[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <Pine.LNX.4.64.0609290906350.23840@schroedinger.engr.sgi.com>
Date: Fri, 29 Sep 2006 09:10:55 -0700 (PDT)
From: Christoph Lameter <clameter@....com>
To: Pekka J Enberg <penberg@...helsinki.fi>
cc: manfred@...orfullife.com, christoph@...eter.com, pj@....com,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [RFC/PATCH] slab: clean up allocation
On Fri, 29 Sep 2006, Pekka J Enberg wrote:
> + * When allocating from current node.
> + */
> +#define SLAB_CURRENT_NODE (-1)
> +
If we want a constant here then we would better define a global one and
use it throughout the kernel.
Something like
#define LOCAL_NODE (-1)
Maybe in include/*/topology.h ?
> #endif
>
> -static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
> +static inline void *cache_alloc_local(struct kmem_cache *cachep, gfp_t flags)
> {
> void *objp;
> struct array_cache *ac;
> @@ -3059,35 +3064,6 @@ static inline void *____cache_alloc(stru
> return objp;
> }
This is not really local in the sense of node local but its processor
local. The speciality here is that we allocate from the per processor
list of objects. cache_alloc_cpu?
The rest looks fine on first glance.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists