On Wed, 4 Mar 2020 13:39:41 -0800
Xi Wang <xii@xxxxxxxxxx> wrote:
> The main purpose of kernel watchdog is to test whether scheduler can
> still schedule tasks on a cpu. In order to reduce latency from
> periodically invoking watchdog reset in thread context, we can simply
> touch watchdog from pick_next_task in scheduler. Compared to actually
> resetting watchdog from cpu stop / migration threads, we lose coverage
> on: a migration thread actually get picked and we actually context
> switch to the migration thread. Both steps are heavily protected by
> kernel locks and unlikely to silently fail. Thus the change would
> provide the same level of protection with less overhead.
Have any measurements showing the drop in overhead?
>
> The new way vs the old way to touch the watchdogs is configurable
> from:
>
> /proc/sys/kernel/watchdog_touch_in_thread_interval
>
> The value means:
> 0: Always touch watchdog from pick_next_task
> 1: Always touch watchdog from migration thread
> N (N>0): Touch watchdog from migration thread once in every N
> invocations, and touch watchdog from pick_next_task for
> other invocations.
>
> Suggested-by: Paul Turner <pjt@xxxxxxxxxx>
> Signed-off-by: Xi Wang <xii@xxxxxxxxxx>
> ---
> kernel/sched/core.c | 36 ++++++++++++++++++++++++++++++++++--
> kernel/sysctl.c | 11 ++++++++++-
> kernel/watchdog.c | 39 ++++++++++++++++++++++++++++++++++-----
> 3 files changed, 78 insertions(+), 8 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 1a9983da4408..9d8e00760d1c 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3898,6 +3898,27 @@ static inline void schedule_debug(struct task_struct *prev, bool preempt)
> schedstat_inc(this_rq()->sched_count);
> }
>
> +#ifdef CONFIG_SOFTLOCKUP_DETECTOR
> +
> +DEFINE_PER_CPU(bool, sched_should_touch_watchdog);
> +
> +void touch_watchdog_from_sched(void);
> +
> +/* Helper called by watchdog code */
> +void resched_for_watchdog(void)
> +{
> + unsigned long flags;
> + struct rq *rq = this_rq();
> +
> + this_cpu_write(sched_should_touch_watchdog, true);
Perhaps we should have a preempt_disable, otherwise it is possible
to get preempted here.
-- Steve
> + raw_spin_lock_irqsave(&rq->lock, flags);
> + /* Trigger resched for code in pick_next_task to touch watchdog */
> + resched_curr(rq);
> + raw_spin_unlock_irqrestore(&rq->lock, flags);
> +}
> +
> +#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
> +
