Re: [CFS Bandwidth Control v4 1/7] sched: introduce primitives to account for CFS bandwidth tracking

[Balbir Singh <balbir@linux.vnet.ibm.com>]

* Paul Turner <pjt@google.com> [2011-02-15 19:18:32]:

> In this patch we introduce the notion of CFS bandwidth, to account for the
> realities of SMP this is partitioned into globally unassigned bandwidth, and
> locally claimed bandwidth:
> - The global bandwidth is per task_group, it represents a pool of unclaimed
>   bandwidth that cfs_rq's can allocate from.  It uses the new cfs_bandwidth
>   structure.
> - The local bandwidth is tracked per-cfs_rq, this represents allotments from
>   the global pool
>   bandwidth assigned to a task_group, this is tracked using the
>   new cfs_bandwidth structure.
> 
> Bandwidth is managed via cgroupfs via two new files in the cpu subsystem:
> - cpu.cfs_period_us : the bandwidth period in usecs
> - cpu.cfs_quota_us : the cpu bandwidth (in usecs) that this tg will be allowed
>   to consume over period above.
> 
> A per-cfs_bandwidth timer is also introduced to handle future refresh at
> period expiration.  There's some minor refactoring here so that
> start_bandwidth_timer() functionality can be shared
> 
> 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>
> ---

Looks good, minor nits below


Acked-by: Balbir Singh <balbir@linux.vnet.ibm.com>
 

>  init/Kconfig        |    9 +
>  kernel/sched.c      |  264 +++++++++++++++++++++++++++++++++++++++++++++++-----
>  kernel/sched_fair.c |   19 +++
>  3 files changed, 269 insertions(+), 23 deletions(-)
> 
> Index: tip/init/Kconfig
> ===================================================================
> --- tip.orig/init/Kconfig
> +++ tip/init/Kconfig
> @@ -698,6 +698,15 @@ config FAIR_GROUP_SCHED
>  	depends on CGROUP_SCHED
>  	default CGROUP_SCHED
> 
> +config CFS_BANDWIDTH
> +	bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
> +	depends on EXPERIMENTAL
> +	depends on FAIR_GROUP_SCHED
> +	default n
> +	help
> +	  This option allows users to define quota and period for cpu
> +	  bandwidth provisioning on a per-cgroup basis.
> +
>  config RT_GROUP_SCHED
>  	bool "Group scheduling for SCHED_RR/FIFO"
>  	depends on EXPERIMENTAL
> Index: tip/kernel/sched.c
> ===================================================================
> --- tip.orig/kernel/sched.c
> +++ tip/kernel/sched.c
> @@ -194,10 +194,28 @@ static inline int rt_bandwidth_enabled(v
>  	return sysctl_sched_rt_runtime >= 0;
>  }
> 
> -static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
> +static void start_bandwidth_timer(struct hrtimer *period_timer, ktime_t period)
>  {
> -	ktime_t now;
> +	unsigned long delta;
> +	ktime_t soft, hard, now;
> +
> +	for (;;) {
> +		if (hrtimer_active(period_timer))
> +			break;
> 
> +		now = hrtimer_cb_get_time(period_timer);
> +		hrtimer_forward(period_timer, now, period);
> +
> +		soft = hrtimer_get_softexpires(period_timer);
> +		hard = hrtimer_get_expires(period_timer);
> +		delta = ktime_to_ns(ktime_sub(hard, soft));
> +		__hrtimer_start_range_ns(period_timer, soft, delta,
> +					 HRTIMER_MODE_ABS_PINNED, 0);
> +	}
> +}
> +
> +static void start_rt_bandwidth(struct rt_bandwidth *rt_b)
> +{
>  	if (!rt_bandwidth_enabled() || rt_b->rt_runtime == RUNTIME_INF)
>  		return;
> 
> @@ -205,22 +223,7 @@ static void start_rt_bandwidth(struct rt
>  		return;
> 
>  	raw_spin_lock(&rt_b->rt_runtime_lock);
> -	for (;;) {
> -		unsigned long delta;
> -		ktime_t soft, hard;
> -
> -		if (hrtimer_active(&rt_b->rt_period_timer))
> -			break;
> -
> -		now = hrtimer_cb_get_time(&rt_b->rt_period_timer);
> -		hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period);
> -
> -		soft = hrtimer_get_softexpires(&rt_b->rt_period_timer);
> -		hard = hrtimer_get_expires(&rt_b->rt_period_timer);
> -		delta = ktime_to_ns(ktime_sub(hard, soft));
> -		__hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta,
> -				HRTIMER_MODE_ABS_PINNED, 0);
> -	}
> +	start_bandwidth_timer(&rt_b->rt_period_timer, rt_b->rt_period);
>  	raw_spin_unlock(&rt_b->rt_runtime_lock);
>  }
> 
> @@ -245,6 +248,15 @@ struct cfs_rq;
> 
>  static LIST_HEAD(task_groups);
> 
> +#ifdef CONFIG_CFS_BANDWIDTH
> +struct cfs_bandwidth {
> +	raw_spinlock_t		lock;
> +	ktime_t			period;
> +	u64			runtime, quota;
> +	struct hrtimer		period_timer;
> +};
> +#endif
> +
>  /* task group related information */
>  struct task_group {
>  	struct cgroup_subsys_state css;
> @@ -276,6 +288,10 @@ struct task_group {
>  #ifdef CONFIG_SCHED_AUTOGROUP
>  	struct autogroup *autogroup;
>  #endif
> +
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	struct cfs_bandwidth cfs_bandwidth;
> +#endif
>  };
> 
>  /* task_group_lock serializes the addition/removal of task groups */
> @@ -370,9 +386,76 @@ struct cfs_rq {
> 
>  	unsigned long load_contribution;
>  #endif
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	u64 quota_assigned, quota_used;
> +#endif
>  #endif
>  };
> 
> +#ifdef CONFIG_CFS_BANDWIDTH
> +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun);
> +
> +static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
> +{
> +	struct cfs_bandwidth *cfs_b =
> +		container_of(timer, struct cfs_bandwidth, period_timer);
> +	ktime_t now;
> +	int overrun;
> +	int idle = 0;
> +
> +	for (;;) {
> +		now = hrtimer_cb_get_time(timer);
> +		overrun = hrtimer_forward(timer, now, cfs_b->period);
> +
> +		if (!overrun)
> +			break;
> +
> +		idle = do_sched_cfs_period_timer(cfs_b, overrun);

This patch just sets up to return do_sched_cfs_period_timer to return
1. I am afraid I don't understand why this function is introduced
here.

> +	}
> +
> +	return idle ? HRTIMER_NORESTART : HRTIMER_RESTART;
> +}
> +
> +static
> +void init_cfs_bandwidth(struct cfs_bandwidth *cfs_b, u64 quota, u64 period)
> +{
> +	raw_spin_lock_init(&cfs_b->lock);
> +	cfs_b->quota = cfs_b->runtime = quota;
> +	cfs_b->period = ns_to_ktime(period);
> +
> +	hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
> +	cfs_b->period_timer.function = sched_cfs_period_timer;
> +}
> +
> +static
> +void init_cfs_rq_quota(struct cfs_rq *cfs_rq)
> +{
> +	cfs_rq->quota_used = 0;
> +	if (cfs_rq->tg->cfs_bandwidth.quota == RUNTIME_INF)
> +		cfs_rq->quota_assigned = RUNTIME_INF;
> +	else
> +		cfs_rq->quota_assigned = 0;
> +}
> +
> +static void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
> +{
> +	if (cfs_b->quota == RUNTIME_INF)
> +		return;
> +
> +	if (hrtimer_active(&cfs_b->period_timer))
> +		return;
> +
> +	raw_spin_lock(&cfs_b->lock);
> +	start_bandwidth_timer(&cfs_b->period_timer, cfs_b->period);
> +	raw_spin_unlock(&cfs_b->lock);
> +}
> +
> +static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
> +{
> +	hrtimer_cancel(&cfs_b->period_timer);
> +}
> +#endif
> +
>  /* Real-Time classes' related field in a runqueue: */
>  struct rt_rq {
>  	struct rt_prio_array active;
> @@ -8038,6 +8121,9 @@ static void init_tg_cfs_entry(struct tas
>  	tg->cfs_rq[cpu] = cfs_rq;
>  	init_cfs_rq(cfs_rq, rq);
>  	cfs_rq->tg = tg;
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	init_cfs_rq_quota(cfs_rq);
> +#endif
> 
>  	tg->se[cpu] = se;
>  	/* se could be NULL for root_task_group */
> @@ -8173,6 +8259,10 @@ void __init sched_init(void)
>  		 * We achieve this by letting root_task_group's tasks sit
>  		 * directly in rq->cfs (i.e root_task_group->se[] = NULL).
>  		 */
> +#ifdef CONFIG_CFS_BANDWIDTH
> +		init_cfs_bandwidth(&root_task_group.cfs_bandwidth,
> +				RUNTIME_INF, sched_cfs_bandwidth_period);
> +#endif
>  		init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
>  #endif /* CONFIG_FAIR_GROUP_SCHED */
> 
> @@ -8415,6 +8505,10 @@ static void free_fair_sched_group(struct
>  {
>  	int i;
> 
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	destroy_cfs_bandwidth(&tg->cfs_bandwidth);
> +#endif
> +
>  	for_each_possible_cpu(i) {
>  		if (tg->cfs_rq)
>  			kfree(tg->cfs_rq[i]);
> @@ -8442,7 +8536,10 @@ int alloc_fair_sched_group(struct task_g
>  		goto err;
> 
>  	tg->shares = NICE_0_LOAD;
> -
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	init_cfs_bandwidth(&tg->cfs_bandwidth, RUNTIME_INF,
> +			sched_cfs_bandwidth_period);
> +#endif
>  	for_each_possible_cpu(i) {
>  		rq = cpu_rq(i);
> 
> @@ -8822,7 +8919,7 @@ static int __rt_schedulable(struct task_
>  	return walk_tg_tree(tg_schedulable, tg_nop, &data);
>  }
> 
> -static int tg_set_bandwidth(struct task_group *tg,
> +static int tg_set_rt_bandwidth(struct task_group *tg,
>  		u64 rt_period, u64 rt_runtime)
>  {
>  	int i, err = 0;
> @@ -8861,7 +8958,7 @@ int sched_group_set_rt_runtime(struct ta
>  	if (rt_runtime_us < 0)
>  		rt_runtime = RUNTIME_INF;
> 
> -	return tg_set_bandwidth(tg, rt_period, rt_runtime);
> +	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
>  }
> 
>  long sched_group_rt_runtime(struct task_group *tg)
> @@ -8886,7 +8983,7 @@ int sched_group_set_rt_period(struct tas
>  	if (rt_period == 0)
>  		return -EINVAL;
> 
> -	return tg_set_bandwidth(tg, rt_period, rt_runtime);
> +	return tg_set_rt_bandwidth(tg, rt_period, rt_runtime);
>  }
> 
>  long sched_group_rt_period(struct task_group *tg)
> @@ -9107,6 +9204,116 @@ static u64 cpu_shares_read_u64(struct cg
> 
>  	return (u64) tg->shares;
>  }
> +
> +#ifdef CONFIG_CFS_BANDWIDTH
> +static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
> +{
> +	int i;
> +	static DEFINE_MUTEX(mutex);
> +
> +	if (tg == &root_task_group)
> +		return -EINVAL;
> +
> +	if (!period)
> +		return -EINVAL;
> +
> +	/*
> +	 * Ensure we have at least one tick of bandwidth every period.  This is
> +	 * to prevent reaching a state of large arrears when throttled via
> +	 * entity_tick() resulting in prolonged exit starvation.
> +	 */
> +	if (NS_TO_JIFFIES(quota) < 1)
> +		return -EINVAL;
> +
> +	mutex_lock(&mutex);
> +	raw_spin_lock_irq(&tg->cfs_bandwidth.lock);
> +	tg->cfs_bandwidth.period = ns_to_ktime(period);
> +	tg->cfs_bandwidth.runtime = tg->cfs_bandwidth.quota = quota;
> +	raw_spin_unlock_irq(&tg->cfs_bandwidth.lock);
> +
> +	for_each_possible_cpu(i) {

Why for each possible cpu - to avoid hotplug handling?

> +		struct cfs_rq *cfs_rq = tg->cfs_rq[i];
> +		struct rq *rq = rq_of(cfs_rq);
> +
> +		raw_spin_lock_irq(&rq->lock);
> +		init_cfs_rq_quota(cfs_rq);
> +		raw_spin_unlock_irq(&rq->lock);
> +	}
> +	mutex_unlock(&mutex);
> +
> +	return 0;
> +}
> +
> +int tg_set_cfs_quota(struct task_group *tg, long cfs_runtime_us)
> +{
> +	u64 quota, period;
> +
> +	period = ktime_to_ns(tg->cfs_bandwidth.period);
> +	if (cfs_runtime_us < 0)
> +		quota = RUNTIME_INF;
> +	else
> +		quota = (u64)cfs_runtime_us * NSEC_PER_USEC;
> +
> +	return tg_set_cfs_bandwidth(tg, period, quota);
> +}
> +
> +long tg_get_cfs_quota(struct task_group *tg)
> +{
> +	u64 quota_us;
> +
> +	if (tg->cfs_bandwidth.quota == RUNTIME_INF)
> +		return -1;
> +
> +	quota_us = tg->cfs_bandwidth.quota;
> +	do_div(quota_us, NSEC_PER_USEC);
> +	return quota_us;
> +}
> +
> +int tg_set_cfs_period(struct task_group *tg, long cfs_period_us)
> +{
> +	u64 quota, period;
> +
> +	period = (u64)cfs_period_us * NSEC_PER_USEC;
> +	quota = tg->cfs_bandwidth.quota;
> +
> +	if (period <= 0)
> +		return -EINVAL;
> +
> +	return tg_set_cfs_bandwidth(tg, period, quota);
> +}
> +
> +long tg_get_cfs_period(struct task_group *tg)
> +{
> +	u64 cfs_period_us;
> +
> +	cfs_period_us = ktime_to_ns(tg->cfs_bandwidth.period);
> +	do_div(cfs_period_us, NSEC_PER_USEC);
> +	return cfs_period_us;
> +}
> +
> +static s64 cpu_cfs_quota_read_s64(struct cgroup *cgrp, struct cftype *cft)
> +{
> +	return tg_get_cfs_quota(cgroup_tg(cgrp));
> +}
> +
> +static int cpu_cfs_quota_write_s64(struct cgroup *cgrp, struct cftype *cftype,
> +				s64 cfs_quota_us)
> +{
> +	return tg_set_cfs_quota(cgroup_tg(cgrp), cfs_quota_us);
> +}
> +
> +static u64 cpu_cfs_period_read_u64(struct cgroup *cgrp, struct cftype *cft)
> +{
> +	return tg_get_cfs_period(cgroup_tg(cgrp));
> +}
> +
> +static int cpu_cfs_period_write_u64(struct cgroup *cgrp, struct cftype *cftype,
> +				u64 cfs_period_us)
> +{
> +	return tg_set_cfs_period(cgroup_tg(cgrp), cfs_period_us);
> +}
> +
> +#endif /* CONFIG_CFS_BANDWIDTH */
>  #endif /* CONFIG_FAIR_GROUP_SCHED */
> 
>  #ifdef CONFIG_RT_GROUP_SCHED
> @@ -9141,6 +9348,18 @@ static struct cftype cpu_files[] = {
>  		.write_u64 = cpu_shares_write_u64,
>  	},
>  #endif
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	{
> +		.name = "cfs_quota_us",
> +		.read_s64 = cpu_cfs_quota_read_s64,
> +		.write_s64 = cpu_cfs_quota_write_s64,
> +	},
> +	{
> +		.name = "cfs_period_us",
> +		.read_u64 = cpu_cfs_period_read_u64,
> +		.write_u64 = cpu_cfs_period_write_u64,
> +	},
> +#endif
>  #ifdef CONFIG_RT_GROUP_SCHED
>  	{
>  		.name = "rt_runtime_us",
> @@ -9450,4 +9669,3 @@ struct cgroup_subsys cpuacct_subsys = {
>  	.subsys_id = cpuacct_subsys_id,
>  };
>  #endif	/* CONFIG_CGROUP_CPUACCT */
> -
> Index: tip/kernel/sched_fair.c
> ===================================================================
> --- tip.orig/kernel/sched_fair.c
> +++ tip/kernel/sched_fair.c
> @@ -88,6 +88,15 @@ const_debug unsigned int sysctl_sched_mi
>   */
>  unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
> 
> +
> +#ifdef CONFIG_CFS_BANDWIDTH
> +/*
> + * default period for cfs group bandwidth.
> + * default: 0.5s, units: nanoseconds
> + */
> +static u64 sched_cfs_bandwidth_period = 500000000ULL;
> +#endif
> +
>  static const struct sched_class fair_sched_class;
> 
>  /**************************************************************
> @@ -397,6 +406,9 @@ static void __enqueue_entity(struct cfs_
> 
>  	rb_link_node(&se->run_node, parent, link);
>  	rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
> +#ifdef CONFIG_CFS_BANDWIDTH
> +	start_cfs_bandwidth(&cfs_rq->tg->cfs_bandwidth);
> +#endif
>  }
> 
>  static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
> @@ -1369,6 +1381,13 @@ static void dequeue_task_fair(struct rq 
>  	hrtick_update(rq);
>  }
> 
> +#ifdef CONFIG_CFS_BANDWIDTH
> +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
> +{
> +	return 1;
> +}
> +#endif
> +
>  #ifdef CONFIG_SMP
> 
>  static void task_waking_fair(struct rq *rq, struct task_struct *p)
> 
> 

-- 
	Three Cheers,
	Balbir