lkml.org 
[lkml]   [2016]   [Nov]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCH 3/3] locking/percpu-rwsem: Avoid unnecessary writer wakeups
On Mon, Nov 21, 2016 at 01:23:44PM +0100, Oleg Nesterov wrote:
> On 11/18, Davidlohr Bueso wrote:
> >
> > +static bool __readers_active_check(struct percpu_rw_semaphore *sem)
> > +{
> > + return !(per_cpu_sum(*sem->read_count) !=0);
> > +}
>
> Hmm,
>
> return per_cpu_sum(*sem->read_count) == 0;
>
> looks more clear, but this is minor,

Very much so; that must be one of the most convoluted statements
possible :-).

>
> > int __percpu_init_rwsem(struct percpu_rw_semaphore *sem,
> > const char *name, struct lock_class_key *rwsem_key)
> > {
> > @@ -103,41 +141,11 @@ void __percpu_up_read(struct percpu_rw_semaphore *sem)
> > __this_cpu_dec(*sem->read_count);
> >
> > /* Prod writer to recheck readers_active */
> > - swake_up(&sem->writer);
> > + if (__readers_active_check(sem))
> > + swake_up(&sem->writer);
>
> Suppose we have 2 active readers which call __percpu_up_read() at the same
> time and the pending writer sleeps.
>
> What guarantees that one of these readers will observe per_cpu_sum() == 0 ?
> They both can read the old value of the remote per-cpu counter, no?

In particular, you're thinking of what provides the guarantee that the
woken CPU observes the same state the wakee saw? Isn't this one of the
Program-Order guarantees the scheduler _should_ provide?

\
 
 \ /
  Last update: 2016-11-21 13:29    [W:0.081 / U:0.696 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site