The patch titled
Subject: mm/slab: refill cpu cache through a new slab without holding a node lock
has been added to the -mm tree. Its filename is
mm-slab-refill-cpu-cache-through-a-new-slab-without-holding-a-node-lock.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-slab-refill-cpu-cache-through-a-new-slab-without-holding-a-node-lock.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-slab-refill-cpu-cache-through-a-new-slab-without-holding-a-node-lock.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Subject: mm/slab: refill cpu cache through a new slab without holding a node lock
Until now, cache growing makes a free slab on node's slab list and then we
can allocate free objects from it. This necessarily requires to hold a
node lock which is very contended. If we refill cpu cache before
attaching it to node's slab list, we can avoid holding a node lock as much
as possible because this newly allocated slab is only visible to the
current task. This will reduce lock contention.
Below is the result of concurrent allocation/free in slab allocation
benchmark made by Christoph a long time ago. I make the output simpler.
The number shows cycle count during alloc/free respectively so less is
better.
* Before
Kmalloc N*alloc N*free(32): Average=355/750
Kmalloc N*alloc N*free(64): Average=452/812
Kmalloc N*alloc N*free(128): Average=559/1070
Kmalloc N*alloc N*free(256): Average=1176/980
Kmalloc N*alloc N*free(512): Average=1939/1189
Kmalloc N*alloc N*free(1024): Average=3521/1278
Kmalloc N*alloc N*free(2048): Average=7152/1838
Kmalloc N*alloc N*free(4096): Average=13438/2013
* After
Kmalloc N*alloc N*free(32): Average=248/966
Kmalloc N*alloc N*free(64): Average=261/949
Kmalloc N*alloc N*free(128): Average=314/1016
Kmalloc N*alloc N*free(256): Average=741/1061
Kmalloc N*alloc N*free(512): Average=1246/1152
Kmalloc N*alloc N*free(1024): Average=2437/1259
Kmalloc N*alloc N*free(2048): Average=4980/1800
Kmalloc N*alloc N*free(4096): Average=9000/2078
It shows that contention is reduced for all the object sizes and
performance increases by 30 ~ 40%.
Signed-off-by: Joonsoo Kim <iamjoonsoo.kim@xxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Pekka Enberg <penberg@xxxxxxxxxx>
Cc: David Rientjes <rientjes@xxxxxxxxxx>
Cc: Jesper Dangaard Brouer <brouer@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/slab.c | 68 +++++++++++++++++++++++++++-------------------------
1 file changed, 36 insertions(+), 32 deletions(-)
diff -puN mm/slab.c~mm-slab-refill-cpu-cache-through-a-new-slab-without-holding-a-node-lock mm/slab.c
--- a/mm/slab.c~mm-slab-refill-cpu-cache-through-a-new-slab-without-holding-a-node-lock
+++ a/mm/slab.c
@@ -2834,6 +2834,30 @@ static noinline void *cache_alloc_pfmema
return obj;
}
+/*
+ * Slab list should be fixed up by fixup_slab_list() for existing slab
+ * or cache_grow_end() for new slab
+ */
+static __always_inline int alloc_block(struct kmem_cache *cachep,
+ struct array_cache *ac, struct page *page, int batchcount)
+{
+ /*
+ * There must be at least one object available for
+ * allocation.
+ */
+ BUG_ON(page->active >= cachep->num);
+
+ while (page->active < cachep->num && batchcount--) {
+ STATS_INC_ALLOCED(cachep);
+ STATS_INC_ACTIVE(cachep);
+ STATS_SET_HIGH(cachep);
+
+ ac->entry[ac->avail++] = slab_get_obj(cachep, page);
+ }
+
+ return batchcount;
+}
+
static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags)
{
int batchcount;
@@ -2846,7 +2870,6 @@ static void *cache_alloc_refill(struct k
check_irq_off();
node = numa_mem_id();
-retry:
ac = cpu_cache_get(cachep);
batchcount = ac->batchcount;
if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
@@ -2876,21 +2899,7 @@ retry:
check_spinlock_acquired(cachep);
- /*
- * The slab was either on partial or free list so
- * there must be at least one object available for
- * allocation.
- */
- BUG_ON(page->active >= cachep->num);
-
- while (page->active < cachep->num && batchcount--) {
- STATS_INC_ALLOCED(cachep);
- STATS_INC_ACTIVE(cachep);
- STATS_SET_HIGH(cachep);
-
- ac->entry[ac->avail++] = slab_get_obj(cachep, page);
- }
-
+ batchcount = alloc_block(cachep, ac, page, batchcount);
fixup_slab_list(cachep, n, page, &list);
}
@@ -2910,21 +2919,18 @@ alloc_done:
}
page = cache_grow_begin(cachep, gfp_exact_node(flags), node);
- cache_grow_end(cachep, page);
/*
* cache_grow_begin() can reenable interrupts,
* then ac could change.
*/
ac = cpu_cache_get(cachep);
- node = numa_mem_id();
+ if (!ac->avail && page)
+ alloc_block(cachep, ac, page, batchcount);
+ cache_grow_end(cachep, page);
- /* no objects in sight? abort */
- if (!page && ac->avail == 0)
+ if (!ac->avail)
return NULL;
-
- if (!ac->avail) /* objects refilled by interrupt? */
- goto retry;
}
ac->touched = 1;
@@ -3118,14 +3124,13 @@ static void *____cache_alloc_node(struct
{
struct page *page;
struct kmem_cache_node *n;
- void *obj;
+ void *obj = NULL;
void *list = NULL;
VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES);
n = get_node(cachep, nodeid);
BUG_ON(!n);
-retry:
check_irq_off();
spin_lock(&n->list_lock);
page = get_first_slab(n, false);
@@ -3147,19 +3152,18 @@ retry:
spin_unlock(&n->list_lock);
fixup_objfreelist_debug(cachep, &list);
- goto done;
+ return obj;
must_grow:
spin_unlock(&n->list_lock);
page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid);
+ if (page) {
+ /* This slab isn't counted yet so don't update free_objects */
+ obj = slab_get_obj(cachep, page);
+ }
cache_grow_end(cachep, page);
- if (page)
- goto retry;
-
- return fallback_alloc(cachep, flags);
-done:
- return obj;
+ return obj ? obj : fallback_alloc(cachep, flags);
}
static __always_inline void *
_
Patches currently in -mm which might be from iamjoonsoo.kim@xxxxxxx are
mm-page_ref-use-page_ref-helper-instead-of-direct-modification-of-_count.patch
mm-rename-_count-field-of-the-struct-page-to-_refcount.patch
mm-slab-hold-a-slab_mutex-when-calling-__kmem_cache_shrink.patch
mm-slab-remove-bad_alien_magic-again.patch
mm-slab-drain-the-free-slab-as-much-as-possible.patch
mm-slab-factor-out-kmem_cache_node-initialization-code.patch
mm-slab-clean-up-kmem_cache_node-setup.patch
mm-slab-dont-keep-free-slabs-if-free_objects-exceeds-free_limit.patch
mm-slab-racy-access-modify-the-slab-color.patch
mm-slab-make-cache_grow-handle-the-page-allocated-on-arbitrary-node.patch
mm-slab-separate-cache_grow-to-two-parts.patch
mm-slab-refill-cpu-cache-through-a-new-slab-without-holding-a-node-lock.patch
mm-slab-lockless-decision-to-grow-cache.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
