On Thu, May 24, 2018 at 05:47:52PM -0400, Steven Rostedt wrote:
> On Wed, 23 May 2018 13:04:58 -0700
> "Paul E. McKenney" <paul...@linux.vnet.ibm.com> wrote:
>
> > Looks plausible to me!
> >
>
> BTW looking at the code:
>
> > /* Invoke the callbacks. */
> > while (list) {
> > next = list->next;
> > local_bh_disable();
> > list->func(list);
> > local_bh_enable();
> > list = next;
> > cond_resched();
> > }
> > schedule_timeout_uninterruptible(HZ/10);
>
> What's the purpose of this final sleep?
To avoid any possibility of rcu_tasks_kthread() getting into a tight loop.
Thanx, Paul
