Re: [RFC][PATCH 12/13] stop_machine: Remove lglock

From: Peter Zijlstra
Date: Wed Jun 24 2015 - 13:58:48 EST


On Wed, Jun 24, 2015 at 10:10:17AM -0700, Paul E. McKenney wrote:
> > The thing is, once you start bailing on this condition your 'queue'
> > drains very fast and this is around the same time sync_rcu() would've
> > released the waiters too.
>
> In my experience, this sort of thing simply melts down on large systems.
> I am reworking this with multiple locks so as to keep the large-system
> contention down to a dull roar.

So with the MCS queue we're got less global trashing than you had with
the start/done tickets. Only the queue head on enqueue.

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