Introduce account_cfs_rq_quota() to account bandwidth usage on the cfs_rq level versus task_groups for which bandwidth has been assigned. This is tracked by whether the local cfs_rq->quota_assigned is finite or infinite (RUNTIME_INF). For cfs_rq's that belong to a bandwidth constrained task_group we introduce tg_request_cfs_quota() which attempts to allocate quota from the global pool for use locally. Updates involving the global pool are currently protected under cfs_bandwidth->lock, local pools are protected by rq->lock. This patch only attempts to assign and track quota, no action is taken in the case that cfs_rq->quota_used exceeds cfs_rq->quota_assigned. Signed-off-by: Paul Turner Signed-off-by: Nikhil Rao Signed-off-by: Bharata B Rao --- include/linux/sched.h | 4 +++ kernel/sched_fair.c | 57 ++++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sysctl.c | 8 +++++++ 3 files changed, 69 insertions(+) Index: tip/kernel/sched_fair.c =================================================================== --- tip.orig/kernel/sched_fair.c +++ tip/kernel/sched_fair.c @@ -96,6 +96,15 @@ unsigned int __read_mostly sysctl_sched_ unsigned int sysctl_sched_cfs_bandwidth_consistent = 1; #endif +#ifdef CONFIG_CFS_BANDWIDTH +/* + * amount of quota to allocate from global tg to local cfs_rq pool on each + * refresh + * default: 5ms, units: microseconds + */ +unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + static const struct sched_class fair_sched_class; /************************************************************** @@ -312,6 +321,8 @@ find_matching_se(struct sched_entity **s #endif /* CONFIG_FAIR_GROUP_SCHED */ +static void account_cfs_rq_quota(struct cfs_rq *cfs_rq, + unsigned long delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -605,6 +616,8 @@ static void update_curr(struct cfs_rq *c cpuacct_charge(curtask, delta_exec); account_group_exec_runtime(curtask, delta_exec); } + + account_cfs_rq_quota(cfs_rq, delta_exec); } static inline void @@ -1276,6 +1289,47 @@ static inline u64 default_cfs_period(voi return 500000000ULL; } +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + +static void request_cfs_rq_quota(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; + + min_amount = sched_cfs_bandwidth_slice() + (-cfs_rq->quota_remaining); + + if (cfs_b->runtime > 0 || cfs_b->quota == RUNTIME_INF) { + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota != RUNTIME_INF) { + amount = min(cfs_b->runtime, min_amount); + cfs_b->runtime -= amount; + } else { + amount = min_amount; + } + raw_spin_unlock(&cfs_b->lock); + } + + cfs_rq->quota_remaining += amount; +} + +static void account_cfs_rq_quota(struct cfs_rq *cfs_rq, + unsigned long delta_exec) +{ + if (!cfs_rq->quota_enabled) + return; + + cfs_rq->quota_remaining -= delta_exec; + + if (cfs_rq->quota_remaining > 0) + return; + + request_cfs_rq_quota(cfs_rq); +} + static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) { return 1; @@ -1285,6 +1339,9 @@ static inline u64 default_cfs_period(voi { return 0; } + +static void account_cfs_rq_quota(struct cfs_rq *cfs_rq, + unsigned long delta_exec) {} #endif Index: tip/kernel/sysctl.c =================================================================== --- tip.orig/kernel/sysctl.c +++ tip/kernel/sysctl.c @@ -371,6 +371,14 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "sched_cfs_bandwidth_slice_us", + .data = &sysctl_sched_cfs_bandwidth_slice, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + }, #endif #ifdef CONFIG_SCHED_AUTOGROUP { Index: tip/include/linux/sched.h =================================================================== --- tip.orig/include/linux/sched.h +++ tip/include/linux/sched.h @@ -1951,6 +1951,10 @@ int sched_cfs_consistent_handler(struct loff_t *ppos); #endif +#ifdef CONFIG_CFS_BANDWIDTH +extern unsigned int sysctl_sched_cfs_bandwidth_slice; +#endif + #ifdef CONFIG_SCHED_AUTOGROUP extern unsigned int sysctl_sched_autogroup_enabled; -- 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/