RE: [PATCH 1/3] slub: set a criteria for slub node partial adding

[Christoph Lameter]

On Wed, 14 Dec 2011, Eric Dumazet wrote:

> > Many people have done patchsets like this.
>
> Things changed a lot recently. There is room for improvements.
>
> At least we can exchange ideas _before_ coding a new patchset ?

Sure but I hope we do not simply rehash what has been said before and
recode what others have code in years past.

> > There are various permutations
> > on SL?B (I dont remember them all SLEB, SLXB, SLQB etc) that have been
> > proposed over the years. Caches tend to grow and get rather numerous (see
> > SLAB) and the design of SLUB was to counter that. There is a reason it was
> > called SLUB. The U stands for Unqueued and was intended to avoid the
> > excessive caching problems that I ended up when reworking SLAB for NUMA
> > support.
>
> Current 'one active slab' per cpu is a one level cache.
>
> It really is a _queue_ containing a fair amount of objects.

In some sense you are right. It is a set of objects linked together. That
can be called a queue and it has certain cache hot effects. It is not a
qeueue in the SLAB sense meaning a configurable array of pointers.

> My initial idea would be to use a cache of 4 slots per cpu, but be able
> to queue many objects per slot, if they all belong to same slab/page.

Nick did that. Please read up on his work. I think it was named SLQB.
--
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/