From ebe909e0fdb34b980c5cf636c495e4f0bb0dfda8 Mon Sep 17 00:00:00 2001 From: Jesper Dangaard Brouer Date: Fri, 4 Sep 2015 15:45:40 -0700 Subject: [PATCH] slub: improve bulk alloc strategy Call slowpath __slab_alloc() from within the bulk loop, as the side-effect of this call likely repopulates c->freelist. Choose to reenable local IRQs while calling slowpath. Saving some optimizations for later. E.g. it is possible to extract parts of __slab_alloc() and avoid the unnecessary and expensive (37 cycles) local_irq_{save,restore}. For now, be happy calling __slab_alloc() this lower icache impact of this func and I don't have to worry about correctness. Measurements on CPU CPU i7-4790K @ 4.00GHz Baseline normal fastpath (alloc+free cost): 42 cycles(tsc) 10.601 ns Bulk- fallback - this-patch 1 - 58 cycles(tsc) 14.516 ns - 49 cycles(tsc) 12.459 ns improved 15.5% 2 - 51 cycles(tsc) 12.930 ns - 38 cycles(tsc) 9.605 ns improved 25.5% 3 - 49 cycles(tsc) 12.274 ns - 34 cycles(tsc) 8.525 ns improved 30.6% 4 - 48 cycles(tsc) 12.058 ns - 32 cycles(tsc) 8.036 ns improved 33.3% 8 - 46 cycles(tsc) 11.609 ns - 31 cycles(tsc) 7.756 ns improved 32.6% 16 - 45 cycles(tsc) 11.451 ns - 32 cycles(tsc) 8.148 ns improved 28.9% 30 - 79 cycles(tsc) 19.865 ns - 68 cycles(tsc) 17.164 ns improved 13.9% 32 - 76 cycles(tsc) 19.212 ns - 66 cycles(tsc) 16.584 ns improved 13.2% 34 - 74 cycles(tsc) 18.600 ns - 63 cycles(tsc) 15.954 ns improved 14.9% 48 - 88 cycles(tsc) 22.092 ns - 77 cycles(tsc) 19.373 ns improved 12.5% 64 - 80 cycles(tsc) 20.043 ns - 68 cycles(tsc) 17.188 ns improved 15.0% 128 - 99 cycles(tsc) 24.818 ns - 89 cycles(tsc) 22.404 ns improved 10.1% 158 - 99 cycles(tsc) 24.977 ns - 92 cycles(tsc) 23.089 ns improved 7.1% 250 - 106 cycles(tsc) 26.552 ns - 99 cycles(tsc) 24.785 ns improved 6.6% Signed-off-by: Jesper Dangaard Brouer Cc: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) diff --git a/mm/slub.c b/mm/slub.c index 30e7dedec664..f98b1b9e7080 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -2779,8 +2779,22 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, for (i = 0; i < size; i++) { void *object = c->freelist; - if (!object) - break; + if (unlikely(!object)) { + local_irq_enable(); + /* + * Invoking slow path likely have side-effect + * of re-populating per CPU c->freelist + */ + p[i] = __slab_alloc(s, flags, NUMA_NO_NODE, + _RET_IP_, c); + if (unlikely(!p[i])) { + __kmem_cache_free_bulk(s, i, p); + return false; + } + local_irq_disable(); + c = this_cpu_ptr(s->cpu_slab); + continue; /* goto for-loop */ + } c->freelist = get_freepointer(s, object); p[i] = object; @@ -2796,14 +2810,6 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, memset(p[j], 0, s->object_size); } - /* Fallback to single elem alloc */ - for (; i < size; i++) { - void *x = p[i] = kmem_cache_alloc(s, flags); - if (unlikely(!x)) { - __kmem_cache_free_bulk(s, i, p); - return false; - } - } return true; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); -- 2.20.1