Re: [PATCH 1/2] memcg: flatten task_struct->memcg_oom

[Peter Zijlstra <peterz@infradead.org>]

On Fri, Dec 11, 2015 at 11:25:54AM -0500, Tejun Heo wrote:
> Hello, Peter, Ingo.
> 
> On Wed, Nov 25, 2015 at 06:44:49PM +0100, Peter Zijlstra wrote:
> > On Wed, Nov 25, 2015 at 06:31:41PM +0300, Andrey Ryabinin wrote:
> > > > +       /* scheduler bits, serialized by scheduler locks */
> > > >         unsigned sched_reset_on_fork:1;
> > > >         unsigned sched_contributes_to_load:1;
> > > >         unsigned sched_migrated:1;
> > > > +       unsigned __padding_sched:29;
> > > 
> > > AFAIK the order of bit fields is implementation defined, so GCC could
> > > sort all these bits as it wants.
> > 
> > We're relying on it doing DTRT in other places, so I'm fairly confident
> > this'll work, otoh
> > 
> > > You could use unnamed zero-widht bit-field to force padding:
> > > 
> > >          unsigned :0; //force aligment to the next boundary.
> > 
> > That's a nice trick I was not aware of, thanks!
> 
> Has this been fixed yet?  While I'm not completely sure and I don't
> think there's a way to be certain after the fact, we have a single
> report of a machine which is showing ~4G as loadavg and one plausible
> explanation could be that one of the ->nr_uninterruptible counters
> underflowed from sched_contributes_to_load getting corrupted, so it'd
> be great to get this one fixed soon.

Nope, lemme write a Changelog and queue it. Thanks for the reminder.

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>