>From the perspective of load-balance and shares distribution, throttled entities should be invisible. However, both of these operations work on 'active' lists and are not inherently aware of what group hierarchies may be present. In some cases this may be side-stepped (e.g. we could sideload via tg_load_down in load balance) while in others (e.g. update_shares()) it is more difficult to compute without incurring some O(n^2) costs. Instead, track hierarchicaal throttled state at time of transition. This allows us to easily identify whether an entity belongs to a throttled hierarchy and avoid incorrect interactions with it. Also, when an entity leaves a throttled hierarchy we need to advance its time averaging for shares averaging so that the elapsed throttled time is not considered as part of the cfs_rq's operation. We also use this information to prevent buddy interactions in the wakeup and yield_to() paths. Signed-off-by: Paul Turner Reviewed-by: Hidetoshi Seto --- kernel/sched.c | 2 - kernel/sched_fair.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 81 insertions(+), 8 deletions(-) Index: tip/kernel/sched_fair.c =================================================================== --- tip.orig/kernel/sched_fair.c +++ tip/kernel/sched_fair.c @@ -741,13 +741,15 @@ static void update_cfs_rq_load_contribut } } +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); + 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) + if (cfs_rq->tg == &root_task_group || throttled_hierarchy(cfs_rq)) return; now = rq_of(cfs_rq)->clock_task; @@ -1421,6 +1423,46 @@ static inline int cfs_rq_throttled(struc return cfs_rq->throttled; } +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return cfs_rq->throttle_count; +} + +struct tg_unthrottle_down_data { + int cpu; + u64 now; +}; + +static int tg_unthrottle_down(struct task_group *tg, void *data) +{ + struct tg_unthrottle_down_data *udd = data; + struct cfs_rq *cfs_rq = tg->cfs_rq[udd->cpu]; + u64 delta; + + cfs_rq->throttle_count--; + if (!cfs_rq->throttle_count) { + /* leaving throttled state, move up windows */ + delta = udd->now - cfs_rq->load_stamp; + cfs_rq->load_stamp += delta; + cfs_rq->load_last += delta; + } + + return 0; +} + +static int tg_throttle_down(struct task_group *tg, void *data) +{ + long cpu = (long)data; + struct cfs_rq *cfs_rq = tg->cfs_rq[cpu]; + + /* group is entering throttled state, record last load */ + if (!cfs_rq->throttle_count) + update_cfs_load(cfs_rq, 0); + cfs_rq->throttle_count++; + + return 0; +} + static void throttle_cfs_rq(struct cfs_rq *cfs_rq) { struct rq *rq = rq_of(cfs_rq); @@ -1431,7 +1473,10 @@ static void throttle_cfs_rq(struct cfs_r se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; /* account load preceding throttle */ - update_cfs_load(cfs_rq, 0); + rcu_read_lock(); + walk_tg_tree_from(cfs_rq->tg, tg_throttle_down, tg_nop, + (void *)(long)rq_of(cfs_rq)->cpu); + rcu_read_unlock(); task_delta = cfs_rq->h_nr_running; for_each_sched_entity(se) { @@ -1504,6 +1549,7 @@ static void unthrottle_cfs_rq(struct cfs struct sched_entity *se; int enqueue = 1; long task_delta; + struct tg_unthrottle_down_data udd; se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))]; @@ -1512,6 +1558,13 @@ static void unthrottle_cfs_rq(struct cfs list_del_rcu(&cfs_rq->throttled_list); raw_spin_unlock(&cfs_b->lock); + update_rq_clock(rq); + /* don't include throttled window for load statistics */ + udd.cpu = rq->cpu; + udd.now = rq->clock_task; + walk_tg_tree_from(cfs_rq->tg, tg_unthrottle_down, tg_nop, + (void *)&udd); + if (!cfs_rq->load.weight) return; @@ -1642,6 +1695,11 @@ static inline int cfs_rq_throttled(struc { return 0; } + +static inline int throttled_hierarchy(struct cfs_rq *cfs_rq) +{ + return 0; +} #endif /************************************************** @@ -2317,6 +2375,14 @@ static void check_preempt_wakeup(struct if (unlikely(se == pse)) return; + /* + * this is possible from callers such as pull_task(), where we + * unconditionally check_prempt_curr() after an enqueue (which may have + * lead to a throttle) + */ + if (unlikely(throttled_hierarchy(cfs_rq_of(pse)))) + return; + if (sched_feat(NEXT_BUDDY) && scale && !(wake_flags & WF_FORK)) { set_next_buddy(pse); next_buddy_marked = 1; @@ -2447,7 +2513,7 @@ static bool yield_to_task_fair(struct rq { struct sched_entity *se = &p->se; - if (!se->on_rq) + if (!se->on_rq || throttled_hierarchy(cfs_rq_of(se))) return false; /* Tell the scheduler that we'd really like pse to run next. */ @@ -2543,6 +2609,9 @@ move_one_task(struct rq *this_rq, int th int pinned = 0; for_each_leaf_cfs_rq(busiest, cfs_rq) { + if (throttled_hierarchy(cfs_rq)) + continue; + list_for_each_entry_safe(p, n, &cfs_rq->tasks, se.group_node) { if (!can_migrate_task(p, busiest, this_cpu, @@ -2635,8 +2704,10 @@ static int update_shares_cpu(struct task raw_spin_lock_irqsave(&rq->lock, flags); - update_rq_clock(rq); - update_cfs_load(cfs_rq, 1); + if (!throttled_hierarchy(cfs_rq)) { + update_rq_clock(rq); + update_cfs_load(cfs_rq, 1); + } /* * We need to update shares after updating tg->load_weight in @@ -2680,9 +2751,11 @@ load_balance_fair(struct rq *this_rq, in u64 rem_load, moved_load; /* - * empty group + * empty group or part of a throttled hierarchy */ - if (!busiest_cfs_rq->task_weight) + if (!busiest_cfs_rq->task_weight || + throttled_hierarchy(busiest_cfs_rq) || + throttled_hierarchy(tg->cfs_rq[this_cpu])) continue; rem_load = (u64)rem_load_move * busiest_weight; Index: tip/kernel/sched.c =================================================================== --- tip.orig/kernel/sched.c +++ tip/kernel/sched.c @@ -399,7 +399,7 @@ struct cfs_rq { u64 runtime_expires; s64 runtime_remaining; - int throttled; + int throttled, throttle_count; struct list_head throttled_list; #endif #endif