From 60daf9c19410604f08c99e146bc378c8a64f4ccd Mon Sep 17 00:00:00 2001 From: Patrick Bellasi Date: Fri, 21 Jun 2019 09:42:03 +0100 Subject: sched/uclamp: Add bucket local max tracking Because of bucketization, different task-specific clamp values are tracked in the same bucket. For example, with 20% bucket size and assuming to have: Task1: util_min=25% Task2: util_min=35% both tasks will be refcounted in the [20..39]% bucket and always boosted only up to 20% thus implementing a simple floor aggregation normally used in histograms. In systems with only few and well-defined clamp values, it would be useful to track the exact clamp value required by a task whenever possible. For example, if a system requires only 23% and 47% boost values then it's possible to track the exact boost required by each task using only 3 buckets of ~33% size each. Introduce a mechanism to max aggregate the requested clamp values of RUNNABLE tasks in the same bucket. Keep it simple by resetting the bucket value to its base value only when a bucket becomes inactive. Allow a limited and controlled overboosting margin for tasks recounted in the same bucket. In systems where the boost values are not known in advance, it is still possible to control the maximum acceptable overboosting margin by tuning the number of clamp groups. For example, 20 groups ensure a 5% maximum overboost. Remove the rq bucket initialization code since a correct bucket value is now computed when a task is refcounted into a CPU's rq. Signed-off-by: Patrick Bellasi Signed-off-by: Peter Zijlstra (Intel) Cc: Alessio Balsini Cc: Dietmar Eggemann Cc: Joel Fernandes Cc: Juri Lelli Cc: Linus Torvalds Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Quentin Perret Cc: Rafael J . Wysocki Cc: Steve Muckle Cc: Suren Baghdasaryan Cc: Tejun Heo Cc: Thomas Gleixner Cc: Todd Kjos Cc: Vincent Guittot Cc: Viresh Kumar Link: https://lkml.kernel.org/r/20190621084217.8167-3-patrick.bellasi@arm.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 43 +++++++++++++++++++++++++------------------ 1 file changed, 25 insertions(+), 18 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d8c1e67afd82..0a6eff8a278b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -785,6 +785,11 @@ static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) return clamp_value / UCLAMP_BUCKET_DELTA; } +static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) +{ + return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); +} + static inline unsigned int uclamp_none(int clamp_id) { if (clamp_id == UCLAMP_MIN) @@ -822,6 +827,11 @@ unsigned int uclamp_rq_max_value(struct rq *rq, unsigned int clamp_id) * When a task is enqueued on a rq, the clamp bucket currently defined by the * task's uclamp::bucket_id is refcounted on that rq. This also immediately * updates the rq's clamp value if required. + * + * Tasks can have a task-specific value requested from user-space, track + * within each bucket the maximum value for tasks refcounted in it. + * This "local max aggregation" allows to track the exact "requested" value + * for each bucket when all its RUNNABLE tasks require the same clamp. */ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, unsigned int clamp_id) @@ -835,8 +845,15 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p, bucket = &uc_rq->bucket[uc_se->bucket_id]; bucket->tasks++; + /* + * Local max aggregation: rq buckets always track the max + * "requested" clamp value of its RUNNABLE tasks. + */ + if (bucket->tasks == 1 || uc_se->value > bucket->value) + bucket->value = uc_se->value; + if (uc_se->value > READ_ONCE(uc_rq->value)) - WRITE_ONCE(uc_rq->value, bucket->value); + WRITE_ONCE(uc_rq->value, uc_se->value); } /* @@ -863,6 +880,12 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p, if (likely(bucket->tasks)) bucket->tasks--; + /* + * Keep "local max aggregation" simple and accept to (possibly) + * overboost some RUNNABLE tasks in the same bucket. + * The rq clamp bucket value is reset to its base value whenever + * there are no more RUNNABLE tasks refcounting it. + */ if (likely(bucket->tasks)) return; @@ -903,25 +926,9 @@ static void __init init_uclamp(void) unsigned int clamp_id; int cpu; - for_each_possible_cpu(cpu) { - struct uclamp_bucket *bucket; - struct uclamp_rq *uc_rq; - unsigned int bucket_id; - + for_each_possible_cpu(cpu) memset(&cpu_rq(cpu)->uclamp, 0, sizeof(struct uclamp_rq)); - for_each_clamp_id(clamp_id) { - uc_rq = &cpu_rq(cpu)->uclamp[clamp_id]; - - bucket_id = 1; - while (bucket_id < UCLAMP_BUCKETS) { - bucket = &uc_rq->bucket[bucket_id]; - bucket->value = bucket_id * UCLAMP_BUCKET_DELTA; - ++bucket_id; - } - } - } - for_each_clamp_id(clamp_id) { uclamp_se_set(&init_task.uclamp[clamp_id], uclamp_none(clamp_id)); -- cgit v1.2.3-55-g7522