[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20201008122256.GW2628@hirez.programming.kicks-ass.net>
Date: Thu, 8 Oct 2020 14:22:56 +0200
From: Peter Zijlstra <peterz@...radead.org>
To: Marcelo Tosatti <mtosatti@...hat.com>
Cc: linux-kernel@...r.kernel.org,
Frederic Weisbecker <frederic@...nel.org>,
Nitesh Narayan Lal <nitesh@...hat.com>,
Peter Xu <peterx@...hat.com>
Subject: Re: [patch 1/2] nohz: only wakeup a single target cpu when kicking a
task
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@...nel.org>
> Suggested-by: Peter Zijlstra <peterz@...radead.org>
> Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
> Signed-off-by: Marcelo Tosatti <mtosatti@...hat.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.
Powered by blists - more mailing lists