nohz_full: only wakeup target CPUs when notifying new tick dependency (v4)
Subsystems (2)
PATCH 3/3 nohz: tick_nohz_kick_task: only IPI if remote task is running
In reply to Marcelo TosattiIf the task is not running, run_posix_cpu_timers has nothing to elapsed, so spare IPI in that case.
kernel/sched/core.c +6 -0
@@ -9182,3 +9182,9 @@ void call_trace_sched_update_nr_running( {trace_sched_update_nr_running_tp (rq, count); } + +bool task_on_rq (struct task_struct *p) +{ +return p->on_rq ==TASK_ON_RQ_QUEUED ; +} +
include/linux/sched.h +2 -0
@@ -232,6 +232,8 @@ extern void io_schedule_finish(int tokenextern long io_schedule_timeout (long timeout);extern void io_schedule (void ); +extern bool task_on_rq (struct task_struct *p); +/** * struct prev_cputime - snapshot of system and user cputime * @utime: time spent in user mode
kernel/time/tick-sched.c +17 -2
@@ -324,8 +324,6 @@ void tick_nohz_full_kick_cpu(int cpu)static void tick_nohz_kick_task (struct task_struct *tsk) { -int cpu =task_cpu (tsk); -/* * If the task concurrently migrates to another cpu, * we guarantee it sees the new tick dependency upon
@@ -340,6 +338,23 @@ static void tick_nohz_kick_task(struct t* tick_nohz_task_switch() smp_mb() (atomic_fetch_or()) * LOAD p->tick_dep_mask LOAD p->cpu */ +int cpu =task_cpu (tsk); + +/* +* If the task is not running, run_posix_cpu_timers +* has nothing to elapsed, can spare IPI in that +* case. +* +* activate_task() STORE p->tick_dep_mask +* STORE p->task_on_rq +* __schedule() (switch to task 'p') smp_mb() (atomic_fetch_or()) +* LOCK rq->lock LOAD p->task_on_rq +* smp_mb__after_spin_lock() +* tick_nohz_task_switch() +* LOAD p->tick_dep_mask +*/ +if (!task_on_rq (tsk)) +return ;preempt_disable ();if (cpu_online (cpu))
PATCH 2/3 nohz: change signal tick dependency to wakeup CPUs of member tasks
In reply to Marcelo TosattiRather than waking up all nohz_full CPUs on the system, only wakeup the target CPUs of member threads of the signal.
Reduces interruptions to nohz_full CPUs.
kernel/time/tick-sched.c +11 -1
@@ -446,7 +446,17 @@ EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_ta*/ void tick_nohz_dep_set_signal (struct signal_struct *sig,enum tick_dep_bits bit) { -tick_nohz_dep_set_all (&sig->tick_dep_mask, bit); +int prev; + + prev =atomic_fetch_or (BIT (bit), &sig->tick_dep_mask); +if (!prev) { +struct task_struct *t; + +rcu_read_lock (); +__for_each_thread (sig, t) +tick_nohz_kick_task (t); +rcu_read_unlock (); + } }void tick_nohz_dep_clear_signal (struct signal_struct *sig,enum tick_dep_bits bit)
cover nohz_full: only wakeup target CPUs when notifying new tick dependency (v4)
When enabling per-CPU posix timers, an IPI to nohz_full CPUs might be performed (to re-read the dependencies and possibly not re-enter nohz_full on a given CPU).
A common case is for applications that run on nohz_full= CPUs to not use POSIX timers (eg DPDK). This patch changes the notification to only IPI the target CPUs where the task(s) whose tick dependencies are being updated are executing.
This reduces interruptions to nohz_full= CPUs.
v4: only IPI if the remote task is on the remote runqueue (PeterZ/Frederic)
v3: replace superfluous rcu_read_lock with lockdep_assert (PeterZ)
PATCH 1/3 nohz: only wakeup a single target cpu when kicking a task
When adding a tick dependency to a task, its necessary to wakeup the CPU where the task resides to reevaluate tick dependencies on that CPU.
However the current code wakes up all nohz_full CPUs, which is unnecessary.
Switch to waking up a single CPU, by using ordering of writes to task->cpu and task->tick_dep_mask.
From: Frederic Weisbecker <[email protected]>
kernel/time/tick-sched.c +27 -13
@@ -322,6 +322,31 @@ void tick_nohz_full_kick_cpu(int cpu)irq_work_queue_on (&per_cpu (nohz_full_kick_work, cpu), cpu); } +static void tick_nohz_kick_task (struct task_struct *tsk) +{ +int cpu =task_cpu (tsk); + +/* +* If the task concurrently migrates to another cpu, +* we guarantee it sees the new tick dependency upon +* schedule. +* +* +* set_task_cpu(p, cpu); +* STORE p->cpu = @cpu +* __schedule() (switch to task 'p') +* LOCK rq->lock +* smp_mb__after_spin_lock() STORE p->tick_dep_mask +* tick_nohz_task_switch() smp_mb() (atomic_fetch_or()) +* LOAD p->tick_dep_mask LOAD p->cpu +*/ + +preempt_disable (); +if (cpu_online (cpu)) +tick_nohz_full_kick_cpu (cpu); +preempt_enable (); +} +/* * Kick all full dynticks CPUs in order to force these to re-evaluate * their dependency on the tick and restart it if necessary.
@@ -404,19 +429,8 @@ EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_cp*/ void tick_nohz_dep_set_task (struct task_struct *tsk,enum tick_dep_bits bit) { -if (!atomic_fetch_or (BIT (bit), &tsk->tick_dep_mask)) { -if (tsk == current) { -preempt_disable (); -tick_nohz_full_kick (); -preempt_enable (); - }else { -/* -* Some future tick_nohz_full_kick_task() -* should optimize this. -*/ -tick_nohz_full_kick_all (); - } - } +if (!atomic_fetch_or (BIT (bit), &tsk->tick_dep_mask)) +tick_nohz_kick_task (tsk); }EXPORT_SYMBOL_GPL (tick_nohz_dep_set_task);