From ec12cb7f31e28854efae7dd6f9544e0a66379040 Mon Sep 17 00:00:00 2001 From: Paul Turner Date: Thu, 21 Jul 2011 09:43:30 -0700 Subject: [PATCH] sched: Accumulate per-cfs_rq cpu usage and charge against bandwidth 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 Signed-off-by: Peter Zijlstra Link: http://lkml.kernel.org/r/20110721184757.179386821@google.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 +++ kernel/sched.c | 4 ++- kernel/sched_fair.c | 79 +++++++++++++++++++++++++++++++++++++++++-- kernel/sysctl.c | 10 ++++++ 4 files changed, 94 insertions(+), 3 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index 4ac2c0578e0f..bc6f5f2e24fa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2040,6 +2040,10 @@ static inline void sched_autogroup_fork(struct signal_struct *sig) { } 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); diff --git a/kernel/sched.c b/kernel/sched.c index ea6850d93b2a..35561c63a490 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -251,7 +251,7 @@ struct cfs_bandwidth { #ifdef CONFIG_CFS_BANDWIDTH raw_spinlock_t lock; ktime_t period; - u64 quota; + u64 quota, runtime; s64 hierarchal_quota; #endif }; @@ -407,6 +407,7 @@ static inline u64 default_cfs_period(void); 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()); } @@ -9107,6 +9108,7 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) raw_spin_lock_irq(&cfs_b->lock); cfs_b->period = ns_to_ktime(period); cfs_b->quota = quota; + cfs_b->runtime = quota; raw_spin_unlock_irq(&cfs_b->lock); for_each_possible_cpu(i) { diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index f24f4171019d..9502aa899f73 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -89,6 +89,20 @@ const_debug unsigned int sysctl_sched_migration_cost = 500000UL; */ 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; /************************************************************** @@ -292,6 +306,8 @@ find_matching_se(struct sched_entity **se, struct sched_entity **pse) #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: @@ -583,6 +599,8 @@ static void update_curr(struct cfs_rq *cfs_rq) cpuacct_charge(curtask, delta_exec); account_group_exec_runtime(curtask, delta_exec); } + + account_cfs_rq_runtime(cfs_rq, delta_exec); } static inline void @@ -1248,6 +1266,58 @@ static inline u64 default_cfs_period(void) { 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 as 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); +} + +static __always_inline void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) +{ + if (!cfs_rq->runtime_enabled) + return; + + __account_cfs_rq_runtime(cfs_rq, delta_exec); +} + +#else +static void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, + unsigned long delta_exec) {} #endif /************************************************** @@ -4266,8 +4336,13 @@ static void set_curr_task_fair(struct rq *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); + /* ensure bandwidth has been allocated on our new cfs_rq */ + account_cfs_rq_runtime(cfs_rq, 0); + } } #ifdef CONFIG_FAIR_GROUP_SCHED diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 11d65b531e50..2d2ecdcc8cdb 100644 --- a/kernel/sysctl.c +++ b/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",