diff options
Diffstat (limited to 'kernel/sched/fair.c')
| -rw-r--r-- | kernel/sched/fair.c | 145 |
1 files changed, 95 insertions, 50 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 4037e19bbca2..7b6535987500 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3020,9 +3020,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) /* * There are a few boundary cases this might miss but it should * get called often enough that that should (hopefully) not be - * a real problem -- added to that it only calls on the local - * CPU, so if we enqueue remotely we'll miss an update, but - * the next tick/schedule should update. + * a real problem. * * It will not get called when we go idle, because the idle * thread is a different class (!fair), nor will the utilization @@ -3091,8 +3089,6 @@ static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3) return c1 + c2 + c3; } -#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT) - /* * Accumulate the three separate parts of the sum; d1 the remainder * of the last (incomplete) period, d2 the span of full periods and d3 @@ -3122,7 +3118,7 @@ accumulate_sum(u64 delta, int cpu, struct sched_avg *sa, u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */ u64 periods; - scale_freq = arch_scale_freq_capacity(NULL, cpu); + scale_freq = arch_scale_freq_capacity(cpu); scale_cpu = arch_scale_cpu_capacity(NULL, cpu); delta += sa->period_contrib; @@ -3413,9 +3409,9 @@ void set_task_rq_fair(struct sched_entity *se, * _IFF_ we look at the pure running and runnable sums. Because they * represent the very same entity, just at different points in the hierarchy. * - * - * Per the above update_tg_cfs_util() is trivial (and still 'wrong') and - * simply copies the running sum over. + * Per the above update_tg_cfs_util() is trivial and simply copies the running + * sum over (but still wrong, because the group entity and group rq do not have + * their PELT windows aligned). * * However, update_tg_cfs_runnable() is more complex. So we have: * @@ -3424,11 +3420,11 @@ void set_task_rq_fair(struct sched_entity *se, * And since, like util, the runnable part should be directly transferable, * the following would _appear_ to be the straight forward approach: * - * grq->avg.load_avg = grq->load.weight * grq->avg.running_avg (3) + * grq->avg.load_avg = grq->load.weight * grq->avg.runnable_avg (3) * * And per (1) we have: * - * ge->avg.running_avg == grq->avg.running_avg + * ge->avg.runnable_avg == grq->avg.runnable_avg * * Which gives: * @@ -3447,27 +3443,28 @@ void set_task_rq_fair(struct sched_entity *se, * to (shortly) return to us. This only works by keeping the weights as * integral part of the sum. We therefore cannot decompose as per (3). * - * OK, so what then? + * Another reason this doesn't work is that runnable isn't a 0-sum entity. + * Imagine a rq with 2 tasks that each are runnable 2/3 of the time. Then the + * rq itself is runnable anywhere between 2/3 and 1 depending on how the + * runnable section of these tasks overlap (or not). If they were to perfectly + * align the rq as a whole would be runnable 2/3 of the time. If however we + * always have at least 1 runnable task, the rq as a whole is always runnable. * + * So we'll have to approximate.. :/ * - * Another way to look at things is: + * Given the constraint: * - * grq->avg.load_avg = \Sum se->avg.load_avg + * ge->avg.running_sum <= ge->avg.runnable_sum <= LOAD_AVG_MAX * - * Therefore, per (2): + * We can construct a rule that adds runnable to a rq by assuming minimal + * overlap. * - * grq->avg.load_avg = \Sum se->load.weight * se->avg.runnable_avg + * On removal, we'll assume each task is equally runnable; which yields: * - * And the very thing we're propagating is a change in that sum (someone - * joined/left). So we can easily know the runnable change, which would be, per - * (2) the already tracked se->load_avg divided by the corresponding - * se->weight. + * grq->avg.runnable_sum = grq->avg.load_sum / grq->load.weight * - * Basically (4) but in differential form: + * XXX: only do this for the part of runnable > running ? * - * d(runnable_avg) += se->avg.load_avg / se->load.weight - * (5) - * ge->avg.load_avg += ge->load.weight * d(runnable_avg) */ static inline void @@ -3479,6 +3476,14 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq if (!delta) return; + /* + * The relation between sum and avg is: + * + * LOAD_AVG_MAX - 1024 + sa->period_contrib + * + * however, the PELT windows are not aligned between grq and gse. + */ + /* Set new sched_entity's utilization */ se->avg.util_avg = gcfs_rq->avg.util_avg; se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX; @@ -3491,33 +3496,68 @@ update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq static inline void update_tg_cfs_runnable(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq) { - long runnable_sum = gcfs_rq->prop_runnable_sum; - long runnable_load_avg, load_avg; - s64 runnable_load_sum, load_sum; + long delta_avg, running_sum, runnable_sum = gcfs_rq->prop_runnable_sum; + unsigned long runnable_load_avg, load_avg; + u64 runnable_load_sum, load_sum = 0; + s64 delta_sum; if (!runnable_sum) return; gcfs_rq->prop_runnable_sum = 0; + if (runnable_sum >= 0) { + /* + * Add runnable; clip at LOAD_AVG_MAX. Reflects that until + * the CPU is saturated running == runnable. + */ + runnable_sum += se->avg.load_sum; + runnable_sum = min(runnable_sum, (long)LOAD_AVG_MAX); + } else { + /* + * Estimate the new unweighted runnable_sum of the gcfs_rq by + * assuming all tasks are equally runnable. + */ + if (scale_load_down(gcfs_rq->load.weight)) { + load_sum = div_s64(gcfs_rq->avg.load_sum, + scale_load_down(gcfs_rq->load.weight)); + } + + /* But make sure to not inflate se's runnable */ + runnable_sum = min(se->avg.load_sum, load_sum); + } + + /* + * runnable_sum can't be lower than running_sum + * As running sum is scale with cpu capacity wehreas the runnable sum + * is not we rescale running_sum 1st + */ + running_sum = se->avg.util_sum / + arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq))); + runnable_sum = max(runnable_sum, running_sum); + load_sum = (s64)se_weight(se) * runnable_sum; load_avg = div_s64(load_sum, LOAD_AVG_MAX); - add_positive(&se->avg.load_sum, runnable_sum); - add_positive(&se->avg.load_avg, load_avg); + delta_sum = load_sum - (s64)se_weight(se) * se->avg.load_sum; + delta_avg = load_avg - se->avg.load_avg; - add_positive(&cfs_rq->avg.load_avg, load_avg); - add_positive(&cfs_rq->avg.load_sum, load_sum); + se->avg.load_sum = runnable_sum; + se->avg.load_avg = load_avg; + add_positive(&cfs_rq->avg.load_avg, delta_avg); + add_positive(&cfs_rq->avg.load_sum, delta_sum); runnable_load_sum = (s64)se_runnable(se) * runnable_sum; runnable_load_avg = div_s64(runnable_load_sum, LOAD_AVG_MAX); + delta_sum = runnable_load_sum - se_weight(se) * se->avg.runnable_load_sum; + delta_avg = runnable_load_avg - se->avg.runnable_load_avg; - add_positive(&se->avg.runnable_load_sum, runnable_sum); - add_positive(&se->avg.runnable_load_avg, runnable_load_avg); + se->avg.runnable_load_sum = runnable_sum; + se->avg.runnable_load_avg = runnable_load_avg; if (se->on_rq) { - add_positive(&cfs_rq->avg.runnable_load_avg, runnable_load_avg); - add_positive(&cfs_rq->avg.runnable_load_sum, runnable_load_sum); + add_positive(&cfs_rq->avg.runnable_load_avg, delta_avg); + add_positive(&cfs_rq->avg.runnable_load_sum, delta_sum); } } @@ -4321,12 +4361,12 @@ static inline bool cfs_bandwidth_used(void) void cfs_bandwidth_usage_inc(void) { - static_key_slow_inc(&__cfs_bandwidth_used); + static_key_slow_inc_cpuslocked(&__cfs_bandwidth_used); } void cfs_bandwidth_usage_dec(void) { - static_key_slow_dec(&__cfs_bandwidth_used); + static_key_slow_dec_cpuslocked(&__cfs_bandwidth_used); } #else /* HAVE_JUMP_LABEL */ static bool cfs_bandwidth_used(void) @@ -5645,8 +5685,8 @@ static int wake_wide(struct task_struct *p) * soonest. For the purpose of speed we only consider the waking and previous * CPU. * - * wake_affine_idle() - only considers 'now', it check if the waking CPU is (or - * will be) idle. + * wake_affine_idle() - only considers 'now', it check if the waking CPU is + * cache-affine and is (or will be) idle. * * wake_affine_weight() - considers the weight to reflect the average * scheduling latency of the CPUs. This seems to work @@ -5657,7 +5697,13 @@ static bool wake_affine_idle(struct sched_domain *sd, struct task_struct *p, int this_cpu, int prev_cpu, int sync) { - if (idle_cpu(this_cpu)) + /* + * If this_cpu is idle, it implies the wakeup is from interrupt + * context. Only allow the move if cache is shared. Otherwise an + * interrupt intensive workload could force all tasks onto one + * node depending on the IO topology or IRQ affinity settings. + */ + if (idle_cpu(this_cpu) && cpus_share_cache(this_cpu, prev_cpu)) return true; if (sync && cpu_rq(this_cpu)->nr_running == 1) @@ -5721,12 +5767,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return affine; } -static inline int task_util(struct task_struct *p); -static int cpu_util_wake(int cpu, struct task_struct *p); +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) { - return capacity_orig_of(cpu) - cpu_util_wake(cpu, p); + return max_t(long, capacity_of(cpu) - cpu_util_wake(cpu, p), 0); } /* @@ -5906,7 +5952,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this } } else if (shallowest_idle_cpu == -1) { load = weighted_cpuload(cpu_rq(i)); - if (load < min_load || (load == min_load && i == this_cpu)) { + if (load < min_load) { min_load = load; least_loaded_cpu = i; } @@ -6203,7 +6249,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) * capacity_orig) as it useful for predicting the capacity required after task * migrations (scheduler-driven DVFS). */ -static int cpu_util(int cpu) +static unsigned long cpu_util(int cpu) { unsigned long util = cpu_rq(cpu)->cfs.avg.util_avg; unsigned long capacity = capacity_orig_of(cpu); @@ -6211,7 +6257,7 @@ static int cpu_util(int cpu) return (util >= capacity) ? capacity : util; } -static inline int task_util(struct task_struct *p) +static inline unsigned long task_util(struct task_struct *p) { return p->se.avg.util_avg; } @@ -6220,7 +6266,7 @@ static inline int task_util(struct task_struct *p) * cpu_util_wake: Compute cpu utilization with any contributions from * the waking task p removed. */ -static int cpu_util_wake(int cpu, struct task_struct *p) +static unsigned long cpu_util_wake(int cpu, struct task_struct *p) { unsigned long util, capacity; @@ -6405,8 +6451,7 @@ static void task_dead_fair(struct task_struct *p) } #endif /* CONFIG_SMP */ -static unsigned long -wakeup_gran(struct sched_entity *curr, struct sched_entity *se) +static unsigned long wakeup_gran(struct sched_entity *se) { unsigned long gran = sysctl_sched_wakeup_granularity; @@ -6448,7 +6493,7 @@ wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se) if (vdiff <= 0) return -1; - gran = wakeup_gran(curr, se); + gran = wakeup_gran(se); if (vdiff > gran) return 1; |