isolation: 1Hz residual tick offloading v7
Subsystems (4)
Frederic Weisbecker
maintainercover isolation: 1Hz residual tick offloading v7
This version addresses comments from Thomas:
* Convert tick_nohz_tick_stopped[_cpu]() to bool
* Add comments to each sched_class::task_tick() to make sure that datas are always fetched from rq and task passed in parameters to allow for remote ticks.
* Add reviewed-by tags
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
sched/0hz-v7
HEAD: b0d4913a0a39c717f354e40c1642264632e76960
Thanks,
Frederic
---
Frederic Weisbecker (7):
sched: Rename init_rq_hrtick to hrtick_rq_init
nohz: Convert tick_nohz_tick_stopped() to bool
nohz: Allow to check if remote CPU tick is stopped sched/isolation: Isolate workqueues when "nohz_full=" is set sched/isolation: Offload residual 1Hz scheduler tick sched/nohz: Remove the 1 Hz tick code
sched/isolation: Update nohz documentation to explain tick offload
Documentation/admin-guide/kernel-parameters.txt | 11 +++ include/linux/sched/isolation.h | 1 + include/linux/sched/nohz.h | 4 - include/linux/tick.h | 4 +- kernel/sched/core.c | 117 ++++++++++++++++++------ kernel/sched/deadline.c | 8 ++ kernel/sched/fair.c | 7 +- kernel/sched/idle_task.c | 9 +- kernel/sched/isolation.c | 7 +- kernel/sched/rt.c | 8 ++ kernel/sched/sched.h | 13 +-- kernel/sched/stop_task.c | 8 ++ kernel/time/tick-sched.c | 15 +-- kernel/workqueue.c | 3 +- 14 files changed, 162 insertions(+), 53 deletions(-)
Frederic Weisbecker
maintainerPATCH 1/7 sched: Rename init_rq_hrtick to hrtick_rq_init
Do that rename in order to normalize the hrtick namespace.
--- kernel/sched/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
kernel/sched/core.c +3 -3
@@ -333,7 +333,7 @@ void hrtick_start(struct rq *rq, u64 delay) }#endif /* CONFIG_SMP */ -static void init_rq_hrtick (struct rq *rq) +static void hrtick_rq_init (struct rq *rq) {#ifdef CONFIG_SMP rq->hrtick_csd_pending =0 ;
@@ -351,7 +351,7 @@ static inline void hrtick_clear(struct rq *rq) { } -static inline void init_rq_hrtick (struct rq *rq) +static inline void hrtick_rq_init (struct rq *rq) { }#endif /* CONFIG_SCHED_HRTICK */
@@ -6028,7 +6028,7 @@ void __init sched_init(void) rq->last_sched_tick =0 ;#endif #endif /* CONFIG_SMP */ -init_rq_hrtick (rq); +hrtick_rq_init (rq);atomic_set (&rq->nr_iowait,0 ); }
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/core: Rename init_rq_hrtick() to hrtick_rq_init()
sched/core: Rename init_rq_hrtick() to hrtick_rq_init()
Commit-ID: 77a021be383ebdacb17594e280242f7fd116095f Gitweb: https://git.kernel.org/tip/77a021be383ebdacb17594e280242f7fd116095f Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:23 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:07 +0100
sched/core: Rename init_rq_hrtick() to hrtick_rq_init()
Do that rename in order to normalize the hrtick namespace.
--- kernel/sched/core.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
kernel/sched/core.c +3 -3
@@ -333,7 +333,7 @@ void hrtick_start(struct rq *rq, u64 delay) }#endif /* CONFIG_SMP */ -static void init_rq_hrtick (struct rq *rq) +static void hrtick_rq_init (struct rq *rq) {#ifdef CONFIG_SMP rq->hrtick_csd_pending =0 ;
@@ -351,7 +351,7 @@ static inline void hrtick_clear(struct rq *rq) { } -static inline void init_rq_hrtick (struct rq *rq) +static inline void hrtick_rq_init (struct rq *rq) { }#endif /* CONFIG_SCHED_HRTICK */
@@ -6028,7 +6028,7 @@ void __init sched_init(void) rq->last_sched_tick =0 ;#endif #endif /* CONFIG_SMP */ -init_rq_hrtick (rq); +hrtick_rq_init (rq);atomic_set (&rq->nr_iowait,0 ); }
Frederic Weisbecker
maintainerPATCH 2/7 nohz: Convert tick_nohz_tick_stopped() to bool
In reply to Frederic WeisbeckerIt makes this function more self-explanatory about what it does and how to use it.
--- include/linux/tick.h | 2 +- kernel/time/tick-sched.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
include/linux/tick.h +1 -1
@@ -113,7 +113,7 @@ enum tick_dep_bits {#ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; -extern int tick_nohz_tick_stopped (void ); +extern bool tick_nohz_tick_stopped (void );extern void tick_nohz_idle_enter (void );extern void tick_nohz_idle_exit (void );extern void tick_nohz_irq_exit (void );
kernel/time/tick-sched.c +1 -1
@@ -481,7 +481,7 @@ static int __init setup_tick_nohz(char *str)__setup ("nohz=" , setup_tick_nohz); -int tick_nohz_tick_stopped (void ) +bool tick_nohz_tick_stopped (void ) {return __this_cpu_read (tick_cpu_sched.tick_stopped); }
Signature · 1 line
2.7.4
Re: [PATCH 2/7] nohz: Convert tick_nohz_tick_stopped() to bool
Quoted 5 lines · Frederic Weisbecker
It makes this function more self-explanatory about what it does and how to use it.
Reported-by Thomas Gleixner <[email protected]>Signed-off-by Frederic Weisbecker <[email protected]>
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] nohz: Convert tick_nohz_tick_stopped() to bool
In reply to Frederic Weisbeckernohz: Convert tick_nohz_tick_stopped() to bool
Commit-ID: a364298359e74a414857bbbf3b725564feb22d09 Gitweb: https://git.kernel.org/tip/a364298359e74a414857bbbf3b725564feb22d09 Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:24 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:08 +0100
nohz: Convert tick_nohz_tick_stopped() to bool
It makes this function more self-explanatory about what it does and how to use it.
--- include/linux/tick.h | 2 +- kernel/time/tick-sched.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
include/linux/tick.h +1 -1
@@ -113,7 +113,7 @@ enum tick_dep_bits {#ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled; -extern int tick_nohz_tick_stopped (void ); +extern bool tick_nohz_tick_stopped (void );extern void tick_nohz_idle_enter (void );extern void tick_nohz_idle_exit (void );extern void tick_nohz_irq_exit (void );
kernel/time/tick-sched.c +1 -1
@@ -481,7 +481,7 @@ static int __init setup_tick_nohz(char *str)__setup ("nohz=" , setup_tick_nohz); -int tick_nohz_tick_stopped (void ) +bool tick_nohz_tick_stopped (void ) {return __this_cpu_read (tick_cpu_sched.tick_stopped); }
Frederic Weisbecker
maintainerPATCH 3/7 nohz: Allow to check if remote CPU tick is stopped
In reply to Frederic WeisbeckerThis check is racy but provides a good heuristic to determine whether a CPU may need a remote tick or not.
--- include/linux/tick.h | 2 ++ kernel/time/tick-sched.c | 7 +++++++ 2 files changed, 9 insertions(+)
include/linux/tick.h +2 -0
@@ -114,6 +114,7 @@ enum tick_dep_bits {#ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled;extern bool tick_nohz_tick_stopped (void ); +extern bool tick_nohz_tick_stopped_cpu (int cpu);extern void tick_nohz_idle_enter (void );extern void tick_nohz_idle_exit (void );extern void tick_nohz_irq_exit (void );
@@ -125,6 +126,7 @@ extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);#else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0)static inline int tick_nohz_tick_stopped (void ) {return 0 ; } +static inline int tick_nohz_tick_stopped_cpu (int cpu) {return 0 ; }static inline void tick_nohz_idle_enter (void ) { }static inline void tick_nohz_idle_exit (void ) { }
kernel/time/tick-sched.c +7 -0
@@ -486,6 +486,13 @@ bool tick_nohz_tick_stopped(void)return __this_cpu_read (tick_cpu_sched.tick_stopped); } +bool tick_nohz_tick_stopped_cpu (int cpu) +{ +struct tick_sched *ts =per_cpu_ptr (&tick_cpu_sched, cpu); + +return ts->tick_stopped; +} +/** * tick_nohz_update_jiffies - update jiffies when idle was interrupted *
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] nohz: Allow to check if remote CPU tick is stopped
nohz: Allow to check if remote CPU tick is stopped
Commit-ID: 22ab8bc02a5f6e8ffc418759894f7a6b0b632331 Gitweb: https://git.kernel.org/tip/22ab8bc02a5f6e8ffc418759894f7a6b0b632331 Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:25 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:08 +0100
nohz: Allow to check if remote CPU tick is stopped
This check is racy but provides a good heuristic to determine whether a CPU may need a remote tick or not.
--- include/linux/tick.h | 2 ++ kernel/time/tick-sched.c | 7 +++++++ 2 files changed, 9 insertions(+)
include/linux/tick.h +2 -0
@@ -114,6 +114,7 @@ enum tick_dep_bits {#ifdef CONFIG_NO_HZ_COMMON extern bool tick_nohz_enabled;extern bool tick_nohz_tick_stopped (void ); +extern bool tick_nohz_tick_stopped_cpu (int cpu);extern void tick_nohz_idle_enter (void );extern void tick_nohz_idle_exit (void );extern void tick_nohz_irq_exit (void );
@@ -125,6 +126,7 @@ extern u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time);#else /* !CONFIG_NO_HZ_COMMON */ #define tick_nohz_enabled (0)static inline int tick_nohz_tick_stopped (void ) {return 0 ; } +static inline int tick_nohz_tick_stopped_cpu (int cpu) {return 0 ; }static inline void tick_nohz_idle_enter (void ) { }static inline void tick_nohz_idle_exit (void ) { }
kernel/time/tick-sched.c +7 -0
@@ -486,6 +486,13 @@ bool tick_nohz_tick_stopped(void)return __this_cpu_read (tick_cpu_sched.tick_stopped); } +bool tick_nohz_tick_stopped_cpu (int cpu) +{ +struct tick_sched *ts =per_cpu_ptr (&tick_cpu_sched, cpu); + +return ts->tick_stopped; +} +/** * tick_nohz_update_jiffies - update jiffies when idle was interrupted *
Frederic Weisbecker
maintainerPATCH 4/7 sched/isolation: Isolate workqueues when "nohz_full=" is set
In reply to Frederic WeisbeckerAs we prepare for offloading the residual 1hz scheduler ticks to workqueue, let's affine those to housekeepers so that they don't interrupt the CPUs that don't want to be disturbed.
--- include/linux/sched/isolation.h | 1 + kernel/sched/isolation.c | 3 ++- kernel/workqueue.c | 3 ++- 3 files changed, 5 insertions(+), 2 deletions(-)
include/linux/sched/isolation.h +1 -0
@@ -12,6 +12,7 @@ enum hk_flags {HK_FLAG_SCHED = (1 <<3 ),HK_FLAG_TICK = (1 <<4 ),HK_FLAG_DOMAIN = (1 <<5 ), + HK_FLAG_WQ = (1 << 6), };#ifdef CONFIG_CPU_ISOLATION
kernel/sched/isolation.c +2 -1
@@ -3,6 +3,7 @@* any CPU: unbound workqueues, timers, kthreads and any offloadable work. * * Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker +* Copyright (C) 2017-2018 SUSE, Frederic Weisbecker * */
@@ -119,7 +120,7 @@ static int __init housekeeping_nohz_full_setup(char *str) {unsigned int flags; - flags =HK_FLAG_TICK |HK_FLAG_TIMER |HK_FLAG_RCU |HK_FLAG_MISC ; + flags =HK_FLAG_TICK |HK_FLAG_WQ |HK_FLAG_TIMER |HK_FLAG_RCU |HK_FLAG_MISC ;return housekeeping_setup (str, flags); }
kernel/workqueue.c +2 -1
@@ -5565,12 +5565,13 @@ static void __init wq_numa_init(void)int __init workqueue_init_early (void ) {int std_nice[NR_STD_WORKER_POOLS ] = {0 ,HIGHPRI_NICE_LEVEL }; +int hk_flags =HK_FLAG_DOMAIN |HK_FLAG_WQ ;int i, cpu;WARN_ON (__alignof__(struct pool_workqueue ) < __alignof__(long long ));BUG_ON (!alloc_cpumask_var (&wq_unbound_cpumask,GFP_KERNEL )); -cpumask_copy (wq_unbound_cpumask,housekeeping_cpumask (HK_FLAG_DOMAIN )); +cpumask_copy (wq_unbound_cpumask,housekeeping_cpumask (hk_flags)); pwq_cache =KMEM_CACHE (pool_workqueue,SLAB_PANIC );
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Isolate workqueues when "nohz_full=" is set
sched/isolation: Isolate workqueues when "nohz_full=" is set
Commit-ID: 1bda3f8087fce9063da0b8aef87f17a3fe541aca Gitweb: https://git.kernel.org/tip/1bda3f8087fce9063da0b8aef87f17a3fe541aca Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:26 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:08 +0100
sched/isolation: Isolate workqueues when "nohz_full=" is set
As we prepare for offloading the residual 1hz scheduler ticks to workqueue, let's affine those to housekeepers so that they don't interrupt the CPUs that don't want to be disturbed.
--- include/linux/sched/isolation.h | 1 + kernel/sched/isolation.c | 3 ++- kernel/workqueue.c | 3 ++- 3 files changed, 5 insertions(+), 2 deletions(-)
include/linux/sched/isolation.h +1 -0
@@ -12,6 +12,7 @@ enum hk_flags {HK_FLAG_SCHED = (1 <<3 ),HK_FLAG_TICK = (1 <<4 ),HK_FLAG_DOMAIN = (1 <<5 ), + HK_FLAG_WQ = (1 << 6), };#ifdef CONFIG_CPU_ISOLATION
kernel/sched/isolation.c +2 -1
@@ -3,6 +3,7 @@* any CPU: unbound workqueues, timers, kthreads and any offloadable work. * * Copyright (C) 2017 Red Hat, Inc., Frederic Weisbecker +* Copyright (C) 2017-2018 SUSE, Frederic Weisbecker * */
@@ -119,7 +120,7 @@ static int __init housekeeping_nohz_full_setup(char *str) {unsigned int flags; - flags =HK_FLAG_TICK |HK_FLAG_TIMER |HK_FLAG_RCU |HK_FLAG_MISC ; + flags =HK_FLAG_TICK |HK_FLAG_WQ |HK_FLAG_TIMER |HK_FLAG_RCU |HK_FLAG_MISC ;return housekeeping_setup (str, flags); }
kernel/workqueue.c +2 -1
@@ -5565,12 +5565,13 @@ static void __init wq_numa_init(void)int __init workqueue_init_early (void ) {int std_nice[NR_STD_WORKER_POOLS ] = {0 ,HIGHPRI_NICE_LEVEL }; +int hk_flags =HK_FLAG_DOMAIN |HK_FLAG_WQ ;int i, cpu;WARN_ON (__alignof__(struct pool_workqueue ) < __alignof__(long long ));BUG_ON (!alloc_cpumask_var (&wq_unbound_cpumask,GFP_KERNEL )); -cpumask_copy (wq_unbound_cpumask,housekeeping_cpumask (HK_FLAG_DOMAIN )); +cpumask_copy (wq_unbound_cpumask,housekeeping_cpumask (hk_flags)); pwq_cache =KMEM_CACHE (pool_workqueue,SLAB_PANIC );
Frederic Weisbecker
maintainerPATCH 5/7 sched/isolation: Offload residual 1Hz scheduler tick
In reply to Frederic WeisbeckerWhen a CPU runs in full dynticks mode, a 1Hz tick remains in order to keep the scheduler stats alive. However this residual tick is a burden for bare metal tasks that can't stand any interruption at all, or want to minimize them.
The usual boot parameters "nohz_full=" or "isolcpus=nohz" will now outsource these scheduler ticks to the global workqueue so that a housekeeping CPU handles those remotely. The sched_class::task_tick() implementations have been audited and look safe to be called remotely as the target runqueue and its current task are passed in parameter and don't seem to be accessed locally.
Note that in the case of using isolcpus, it's still up to the user to affine the global workqueues to the housekeeping CPUs through /sys/devices/virtual/workqueue/cpumask or domains isolation "isolcpus=nohz,domain".
--- kernel/sched/core.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched/deadline.c | 8 +++++ kernel/sched/fair.c | 7 +++- kernel/sched/idle_task.c | 8 +++++ kernel/sched/isolation.c | 4 +++ kernel/sched/rt.c | 8 +++++ kernel/sched/sched.h | 2 ++ kernel/sched/stop_task.c | 8 +++++ 8 files changed, 136 insertions(+), 1 deletion(-)
kernel/sched/core.c +92 -0
@@ -3125,6 +3125,96 @@ u64 scheduler_tick_max_deferment(void)return jiffies_to_nsecs (next - now); } + +struct tick_work { +int cpu; +struct delayed_work work; +}; + +static struct tick_work __percpu *tick_work_cpu; + +static void sched_tick_remote (struct work_struct *work) +{ +struct delayed_work *dwork =to_delayed_work (work); + struct tick_work *twork = container_of(dwork, struct tick_work, work); +int cpu = twork->cpu; +struct rq *rq =cpu_rq (cpu); +struct rq_flags rf; + +/* +* Handle the tick only if it appears the remote CPU is running in full +* dynticks mode. The check is racy by nature, but missing a tick or +* having one too much is no big deal because the scheduler tick updates +* statistics and checks timeslices in a time-independent way, regardless +* of when exactly it is running. +*/ +if (!idle_cpu (cpu) &&tick_nohz_tick_stopped_cpu (cpu)) { +struct task_struct *curr; +u64 delta; + +rq_lock_irq (rq, &rf); +update_rq_clock (rq); + curr = rq->curr; + delta =rq_clock_task (rq) - curr->se.exec_start; + +/* +* Make sure the next tick runs within a reasonable +* amount of time. +*/ +WARN_ON_ONCE (delta > (u64 )NSEC_PER_SEC *3 ); + curr->sched_class->task_tick (rq, curr,0 ); +rq_unlock_irq (rq, &rf); + } + +/* +* Run the remote tick once per second (1Hz). This arbitrary +* frequency is large enough to avoid overload but short enough +* to keep scheduler internal stats reasonably up to date. +*/ +queue_delayed_work (system_unbound_wq, dwork,HZ ); +} + +static void sched_tick_start (int cpu) +{ +struct tick_work *twork; + +if (housekeeping_cpu (cpu,HK_FLAG_TICK )) +return ; + +WARN_ON_ONCE (!tick_work_cpu); + + twork =per_cpu_ptr (tick_work_cpu, cpu); + twork->cpu = cpu; +INIT_DELAYED_WORK (&twork->work, sched_tick_remote); +queue_delayed_work (system_unbound_wq, &twork->work,HZ ); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void sched_tick_stop (int cpu) +{ +struct tick_work *twork; + +if (housekeeping_cpu (cpu,HK_FLAG_TICK )) +return ; + +WARN_ON_ONCE (!tick_work_cpu); + + twork =per_cpu_ptr (tick_work_cpu, cpu); +cancel_delayed_work_sync (&twork->work); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +int __init sched_tick_offload_init (void ) +{ + tick_work_cpu = alloc_percpu(struct tick_work); +BUG_ON (!tick_work_cpu); + +return 0 ; +} + +#else /* !CONFIG_NO_HZ_FULL */ +static inline void sched_tick_start (int cpu) { } +static inline void sched_tick_stop (int cpu) { }#endif #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
@@ -5786,6 +5876,7 @@ int sched_cpu_starting(unsigned int cpu) {set_cpu_rq_start_time (cpu);sched_rq_cpu_starting (cpu); +sched_tick_start (cpu);return 0 ; }
@@ -5797,6 +5888,7 @@ int sched_cpu_dying(unsigned int cpu)/* Handle pending wakeups and then migrate everything off */ sched_ttwu_pending (); +sched_tick_stop (cpu);rq_lock_irqsave (rq, &rf);if (rq->rd) {
kernel/sched/deadline.c +8 -0
@@ -1776,6 +1776,14 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)enqueue_pushable_dl_task (rq, p); } +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_dl (struct rq *rq,struct task_struct *p,int queued) {update_curr_dl (rq);
kernel/sched/fair.c +6 -1
@@ -9440,7 +9440,12 @@ static void rq_offline_fair(struct rq *rq)#endif /* CONFIG_SMP */ /* -* scheduler tick hitting a task of our scheduling class: +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. */ static void task_tick_fair (struct rq *rq,struct task_struct *curr,int queued) {
kernel/sched/idle_task.c +8 -0
@@ -51,6 +51,14 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)rq_last_tick_reset (rq); } +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_idle (struct rq *rq,struct task_struct *curr,int queued) { }
kernel/sched/isolation.c +4 -0
@@ -13,6 +13,7 @@#include <linux/kernel.h> #include <linux/static_key.h> #include <linux/ctype.h> +#include "sched.h" DEFINE_STATIC_KEY_FALSE (housekeeping_overriden);EXPORT_SYMBOL_GPL (housekeeping_overriden);
@@ -61,6 +62,9 @@ void __init housekeeping_init(void)static_branch_enable (&housekeeping_overriden); +if (housekeeping_flags &HK_FLAG_TICK ) +sched_tick_offload_init (); +/* We need at least one CPU to handle housekeeping work */ WARN_ON_ONCE (cpumask_empty (housekeeping_mask)); }
kernel/sched/rt.c +8 -0
@@ -2292,6 +2292,14 @@ static void watchdog(struct rq *rq, struct task_struct *p)static inline void watchdog (struct rq *rq,struct task_struct *p) { }#endif +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_rt (struct rq *rq,struct task_struct *p,int queued) {struct sched_rt_entity *rt_se = &p->rt;
kernel/sched/sched.h +2 -0
@@ -1574,6 +1574,7 @@ extern void post_init_entity_util_avg(struct sched_entity *se);#ifdef CONFIG_NO_HZ_FULL extern bool sched_can_stop_tick (struct rq *rq); +extern int __init sched_tick_offload_init (void );/* * Tick may be needed by tasks in the runqueue depending on their policy and
@@ -1598,6 +1599,7 @@ static inline void sched_update_tick_dependency(struct rq *rq) tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); }#else +static inline int sched_tick_offload_init (void ) {return 0 ; }static inline void sched_update_tick_dependency (struct rq *rq) { }#endif
kernel/sched/stop_task.c +8 -0
@@ -75,6 +75,14 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)cgroup_account_cputime (curr, delta_exec); } +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_stop (struct rq *rq,struct task_struct *curr,int queued) { }
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Offload residual 1Hz scheduler tick
sched/isolation: Offload residual 1Hz scheduler tick
Commit-ID: d84b31313ef8a8de55a2cbfb72f76f36d8c927fb Gitweb: https://git.kernel.org/tip/d84b31313ef8a8de55a2cbfb72f76f36d8c927fb Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:27 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:09 +0100
sched/isolation: Offload residual 1Hz scheduler tick
When a CPU runs in full dynticks mode, a 1Hz tick remains in order to keep the scheduler stats alive. However this residual tick is a burden for bare metal tasks that can't stand any interruption at all, or want to minimize them.
The usual boot parameters "nohz_full=" or "isolcpus=nohz" will now outsource these scheduler ticks to the global workqueue so that a housekeeping CPU handles those remotely. The sched_class::task_tick() implementations have been audited and look safe to be called remotely as the target runqueue and its current task are passed in parameter and don't seem to be accessed locally.
Note that in the case of using isolcpus, it's still up to the user to affine the global workqueues to the housekeeping CPUs through /sys/devices/virtual/workqueue/cpumask or domains isolation "isolcpus=nohz,domain".
--- kernel/sched/core.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++ kernel/sched/deadline.c | 8 +++++ kernel/sched/fair.c | 7 +++- kernel/sched/idle_task.c | 8 +++++ kernel/sched/isolation.c | 4 +++ kernel/sched/rt.c | 8 +++++ kernel/sched/sched.h | 2 ++ kernel/sched/stop_task.c | 8 +++++ 8 files changed, 136 insertions(+), 1 deletion(-)
kernel/sched/core.c +92 -0
@@ -3125,6 +3125,96 @@ u64 scheduler_tick_max_deferment(void)return jiffies_to_nsecs (next - now); } + +struct tick_work { +int cpu; +struct delayed_work work; +}; + +static struct tick_work __percpu *tick_work_cpu; + +static void sched_tick_remote (struct work_struct *work) +{ +struct delayed_work *dwork =to_delayed_work (work); + struct tick_work *twork = container_of(dwork, struct tick_work, work); +int cpu = twork->cpu; +struct rq *rq =cpu_rq (cpu); +struct rq_flags rf; + +/* +* Handle the tick only if it appears the remote CPU is running in full +* dynticks mode. The check is racy by nature, but missing a tick or +* having one too much is no big deal because the scheduler tick updates +* statistics and checks timeslices in a time-independent way, regardless +* of when exactly it is running. +*/ +if (!idle_cpu (cpu) &&tick_nohz_tick_stopped_cpu (cpu)) { +struct task_struct *curr; +u64 delta; + +rq_lock_irq (rq, &rf); +update_rq_clock (rq); + curr = rq->curr; + delta =rq_clock_task (rq) - curr->se.exec_start; + +/* +* Make sure the next tick runs within a reasonable +* amount of time. +*/ +WARN_ON_ONCE (delta > (u64 )NSEC_PER_SEC *3 ); + curr->sched_class->task_tick (rq, curr,0 ); +rq_unlock_irq (rq, &rf); + } + +/* +* Run the remote tick once per second (1Hz). This arbitrary +* frequency is large enough to avoid overload but short enough +* to keep scheduler internal stats reasonably up to date. +*/ +queue_delayed_work (system_unbound_wq, dwork,HZ ); +} + +static void sched_tick_start (int cpu) +{ +struct tick_work *twork; + +if (housekeeping_cpu (cpu,HK_FLAG_TICK )) +return ; + +WARN_ON_ONCE (!tick_work_cpu); + + twork =per_cpu_ptr (tick_work_cpu, cpu); + twork->cpu = cpu; +INIT_DELAYED_WORK (&twork->work, sched_tick_remote); +queue_delayed_work (system_unbound_wq, &twork->work,HZ ); +} + +#ifdef CONFIG_HOTPLUG_CPU +static void sched_tick_stop (int cpu) +{ +struct tick_work *twork; + +if (housekeeping_cpu (cpu,HK_FLAG_TICK )) +return ; + +WARN_ON_ONCE (!tick_work_cpu); + + twork =per_cpu_ptr (tick_work_cpu, cpu); +cancel_delayed_work_sync (&twork->work); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +int __init sched_tick_offload_init (void ) +{ + tick_work_cpu = alloc_percpu(struct tick_work); +BUG_ON (!tick_work_cpu); + +return 0 ; +} + +#else /* !CONFIG_NO_HZ_FULL */ +static inline void sched_tick_start (int cpu) { } +static inline void sched_tick_stop (int cpu) { }#endif #if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \
@@ -5786,6 +5876,7 @@ int sched_cpu_starting(unsigned int cpu) {set_cpu_rq_start_time (cpu);sched_rq_cpu_starting (cpu); +sched_tick_start (cpu);return 0 ; }
@@ -5797,6 +5888,7 @@ int sched_cpu_dying(unsigned int cpu)/* Handle pending wakeups and then migrate everything off */ sched_ttwu_pending (); +sched_tick_stop (cpu);rq_lock_irqsave (rq, &rf);if (rq->rd) {
kernel/sched/deadline.c +8 -0
@@ -1776,6 +1776,14 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)enqueue_pushable_dl_task (rq, p); } +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_dl (struct rq *rq,struct task_struct *p,int queued) {update_curr_dl (rq);
kernel/sched/fair.c +6 -1
@@ -9515,7 +9515,12 @@ static void rq_offline_fair(struct rq *rq)#endif /* CONFIG_SMP */ /* -* scheduler tick hitting a task of our scheduling class: +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. */ static void task_tick_fair (struct rq *rq,struct task_struct *curr,int queued) {
kernel/sched/idle_task.c +8 -0
@@ -51,6 +51,14 @@ static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)rq_last_tick_reset (rq); } +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_idle (struct rq *rq,struct task_struct *curr,int queued) { }
kernel/sched/isolation.c +4 -0
@@ -13,6 +13,7 @@#include <linux/kernel.h> #include <linux/static_key.h> #include <linux/ctype.h> +#include "sched.h" DEFINE_STATIC_KEY_FALSE (housekeeping_overriden);EXPORT_SYMBOL_GPL (housekeeping_overriden);
@@ -61,6 +62,9 @@ void __init housekeeping_init(void)static_branch_enable (&housekeeping_overriden); +if (housekeeping_flags &HK_FLAG_TICK ) +sched_tick_offload_init (); +/* We need at least one CPU to handle housekeeping work */ WARN_ON_ONCE (cpumask_empty (housekeeping_mask)); }
kernel/sched/rt.c +8 -0
@@ -2292,6 +2292,14 @@ static void watchdog(struct rq *rq, struct task_struct *p)static inline void watchdog (struct rq *rq,struct task_struct *p) { }#endif +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_rt (struct rq *rq,struct task_struct *p,int queued) {struct sched_rt_entity *rt_se = &p->rt;
kernel/sched/sched.h +2 -0
@@ -1574,6 +1574,7 @@ extern void post_init_entity_util_avg(struct sched_entity *se);#ifdef CONFIG_NO_HZ_FULL extern bool sched_can_stop_tick (struct rq *rq); +extern int __init sched_tick_offload_init (void );/* * Tick may be needed by tasks in the runqueue depending on their policy and
@@ -1598,6 +1599,7 @@ static inline void sched_update_tick_dependency(struct rq *rq) tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED); }#else +static inline int sched_tick_offload_init (void ) {return 0 ; }static inline void sched_update_tick_dependency (struct rq *rq) { }#endif
kernel/sched/stop_task.c +8 -0
@@ -75,6 +75,14 @@ static void put_prev_task_stop(struct rq *rq, struct task_struct *prev)cgroup_account_cputime (curr, delta_exec); } +/* +* scheduler tick hitting a task of our scheduling class. +* +* NOTE: This function can be called remotely by the tick offload that +* goes along full dynticks. Therefore no local assumption can be made +* and everything must be accessed through the @rq and @curr passed in +* parameters. +*/ static void task_tick_stop (struct rq *rq,struct task_struct *curr,int queued) { }
Frederic Weisbecker
maintainerPATCH 6/7 sched/nohz: Remove the 1 Hz tick code
In reply to Frederic WeisbeckerNow that the 1Hz tick is offloaded to workqueues, we can safely remove the residual code that used to handle it locally.
--- include/linux/sched/nohz.h | 4 ---- kernel/sched/core.c | 29 ----------------------------- kernel/sched/idle_task.c | 1 - kernel/sched/sched.h | 11 +---------- kernel/time/tick-sched.c | 6 ------ 5 files changed, 1 insertion(+), 50 deletions(-)
include/linux/sched/nohz.h +0 -4
@@ -37,8 +37,4 @@ extern void wake_up_nohz_cpu(int cpu);static inline void wake_up_nohz_cpu (int cpu) { }#endif -#ifdef CONFIG_NO_HZ_FULL -extern u64 scheduler_tick_max_deferment (void ); -#endif -#endif /* _LINUX_SCHED_NOHZ_H */
kernel/sched/core.c +0 -29
@@ -3096,35 +3096,9 @@ void scheduler_tick(void) rq->idle_balance =idle_cpu (cpu);trigger_load_balance (rq);#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. - * - * Return: Maximum deferment in nanoseconds. - */ -u64 scheduler_tick_max_deferment(void) -{ - struct rq *rq = this_rq(); - unsigned long next, now = READ_ONCE(jiffies); - - next = rq->last_sched_tick + HZ; - - if (time_before_eq(next, now)) - return 0; - - return jiffies_to_nsecs(next - now); -} struct tick_work { int cpu;
@@ -6116,9 +6090,6 @@ void __init sched_init(void) rq->last_load_update_tick = jiffies; rq->nohz_flags =0 ;#endif -#ifdef CONFIG_NO_HZ_FULL - rq->last_sched_tick =0 ; -#endif #endif /* CONFIG_SMP */ hrtick_rq_init (rq);atomic_set (&rq->nr_iowait,0 );
kernel/sched/idle_task.c +0 -1
@@ -48,7 +48,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)static void put_prev_task_idle (struct rq *rq,struct task_struct *prev) { -rq_last_tick_reset (rq); }/*
kernel/sched/sched.h +1 -10
@@ -727,9 +727,7 @@ struct rq {#endif /* CONFIG_SMP */ unsigned long nohz_flags;#endif /* CONFIG_NO_HZ_COMMON */ -#ifdef CONFIG_NO_HZ_FULL -unsigned long last_sched_tick; -#endif +/* capture load from *all* tasks on this cpu: */ struct load_weight load;unsigned long nr_load_updates;
@@ -1626,13 +1624,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)sched_update_tick_dependency (rq); } -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);
kernel/time/tick-sched.c +0 -6
@@ -748,12 +748,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, delta =KTIME_MAX ; } -#ifdef CONFIG_NO_HZ_FULL -/* Limit the tick delta to the maximum scheduler deferment */ -if (!ts->inidle) - delta =min (delta,scheduler_tick_max_deferment ()); -#endif -/* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta;
Signature · 1 line
2.7.4
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/nohz: Remove the 1 Hz tick code
sched/nohz: Remove the 1 Hz tick code
Commit-ID: dcdedb24159be3487e3dbbe1faa79ae7d00c92ac Gitweb: https://git.kernel.org/tip/dcdedb24159be3487e3dbbe1faa79ae7d00c92ac Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:28 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:09 +0100
sched/nohz: Remove the 1 Hz tick code
Now that the 1Hz tick is offloaded to workqueues, we can safely remove the residual code that used to handle it locally.
--- include/linux/sched/nohz.h | 4 ---- kernel/sched/core.c | 29 ----------------------------- kernel/sched/idle_task.c | 1 - kernel/sched/sched.h | 11 +---------- kernel/time/tick-sched.c | 6 ------ 5 files changed, 1 insertion(+), 50 deletions(-)
include/linux/sched/nohz.h +0 -4
@@ -37,8 +37,4 @@ extern void wake_up_nohz_cpu(int cpu);static inline void wake_up_nohz_cpu (int cpu) { }#endif -#ifdef CONFIG_NO_HZ_FULL -extern u64 scheduler_tick_max_deferment (void ); -#endif -#endif /* _LINUX_SCHED_NOHZ_H */
kernel/sched/core.c +0 -29
@@ -3096,35 +3096,9 @@ void scheduler_tick(void) rq->idle_balance =idle_cpu (cpu);trigger_load_balance (rq);#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. - * - * Return: Maximum deferment in nanoseconds. - */ -u64 scheduler_tick_max_deferment(void) -{ - struct rq *rq = this_rq(); - unsigned long next, now = READ_ONCE(jiffies); - - next = rq->last_sched_tick + HZ; - - if (time_before_eq(next, now)) - return 0; - - return jiffies_to_nsecs(next - now); -} struct tick_work { int cpu;
@@ -6116,9 +6090,6 @@ void __init sched_init(void) rq->last_load_update_tick = jiffies; rq->nohz_flags =0 ;#endif -#ifdef CONFIG_NO_HZ_FULL - rq->last_sched_tick =0 ; -#endif #endif /* CONFIG_SMP */ hrtick_rq_init (rq);atomic_set (&rq->nr_iowait,0 );
kernel/sched/idle_task.c +0 -1
@@ -48,7 +48,6 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)static void put_prev_task_idle (struct rq *rq,struct task_struct *prev) { -rq_last_tick_reset (rq); }/*
kernel/sched/sched.h +1 -10
@@ -727,9 +727,7 @@ struct rq {#endif /* CONFIG_SMP */ unsigned long nohz_flags;#endif /* CONFIG_NO_HZ_COMMON */ -#ifdef CONFIG_NO_HZ_FULL -unsigned long last_sched_tick; -#endif +/* capture load from *all* tasks on this cpu: */ struct load_weight load;unsigned long nr_load_updates;
@@ -1626,13 +1624,6 @@ static inline void sub_nr_running(struct rq *rq, unsigned count)sched_update_tick_dependency (rq); } -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);
kernel/time/tick-sched.c +0 -6
@@ -748,12 +748,6 @@ static ktime_t tick_nohz_stop_sched_tick(struct tick_sched *ts, delta =KTIME_MAX ; } -#ifdef CONFIG_NO_HZ_FULL -/* Limit the tick delta to the maximum scheduler deferment */ -if (!ts->inidle) - delta =min (delta,scheduler_tick_max_deferment ()); -#endif -/* Calculate the next expiry time */ if (delta < (KTIME_MAX - basemono)) expires = basemono + delta;
Frederic Weisbecker
maintainerPATCH 7/7 sched/isolation: Update nohz documentation to explain tick offload
In reply to Frederic WeisbeckerUpdate the documentation to reflect the 1Hz tick offload changes.
--- Documentation/admin-guide/kernel-parameters.txt | 11 +++++++++++ 1 file changed, 11 insertions(+)
Documentation/admin-guide/kernel-parameters.txt +11 -0
@@ -1766,6 +1766,17 @@ nohz Disable the tick when a single task runs. + + A residual 1Hz tick is offloaded to workqueues, which you + need to affine to housekeeping through the global + workqueue's affinity configured via the + /sys/devices/virtual/workqueue/cpumask sysfs file, or + by using the 'domain' flag described below. + + NOTE: by default the global workqueue runs on all CPUs, + so to protect individual CPUs the 'cpumask' file has to + be configured manually after bootup. + domain Isolate from the general SMP balancing and scheduling algorithms. Note that performing domain isolation this way
Signature · 1 line
2.7.4
Re: [PATCH 7/7] sched/isolation: Update nohz documentation to explain tick offload
Quoted 3 lines · Frederic Weisbecker
Update the documentation to reflect the 1Hz tick offload changes.
Signed-off-by Frederic Weisbecker <[email protected]>
tip-bot for Frederic Weisbecker
merge bot[tip:sched/core] sched/isolation: Update nohz documentation to explain tick offload
In reply to Frederic Weisbeckersched/isolation: Update nohz documentation to explain tick offload
Commit-ID: 083c6eeab2cc13894618d188b854f2fc6b5b2303 Gitweb: https://git.kernel.org/tip/083c6eeab2cc13894618d188b854f2fc6b5b2303 Author: Frederic Weisbecker <[email protected]> AuthorDate: Wed, 21 Feb 2018 05:17:29 +0100 Committer: Ingo Molnar <[email protected]> CommitDate: Wed, 21 Feb 2018 09:49:10 +0100
sched/isolation: Update nohz documentation to explain tick offload
Update the documentation to reflect the 1Hz tick offload changes.
--- Documentation/admin-guide/kernel-parameters.txt | 11 +++++++++++ 1 file changed, 11 insertions(+)
Documentation/admin-guide/kernel-parameters.txt +11 -0
@@ -1766,6 +1766,17 @@ nohz Disable the tick when a single task runs. + + A residual 1Hz tick is offloaded to workqueues, which you + need to affine to housekeeping through the global + workqueue's affinity configured via the + /sys/devices/virtual/workqueue/cpumask sysfs file, or + by using the 'domain' flag described below. + + NOTE: by default the global workqueue runs on all CPUs, + so to protect individual CPUs the 'cpumask' file has to + be configured manually after bootup. + domain Isolate from the general SMP balancing and scheduling algorithms. Note that performing domain isolation this way