Since quota is managed using a global state but consumed on a per-cpu basis we need to ensure that our per-cpu state is appropriately synchronized. Most importantly, runtime that is state (from a previous period) should not be locally consumable. We take advantage of existing sched_clock synchronization about the jiffy to efficiently detect whether we have (globally) crossed a quota boundary above. One catch is that the direction of spread on sched_clock is undefined, specifically, we don't know whether our local clock is behind or ahead of the one responsible for the current expiration time. Fortunately we can differentiate these by considering whether the global deadline has advanced. If it has not, then we assume our clock to be "fast" and advance our local expiration; otherwise, we know the deadline has truly passed and we expire our local runtime. Signed-off-by: Paul Turner Reviewed-by: Hidetoshi Seto --- kernel/sched.c | 4 +- kernel/sched_fair.c | 83 +++++++++++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 82 insertions(+), 5 deletions(-) Index: tip/kernel/sched_fair.c =================================================================== --- tip.orig/kernel/sched_fair.c +++ tip/kernel/sched_fair.c @@ -1294,11 +1294,30 @@ static inline u64 sched_cfs_bandwidth_sl return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; } +/* + * Replenish runtime according to assigned quota and update expiration time. + * We use sched_clock_cpu directly instead of rq->clock to avoid adding + * additional synchronization around rq->lock. + * + * requires cfs_b->lock + */ +static void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b) +{ + u64 now; + + if (cfs_b->quota == RUNTIME_INF) + return; + + now = sched_clock_cpu(smp_processor_id()); + cfs_b->runtime = cfs_b->quota; + cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period); +} + static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq) { struct task_group *tg = cfs_rq->tg; struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg); - u64 amount = 0, min_amount; + u64 amount = 0, min_amount, expires; /* note: this is a positive sum as runtime_remaining <= 0 */ min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; @@ -1307,9 +1326,16 @@ static void assign_cfs_rq_runtime(struct if (cfs_b->quota == RUNTIME_INF) amount = min_amount; else { - /* ensure bandwidth timer remains active under consumption */ - if (!cfs_b->timer_active) + /* + * If the bandwidth pool has become inactive, then at least one + * period must have elapsed since the last consumption. + * Refresh the global state and ensure bandwidth timer becomes + * active. + */ + if (!cfs_b->timer_active) { + __refill_cfs_bandwidth_runtime(cfs_b); __start_cfs_bandwidth(cfs_b); + } if (cfs_b->runtime > 0) { amount = min(cfs_b->runtime, min_amount); @@ -1317,9 +1343,51 @@ static void assign_cfs_rq_runtime(struct cfs_b->idle = 0; } } + expires = cfs_b->runtime_expires; raw_spin_unlock(&cfs_b->lock); cfs_rq->runtime_remaining += amount; + /* + * we may have advanced our local expiration to account for allowed + * spread between our sched_clock and the one on which runtime was + * issued. + */ + if ((s64)(expires - cfs_rq->runtime_expires) > 0) + cfs_rq->runtime_expires = expires; +} + +/* + * Note: This depends on the synchronization provided by sched_clock and the + * fact that rq->clock snapshots this value. + */ +static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) +{ + struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); + struct rq *rq = rq_of(cfs_rq); + + if (cfs_rq->runtime_remaining < 0) + return; + + /* if the deadline is ahead of our clock, nothing to do */ + if ((s64)(rq->clock - cfs_rq->runtime_expires) < 0) + return; + + /* + * If the local deadline has passed we have to consider the + * possibility that our sched_clock is 'fast' and the global deadline + * has not truly expired. + * + * Fortunately we can check determine whether this the case by checking + * whether the global deadline has advanced. + */ + + if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) { + /* extend local deadline, drift is bounded above by 2 ticks */ + cfs_rq->runtime_expires += TICK_NSEC; + } else { + /* global deadline is ahead, expiration has passed */ + cfs_rq->runtime_remaining = 0; + } } static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, @@ -1328,7 +1396,10 @@ static void account_cfs_rq_runtime(struc if (!cfs_rq->runtime_enabled) return; + /* dock delta_exec before expiring quota (as it could span periods) */ cfs_rq->runtime_remaining -= delta_exec; + expire_cfs_rq_runtime(cfs_rq); + if (cfs_rq->runtime_remaining > 0) return; @@ -1351,7 +1422,11 @@ static int do_sched_cfs_period_timer(str goto out_unlock; idle = cfs_b->idle; - cfs_b->runtime = cfs_b->quota; + /* if we're going inactive then everything else can be deferred */ + if (idle) + goto out_unlock; + + __refill_cfs_bandwidth_runtime(cfs_b); /* mark as potentially idle for the upcoming period */ cfs_b->idle = 1; Index: tip/kernel/sched.c =================================================================== --- tip.orig/kernel/sched.c +++ tip/kernel/sched.c @@ -253,6 +253,7 @@ struct cfs_bandwidth { ktime_t period; u64 quota, runtime; s64 hierarchal_quota; + u64 runtime_expires; int idle, timer_active; struct hrtimer period_timer; @@ -393,6 +394,7 @@ struct cfs_rq { #endif #ifdef CONFIG_CFS_BANDWIDTH int runtime_enabled; + u64 runtime_expires; s64 runtime_remaining; #endif #endif @@ -8979,8 +8981,8 @@ static int tg_set_cfs_bandwidth(struct t raw_spin_lock_irq(&cfs_b->lock); cfs_b->period = ns_to_ktime(period); cfs_b->quota = quota; - cfs_b->runtime = quota; + __refill_cfs_bandwidth_runtime(cfs_b); /* restart the period timer (if active) to handle new period expiry */ if (runtime_enabled && cfs_b->timer_active) { /* force a reprogram */ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/