Re: [PATCH RFC] fix RCU-callback-after-kmem_cache_destroy problem in sl[aou]b

[Pekka Enberg <penberg@cs.helsinki.fi>]

Hi Christoph,

On Tue, 30 Jun 2009, Pekka Enberg wrote:
>> I don't even claim to understand all the RCU details here but I don't
>> see why we should care about _kmem_cache_destroy()_ performance at
>> this level. Christoph, hmmm?

On Tue, Jun 30, 2009 at 5:20 PM, Christoph
Lameter<cl@linux-foundation.org> wrote:
> Well it was surprising to me that kmem_cache_destroy() would perform rcu
> actions in the first place. RCU is usually handled externally and not
> within the slab allocator. The only reason that SLAB_DESTROY_BY_RCU exists
> is because the user cannot otherwise control the final release of memory
> to the page allocator.

Right. A quick grep for git logs reveals that it's been like that in
mm/slab.c at least since 2.6.12-rc2 so I think we should consider it
as part of the slab API and Paul's patch is an obvious bugfix to it.

                                           Pekka

--
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>