The patch titled
slab: NUMA kmem_cache diet
has been added to the -mm tree. Its filename is
slab-numa-kmem_cache-diet.patch
*** Remember to use Documentation/SubmitChecklist when testing your code ***
See http://www.zip.com.au/~akpm/linux/patches/stuff/added-to-mm.txt to find
out what to do about this
------------------------------------------------------
Subject: slab: NUMA kmem_cache diet
From: Eric Dumazet <dada1@xxxxxxxxxxxxx>
Some NUMA machines have a big MAX_NUMNODES (possibly 1024), but fewer
possible nodes. This patch dynamically sizes the 'struct kmem_cache' to
allocate only needed space.
I moved nodelists[] field at the end of struct kmem_cache, and use the
following computation in kmem_cache_init()
cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
nr_node_ids * sizeof(struct kmem_list3 *);
On my two nodes x86_64 machine, kmem_cache.obj_size is now 192 instead of 704
(This is because on x86_64, MAX_NUMNODES is 64)
On bigger NUMA setups, this might reduce the gfporder of "cache_cache"
Signed-off-by: Eric Dumazet <dada1@xxxxxxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxxxxxx>
Cc: Andy Whitcroft <apw@xxxxxxxxxxxx>
Cc: Christoph Lameter <clameter@xxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/slab.c | 24 ++++++++++++++++++++----
1 file changed, 20 insertions(+), 4 deletions(-)
diff -puN mm/slab.c~slab-numa-kmem_cache-diet mm/slab.c
--- a/mm/slab.c~slab-numa-kmem_cache-diet
+++ a/mm/slab.c
@@ -389,7 +389,6 @@ struct kmem_cache {
unsigned int buffer_size;
u32 reciprocal_buffer_size;
/* 3) touched by every alloc & free from the backend */
- struct kmem_list3 *nodelists[MAX_NUMNODES];
unsigned int flags; /* constant flags */
unsigned int num; /* # of objs per slab */
@@ -444,6 +443,17 @@ struct kmem_cache {
int obj_offset;
int obj_size;
#endif
+ /*
+ * We put nodelists[] at the end of kmem_cache, because we want to size
+ * this array to nr_node_ids slots instead of MAX_NUMNODES
+ * (see kmem_cache_init())
+ * We still use [MAX_NUMNODES] and not [1] or [0] because cache_cache
+ * is statically defined, so we reserve the max number of nodes.
+ */
+ struct kmem_list3 *nodelists[MAX_NUMNODES];
+ /*
+ * Do not add fields after nodelists[]
+ */
};
#define CFLGS_OFF_SLAB (0x80000000UL)
@@ -678,9 +688,6 @@ static struct kmem_cache cache_cache = {
.shared = 1,
.buffer_size = sizeof(struct kmem_cache),
.name = "kmem_cache",
-#if DEBUG
- .obj_size = sizeof(struct kmem_cache),
-#endif
};
#define BAD_ALIEN_MAGIC 0x01020304ul
@@ -1437,6 +1444,15 @@ void __init kmem_cache_init(void)
cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE];
+ /*
+ * struct kmem_cache size depends on nr_node_ids, which
+ * can be less than MAX_NUMNODES.
+ */
+ cache_cache.buffer_size = offsetof(struct kmem_cache, nodelists) +
+ nr_node_ids * sizeof(struct kmem_list3 *);
+#if DEBUG
+ cache_cache.obj_size = cache_cache.buffer_size;
+#endif
cache_cache.buffer_size = ALIGN(cache_cache.buffer_size,
cache_line_size());
cache_cache.reciprocal_buffer_size =
_
Patches currently in -mm which might be from dada1@xxxxxxxxxxxxx are
git-net.patch
slab-use-num_possible_cpus-in-enable_cpucache.patch
slab-dont-allocate-empty-shared-caches.patch
slab-numa-kmem_cache-diet.patch
optimize-timespec_trunc.patch
procfs-reorder-struct-pid_dentry-to-save-space-on-64bit-archs-and-constify-them.patch
vfs-delay-the-dentry-name-generation-on-sockets-and.patch
getrusage-fill-ru_inblock-and-ru_oublock-fields-if-possible.patch
time-smp-friendly-alignment-of-struct-clocksource.patch
make-static-counters-in-new_inode-and-iunique-be-32-bits.patch
speedup-divides-by-cpu_power-in-scheduler.patch
-
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
