diff options
author | Paul Turner <pjt@google.com> | 2011-07-21 09:43:30 -0700 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2011-08-14 12:03:26 +0200 |
commit | ec12cb7f31e28854efae7dd6f9544e0a66379040 (patch) | |
tree | 30a7293a4f9d566043f524bb4c43d4ae8b0560db /kernel/sched_fair.c | |
parent | a790de99599a29ad3f18667530cf4b9f4b7e3234 (diff) | |
download | linux-rt-ec12cb7f31e28854efae7dd6f9544e0a66379040.tar.gz |
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 <pjt@google.com>
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184757.179386821@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'kernel/sched_fair.c')
-rw-r--r-- | kernel/sched_fair.c | 79 |
1 files changed, 77 insertions, 2 deletions
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 |