From 1c20091e77fc5a9b7d7d905176443b4822a23cdb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Aug 2011 23:21:01 +0200 Subject: nohz: Wake up full dynticks CPUs when a timer gets enqueued Wake up a CPU when a timer list timer is enqueued there and the target is part of the full dynticks range. Sending an IPI to it makes it reconsidering the next timer to program on top of recent updates. This may later be improved by checking if the tick is really stopped on the target. This would need some careful synchronization though. So deal with such optimization later and start simple. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 20 +++++++++++++++++++- 1 file changed, 19 insertions(+), 1 deletion(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 849deb96e61e..e91ee589f793 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -587,7 +587,7 @@ unlock: * account when the CPU goes back to idle and evaluates the timer * wheel for the next timer event. */ -void wake_up_idle_cpu(int cpu) +static void wake_up_idle_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -617,6 +617,24 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } +static bool wake_up_extended_nohz_cpu(int cpu) +{ + if (tick_nohz_extended_cpu(cpu)) { + if (cpu != smp_processor_id() || + tick_nohz_tick_stopped()) + smp_send_reschedule(cpu); + return true; + } + + return false; +} + +void wake_up_nohz_cpu(int cpu) +{ + if (!wake_up_extended_nohz_cpu(cpu)) + wake_up_idle_cpu(cpu); +} + static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); -- cgit v1.2.3 From 3451d0243c3cdfd729b36f9684a14659d4895ca3 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Wed, 10 Aug 2011 23:21:01 +0200 Subject: nohz: Rename CONFIG_NO_HZ to CONFIG_NO_HZ_COMMON We are planning to convert the dynticks Kconfig options layout into a choice menu. The user must be able to easily pick any of the following implementations: constant periodic tick, idle dynticks, full dynticks. As this implies a mutual exclusion, the two dynticks implementions need to converge on the selection of a common Kconfig option in order to ease the sharing of a common infrastructure. It would thus seem pretty natural to reuse CONFIG_NO_HZ to that end. It already implements all the idle dynticks code and the full dynticks depends on all that code for now. So ideally the choice menu would propose CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED then both would select CONFIG_NO_HZ. On the other hand we want to stay backward compatible: if CONFIG_NO_HZ is set in an older config file, we want to enable CONFIG_NO_HZ_IDLE by default. But we can't afford both at the same time or we run into a circular dependency: 1) CONFIG_NO_HZ_IDLE and CONFIG_NO_HZ_EXTENDED both select CONFIG_NO_HZ 2) If CONFIG_NO_HZ is set, we default to CONFIG_NO_HZ_IDLE We might be able to support that from Kconfig/Kbuild but it may not be wise to introduce such a confusing behaviour. So to solve this, create a new CONFIG_NO_HZ_COMMON option which gathers the common code between idle and full dynticks (that common code for now is simply the idle dynticks code) and select it from their referring Kconfig. Then we'll later create CONFIG_NO_HZ_IDLE and map CONFIG_NO_HZ to it for backward compatibility. Signed-off-by: Frederic Weisbecker Cc: Andrew Morton Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Namhyung Kim Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 18 +++++++++--------- kernel/sched/fair.c | 10 +++++----- kernel/sched/sched.h | 4 ++-- 3 files changed, 16 insertions(+), 16 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e91ee589f793..9bb397da63d6 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -549,7 +549,7 @@ void resched_cpu(int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * In the semi idle case, use the nearest busy cpu for migrating timers * from an idle cpu. This is good for power-savings. @@ -641,14 +641,14 @@ static inline bool got_nohz_idle_kick(void) return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); } -#else /* CONFIG_NO_HZ */ +#else /* CONFIG_NO_HZ_COMMON */ static inline bool got_nohz_idle_kick(void) { return false; } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ void sched_avg_update(struct rq *rq) { @@ -2139,7 +2139,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return load >> FSHIFT; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. * @@ -2365,12 +2365,12 @@ static void calc_global_nohz(void) smp_wmb(); calc_load_idx++; } -#else /* !CONFIG_NO_HZ */ +#else /* !CONFIG_NO_HZ_COMMON */ static inline long calc_load_fold_idle(void) { return 0; } static inline void calc_global_nohz(void) { } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * calc_load - update the avenrun load estimates 10 ticks after the @@ -2530,7 +2530,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, sched_avg_update(this_rq); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * There is no sane way to deal with nohz on smp when using jiffies because the * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading @@ -2590,7 +2590,7 @@ void update_cpu_load_nohz(void) } raw_spin_unlock(&this_rq->lock); } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * Called from scheduler_tick() @@ -7023,7 +7023,7 @@ void __init sched_init(void) INIT_LIST_HEAD(&rq->cfs_tasks); rq_attach_root(rq, &def_root_domain); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON rq->nohz_flags = 0; #endif #endif diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 539760ef00c4..5c97fca091a7 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -5331,7 +5331,7 @@ out_unlock: return 0; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * idle load balancing details * - When one of the busy CPUs notice that there may be an idle rebalancing @@ -5541,9 +5541,9 @@ out: rq->next_balance = next_balance; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* - * In CONFIG_NO_HZ case, the idle balance kickee will do the + * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the * rebalancing for all the cpus for whom scheduler ticks are stopped. */ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) @@ -5686,7 +5686,7 @@ void trigger_load_balance(struct rq *rq, int cpu) if (time_after_eq(jiffies, rq->next_balance) && likely(!on_null_domain(cpu))) raise_softirq(SCHED_SOFTIRQ); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) nohz_balancer_kick(cpu); #endif @@ -6156,7 +6156,7 @@ __init void init_sched_fair_class(void) #ifdef CONFIG_SMP open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON nohz.next_balance = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); cpu_notifier(sched_ilb_notifier, 0); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 3bd15a43eebc..889904dd6d77 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -404,7 +404,7 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; unsigned long last_load_update_tick; -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON u64 nohz_stamp; unsigned long nohz_flags; #endif @@ -1333,7 +1333,7 @@ extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); extern void account_cfs_bandwidth_used(int enabled, int was_enabled); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON enum rq_nohz_flag_bits { NOHZ_TICK_STOPPED, NOHZ_BALANCE_KICK, -- cgit v1.2.3 From c5bfece2d6129131b4ade985e63bc35ddf5868d4 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 12 Apr 2013 16:45:34 +0200 Subject: nohz: Switch from "extended nohz" to "full nohz" based naming "Extended nohz" was used as a naming base for the full dynticks API and Kconfig symbols. It reflects the fact the system tries to stop the tick in more places than just idle. But that "extended" name is a bit opaque and vague. Rename it to "full" makes it clearer what the system tries to do under this config: try to shutdown the tick anytime it can. The various constraints that prevent that to happen shouldn't be considered as fundamental properties of this feature but rather technical issues that may be solved in the future. Reported-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9bb397da63d6..0f0a5b3fd62c 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -617,9 +617,9 @@ static void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } -static bool wake_up_extended_nohz_cpu(int cpu) +static bool wake_up_full_nohz_cpu(int cpu) { - if (tick_nohz_extended_cpu(cpu)) { + if (tick_nohz_full_cpu(cpu)) { if (cpu != smp_processor_id() || tick_nohz_tick_stopped()) smp_send_reschedule(cpu); @@ -631,7 +631,7 @@ static bool wake_up_extended_nohz_cpu(int cpu) void wake_up_nohz_cpu(int cpu) { - if (!wake_up_extended_nohz_cpu(cpu)) + if (!wake_up_full_nohz_cpu(cpu)) wake_up_idle_cpu(cpu); } -- cgit v1.2.3 From 9f3660c2c1a221c886474587103c69f6034d3e4f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 14:35:09 +0200 Subject: sched: Kick full dynticks CPU that have more than one task enqueued. Kick the tick on full dynticks CPUs when they get more than one task running on their queue. This makes sure that local fairness is maintained by the tick on the destination. This is done regardless of these tasks' class. We should be able to be more clever in the future depending on these. eg: a CPU that runs a SCHED_FIFO task doesn't need to maintain fairness against local pending tasks of the fair class. But keep things simple for now. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/sched.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 889904dd6d77..eb363aa5d83c 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,6 +5,7 @@ #include #include #include +#include #include "cpupri.h" @@ -1106,6 +1107,16 @@ static inline u64 steal_ticks(u64 steal) static inline void inc_nr_running(struct rq *rq) { rq->nr_running++; + +#ifdef CONFIG_NO_HZ_FULL + if (rq->nr_running == 2) { + if (tick_nohz_full_cpu(rq->cpu)) { + /* Order rq->nr_running write against the IPI */ + smp_wmb(); + smp_send_reschedule(rq->cpu); + } + } +#endif } static inline void dec_nr_running(struct rq *rq) -- cgit v1.2.3 From ce831b38ca4920739a7a5b0c73b921da41f03718 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 15:15:35 +0200 Subject: sched: New helper to prevent from stopping the tick in full dynticks Provide a new helper to be called from the full dynticks engine before stopping the tick in order to make sure we don't stop it when there is more than one task running on the CPU. This way we make sure that the tick stays alive to maintain fairness. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0f0a5b3fd62c..69f71335984f 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -650,6 +650,24 @@ static inline bool got_nohz_idle_kick(void) #endif /* CONFIG_NO_HZ_COMMON */ +#ifdef CONFIG_NO_HZ_FULL +bool sched_can_stop_tick(void) +{ + struct rq *rq; + + rq = this_rq(); + + /* Make sure rq->nr_running update is visible after the IPI */ + smp_rmb(); + + /* More than one running task need preemption */ + if (rq->nr_running > 1) + return false; + + return true; +} +#endif /* CONFIG_NO_HZ_FULL */ + void sched_avg_update(struct rq *rq) { s64 period = sched_avg_period(); -- cgit v1.2.3 From ff442c51f6543378cf23107c75b7949dc64a9119 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 15:27:08 +0200 Subject: nohz: Re-evaluate the tick from the scheduler IPI The scheduler IPI is used by the scheduler to kick full dynticks CPUs asynchronously when more than one task are running or when a new timer list timer is enqueued. This way the destination CPU can decide to restart the tick to handle this new situation. Now let's call that kick in the scheduler IPI. (Reusing the scheduler IPI rather than implementing a new IPI was suggested by Peter Zijlstra a while ago) Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 69f71335984f..9ad35005f1cb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1398,7 +1398,8 @@ static void sched_ttwu_pending(void) void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick() + && !tick_nohz_full_cpu(smp_processor_id())) return; /* @@ -1415,6 +1416,7 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); + tick_nohz_full_check(); sched_ttwu_pending(); /* -- cgit v1.2.3 From 99e5ada9407cc19d7c4c05ce2165f20dc46fc093 Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Sat, 20 Apr 2013 17:11:50 +0200 Subject: nohz: Re-evaluate the tick for the new task after a context switch When a task is scheduled in, it may have some properties of its own that could make the CPU reconsider the need for the tick: posix cpu timers, perf events, ... So notify the full dynticks subsystem when a task gets scheduled in and re-check the tick dependency at this stage. This is done through a self IPI to avoid messing up with any current lock scenario. Signed-off-by: Frederic Weisbecker Cc: Chris Metcalf Cc: Christoph Lameter Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Oleg Nesterov Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 9ad35005f1cb..dd09def88567 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1896,6 +1896,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) kprobe_flush_task(prev); put_task_struct(prev); } + + tick_nohz_task_switch(current); } #ifdef CONFIG_SMP -- cgit v1.2.3 From 265f22a975c1e4cc3a4d1f94a3ec53ffbb6f5b9f Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Fri, 3 May 2013 03:39:05 +0200 Subject: sched: Keep at least 1 tick per second for active dynticks tasks The scheduler doesn't yet fully support environments with a single task running without a periodic tick. In order to ensure we still maintain the duties of scheduler_tick(), keep at least 1 tick per second. This makes sure that we keep the progression of various scheduler accounting and background maintainance even with a very low granularity. Examples include cpu load, sched average, CFS entity vruntime, avenrun and events such as load balancing, amongst other details handled in sched_class::task_tick(). This limitation will be removed in the future once we get these individual items to work in full dynticks CPUs. Suggested-by: Ingo Molnar Signed-off-by: Frederic Weisbecker Cc: Christoph Lameter Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Li Zhong Cc: Paul E. McKenney Cc: Paul Gortmaker Cc: Peter Zijlstra Cc: Steven Rostedt Cc: Thomas Gleixner --- kernel/sched/core.c | 30 ++++++++++++++++++++++++++++++ kernel/sched/idle_task.c | 1 + kernel/sched/sched.h | 10 ++++++++++ 3 files changed, 41 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index e94842d4400c..3bdf986a091a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2736,8 +2736,35 @@ void scheduler_tick(void) rq->idle_balance = idle_cpu(cpu); trigger_load_balance(rq, cpu); #endif + rq_last_tick_reset(rq); } +#ifdef CONFIG_NO_HZ_FULL +/** + * scheduler_tick_max_deferment + * + * Keep at least one tick per second when a single + * active task is running because the scheduler doesn't + * yet completely support full dynticks environment. + * + * This makes sure that uptime, CFS vruntime, load + * balancing, etc... continue to move forward, even + * with a very low granularity. + */ +u64 scheduler_tick_max_deferment(void) +{ + struct rq *rq = this_rq(); + unsigned long next, now = ACCESS_ONCE(jiffies); + + next = rq->last_sched_tick + HZ; + + if (time_before_eq(next, now)) + return 0; + + return jiffies_to_usecs(next - now) * NSEC_PER_USEC; +} +#endif + notrace unsigned long get_parent_ip(unsigned long addr) { if (in_lock_functions(addr)) { @@ -6993,6 +7020,9 @@ void __init sched_init(void) #ifdef CONFIG_NO_HZ_COMMON rq->nohz_flags = 0; #endif +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = 0; +#endif #endif init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index b8ce77328341..d8da01008d39 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -17,6 +17,7 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) static void pre_schedule_idle(struct rq *rq, struct task_struct *prev) { idle_exit_fair(rq); + rq_last_tick_reset(rq); } static void post_schedule_idle(struct rq *rq) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 24dc29897749..ce39224d6155 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -409,6 +409,9 @@ struct rq { #ifdef CONFIG_NO_HZ_COMMON u64 nohz_stamp; unsigned long nohz_flags; +#endif +#ifdef CONFIG_NO_HZ_FULL + unsigned long last_sched_tick; #endif int skip_clock_update; @@ -1090,6 +1093,13 @@ static inline void dec_nr_running(struct rq *rq) rq->nr_running--; } +static inline void rq_last_tick_reset(struct rq *rq) +{ +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = jiffies; +#endif +} + extern void update_rq_clock(struct rq *rq); extern void activate_task(struct rq *rq, struct task_struct *p, int flags); -- cgit v1.2.3