = group->sgc->capacity;
- capacity_orig = group->sgc->capacity_orig;
- cpus = group->group_weight;
+ if ((sgs->group_capacity * 100) >
+ (sgs->group_usage * env->sd->imbalance_pct))
+ return true;
- /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */
- smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig);
- capacity_factor = cpus / smt; /* cores */
+ return false;
+}
+
+/*
+ * group_is_overloaded returns true if the group has more tasks than it can
+ * handle.
+ * group_is_overloaded is not equals to !group_has_capacity because a group
+ * with the exact right number of tasks, has no more spare capacity but is not
+ * overloaded so both group_has_capacity and group_is_overloaded return
+ * false.
+ */
+static inline bool
+group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs)
+{
+ if (sgs->sum_nr_running <= sgs->group_weight)
+ return false;
- capacity_factor = min_t(unsigned,
- capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE));
- if (!capacity_factor)
- capacity_factor = fix_small_capacity(env->sd, group);
+ if ((sgs->group_capacity * 100) <
+ (sgs->group_usage * env->sd->imbalance_pct))
+ return true;
- return capacity_factor;
+ return false;
}
-static enum group_type
-group_classify(struct sched_group *group, struct sg_lb_stats *sgs)
+static enum group_type group_classify(struct lb_env *env,
+ struct sched_group *group,
+ struct sg_lb_stats *sgs)
{
- if (sgs->sum_nr_running > sgs->group_capacity_factor)
+ if (sgs->group_no_capacity)
return group_overloaded;
if (sg_imbalanced(group))
@@ -6204,6 +6275,7 @@ static inline void update_sg_lb_stats(struct lb_env *env,
load = source_load(i, load_idx);
sgs->group_load += load;
+ sgs->group_usage += get_cpu_usage(i);
sgs->sum_nr_running += rq->cfs.h_nr_running;
if (rq->nr_running > 1)
@@ -6226,11 +6298,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
sgs->group_weight = group->group_weight;
- sgs->group_capacity_factor = sg_capacity_factor(env, group);
- sgs->group_type = group_classify(group, sgs);
- if (sgs->group_capacity_factor > sgs->sum_nr_running)
- sgs->group_has_free_capacity = 1;
+ sgs->group_no_capacity = group_is_overloaded(env, sgs);
+ sgs->group_type = group_classify(env, group, sgs);
}
/**
@@ -6352,18 +6422,19 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
/*
* In case the child domain prefers tasks go to siblings
- * first, lower the sg capacity factor to one so that we'll try
+ * first, lower the sg capacity so that we'll try
* and move all the excess tasks away. We lower the capacity
* of a group only if the local group has the capacity to fit
- * these excess tasks, i.e. nr_running < group_capacity_factor. The
- * extra check prevents the case where you always pull from the
- * heaviest group when it is already under-utilized (possible
- * with a large weight task outweighs the tasks on the system).
+ * these excess tasks. The extra check prevents the case where
+ * you always pull from the heaviest group when it is already
+ * under-utilized (possible with a large weight task outweighs
+ * the tasks on the system).
*/
if (prefer_sibling && sds->local &&
- sds->local_stat.group_has_free_capacity) {
- sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U);
- sgs->group_type = group_classify(sg, sgs);
+ group_has_capacity(env, &sds->local_stat) &&
+ (sgs->sum_nr_running > 1)) {
+ sgs->group_no_capacity = 1;
+ sgs->group_type = group_overloaded;
}
if (update_sd_pick_busiest(env, sds, sg, sgs)) {
@@ -6543,11 +6614,12 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
*/
if (busiest->group_type == group_overloaded &&
local->group_type == group_overloaded) {
- load_above_capacity =
- (busiest->sum_nr_running - busiest->group_capacity_factor);
-
- load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE);
- load_above_capacity /= busiest->group_capacity;
+ load_above_capacity = busiest->sum_nr_running *
+ SCHED_LOAD_SCALE;
+ if (load_above_capacity > busiest->group_capacity)
+ load_above_capacity -= busiest->group_capacity;
+ else
+ load_above_capacity = ~0UL;
}
/*
@@ -6610,6 +6682,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
local = &sds.local_stat;
busiest = &sds.busiest_stat;
+ /* ASYM feature bypasses nice load balance check */
if ((env->idle == CPU_IDLE || env->idle == CPU_NEWLY_IDLE) &&
check_asym_packing(env, &sds))
return sds.busiest;
@@ -6630,8 +6703,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
goto force_balance;
/* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
- if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity &&
- !busiest->group_has_free_capacity)
+ if (env->idle == CPU_NEWLY_IDLE && group_has_capacity(env, local) &&
+ busiest->group_no_capacity)
goto force_balance;
/*
@@ -6690,7 +6763,7 @@ static struct rq *find_busiest_queue(struct lb_env *env,
int i;
for_each_cpu_and(i, sched_group_cpus(group), env->cpus) {
- unsigned long capacity, capacity_factor, wl;
+ unsigned long capacity, wl;
enum fbq_type rt;
rq = cpu_rq(i);
@@ -6719,9 +6792,6 @@ static struct rq *find_busiest_queue(struct lb_env *env,
continue;
capacity = capacity_of(i);
- capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE);
- if (!capacity_factor)
- capacity_factor = fix_small_capacity(env->sd, group);
wl = weighted_cpuload(i);
@@ -6729,7 +6799,9 @@ static struct rq *find_busiest_queue(struct lb_env *env,
* When comparing with imbalance, use weighted_cpuload()
* which is not scaled with the cpu capacity.
*/
- if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance)
+
+ if (rq->nr_running == 1 && wl > env->imbalance &&
+ !check_cpu_capacity(rq, env->sd))
continue;
/*
@@ -6777,6 +6849,19 @@ static int need_active_balance(struct lb_env *env)
return 1;
}
+ /*
+ * The dst_cpu is idle and the src_cpu CPU has only 1 CFS task.
+ * It's worth migrating the task if the src_cpu's capacity is reduced
+ * because of other sched_class or IRQs if more capacity stays
+ * available on dst_cpu.
+ */
+ if ((env->idle != CPU_NOT_IDLE) &&
+ (env->src_rq->cfs.h_nr_running == 1)) {
+ if ((check_cpu_capacity(env->src_rq, sd)) &&
+ (capacity_of(env->src_cpu)*sd->imbalance_pct < capacity_of(env->dst_cpu)*100))
+ return 1;
+ }
+
return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2);
}
@@ -6876,6 +6961,9 @@ redo:
schedstat_add(sd, lb_imbalance[idle], env.imbalance);
+ env.src_cpu = busiest->cpu;
+ env.src_rq = busiest;
+
ld_moved = 0;
if (busiest->nr_running > 1) {
/*
@@ -6885,8 +6973,6 @@ redo:
* correctly treated as an imbalance.
*/
env.flags |= LBF_ALL_PINNED;
- env.src_cpu = busiest->cpu;
- env.src_rq = busiest;
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
more_balance:
@@ -7586,22 +7672,25 @@ end:
/*
* Current heuristic for kicking the idle load balancer in the presence
- * of an idle cpu is the system.
+ * of an idle cpu in the system.
* - This rq has more than one task.
- * - At any scheduler domain level, this cpu's scheduler group has multiple
- * busy cpu's exceeding the group's capacity.
+ * - This rq has at least one CFS task and the capacity of the CPU is
+ * significantly reduced because of RT tasks or IRQs.
+ * - At parent of LLC scheduler domain level, this cpu's scheduler group has
+ * multiple busy cpu.
* - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
* domain span are idle.
*/
-static inline int nohz_kick_needed(struct rq *rq)
+static inline bool nohz_kick_needed(struct rq *rq)
{
unsigned long now = jiffies;
struct sched_domain *sd;
struct sched_group_capacity *sgc;
int nr_busy, cpu = rq->cpu;
+ bool kick = false;
if (unlikely(rq->idle_balance))
- return 0;
+ return false;
/*
* We may be recently in ticked or tickless idle mode. At the first
@@ -7615,38 +7704,46 @@ static inline int nohz_kick_needed(struct rq *rq)
* balancing.
*/
if (likely(!atomic_read(&nohz.nr_cpus)))
- return 0;
+ return false;
if (time_before(now, nohz.next_balance))
- return 0;
+ return false;
if (rq->nr_running >= 2)
- goto need_kick;
+ return true;
rcu_read_lock();
sd = rcu_dereference(per_cpu(sd_busy, cpu));
-
if (sd) {
sgc = sd->groups->sgc;
nr_busy = atomic_read(&sgc->nr_busy_cpus);
- if (nr_busy > 1)
- goto need_kick_unlock;
+ if (nr_busy > 1) {
+ kick = true;
+ goto unlock;
+ }
+
}
- sd = rcu_dereference(per_cpu(sd_asym, cpu));
+ sd = rcu_dereference(rq->sd);
+ if (sd) {
+ if ((rq->cfs.h_nr_running >= 1) &&
+ check_cpu_capacity(rq, sd)) {
+ kick = true;
+ goto unlock;
+ }
+ }
+ sd = rcu_dereference(per_cpu(sd_asym, cpu));
if (sd && (cpumask_first_and(nohz.idle_cpus_mask,
- sched_domain_span(sd)) < cpu))
- goto need_kick_unlock;
-
- rcu_read_unlock();
- return 0;
+ sched_domain_span(sd)) < cpu)) {
+ kick = true;
+ goto unlock;
+ }
-need_kick_unlock:
+unlock:
rcu_read_unlock();
-need_kick:
- return 1;
+ return kick;
}
#else
static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) { }
@@ -7662,14 +7759,16 @@ static void run_rebalance_domains(struct softirq_action *h)
enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;
- rebalance_domains(this_rq, idle);
-
/*
* If this cpu has a pending nohz_balance_kick, then do the
* balancing on behalf of the other idle cpus whose ticks are
- * stopped.
+ * stopped. Do nohz_idle_balance *before* rebalance_domains to
+ * give the idle cpus a chance to load balance. Else we may
+ * load balance only within the local sched_domain hierarchy
+ * and abort nohz_idle_balance altogether if we pull some load.
*/
nohz_idle_balance(this_rq, idle);
+ rebalance_domains(this_rq, idle);
}
/*