Re: [PATCH v2] futex: lower the lock contention on the HB lock during wake up

[Mike Galbraith]

On Wed, 2015-06-17 at 16:28 +0200, Sebastian Andrzej Siewior wrote:
> On 06/17/2015 04:17 PM, Mike Galbraith wrote:
> > On Wed, 2015-06-17 at 10:33 +0200, Sebastian Andrzej Siewior wrote:
> >> wake_futex_pi() wakes the task before releasing the hash bucket lock
> >> (HB). The first thing the woken up task usually does is to acquire the
> >> lock which requires the HB lock. On SMP Systems this leads to blocking
> >> on the HB lock which is released by the owner shortly after.
> >> This patch rearranges the unlock path by first releasing the HB lock and
> >> then waking up the task.
> >>
> >> [bigeasy: redo ontop of lockless wake-queues]
> >> Signed-off-by: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
> >> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@xxxxxxxxxxxxx>
> > 
> > 4.1-rc8-rt4 contains this via 4.0-rt4, and seems fine on my 64 core
> > DL980.  I ran a few iterations of futextests and stockfish, then mixed
> > two loops of futextest at different rt prios, with stockfish also rt,
> > and ltplight as tossed in as... crack filler.  Box is still doing that,
> > is way too busy, but not griping about it.  
> 
> There are two patches mostly doing the same thing. The patch posted
> here is a redo ontop of "lockless wake-queues". It does hb-unlock,
> wakeup, de-boost. The patch merged into -RT is the original approach
> not using "lockless wake-queues" and performing wakeup, hb-unlock,
> de-boost.
> 
> I plan to get into -RT the final solution once it hits upstream.

I plugged patch1 and tip version into rt and beat it, seems solid.

Converting the rest of rtmutex.c to use wake queues with ->save_state to
select wake function went less well.  Kernel does a good impersonation
of a working kernel until I beat it up, then it loses wakeups.  Hohum,
so much for yet another early morning tinker session.

	-Mike

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
Please read the FAQ at  http://www.tux.org/lkml/