Message-ID: <1422986041.2368.3.camel@j-VirtualBox>
Subject: Re: [PATCH 4/5] locking/rwsem: Avoid deceiving lock spinners
From: Jason Low <jason.low2@hp.com>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>, Peter Zijlstra <peterz@infradead.org>,
        Ingo Molnar <mingo@kernel.org>,
        "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>,
        Michel Lespinasse <walken@google.com>, linux-kernel@vger.kernel.org,
        jason.low2@hp.com
Date: Tue, 03 Feb 2015 09:54:01 -0800
In-Reply-To: <1422983812.9530.43.camel@schen9-desk2.jf.intel.com>
References: <1422609267-15102-1-git-send-email-dave@stgolabs.net>
	 <1422609267-15102-5-git-send-email-dave@stgolabs.net>
	 <1422669098.9530.33.camel@schen9-desk2.jf.intel.com>
	 <1422671289.28351.1.camel@stgolabs.net>
	 <1422983812.9530.43.camel@schen9-desk2.jf.intel.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: 7bit
Mime-Version: 1.0
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1774
Lines: 42

On Tue, 2015-02-03 at 09:16 -0800, Tim Chen wrote:
> > > >  
> > > > +	if (READ_ONCE(sem->owner))
> > > > +		return true; /* new owner, continue spinning */
> > > > +
> > > 
> > > Do you have some comparison data of whether it is more advantageous
> > > to continue spinning when owner changes?  After the above change, 
> > > rwsem will behave more like a spin lock for write lock and 
> > > will keep spinning when the lock changes ownership.
> > 
> > But recall we still abort when need_resched, so the spinning isn't
> > infinite. Never has been.
> > 
> > >  Now during heavy
> > > lock contention, if we don't continue spinning and sleep, we may use the
> > > clock cycles for actually running other threads. 
> > 
> > Under heavy contention, time spinning will force us to ultimately block
> > anyway.
> 
> The question is under heavy contention, if we are going to block anyway,
> won't it be more advantageous not to continue spinning so we can use
> the cycles for useful task?

Hi Tim,

Now that we have the OSQ logic, under heavy contention, there will still
only be 1 thread that is spinning on owner at a time. So if another
thread is able to obtain the lock before the spinner, we're only sending
the top spinner of the lock to the slowpath. As long as the new lock
owner is running, there is a chance for this top spinner to obtain the
lock, and spinning would be useful.

Since we have the need_resched() checks, this thread will block when
there really is another task that should run over the spinning thread.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/