Messages in this thread | | | Date | Tue, 18 Jun 2013 16:27:45 +0200 | From | Frederic Weisbecker <> | Subject | Re: [PATCH 6/8] sched: task_sched_runtime introduce micro optimization |
| |
On Sun, May 26, 2013 at 05:35:47PM -0400, kosaki.motohiro@gmail.com wrote: > From: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> > > rq lock in task_sched_runtime() is necessary for two reasons. 1) > accessing se.sum_exec_runtime is not atomic on 32bit and 2) > do_task_delta_exec() require it. > > So, 64bit can avoid holding rq lock when add_delta is false and > delta_exec is 0. > > Cc: Olivier Langlois <olivier@trillion01.com> > Cc: Thomas Gleixner <tglx@linutronix.de> > Cc: Frederic Weisbecker <fweisbec@gmail.com> > Cc: Ingo Molnar <mingo@kernel.org> > Suggested-by: Paul Turner <pjt@google.com> > Acked-by: Peter Zijlstra <peterz@infradead.org> > Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> > --- > kernel/sched/core.c | 15 +++++++++++++++ > 1 files changed, 15 insertions(+), 0 deletions(-) > > diff --git a/kernel/sched/core.c b/kernel/sched/core.c > index 96512e9..0f859cc 100644 > --- a/kernel/sched/core.c > +++ b/kernel/sched/core.c > @@ -2692,6 +2692,21 @@ unsigned long long task_sched_runtime(struct task_struct *p, bool add_delta) > struct rq *rq; > u64 ns = 0; > > +#ifdef CONFIG_64BIT > + /* > + * 64-bit doesn't need locks to atomically read a 64bit value. So we > + * have two optimization chances, 1) when caller doesn't need > + * delta_exec and 2) when the task's delta_exec is 0. The former is > + * obvious. The latter is complicated. reading ->on_cpu is racy, but > + * this is ok. If we race with it leaving cpu, we'll take a lock. So > + * we're correct. If we race with it entering cpu, unaccounted time > + * is 0. This is indistinguishable from the read occurring a few > + * cycles earlier. > + */ > + if (!add_delta || !p->on_cpu) > + return p->se.sum_exec_runtime;
I'm not sure this is correct from an smp ordering POV. p->on_cpu may appear to be 0 whereas the task is actually running for a while and p->se.sum_exec_runtime can then be past the actual value on the remote CPU.
> +#endif > + > rq = task_rq_lock(p, &flags); > ns = p->se.sum_exec_runtime; > if (add_delta) > -- > 1.7.1 >
| |