Re: [PATCH v3 04/19] mm: slub: implement SLUB version of obj_to_index()

[Roman Gushchin]

On Wed, Apr 22, 2020 at 11:52:13PM +0000, Christoph Lameter wrote:
> On Wed, 22 Apr 2020, Roman Gushchin wrote:
> 
> >  enum stat_item {
> >  	ALLOC_FASTPATH,		/* Allocation from cpu slab */
> > @@ -86,6 +87,7 @@ struct kmem_cache {
> >  	unsigned long min_partial;
> >  	unsigned int size;	/* The size of an object including metadata */
> >  	unsigned int object_size;/* The size of an object without metadata */
> > +	struct reciprocal_value reciprocal_size;
> 
> 
> This needs to be moved further back since it is not an item that needs to
> be cache hot for the hotpaths.

It could be relatively hot, because it's accessed for reading on every
accounted allocation.

> Place it with "align", inuse etc?
> 
> Hmmm. the same applies to min_partial maybe?
> 
> 

And min_partial should much colder.

So maybe a patch on top of the series which moves both fields can work?

Thanks!