Message-ID: <1304724519.20980.139.camel@work-vm>
Date:	Fri, 06 May 2011 16:28:39 -0700
From:	john stultz <johnstul@...ibm.com>
To:	Eric Dumazet <eric.dumazet@...il.com>
Cc:	Andi Kleen <andi@...stfloor.org>,
	Thomas Gleixner <tglx@...utronix.de>,
	lkml <linux-kernel@...r.kernel.org>,
	Paul Mackerras <paulus@...ba.org>,
	"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
	Anton Blanchard <anton@...ba.org>, Ingo Molnar <mingo@...e.hu>
Subject: Re: [RFC] time: xtime_lock is held too long

On Sat, 2011-05-07 at 01:00 +0200, Eric Dumazet wrote:
> Le vendredi 06 mai 2011 à 15:46 -0700, john stultz a écrit :
> > On Sat, 2011-05-07 at 00:30 +0200, Eric Dumazet wrote:
> > > I can see many cpus entering tick_do_update_jiffies64() and all are
> > > calling write_seqlock(&xtime_lock);
> > > 
> > > Only first one can perform the work, but all others are waiting on the
> > > spinlock, get it, change seqcount, and realize they have nothing to
> > > do...
> > 
> > Huh. So who is calling tick_do_update_jiffies64 in your case? I know the
> > sched_tick_timer and tick_nohz_handler checks to make sure
> > tick_do_timer_cpu == cpu to avoid exactly the thundering heard problem
> > on the jiffies update.
> > 
> > There's other spots that call tick_do_update_jiffies64, but I thought
> > those were more rare. So there may be something else wrong going on
> > here.
> > 
> 
> That I can answer :
[snip]
> (I added do_timestamp1/do_timestamp2) after/before write_seqlock()/write_sequnlock()
> 
>          <idle>-0     [003]   920.355377: do_timestamp1 <-tick_do_update_jiffies64
>           <idle>-0     [006]   920.355377: tick_do_update_jiffies64 <-tick_sched_timer
>           <idle>-0     [003]   920.355378: do_timestamp2 <-tick_do_update_jiffies64
>           <idle>-0     [000]   920.355657: tick_do_update_jiffies64 <-tick_check_idle
>           <idle>-0     [000]   920.355660: tick_do_update_jiffies64 <-tick_nohz_restart_sched_tick

Thomas, any clues why this would be getting hammered?



> > >  	/* Reevalute with xtime_lock held */
> > > -	write_seqlock(&xtime_lock);
> > > +	spin_lock(&xtime_lock.lock);
> > 
> > Oof.. No, this is too ugly and really just abuses the seqlock structure.
> > 
> 
> That was a hack/POC, of course, but we can cleanup seqlock.h to provide
> clean thing. A seqlock_t should include a seqcount_t and a spinlock_t.

Maybe I'm misunderstanding, but you seem to be trying to create some
sort of a layered lock from the seqlock ? I don't quite understand why
your proposing this instead of actually splitting the lock out?


> > If you really want to untangle what xtime_lock protects, you need to
> > introduce a new lock (I suggest in the timekeeper structure) to protect
> > the timekeeping data.
> > 
> > Then we can refine xtime_lock to also just protect the jiffies/tick
> > management bits as well if needed.
> 
> For the moment I am trying to understand the code. Its quite complex and
> uses a monolithic seqlock, defeating seqlock power.

Defeating seqlock power? My thoughts are that seqlocks are nice
lightweight reader/writer locks that avoid writer starvation. You seem
to be trying to redefine or extend them to be something else which is
more subtle. 

I agree, the code is complex!  I'm just not sure adding more
complicated/subtle locking mechanisms is a good solution. Instead I'd
suggest simply splitting up the locks (by using new locks) to reduce the
amount of data that is being protected by a single lock.

But again, maybe I'm misunderstanding you?

thanks
-john




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

Powered by blists - more mailing lists