lkml.org 
[lkml]   [2006]   [Feb]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
SubjectRe: [RFT/PATCH] slab: consolidate allocation paths
From
Date
On Sat, 4 Feb 2006, Pekka Enberg wrote:
> > I don't have access to NUMA machine and would appreciate if someone
> > could give this patch a spin and let me know I didn't break anything.

On Sat, 2006-02-04 at 07:11 -0800, Christoph Lameter wrote:
> No time to do a full review (off to traffic school... sigh), I did not
> see anything by just glancing over it but the patch will conflict with
> Paul Jacksons patchset to implement memory spreading.

Here's the same patch rediffed on top of the cpuset changes.

Pekka

Subject: slab: consolidate allocation paths
From: Pekka Enberg <penberg@cs.helsinki.fi>

This patch consolidates the UMA and NUMA memory allocation paths in the
slab allocator. This is accomplished by making the UMA-path look like
we are on NUMA but always allocating from the current node.

Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Christoph Lameter <christoph@lameter.com>
Signed-off-by: Pekka Enberg <penberg@cs.helsinki.fi>
---

mm/slab.c | 132 +++++++++++++++++++++++++++++++-------------------------------
1 file changed, 67 insertions(+), 65 deletions(-)

Index: 2.6-cpuset/mm/slab.c
===================================================================
--- 2.6-cpuset.orig/mm/slab.c
+++ 2.6-cpuset/mm/slab.c
@@ -829,8 +829,6 @@ static struct array_cache *alloc_arrayca
}

#ifdef CONFIG_NUMA
-static void *__cache_alloc_node(struct kmem_cache *, gfp_t, int);
-static void *alternate_node_alloc(struct kmem_cache *, gfp_t);

static struct array_cache **alloc_alien_cache(int node, int limit)
{
@@ -2667,17 +2665,12 @@ static void *cache_alloc_debugcheck_afte
#define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
#endif

-static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
+static inline void *cache_alloc_cpucache(struct kmem_cache *cachep,
+ gfp_t flags)
{
void *objp;
struct array_cache *ac;

-#ifdef CONFIG_NUMA
- if (unlikely(current->flags & (PF_MEM_SPREAD|PF_MEMPOLICY)))
- if ((objp = alternate_node_alloc(cachep, flags)) != NULL)
- return objp;
-#endif
-
check_irq_off();
ac = cpu_cache_get(cachep);
if (likely(ac->avail)) {
@@ -2691,44 +2684,8 @@ static inline void *____cache_alloc(stru
return objp;
}

-static __always_inline void *
-__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
-{
- unsigned long save_flags;
- void *objp;
-
- cache_alloc_debugcheck_before(cachep, flags);
-
- local_irq_save(save_flags);
- objp = ____cache_alloc(cachep, flags);
- local_irq_restore(save_flags);
- objp = cache_alloc_debugcheck_after(cachep, flags, objp,
- caller);
- prefetchw(objp);
- return objp;
-}
-
#ifdef CONFIG_NUMA
/*
- * Try allocating on another node if PF_MEM_SPREAD or PF_MEMPOLICY.
- */
-static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
-{
- int nid_alloc, nid_here;
-
- if (in_interrupt())
- return NULL;
- nid_alloc = nid_here = numa_node_id();
- if (cpuset_mem_spread_check() && (cachep->flags & SLAB_MEM_SPREAD))
- nid_alloc = cpuset_mem_spread_node();
- else if (current->mempolicy)
- nid_alloc = slab_node(current->mempolicy);
- if (nid_alloc != nid_here)
- return __cache_alloc_node(cachep, flags, nid_alloc);
- return NULL;
-}
-
-/*
* A interface to enable slab creation on nodeid
*/
static void *__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
@@ -2788,8 +2745,69 @@ static void *__cache_alloc_node(struct k
done:
return obj;
}
+
+/*
+ * Try allocating on another node if PF_MEM_SPREAD or PF_MEMPOLICY.
+ */
+static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
+{
+ int nid_alloc, nid_here;
+
+ if (in_interrupt())
+ return NULL;
+ nid_alloc = nid_here = numa_node_id();
+ if (cpuset_mem_spread_check() && (cachep->flags & SLAB_MEM_SPREAD))
+ nid_alloc = cpuset_mem_spread_node();
+ else if (current->mempolicy)
+ nid_alloc = slab_node(current->mempolicy);
+ if (nid_alloc != nid_here)
+ return __cache_alloc_node(cachep, flags, nid_alloc);
+ return NULL;
+}
+
+static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
+ gfp_t flags, int nodeid)
+{
+ if (unlikely(current->flags & (PF_MEM_SPREAD|PF_MEMPOLICY))) {
+ void *obj = alternate_node_alloc(cachep, flags);
+ if (obj)
+ return obj;
+ }
+ return cache_alloc_cpucache(cachep, flags);
+}
+
+#else
+
+/*
+ * On UMA, we always allocate directly from the per-CPU cache.
+ */
+
+static __always_inline void *__cache_alloc(struct kmem_cache *cachep,
+ gfp_t flags, int nodeid)
+{
+ return cache_alloc_cpucache(cachep, flags);
+}
+
#endif

+static __always_inline void * cache_alloc(struct kmem_cache *cachep,
+ gfp_t flags, int nodeid,
+ void *caller)
+{
+ unsigned long save_flags;
+ void *objp;
+
+ cache_alloc_debugcheck_before(cachep, flags);
+ local_irq_save(save_flags);
+
+ objp = __cache_alloc(cachep, flags, nodeid);
+
+ local_irq_restore(save_flags);
+ objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
+ prefetchw(objp);
+ return objp;
+}
+
/*
* Caller needs to acquire correct kmem_list's list_lock
*/
@@ -2951,7 +2969,7 @@ static inline void __cache_free(struct k
*/
void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
- return __cache_alloc(cachep, flags, __builtin_return_address(0));
+ return cache_alloc(cachep, flags, -1, __builtin_return_address(0));
}
EXPORT_SYMBOL(kmem_cache_alloc);

@@ -3012,23 +3030,7 @@ int fastcall kmem_ptr_validate(struct km
*/
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
- unsigned long save_flags;
- void *ptr;
-
- cache_alloc_debugcheck_before(cachep, flags);
- local_irq_save(save_flags);
-
- if (nodeid == -1 || nodeid == numa_node_id() ||
- !cachep->nodelists[nodeid])
- ptr = ____cache_alloc(cachep, flags);
- else
- ptr = __cache_alloc_node(cachep, flags, nodeid);
- local_irq_restore(save_flags);
-
- ptr = cache_alloc_debugcheck_after(cachep, flags, ptr,
- __builtin_return_address(0));
-
- return ptr;
+ return cache_alloc(cachep, flags, nodeid, __builtin_return_address(0));
}
EXPORT_SYMBOL(kmem_cache_alloc_node);

@@ -3039,7 +3041,7 @@ void *kmalloc_node(size_t size, gfp_t fl
cachep = kmem_find_general_cachep(size, flags);
if (unlikely(cachep == NULL))
return NULL;
- return kmem_cache_alloc_node(cachep, flags, node);
+ return cache_alloc(cachep, flags, node, __builtin_return_address(0));
}
EXPORT_SYMBOL(kmalloc_node);
#endif
@@ -3078,7 +3080,7 @@ static __always_inline void *__do_kmallo
cachep = __find_general_cachep(size, flags);
if (unlikely(cachep == NULL))
return NULL;
- return __cache_alloc(cachep, flags, caller);
+ return cache_alloc(cachep, flags, -1, caller);
}

#ifndef CONFIG_DEBUG_SLAB

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2006-02-04 17:28    [W:0.058 / U:0.020 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site