sched: Expire invalid runtime
Since quota is managed using a global state but consumed on a per-cpu basis we need to ensure that our per-cpu state is appropriately synchronized. Most importantly, runtime that is state (from a previous period) should not be locally consumable. We take advantage of existing sched_clock synchronization about the jiffy to efficiently detect whether we have (globally) crossed a quota boundary above. One catch is that the direction of spread on sched_clock is undefined, specifically, we don't know whether our local clock is behind or ahead of the one responsible for the current expiration time. Fortunately we can differentiate these by considering whether the global deadline has advanced. If it has not, then we assume our clock to be "fast" and advance our local expiration; otherwise, we know the deadline has truly passed and we expire our local runtime. Signed-off-by: Paul Turner <pjt@google.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/20110721184757.379275352@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
parent
58088ad015
commit
a9cf55b286
|
@ -256,6 +256,7 @@ struct cfs_bandwidth {
|
||||||
ktime_t period;
|
ktime_t period;
|
||||||
u64 quota, runtime;
|
u64 quota, runtime;
|
||||||
s64 hierarchal_quota;
|
s64 hierarchal_quota;
|
||||||
|
u64 runtime_expires;
|
||||||
|
|
||||||
int idle, timer_active;
|
int idle, timer_active;
|
||||||
struct hrtimer period_timer;
|
struct hrtimer period_timer;
|
||||||
|
@ -396,6 +397,7 @@ struct cfs_rq {
|
||||||
#endif
|
#endif
|
||||||
#ifdef CONFIG_CFS_BANDWIDTH
|
#ifdef CONFIG_CFS_BANDWIDTH
|
||||||
int runtime_enabled;
|
int runtime_enabled;
|
||||||
|
u64 runtime_expires;
|
||||||
s64 runtime_remaining;
|
s64 runtime_remaining;
|
||||||
#endif
|
#endif
|
||||||
#endif
|
#endif
|
||||||
|
@ -9166,8 +9168,8 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
|
||||||
raw_spin_lock_irq(&cfs_b->lock);
|
raw_spin_lock_irq(&cfs_b->lock);
|
||||||
cfs_b->period = ns_to_ktime(period);
|
cfs_b->period = ns_to_ktime(period);
|
||||||
cfs_b->quota = quota;
|
cfs_b->quota = quota;
|
||||||
cfs_b->runtime = quota;
|
|
||||||
|
|
||||||
|
__refill_cfs_bandwidth_runtime(cfs_b);
|
||||||
/* restart the period timer (if active) to handle new period expiry */
|
/* restart the period timer (if active) to handle new period expiry */
|
||||||
if (runtime_enabled && cfs_b->timer_active) {
|
if (runtime_enabled && cfs_b->timer_active) {
|
||||||
/* force a reprogram */
|
/* force a reprogram */
|
||||||
|
|
|
@ -1272,11 +1272,30 @@ static inline u64 sched_cfs_bandwidth_slice(void)
|
||||||
return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
|
return (u64)sysctl_sched_cfs_bandwidth_slice * NSEC_PER_USEC;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Replenish runtime according to assigned quota and update expiration time.
|
||||||
|
* We use sched_clock_cpu directly instead of rq->clock to avoid adding
|
||||||
|
* additional synchronization around rq->lock.
|
||||||
|
*
|
||||||
|
* requires cfs_b->lock
|
||||||
|
*/
|
||||||
|
static void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
|
||||||
|
{
|
||||||
|
u64 now;
|
||||||
|
|
||||||
|
if (cfs_b->quota == RUNTIME_INF)
|
||||||
|
return;
|
||||||
|
|
||||||
|
now = sched_clock_cpu(smp_processor_id());
|
||||||
|
cfs_b->runtime = cfs_b->quota;
|
||||||
|
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
|
||||||
|
}
|
||||||
|
|
||||||
static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
||||||
{
|
{
|
||||||
struct task_group *tg = cfs_rq->tg;
|
struct task_group *tg = cfs_rq->tg;
|
||||||
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
|
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
|
||||||
u64 amount = 0, min_amount;
|
u64 amount = 0, min_amount, expires;
|
||||||
|
|
||||||
/* note: this is a positive sum as runtime_remaining <= 0 */
|
/* note: this is a positive sum as runtime_remaining <= 0 */
|
||||||
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
|
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
|
||||||
|
@ -1285,9 +1304,16 @@ static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
||||||
if (cfs_b->quota == RUNTIME_INF)
|
if (cfs_b->quota == RUNTIME_INF)
|
||||||
amount = min_amount;
|
amount = min_amount;
|
||||||
else {
|
else {
|
||||||
/* ensure bandwidth timer remains active under consumption */
|
/*
|
||||||
if (!cfs_b->timer_active)
|
* If the bandwidth pool has become inactive, then at least one
|
||||||
|
* period must have elapsed since the last consumption.
|
||||||
|
* Refresh the global state and ensure bandwidth timer becomes
|
||||||
|
* active.
|
||||||
|
*/
|
||||||
|
if (!cfs_b->timer_active) {
|
||||||
|
__refill_cfs_bandwidth_runtime(cfs_b);
|
||||||
__start_cfs_bandwidth(cfs_b);
|
__start_cfs_bandwidth(cfs_b);
|
||||||
|
}
|
||||||
|
|
||||||
if (cfs_b->runtime > 0) {
|
if (cfs_b->runtime > 0) {
|
||||||
amount = min(cfs_b->runtime, min_amount);
|
amount = min(cfs_b->runtime, min_amount);
|
||||||
|
@ -1295,19 +1321,61 @@ static void assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
||||||
cfs_b->idle = 0;
|
cfs_b->idle = 0;
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
expires = cfs_b->runtime_expires;
|
||||||
raw_spin_unlock(&cfs_b->lock);
|
raw_spin_unlock(&cfs_b->lock);
|
||||||
|
|
||||||
cfs_rq->runtime_remaining += amount;
|
cfs_rq->runtime_remaining += amount;
|
||||||
|
/*
|
||||||
|
* we may have advanced our local expiration to account for allowed
|
||||||
|
* spread between our sched_clock and the one on which runtime was
|
||||||
|
* issued.
|
||||||
|
*/
|
||||||
|
if ((s64)(expires - cfs_rq->runtime_expires) > 0)
|
||||||
|
cfs_rq->runtime_expires = expires;
|
||||||
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Note: This depends on the synchronization provided by sched_clock and the
|
||||||
|
* fact that rq->clock snapshots this value.
|
||||||
|
*/
|
||||||
|
static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
|
||||||
|
{
|
||||||
|
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
|
||||||
|
struct rq *rq = rq_of(cfs_rq);
|
||||||
|
|
||||||
|
/* if the deadline is ahead of our clock, nothing to do */
|
||||||
|
if (likely((s64)(rq->clock - cfs_rq->runtime_expires) < 0))
|
||||||
|
return;
|
||||||
|
|
||||||
|
if (cfs_rq->runtime_remaining < 0)
|
||||||
|
return;
|
||||||
|
|
||||||
|
/*
|
||||||
|
* If the local deadline has passed we have to consider the
|
||||||
|
* possibility that our sched_clock is 'fast' and the global deadline
|
||||||
|
* has not truly expired.
|
||||||
|
*
|
||||||
|
* Fortunately we can check determine whether this the case by checking
|
||||||
|
* whether the global deadline has advanced.
|
||||||
|
*/
|
||||||
|
|
||||||
|
if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) {
|
||||||
|
/* extend local deadline, drift is bounded above by 2 ticks */
|
||||||
|
cfs_rq->runtime_expires += TICK_NSEC;
|
||||||
|
} else {
|
||||||
|
/* global deadline is ahead, expiration has passed */
|
||||||
|
cfs_rq->runtime_remaining = 0;
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
|
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq,
|
||||||
unsigned long delta_exec)
|
unsigned long delta_exec)
|
||||||
{
|
{
|
||||||
if (!cfs_rq->runtime_enabled)
|
/* dock delta_exec before expiring quota (as it could span periods) */
|
||||||
return;
|
|
||||||
|
|
||||||
cfs_rq->runtime_remaining -= delta_exec;
|
cfs_rq->runtime_remaining -= delta_exec;
|
||||||
if (cfs_rq->runtime_remaining > 0)
|
expire_cfs_rq_runtime(cfs_rq);
|
||||||
|
|
||||||
|
if (likely(cfs_rq->runtime_remaining > 0))
|
||||||
return;
|
return;
|
||||||
|
|
||||||
assign_cfs_rq_runtime(cfs_rq);
|
assign_cfs_rq_runtime(cfs_rq);
|
||||||
|
@ -1338,7 +1406,12 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun)
|
||||||
goto out_unlock;
|
goto out_unlock;
|
||||||
|
|
||||||
idle = cfs_b->idle;
|
idle = cfs_b->idle;
|
||||||
cfs_b->runtime = cfs_b->quota;
|
/* if we're going inactive then everything else can be deferred */
|
||||||
|
if (idle)
|
||||||
|
goto out_unlock;
|
||||||
|
|
||||||
|
__refill_cfs_bandwidth_runtime(cfs_b);
|
||||||
|
|
||||||
|
|
||||||
/* mark as potentially idle for the upcoming period */
|
/* mark as potentially idle for the upcoming period */
|
||||||
cfs_b->idle = 1;
|
cfs_b->idle = 1;
|
||||||
|
@ -1557,7 +1630,6 @@ static long effective_load(struct task_group *tg, int cpu, long wl, long wg)
|
||||||
|
|
||||||
return wl;
|
return wl;
|
||||||
}
|
}
|
||||||
|
|
||||||
#else
|
#else
|
||||||
|
|
||||||
static inline unsigned long effective_load(struct task_group *tg, int cpu,
|
static inline unsigned long effective_load(struct task_group *tg, int cpu,
|
||||||
|
|
Loading…
Reference in New Issue