Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759275AbcDAPUl (ORCPT ); Fri, 1 Apr 2016 11:20:41 -0400 Received: from mail-wm0-f43.google.com ([74.125.82.43]:33262 "EHLO mail-wm0-f43.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932120AbcDAPSZ (ORCPT ); Fri, 1 Apr 2016 11:18:25 -0400 From: Luca Abeni To: linux-kernel@vger.kernel.org Cc: Peter Zijlstra , Ingo Molnar , Juri Lelli , Luca Abeni Subject: [RFC v2 3/7] Improve the tracking of active utilisation Date: Fri, 1 Apr 2016 17:12:29 +0200 Message-Id: <1459523553-29089-4-git-send-email-luca.abeni@unitn.it> X-Mailer: git-send-email 2.5.0 In-Reply-To: <1459523553-29089-1-git-send-email-luca.abeni@unitn.it> References: <1459523553-29089-1-git-send-email-luca.abeni@unitn.it> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 9338 Lines: 306 This patch implements a more theoretically sound algorithm for thracking the active utilisation: instead of decreasing it when a task blocks, use a timer (the "inactive timer", named after the "Inactive" task state of the GRUB algorithm) to decrease the active utilisaation at the so called "0-lag time". Signed-off-by: Luca Abeni --- include/linux/sched.h | 1 + kernel/sched/core.c | 1 + kernel/sched/deadline.c | 158 +++++++++++++++++++++++++++++++++++++++++------- kernel/sched/sched.h | 1 + 4 files changed, 139 insertions(+), 22 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index c617ea1..f285461 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1351,6 +1351,7 @@ struct sched_dl_entity { * own bandwidth to be enforced, thus we need one timer per task. */ struct hrtimer dl_timer; + struct hrtimer inactive_timer; }; union rcu_special { diff --git a/kernel/sched/core.c b/kernel/sched/core.c index de38077..23d235c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2076,6 +2076,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) RB_CLEAR_NODE(&p->dl.rb_node); init_dl_task_timer(&p->dl); + init_inactive_task_timer(&p->dl); __dl_clear_params(p); INIT_LIST_HEAD(&p->rt.run_list); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 05cfccb..97cd5f2 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -47,6 +47,7 @@ static void add_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { u64 se_bw = dl_se->dl_bw; + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); dl_rq->running_bw += se_bw; } @@ -54,11 +55,59 @@ static void sub_running_bw(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { u64 se_bw = dl_se->dl_bw; + lockdep_assert_held(&(rq_of_dl_rq(dl_rq))->lock); dl_rq->running_bw -= se_bw; if (WARN_ON(dl_rq->running_bw < 0)) dl_rq->running_bw = 0; } +static void task_go_inactive(struct task_struct *p) +{ + struct sched_dl_entity *dl_se = &p->dl; + struct hrtimer *timer = &dl_se->inactive_timer; + struct dl_rq *dl_rq = dl_rq_of_se(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq); + ktime_t now, act; + s64 delta; + u64 zerolag_time; + + WARN_ON(dl_se->dl_runtime == 0); + + /* If the inactive timer is already armed, return immediately */ + if (hrtimer_active(&dl_se->inactive_timer)) + return; + + + /* + * We want the timer to fire at the "0 lag time", but considering + * that it is actually coming from rq->clock and not from + * hrtimer's time base reading. + */ + zerolag_time = dl_se->deadline - + div64_long((dl_se->runtime * dl_se->dl_period), + dl_se->dl_runtime); + + act = ns_to_ktime(zerolag_time); + now = hrtimer_cb_get_time(timer); + delta = ktime_to_ns(now) - rq_clock(rq); + act = ktime_add_ns(act, delta); + + /* + * If the "0-lag time" already passed, decrease the active + * utilization now, instead of starting a timer + */ + if (ktime_us_delta(act, now) < 0) { + sub_running_bw(dl_se, dl_rq); + if (!dl_task(p)) + __dl_clear_params(p); + + return; + } + + get_task_struct(p); + hrtimer_start(timer, act, HRTIMER_MODE_ABS); +} + static inline int is_leftmost(struct task_struct *p, struct dl_rq *dl_rq) { struct sched_dl_entity *dl_se = &p->dl; @@ -526,7 +575,18 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq = dl_rq_of_se(dl_se); struct rq *rq = rq_of_dl_rq(dl_rq); - add_running_bw(dl_se, dl_rq); + /* + * If the "inactive timer" is still active, stop it and leave + * the active utilisation unchanged. + * Otherwise, increase the active utilisation. + * If the timer cannot be cancelled, inactive_task_timer() will + * find the task state as TASK_RUNNING, and will do nothing, so + * we are still safe. + */ + if (hrtimer_active(&dl_se->inactive_timer)) + hrtimer_try_to_cancel(&dl_se->inactive_timer); + else + add_running_bw(dl_se, dl_rq); if (dl_time_before(dl_se->deadline, rq_clock(rq)) || dl_entity_overflow(dl_se, pi_se, rq_clock(rq))) { @@ -614,14 +674,8 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) rq = task_rq_lock(p, &flags); - /* - * The task might have changed its scheduling policy to something - * different than SCHED_DEADLINE (through switched_fromd_dl()). - */ - if (!dl_task(p)) { - __dl_clear_params(p); + if (!dl_task(p)) goto unlock; - } /* * The task might have been boosted by someone else and might be in the @@ -800,6 +854,44 @@ throttle: } } +static enum hrtimer_restart inactive_task_timer(struct hrtimer *timer) +{ + struct sched_dl_entity *dl_se = container_of(timer, + struct sched_dl_entity, + inactive_timer); + struct task_struct *p = dl_task_of(dl_se); + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + + if (!dl_task(p)) { + __dl_clear_params(p); + + goto unlock; + } + if (p->state == TASK_RUNNING) + goto unlock; + + sched_clock_tick(); + update_rq_clock(rq); + + sub_running_bw(dl_se, &rq->dl); +unlock: + task_rq_unlock(rq, p, &flags); + put_task_struct(p); + + return HRTIMER_NORESTART; +} + +void init_inactive_task_timer(struct sched_dl_entity *dl_se) +{ + struct hrtimer *timer = &dl_se->inactive_timer; + + hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + timer->function = inactive_task_timer; +} + #ifdef CONFIG_SMP static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) @@ -976,7 +1068,8 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) * run yet) will take care of this. */ if (p->dl.dl_throttled && !(flags & ENQUEUE_REPLENISH)) { - add_running_bw(&p->dl, &rq->dl); + if (hrtimer_try_to_cancel(&p->dl.inactive_timer) < 0) + add_running_bw(&p->dl, &rq->dl); return; } @@ -997,7 +1090,7 @@ static void dequeue_task_dl(struct rq *rq, struct task_struct *p, int flags) update_curr_dl(rq); __dequeue_task_dl(rq, p, flags); if (flags & DEQUEUE_SLEEP) - sub_running_bw(&p->dl, &rq->dl); + task_go_inactive(p); } /* @@ -1071,6 +1164,23 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) } rcu_read_unlock(); + if (rq != cpu_rq(cpu)) { + int migrate_active; + + raw_spin_lock(&rq->lock); + migrate_active = hrtimer_active(&p->dl.inactive_timer); + if (migrate_active) + sub_running_bw(&p->dl, &rq->dl); + raw_spin_unlock(&rq->lock); + if (migrate_active) { + rq = cpu_rq(cpu); + raw_spin_lock(&rq->lock); + add_running_bw(&p->dl, &rq->dl); + raw_spin_unlock(&rq->lock); + } + } + + out: return cpu; } @@ -1232,8 +1342,6 @@ static void task_fork_dl(struct task_struct *p) static void task_dead_dl(struct task_struct *p) { struct dl_bw *dl_b = dl_bw_of(task_cpu(p)); - struct dl_rq *dl_rq = dl_rq_of_se(&p->dl); - struct rq *rq = rq_of_dl_rq(dl_rq); /* * Since we are TASK_DEAD we won't slip out of the domain! @@ -1242,9 +1350,6 @@ static void task_dead_dl(struct task_struct *p) /* XXX we should retain the bw until 0-lag */ dl_b->total_bw -= p->dl.dl_bw; raw_spin_unlock_irq(&dl_b->lock); - - if (task_on_rq_queued(p)) - sub_running_bw(&p->dl, &rq->dl); } static void set_curr_task_dl(struct rq *rq) @@ -1720,15 +1825,23 @@ void __init init_sched_dl_class(void) static void switched_from_dl(struct rq *rq, struct task_struct *p) { /* - * Start the deadline timer; if we switch back to dl before this we'll - * continue consuming our current CBS slice. If we stay outside of - * SCHED_DEADLINE until the deadline passes, the timer will reset the - * task. + * task_go_inactive() can start the "inactive timer" (if the 0-lag + * time is in the future). If the task switches back to dl before + * the "inactive timer" fires, it can continue to consume its current + * runtime using its current deadline. If it stays outside of + * SCHED_DEADLINE until the 0-lag time passes, inactive_task_timer() + * will reset the task parameters. */ - if (!start_dl_timer(p)) - __dl_clear_params(p); + if (task_on_rq_queued(p) && p->dl.dl_runtime) + task_go_inactive(p); - if (task_on_rq_queued(p)) + /* + * We cannot use inactive_task_timer() to invoke sub_running_bw() + * at the 0-lag time, because the task could have been migrated + * while SCHED_OTHER in the meanwhile. + */ + if (hrtimer_active(&p->dl.inactive_timer) && + !hrtimer_callback_running(&p->dl.inactive_timer)) sub_running_bw(&p->dl, &rq->dl); /* @@ -1750,6 +1863,7 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) { if (dl_time_before(p->dl.deadline, rq_clock(rq))) setup_new_dl_entity(&p->dl, &p->dl); + add_running_bw(&p->dl, &rq->dl); if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index bc05c29..22d36b2 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1315,6 +1315,7 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime extern struct dl_bandwidth def_dl_bandwidth; extern void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime); extern void init_dl_task_timer(struct sched_dl_entity *dl_se); +extern void init_inactive_task_timer(struct sched_dl_entity *dl_se); unsigned long to_ratio(u64 period, u64 runtime); -- 2.5.0