LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Davidlohr Bueso <dave@stgolabs.net>
Cc: Ingo Molnar <mingo@kernel.org>,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
	Jason Low <jason.low2@hp.com>,
	Michel Lespinasse <walken@google.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	linux-kernel@vger.kernel.org, Davidlohr Bueso <dbueso@suse.de>
Subject: Re: [PATCH 5/6] locking/rwsem: Optimize slowpath/sleeping
Date: Tue, 27 Jan 2015 18:34:42 +0100	[thread overview]
Message-ID: <20150127173442.GK21418@twins.programming.kicks-ass.net> (raw)
In-Reply-To: <1422257769-14083-6-git-send-email-dave@stgolabs.net>

On Sun, Jan 25, 2015 at 11:36:08PM -0800, Davidlohr Bueso wrote:
> When blocking , we incur in multiple barriers when setting the
> task's uninterruptable state. This is particularly bad when the
> lock keeps getting stolen from the task trying to acquire the sem.
> These changes propose delaying setting the task's new state until
> we are sure that calling schedule is inevitable.
> 
> This implies that we do the trylock and active check (both basically
> ->counter checks) as TASK_RUNNING. For the trylock we hold the wait
> lock with interrupts disabled, so no risk there. And for the active
> check, the window for which we could get interrupted is quite small
> and makes no tangible difference.
> 
> This patch increases Unixbench's 'execl' throughput by 25% on a 40
> core machine.
> 
> Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
> ---
>  kernel/locking/rwsem-xadd.c | 20 +++++++++++++++-----
>  1 file changed, 15 insertions(+), 5 deletions(-)
> 
> diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
> index 18a50da..88b3468 100644
> --- a/kernel/locking/rwsem-xadd.c
> +++ b/kernel/locking/rwsem-xadd.c
> @@ -459,17 +459,27 @@ struct rw_semaphore __sched *rwsem_down_write_failed(struct rw_semaphore *sem)
>  		count = rwsem_atomic_update(RWSEM_WAITING_BIAS, sem);
>  
>  	/* wait until we successfully acquire the lock */
>  	while (true) {
>  		if (rwsem_try_write_lock(count, sem))
>  			break;
> +
> +		__set_current_state(TASK_UNINTERRUPTIBLE);
>  		raw_spin_unlock_irq(&sem->wait_lock);
>  
> +		/*
> +		 * When there are active locks after we wake up,
> +		 * the lock was probably stolen from us. Thus,
> +		 * go immediately back to sleep and avoid taking
> +		 * the wait_lock.
> +		 */
> +		while (true) {
>  			schedule();
> +
> +			count = READ_ONCE(sem->count);
> +			if (!(count & RWSEM_ACTIVE_MASK))
> +				break;
> +			__set_current_state(TASK_UNINTERRUPTIBLE);
> +		}

So its late and I'm not seeing it; why is this safe? How will we not
miss the wakeup that makes condition true?

>  
>  		raw_spin_lock_irq(&sem->wait_lock);
>  	}

  reply	other threads:[~2015-01-27 17:34 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-01-26  7:36 [PATCH -tip 0/6] rwsem: Fine tuning Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 1/6] locking/rwsem: Use task->state helpers Davidlohr Bueso
2015-02-04 14:38   ` [tip:locking/core] " tip-bot for Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 2/6] locking/rwsem: Document barrier need when waking tasks Davidlohr Bueso
2015-01-27 17:07   ` Peter Zijlstra
2015-01-27 20:30     ` Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 3/6] locking/rwsem: Set lock ownership ASAP Davidlohr Bueso
2015-01-27 17:10   ` Peter Zijlstra
2015-01-27 19:18     ` Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 4/6] locking/rwsem: Avoid deceiving lock spinners Davidlohr Bueso
2015-01-27 17:23   ` Jason Low
2015-01-28  3:54     ` Davidlohr Bueso
2015-01-28 17:01       ` Tim Chen
2015-01-28 21:03       ` Jason Low
2015-01-29  1:10         ` Davidlohr Bueso
2015-01-29 20:13           ` Jason Low
2015-01-29 20:18             ` Jason Low
2015-01-29 23:15               ` Davidlohr Bueso
2015-01-30  1:52                 ` Refactoring mutex spin on owner code Jason Low
2015-01-30  7:14                   ` Davidlohr Bueso
2015-01-30  7:51                     ` Peter Zijlstra
2015-01-26  7:36 ` [PATCH 5/6] locking/rwsem: Optimize slowpath/sleeping Davidlohr Bueso
2015-01-27 17:34   ` Peter Zijlstra [this message]
2015-01-27 21:57     ` Davidlohr Bueso
2015-01-26  7:36 ` [PATCH 6/6] locking/rwsem: Check for active lock before bailing on spinning Davidlohr Bueso
2015-01-27 18:11   ` Jason Low

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=20150127173442.GK21418@twins.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=dave@stgolabs.net \
    --cc=dbueso@suse.de \
    --cc=jason.low2@hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=tim.c.chen@linux.intel.com \
    --cc=walken@google.com \
    --subject='Re: [PATCH 5/6] locking/rwsem: Optimize slowpath/sleeping' \
    /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

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).