Re: [PATCH] mm,slab,vmscan: accumulate gradual pressure on small slabs

[Andrew Morton]

On Mon, 28 Jan 2019 15:03:28 -0500 Rik van Riel <riel@xxxxxxxxxxx> wrote:

> On Mon, 2019-01-28 at 11:54 -0800, Andrew Morton wrote:
> > On Mon, 28 Jan 2019 14:35:35 -0500 Rik van Riel <riel@xxxxxxxxxxx>
> > wrote:
> > 
> > >  	/*
> > >  	 * Make sure we apply some minimal pressure on default priority
> > > -	 * even on small cgroups. Stale objects are not only consuming
> > > memory
> > > +	 * even on small cgroups, by accumulating pressure across
> > > multiple
> > > +	 * slab shrinker runs. Stale objects are not only consuming
> > > memory
> > >  	 * by themselves, but can also hold a reference to a dying
> > > cgroup,
> > >  	 * preventing it from being reclaimed. A dying cgroup with all
> > >  	 * corresponding structures like per-cpu stats and kmem caches
> > >  	 * can be really big, so it may lead to a significant waste of
> > > memory.
> > >  	 */
> > > -	delta = max_t(unsigned long long, delta, min(freeable,
> > > batch_size));
> > > +	if (!delta) {
> > > +		shrinker->small_scan += freeable;
> > > +
> > > +		delta = shrinker->small_scan >> priority;
> > > +		shrinker->small_scan -= delta << priority;
> > > +
> > > +		delta *= 4;
> > > +		do_div(delta, shrinker->seeks);
> > 
> > What prevents shrinker->small_scan from over- or underflowing over
> > time?
> 
> We only go into this code path if
> delta >> DEF_PRIORITY is zero.
> 
> That is, freeable is smaller than 4096.
> 

I'm still not understanding.  If `freeable' always has a value of (say)
1, we'll eventually overflow shrinker->small_scan?  Or at least, it's
unobvious why this cannot happen.