Re: [PATCH v3 3/9] slab: defer slab_destroy in free_block()

[Joonsoo Kim]

On Tue, Jul 01, 2014 at 03:25:04PM -0700, David Rientjes wrote:
> On Tue, 1 Jul 2014, Joonsoo Kim wrote:
> 
> > In free_block(), if freeing object makes new free slab and number of
> > free_objects exceeds free_limit, we start to destroy this new free slab
> > with holding the kmem_cache node lock. Holding the lock is useless and,
> > generally, holding a lock as least as possible is good thing. I never
> > measure performance effect of this, but we'd be better not to hold the lock
> > as much as possible.
> > 
> > Commented by Christoph:
> >   This is also good because kmem_cache_free is no longer called while
> >   holding the node lock. So we avoid one case of recursion.
> > 
> > Acked-by: Christoph Lameter <cl@xxxxxxxxx>
> > Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
> 
> Not sure what happened to my
> 
> Acked-by: David Rientjes <rientjes@xxxxxxxxxx>
> 
> from http://marc.info/?l=linux-kernel&m=139951092124314, and for the 
> record, I still think the free_block() "list" formal should be commented.


Really sorry about that.
My mail client didn't have this mail due to unknow reason, so I missed it.

Here goes the new one with applying your comment.

--------->8------------