Messages in this thread | | | Date | Tue, 13 Oct 2020 14:13:28 -0300 | From | Marcelo Tosatti <> | Subject | Re: [patch 1/2] nohz: only wakeup a single target cpu when kicking a task |
| |
On Thu, Oct 08, 2020 at 09:54:44PM +0200, Frederic Weisbecker wrote: > On Thu, Oct 08, 2020 at 02:54:09PM -0300, Marcelo Tosatti wrote: > > On Thu, Oct 08, 2020 at 02:22:56PM +0200, Peter Zijlstra wrote: > > > On Wed, Oct 07, 2020 at 03:01:52PM -0300, Marcelo Tosatti wrote: > > > > 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 <frederic@kernel.org> > > > > Suggested-by: Peter Zijlstra <peterz@infradead.org> > > > > Signed-off-by: Frederic Weisbecker <frederic@kernel.org> > > > > Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com> > > > > > > > > Index: linux-2.6/kernel/time/tick-sched.c > > > > =================================================================== > > > > --- linux-2.6.orig/kernel/time/tick-sched.c > > > > +++ linux-2.6/kernel/time/tick-sched.c > > > > @@ -274,6 +274,31 @@ 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(); > > > > +} > > > > > > So we need to kick the CPU unconditionally, or only when the task is > > > actually running? AFAICT we only care about current->tick_dep_mask. > > > > tick is necessary to execute run_posix_cpu_timers, from tick interrupt, > > even if task is not running. > > Yes but if the task isn't running, run_posix_cpu_timers() doesn't have > anything to elapse. So indeed we can spare the IPI if the task is not > running. Provided ordering makes sure that the task sees the new dependency > when it schedules in of course.
True.
* p->on_cpu <- { 0, 1 }: * * is set by prepare_task() and cleared by finish_task() such that it will be * set before p is scheduled-in and cleared after p is scheduled-out, both * under rq->lock. Non-zero indicates the task is running on its CPU.
CPU-0 (tick_set_dep) CPU-1 (task switch)
STORE p->tick_dep_mask smp_mb() (atomic_fetch_or()) LOAD p->on_cpu
context_switch(prev, next) STORE next->on_cpu = 1 ... [*]
LOAD current->tick_dep_mask
Don't see any explicit memory barrier in the [*] section?
| |