Account bandwidth usage on the cfs_rq level versus the task_groups to which they belong. Whether we are tracking bandwidth on a given cfs_rq is maintained under cfs_rq->runtime_enabled. cfs_rq's which belong to a bandwidth constrained task_group have their runtime accounted via the update_curr() path, which withdraws bandwidth from the global pool as desired. Updates involving the global pool are currently protected under cfs_bandwidth->lock, local runtime is protected by rq->lock. This patch only assigns and tracks quota, no action is taken in the case that cfs_rq->runtime_used exceeds cfs_rq->runtime_assigned. Signed-off-by: Paul Turner Signed-off-by: Nikhil Rao Signed-off-by: Bharata B Rao Reviewed-by: Hidetoshi Seto --- include/linux/sched.h | 4 ++ kernel/sched.c | 3 +- kernel/sched_fair.c | 72 ++++++++++++++++++++++++++++++++++++++++++++++++-- kernel/sysctl.c | 10 ++++++ 4 files changed, 86 insertions(+), 3 deletions(-) Index: tip/kernel/sched_fair.c =================================================================== --- tip.orig/kernel/sched_fair.c +++ tip/kernel/sched_fair.c @@ -89,6 +89,20 @@ const_debug unsigned int sysctl_sched_mi */ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; +#ifdef CONFIG_CFS_BANDWIDTH +/* + * Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool + * each time a cfs_rq requests quota. + * + * Note: in the case that the slice exceeds the runtime remaining (either due + * to consumption or the quota being specified to be smaller than the slice) + * we will always only issue the remaining available time. + * + * default: 5 msec, units: microseconds + */ +unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; +#endif + static const struct sched_class fair_sched_class; /************************************************************** @@ -305,6 +319,8 @@ find_matching_se(struct sched_entity **s #endif /* CONFIG_FAIR_GROUP_SCHED */ +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec); /************************************************************** * Scheduling class tree data structure manipulation methods: @@ -602,6 +618,8 @@ static void update_curr(struct cfs_rq *c cpuacct_charge(curtask, delta_exec); account_group_exec_runtime(curtask, delta_exec); } + + account_cfs_rq_runtime(cfs_rq, delta_exec); } static inline void @@ -1270,6 +1288,48 @@ static inline u64 default_cfs_period(voi { return 100000000ULL; } + +static inline u64 sched_cfs_bandwidth_slice(void) +{ + return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC; +} + +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; + + /* note: this is a positive sum, runtime_remaining <= 0 */ + min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining; + + raw_spin_lock(&cfs_b->lock); + if (cfs_b->quota == RUNTIME_INF) + amount = min_amount; + else if (cfs_b->runtime > 0) { + amount = min(cfs_b->runtime, min_amount); + cfs_b->runtime -= amount; + } + raw_spin_unlock(&cfs_b->lock); + + cfs_rq->runtime_remaining += amount; +} + +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) +{ + if (!cfs_rq->runtime_enabled) + return; + + cfs_rq->runtime_remaining -= delta_exec; + if (cfs_rq->runtime_remaining > 0) + return; + + assign_cfs_rq_runtime(cfs_rq); +} +#else +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) {} #endif /************************************************** @@ -4264,8 +4324,16 @@ static void set_curr_task_fair(struct rq { struct sched_entity *se = &rq->curr->se; - for_each_sched_entity(se) - set_next_entity(cfs_rq_of(se), se); + for_each_sched_entity(se) { + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + set_next_entity(cfs_rq, se); + /* + * if bandwidth is enabled, make sure it is up-to-date or + * reschedule for the case of a move into a throttled cpu. + */ + account_cfs_rq_runtime(cfs_rq, 0); + } } #ifdef CONFIG_FAIR_GROUP_SCHED Index: tip/kernel/sysctl.c =================================================================== --- tip.orig/kernel/sysctl.c +++ tip/kernel/sysctl.c @@ -379,6 +379,16 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .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_PROVE_LOCKING { .procname = "prove_locking", Index: tip/kernel/sched.c =================================================================== --- tip.orig/kernel/sched.c +++ tip/kernel/sched.c @@ -248,7 +248,7 @@ struct cfs_bandwidth { #ifdef CONFIG_CFS_BANDWIDTH raw_spinlock_t lock; ktime_t period; - u64 quota; + u64 quota, runtime; s64 hierarchal_quota; #endif }; @@ -403,6 +403,7 @@ static inline u64 default_cfs_period(voi static void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b) { raw_spin_lock_init(&cfs_b->lock); + cfs_b->runtime = 0; cfs_b->quota = RUNTIME_INF; cfs_b->period = ns_to_ktime(default_cfs_period()); } Index: tip/include/linux/sched.h =================================================================== --- tip.orig/include/linux/sched.h +++ tip/include/linux/sched.h @@ -2012,6 +2012,10 @@ static inline void sched_autogroup_fork( static inline void sched_autogroup_exit(struct signal_struct *sig) { } #endif +#ifdef CONFIG_CFS_BANDWIDTH +extern unsigned int sysctl_sched_cfs_bandwidth_slice; +#endif + #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio);