diff options
author | Chris Redpath <chris.redpath@arm.com> | 2015-02-03 16:23:22 +0900 |
---|---|---|
committer | Seung-Woo Kim <sw0312.kim@samsung.com> | 2016-12-14 13:41:43 +0900 |
commit | c7ae8e3810adfb550179f0d269539f355afb3705 (patch) | |
tree | 2d97a069c285435c6d4292e09a47010ce61f426f /kernel | |
parent | 7a91f6f298353c007ce509f83ab742a80f56a180 (diff) |
HMP: Modify the runqueue stats to add a new child stat
The original intent here was to track unweighted runqueue load
with less resolution so we could use the least-recently-disturbed
runqueue to choose between 'closely related' load levels.
However, after experimenting with the resolution it turns out
that the following algorithm is highly beneficial for mobile
workloads.
In hmp_domain_min_load:
* If any CPU is zero, the overall load is zero
* If no CPUs are idle, the domain is 'fully loaded'
Additionally, the time since last migration count is used to
discriminate between idle CPUs.
Signed-off-by: Chris Redpath <chris.redpath@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Jon Medhurst <tixy@linaro.org>
[k.kozlowski: rebased on 4.1, no signed-off-by of previous committer]
Signed-off-by: Krzysztof Kozlowski <k.kozlowski@samsung.com>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/sched/core.c | 2 | ||||
-rw-r--r-- | kernel/sched/fair.c | 27 |
2 files changed, 17 insertions, 12 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2ef8640a66d7..7a00317cbd56 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1838,7 +1838,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) p->se.avg.load_avg_ratio = 1023; p->se.avg.load_avg_contrib = (1023 * scale_load_down(p->se.load.weight)); - p->se.avg.runnable_avg_period = LOAD_AVG_MAX; + p->se.avg.avg_period = LOAD_AVG_MAX; p->se.avg.runnable_avg_sum = LOAD_AVG_MAX; p->se.avg.usage_avg_sum = LOAD_AVG_MAX; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 9d8e20708bbf..041d45df7bfb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2869,7 +2869,6 @@ static inline void __update_group_entity_contrib(struct sched_entity *se) static inline void update_rq_runnable_avg(struct rq *rq, int runnable) { - u32 contrib; int cpu = -1; /* not used in normal case */ #ifdef CONFIG_HMP_FREQUENCY_INVARIANT_SCALE @@ -2878,9 +2877,7 @@ static inline void update_rq_runnable_avg(struct rq *rq, int runnable) __update_entity_runnable_avg(rq_clock_task(rq), cpu, &rq->avg, runnable, runnable); __update_tg_runnable_avg(&rq->avg, &rq->cfs); - contrib = rq->avg.runnable_avg_sum * scale_load_down(1024); - contrib /= (rq->avg.avg_period + 1); - trace_sched_rq_runnable_ratio(cpu_of(rq), scale_load(contrib)); + trace_sched_rq_runnable_ratio(cpu_of(rq), rq->avg.load_avg_ratio); trace_sched_rq_runnable_load(cpu_of(rq), rq->cfs.runnable_load_avg); } #else /* CONFIG_FAIR_GROUP_SCHED */ @@ -2908,9 +2905,10 @@ static inline void __update_task_entity_contrib(struct sched_entity *se) } /* Compute the current contribution to load_avg by se, return any delta */ -static long __update_entity_load_avg_contrib(struct sched_entity *se) +static long __update_entity_load_avg_contrib(struct sched_entity *se, long *ratio) { long old_contrib = se->avg.load_avg_contrib; + long old_ratio = se->avg.load_avg_ratio; if (entity_is_task(se)) { __update_task_entity_contrib(se); @@ -2919,6 +2917,8 @@ static long __update_entity_load_avg_contrib(struct sched_entity *se) __update_group_entity_contrib(se); } + if (ratio) + *ratio = se->avg.load_avg_ratio - old_ratio; return se->avg.load_avg_contrib - old_contrib; } @@ -2962,7 +2962,7 @@ 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, utilization_delta; + long contrib_delta, utilization_delta, ratio_delta; u64 now; int cpu = -1; /* not used in normal case */ @@ -2982,7 +2982,7 @@ static inline void update_entity_load_avg(struct sched_entity *se, cfs_rq->curr == se)) return; - contrib_delta = __update_entity_load_avg_contrib(se); + contrib_delta = __update_entity_load_avg_contrib(se, &ratio_delta); utilization_delta = __update_entity_utilization_avg_contrib(se); if (!update_cfs_rq) @@ -2991,6 +2991,7 @@ static inline void update_entity_load_avg(struct sched_entity *se, if (se->on_rq) { cfs_rq->runnable_load_avg += contrib_delta; cfs_rq->utilization_load_avg += utilization_delta; + rq_of(cfs_rq)->avg.load_avg_ratio += ratio_delta; } else { subtract_blocked_load_contrib(cfs_rq, -contrib_delta); } @@ -3069,6 +3070,7 @@ 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); } @@ -3088,6 +3090,7 @@ static inline void dequeue_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; + if (sleep) { cfs_rq->blocked_load_avg += se->avg.load_avg_contrib; se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); @@ -5459,15 +5462,15 @@ static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd, unsigned long contrib, scaled_contrib; struct sched_avg *avg; - for_each_cpu_mask(cpu, hmpd->cpus) { + for_each_cpu(cpu, &hmpd->cpus) { avg = &cpu_rq(cpu)->avg; /* used for both up and down migration */ curr_last_migration = avg->hmp_last_up_migration ? avg->hmp_last_up_migration : avg->hmp_last_down_migration; /* don't use the divisor in the loop, just at the end */ - contrib = avg->runnable_avg_sum * scale_load_down(1024); - scaled_contrib = contrib >> 22; + contrib = avg->load_avg_ratio * scale_load_down(1024); + scaled_contrib = contrib >> 13; if ((contrib < min_runnable_load) || (scaled_contrib == scaled_min_runnable_load && @@ -5490,7 +5493,9 @@ static inline unsigned int hmp_domain_min_load(struct hmp_domain *hmpd, *min_cpu = min_cpu_runnable_temp; /* domain will often have at least one empty CPU */ - return min_runnable_load ? min_runnable_load / (LOAD_AVG_MAX + 1) : 0; + trace_printk("hmp_domain_min_load returning %lu\n", + min_runnable_load > 1023 ? 1023 : min_runnable_load); + return min_runnable_load > 1023 ? 1023 : min_runnable_load; } /* |