Messages in this thread | | | Date | Mon, 1 Jul 2013 08:33:59 -0700 | From | Josh Triplett <> | Subject | Re: [PATCH RFC nohz_full v2 3/7] nohz_full: Add per-CPU idle-state tracking |
| |
On Fri, Jun 28, 2013 at 01:10:18PM -0700, Paul E. McKenney wrote: > From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> > > This commit adds the code that updates the rcu_dyntick structure's > new fields to track the per-CPU idle state based on interrupts and > transitions into and out of the idle loop (NMIs are ignored because NMI > handlers cannot cleanly read out the time anyway). This code is similar > to the code that maintains RCU's idea of per-CPU idleness, but differs > in that RCU treats CPUs running in user mode as idle, where this new > code does not. [...] > --- a/kernel/rcutree_plugin.h > +++ b/kernel/rcutree_plugin.h > @@ -2380,6 +2380,76 @@ static void rcu_kick_nohz_cpu(int cpu) > #ifdef CONFIG_NO_HZ_FULL_SYSIDLE > > /* > + * Invoked to note exit from irq or task transition to idle. Note that > + * usermode execution does -not- count as idle here! The caller must > + * have disabled interrupts.
Can you explain in the comments why this code doesn't treat userspace as idle/quiesced?
- Josh Triplett
| |