From: Oleg Nesterov <oleg@redhat.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: Davidlohr Bueso <dave@stgolabs.net>,
mingo@kernel.org, john.stultz@linaro.org, dimitrysh@google.com,
linux-kernel@vger.kernel.org, Davidlohr Bueso <dbueso@suse.de>
Subject: Re: [PATCH 3/3] locking/percpu-rwsem: Avoid unnecessary writer wakeups
Date: Mon, 21 Nov 2016 13:47:23 +0100 [thread overview]
Message-ID: <20161121124722.GA1459@redhat.com> (raw)
In-Reply-To: <20161121122935.GD3092@twins.programming.kicks-ass.net>
On 11/21, Peter Zijlstra wrote:
>
> On Mon, Nov 21, 2016 at 01:23:44PM +0100, Oleg Nesterov wrote:
> > > 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?
No, no, I meant that afaics both readers can see per_cpu_sum() != 0 and
thus the writer won't be woken up. Till the next down_read/up_read.
Suppose that we have 2 CPU's, both counters == 1, both readers decrement.
its counter at the same time.
READER_ON_CPU_0 READER_ON_CPU_1
--ctr_0; --ctr_1;
if (ctr_0 + ctr_1) if (ctr_0 + ctr_1)
wakeup(); wakeup();
Why we can't miss a wakeup?
This patch doesn't even add a barrier, but I think wmb() won't be enough
anyway.
Oleg.
next prev parent reply other threads:[~2016-11-21 12:47 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2016-11-18 18:54 [PATCH -tip 0/3] locking/percpu-rwsem: writer-side optimizations Davidlohr Bueso
2016-11-18 18:54 ` [PATCH 1/3] locking/percpu-rwsem: Move text file into Documentation/locking/ Davidlohr Bueso
2016-11-18 18:54 ` [PATCH 2/3] locking/percpu-rwsem: Replace bulky wait-queues with swait Davidlohr Bueso
2016-11-21 12:55 ` Oleg Nesterov
2016-11-21 17:26 ` Davidlohr Bueso
2016-12-03 2:18 ` [PATCH v2 2/3] locking/percpu-rwsem: Rework writer block/wake to not use wait-queues Davidlohr Bueso
2016-12-05 8:36 ` Peter Zijlstra
2016-12-05 11:26 ` Oleg Nesterov
2016-12-05 11:32 ` Oleg Nesterov
2016-12-05 17:37 ` Davidlohr Bueso
2016-12-05 17:19 ` Oleg Nesterov
2016-12-05 17:13 ` Oleg Nesterov
2016-11-18 18:54 ` [PATCH 3/3] locking/percpu-rwsem: Avoid unnecessary writer wakeups Davidlohr Bueso
2016-11-21 12:23 ` Oleg Nesterov
2016-11-21 12:29 ` Peter Zijlstra
2016-11-21 12:47 ` Oleg Nesterov [this message]
2016-11-21 15:07 ` Oleg Nesterov
2016-11-22 3:59 ` Davidlohr Bueso
2016-11-23 14:43 ` Oleg Nesterov
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20161121124722.GA1459@redhat.com \
--to=oleg@redhat.com \
--cc=dave@stgolabs.net \
--cc=dbueso@suse.de \
--cc=dimitrysh@google.com \
--cc=john.stultz@linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@kernel.org \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).