Messages in this thread | | | Date | Wed, 30 Jul 2014 00:04:45 +0200 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 09/10] nohz: Switch nohz full timekeeper to dynticks idle on top of sysidle detection |
| |
On Tue, Jul 29, 2014 at 02:17:53PM +0200, Peter Zijlstra wrote: > On Mon, Jul 28, 2014 at 07:37:35PM +0200, Frederic Weisbecker wrote: > > > @@ -745,7 +747,7 @@ static bool can_stop_idle_tick(int cpu, struct tick_sched *ts) > > * if there are full dynticks CPUs around > > */ > > if (tick_do_timer_cpu == cpu) > > - return false; > > + return rcu_sys_is_idle(); > > } > > I still feel its entirely upside down to rely on RCU for this...
RCU had this feature internally for a while. Then comes nohz. I guess in a perfect world we would make it a library that RCU and nohz could use. It's probably possible to do but right now it is too tied to RCU internals.
| |