sched: Replace update_shares weight distribution with per-entity computation
Now that the machinery in place is in place to compute contributed load in a bottom up fashion; replace the shares distribution code within update_shares() accordingly. Signed-off-by: Paul Turner <pjt@google.com> Reviewed-by: Ben Segall <bsegall@google.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120823141507.061208672@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
f1b17280ef
commit
82958366cf
|
@ -218,14 +218,6 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
|
|||
SEQ_printf(m, " .%-30s: %ld\n", "load", cfs_rq->load.weight);
|
||||
#ifdef CONFIG_FAIR_GROUP_SCHED
|
||||
#ifdef CONFIG_SMP
|
||||
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_avg",
|
||||
SPLIT_NS(cfs_rq->load_avg));
|
||||
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "load_period",
|
||||
SPLIT_NS(cfs_rq->load_period));
|
||||
SEQ_printf(m, " .%-30s: %ld\n", "load_contrib",
|
||||
cfs_rq->load_contribution);
|
||||
SEQ_printf(m, " .%-30s: %d\n", "load_tg",
|
||||
atomic_read(&cfs_rq->tg->load_weight));
|
||||
SEQ_printf(m, " .%-30s: %lld\n", "runnable_load_avg",
|
||||
cfs_rq->runnable_load_avg);
|
||||
SEQ_printf(m, " .%-30s: %lld\n", "blocked_load_avg",
|
||||
|
|
|
@ -658,9 +658,6 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|||
return calc_delta_fair(sched_slice(cfs_rq, se), se);
|
||||
}
|
||||
|
||||
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update);
|
||||
static void update_cfs_shares(struct cfs_rq *cfs_rq);
|
||||
|
||||
/*
|
||||
* Update the current task's runtime statistics. Skip current tasks that
|
||||
* are not in our scheduling class.
|
||||
|
@ -680,10 +677,6 @@ __update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
|
|||
|
||||
curr->vruntime += delta_exec_weighted;
|
||||
update_min_vruntime(cfs_rq);
|
||||
|
||||
#if defined CONFIG_SMP && defined CONFIG_FAIR_GROUP_SCHED
|
||||
cfs_rq->load_unacc_exec_time += delta_exec;
|
||||
#endif
|
||||
}
|
||||
|
||||
static void update_curr(struct cfs_rq *cfs_rq)
|
||||
|
@ -806,72 +799,7 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
|
|||
}
|
||||
|
||||
#ifdef CONFIG_FAIR_GROUP_SCHED
|
||||
/* we need this in update_cfs_load and load-balance functions below */
|
||||
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
|
||||
# ifdef CONFIG_SMP
|
||||
static void update_cfs_rq_load_contribution(struct cfs_rq *cfs_rq,
|
||||
int global_update)
|
||||
{
|
||||
struct task_group *tg = cfs_rq->tg;
|
||||
long load_avg;
|
||||
|
||||
load_avg = div64_u64(cfs_rq->load_avg, cfs_rq->load_period+1);
|
||||
load_avg -= cfs_rq->load_contribution;
|
||||
|
||||
if (global_update || abs(load_avg) > cfs_rq->load_contribution / 8) {
|
||||
atomic_add(load_avg, &tg->load_weight);
|
||||
cfs_rq->load_contribution += load_avg;
|
||||
}
|
||||
}
|
||||
|
||||
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
|
||||
{
|
||||
u64 period = sysctl_sched_shares_window;
|
||||
u64 now, delta;
|
||||
unsigned long load = cfs_rq->load.weight;
|
||||
|
||||
if (cfs_rq->tg == &root_task_group || throttled_hierarchy(cfs_rq))
|
||||
return;
|
||||
|
||||
now = rq_of(cfs_rq)->clock_task;
|
||||
delta = now - cfs_rq->load_stamp;
|
||||
|
||||
/* truncate load history at 4 idle periods */
|
||||
if (cfs_rq->load_stamp > cfs_rq->load_last &&
|
||||
now - cfs_rq->load_last > 4 * period) {
|
||||
cfs_rq->load_period = 0;
|
||||
cfs_rq->load_avg = 0;
|
||||
delta = period - 1;
|
||||
}
|
||||
|
||||
cfs_rq->load_stamp = now;
|
||||
cfs_rq->load_unacc_exec_time = 0;
|
||||
cfs_rq->load_period += delta;
|
||||
if (load) {
|
||||
cfs_rq->load_last = now;
|
||||
cfs_rq->load_avg += delta * load;
|
||||
}
|
||||
|
||||
/* consider updating load contribution on each fold or truncate */
|
||||
if (global_update || cfs_rq->load_period > period
|
||||
|| !cfs_rq->load_period)
|
||||
update_cfs_rq_load_contribution(cfs_rq, global_update);
|
||||
|
||||
while (cfs_rq->load_period > period) {
|
||||
/*
|
||||
* Inline assembly required to prevent the compiler
|
||||
* optimising this loop into a divmod call.
|
||||
* See __iter_div_u64_rem() for another example of this.
|
||||
*/
|
||||
asm("" : "+rm" (cfs_rq->load_period));
|
||||
cfs_rq->load_period /= 2;
|
||||
cfs_rq->load_avg /= 2;
|
||||
}
|
||||
|
||||
if (!cfs_rq->curr && !cfs_rq->nr_running && !cfs_rq->load_avg)
|
||||
list_del_leaf_cfs_rq(cfs_rq);
|
||||
}
|
||||
|
||||
static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
|
||||
{
|
||||
long tg_weight;
|
||||
|
@ -881,8 +809,8 @@ static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
|
|||
* to gain a more accurate current total weight. See
|
||||
* update_cfs_rq_load_contribution().
|
||||
*/
|
||||
tg_weight = atomic_read(&tg->load_weight);
|
||||
tg_weight -= cfs_rq->load_contribution;
|
||||
tg_weight = atomic64_read(&tg->load_avg);
|
||||
tg_weight -= cfs_rq->tg_load_contrib;
|
||||
tg_weight += cfs_rq->load.weight;
|
||||
|
||||
return tg_weight;
|
||||
|
@ -906,27 +834,11 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
|
|||
|
||||
return shares;
|
||||
}
|
||||
|
||||
static void update_entity_shares_tick(struct cfs_rq *cfs_rq)
|
||||
{
|
||||
if (cfs_rq->load_unacc_exec_time > sysctl_sched_shares_window) {
|
||||
update_cfs_load(cfs_rq, 0);
|
||||
update_cfs_shares(cfs_rq);
|
||||
}
|
||||
}
|
||||
# else /* CONFIG_SMP */
|
||||
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
|
||||
{
|
||||
}
|
||||
|
||||
static inline long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
|
||||
{
|
||||
return tg->shares;
|
||||
}
|
||||
|
||||
static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
|
||||
{
|
||||
}
|
||||
# endif /* CONFIG_SMP */
|
||||
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
|
||||
unsigned long weight)
|
||||
|
@ -944,6 +856,8 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
|
|||
account_entity_enqueue(cfs_rq, se);
|
||||
}
|
||||
|
||||
static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
|
||||
|
||||
static void update_cfs_shares(struct cfs_rq *cfs_rq)
|
||||
{
|
||||
struct task_group *tg;
|
||||
|
@ -963,17 +877,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq)
|
|||
reweight_entity(cfs_rq_of(se), se, shares);
|
||||
}
|
||||
#else /* CONFIG_FAIR_GROUP_SCHED */
|
||||
static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
|
||||
{
|
||||
}
|
||||
|
||||
static inline void update_cfs_shares(struct cfs_rq *cfs_rq)
|
||||
{
|
||||
}
|
||||
|
||||
static inline void update_entity_shares_tick(struct cfs_rq *cfs_rq)
|
||||
{
|
||||
}
|
||||
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
|
@ -1490,7 +1396,6 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
|
|||
* Update run-time statistics of the 'current'.
|
||||
*/
|
||||
update_curr(cfs_rq);
|
||||
update_cfs_load(cfs_rq, 0);
|
||||
enqueue_entity_load_avg(cfs_rq, se, flags & ENQUEUE_WAKEUP);
|
||||
account_entity_enqueue(cfs_rq, se);
|
||||
update_cfs_shares(cfs_rq);
|
||||
|
@ -1587,7 +1492,6 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
|
|||
if (se != cfs_rq->curr)
|
||||
__dequeue_entity(cfs_rq, se);
|
||||
se->on_rq = 0;
|
||||
update_cfs_load(cfs_rq, 0);
|
||||
account_entity_dequeue(cfs_rq, se);
|
||||
|
||||
/*
|
||||
|
@ -1756,11 +1660,6 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
|
|||
update_entity_load_avg(curr, 1);
|
||||
update_cfs_rq_blocked_load(cfs_rq, 1);
|
||||
|
||||
/*
|
||||
* Update share accounting for long-running entities.
|
||||
*/
|
||||
update_entity_shares_tick(cfs_rq);
|
||||
|
||||
#ifdef CONFIG_SCHED_HRTICK
|
||||
/*
|
||||
* queued ticks are scheduled to match the slice, so don't bother
|
||||
|
@ -2005,18 +1904,9 @@ static int tg_unthrottle_up(struct task_group *tg, void *data)
|
|||
cfs_rq->throttle_count--;
|
||||
#ifdef CONFIG_SMP
|
||||
if (!cfs_rq->throttle_count) {
|
||||
u64 delta = rq->clock_task - cfs_rq->load_stamp;
|
||||
|
||||
/* leaving throttled state, advance shares averaging windows */
|
||||
cfs_rq->load_stamp += delta;
|
||||
cfs_rq->load_last += delta;
|
||||
|
||||
/* adjust cfs_rq_clock_task() */
|
||||
cfs_rq->throttled_clock_task_time += rq->clock_task -
|
||||
cfs_rq->throttled_clock_task;
|
||||
|
||||
/* update entity weight now that we are on_rq again */
|
||||
update_cfs_shares(cfs_rq);
|
||||
}
|
||||
#endif
|
||||
|
||||
|
@ -2028,11 +1918,9 @@ static int tg_throttle_down(struct task_group *tg, void *data)
|
|||
struct rq *rq = data;
|
||||
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
|
||||
|
||||
/* group is entering throttled state, record last load */
|
||||
if (!cfs_rq->throttle_count) {
|
||||
update_cfs_load(cfs_rq, 0);
|
||||
/* group is entering throttled state, stop time */
|
||||
if (!cfs_rq->throttle_count)
|
||||
cfs_rq->throttled_clock_task = rq->clock_task;
|
||||
}
|
||||
cfs_rq->throttle_count++;
|
||||
|
||||
return 0;
|
||||
|
@ -2630,7 +2518,6 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
|
|||
if (cfs_rq_throttled(cfs_rq))
|
||||
break;
|
||||
|
||||
update_cfs_load(cfs_rq, 0);
|
||||
update_cfs_shares(cfs_rq);
|
||||
update_entity_load_avg(se, 1);
|
||||
}
|
||||
|
@ -2692,7 +2579,6 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
|
|||
if (cfs_rq_throttled(cfs_rq))
|
||||
break;
|
||||
|
||||
update_cfs_load(cfs_rq, 0);
|
||||
update_cfs_shares(cfs_rq);
|
||||
update_entity_load_avg(se, 1);
|
||||
}
|
||||
|
@ -3755,27 +3641,36 @@ next:
|
|||
*/
|
||||
static int update_shares_cpu(struct task_group *tg, int cpu)
|
||||
{
|
||||
struct sched_entity *se;
|
||||
struct cfs_rq *cfs_rq;
|
||||
unsigned long flags;
|
||||
struct rq *rq;
|
||||
|
||||
if (!tg->se[cpu])
|
||||
return 0;
|
||||
|
||||
rq = cpu_rq(cpu);
|
||||
se = tg->se[cpu];
|
||||
cfs_rq = tg->cfs_rq[cpu];
|
||||
|
||||
raw_spin_lock_irqsave(&rq->lock, flags);
|
||||
|
||||
update_rq_clock(rq);
|
||||
update_cfs_load(cfs_rq, 1);
|
||||
update_cfs_rq_blocked_load(cfs_rq, 1);
|
||||
|
||||
/*
|
||||
* We need to update shares after updating tg->load_weight in
|
||||
* order to adjust the weight of groups with long running tasks.
|
||||
*/
|
||||
update_cfs_shares(cfs_rq);
|
||||
if (se) {
|
||||
update_entity_load_avg(se, 1);
|
||||
/*
|
||||
* We pivot on our runnable average having decayed to zero for
|
||||
* list removal. This generally implies that all our children
|
||||
* have also been removed (modulo rounding error or bandwidth
|
||||
* control); however, such cases are rare and we can fix these
|
||||
* at enqueue.
|
||||
*
|
||||
* TODO: fix up out-of-order children on enqueue.
|
||||
*/
|
||||
if (!se->avg.runnable_avg_sum && !cfs_rq->nr_running)
|
||||
list_del_leaf_cfs_rq(cfs_rq);
|
||||
} else {
|
||||
update_rq_runnable_avg(rq, rq->nr_running);
|
||||
}
|
||||
|
||||
raw_spin_unlock_irqrestore(&rq->lock, flags);
|
||||
|
||||
|
@ -5702,10 +5597,6 @@ void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq,
|
|||
|
||||
cfs_rq->tg = tg;
|
||||
cfs_rq->rq = rq;
|
||||
#ifdef CONFIG_SMP
|
||||
/* allow initial update_cfs_load() to truncate */
|
||||
cfs_rq->load_stamp = 1;
|
||||
#endif
|
||||
init_cfs_rq_runtime(cfs_rq);
|
||||
|
||||
tg->cfs_rq[cpu] = cfs_rq;
|
||||
|
|
|
@ -234,11 +234,21 @@ struct cfs_rq {
|
|||
u64 runnable_load_avg, blocked_load_avg;
|
||||
atomic64_t decay_counter, removed_load;
|
||||
u64 last_decay;
|
||||
|
||||
#ifdef CONFIG_FAIR_GROUP_SCHED
|
||||
u32 tg_runnable_contrib;
|
||||
u64 tg_load_contrib;
|
||||
#endif
|
||||
#endif
|
||||
#endif /* CONFIG_FAIR_GROUP_SCHED */
|
||||
|
||||
/*
|
||||
* h_load = weight * f(tg)
|
||||
*
|
||||
* Where f(tg) is the recursive weight fraction assigned to
|
||||
* this group.
|
||||
*/
|
||||
unsigned long h_load;
|
||||
#endif /* CONFIG_SMP */
|
||||
|
||||
#ifdef CONFIG_FAIR_GROUP_SCHED
|
||||
struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */
|
||||
|
||||
|
@ -254,28 +264,6 @@ struct cfs_rq {
|
|||
struct list_head leaf_cfs_rq_list;
|
||||
struct task_group *tg; /* group that "owns" this runqueue */
|
||||
|
||||
#ifdef CONFIG_SMP
|
||||
/*
|
||||
* h_load = weight * f(tg)
|
||||
*
|
||||
* Where f(tg) is the recursive weight fraction assigned to
|
||||
* this group.
|
||||
*/
|
||||
unsigned long h_load;
|
||||
|
||||
/*
|
||||
* Maintaining per-cpu shares distribution for group scheduling
|
||||
*
|
||||
* load_stamp is the last time we updated the load average
|
||||
* load_last is the last time we updated the load average and saw load
|
||||
* load_unacc_exec_time is currently unaccounted execution time
|
||||
*/
|
||||
u64 load_avg;
|
||||
u64 load_period;
|
||||
u64 load_stamp, load_last, load_unacc_exec_time;
|
||||
|
||||
unsigned long load_contribution;
|
||||
#endif /* CONFIG_SMP */
|
||||
#ifdef CONFIG_CFS_BANDWIDTH
|
||||
int runtime_enabled;
|
||||
u64 runtime_expires;
|
||||
|
|
Loading…
Reference in New Issue