From 5387c90490f7f42df3209154ca955a453ee01b41 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Mon, 28 Jun 2021 19:37:27 -0700 Subject: [PATCH] mm/memcg: improve refill_obj_stock() performance There are two issues with the current refill_obj_stock() code. First of all, when nr_bytes reaches over PAGE_SIZE, it calls drain_obj_stock() to atomically flush out remaining bytes to obj_cgroup, clear cached_objcg and do a obj_cgroup_put(). It is likely that the same obj_cgroup will be used again which leads to another call to drain_obj_stock() and obj_cgroup_get() as well as atomically retrieve the available byte from obj_cgroup. That is costly. Instead, we should just uncharge the excess pages, reduce the stock bytes and be done with it. The drain_obj_stock() function should only be called when obj_cgroup changes. Secondly, when charging an object of size not less than a page in obj_cgroup_charge(), it is possible that the remaining bytes to be refilled to the stock will overflow a page and cause refill_obj_stock() to uncharge 1 page. To avoid the additional uncharge in this case, a new allow_uncharge flag is added to refill_obj_stock() which will be set to false when called from obj_cgroup_charge() so that an uncharge_pages() call won't be issued right after a charge_pages() call unless the objcg changes. A multithreaded kmalloc+kfree microbenchmark on a 2-socket 48-core 96-thread x86-64 system with 96 testing threads were run. Before this patch, the total number of kilo kmalloc+kfree operations done for a 4k large object by all the testing threads per second were 4,304 kops/s (cgroup v1) and 8,478 kops/s (cgroup v2). After applying this patch, the number were 4,731 (cgroup v1) and 418,142 (cgroup v2) respectively. This represents a performance improvement of 1.10X (cgroup v1) and 49.3X (cgroup v2). Link: https://lkml.kernel.org/r/20210506150007.16288-4-longman@redhat.com Signed-off-by: Waiman Long Reviewed-by: Shakeel Butt Cc: Alex Shi Cc: Chris Down Cc: Christoph Lameter Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Masayoshi Mizuma Cc: Matthew Wilcox Cc: Michal Hocko Cc: Muchun Song Cc: Pekka Enberg Cc: Roman Gushchin Cc: Tejun Heo Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xing Zhengjun Cc: Yafang Shao Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 48 +++++++++++++++++++++++++++++++++++------------- 1 file changed, 35 insertions(+), 13 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b4624580d18a..17d38c7f630f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -3157,10 +3157,12 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, return false; } -static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) +static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes, + bool allow_uncharge) { struct memcg_stock_pcp *stock; unsigned long flags; + unsigned int nr_pages = 0; local_irq_save(flags); @@ -3169,14 +3171,21 @@ static void refill_obj_stock(struct obj_cgroup *objcg, unsigned int nr_bytes) drain_obj_stock(stock); obj_cgroup_get(objcg); stock->cached_objcg = objcg; - stock->nr_bytes = atomic_xchg(&objcg->nr_charged_bytes, 0); + stock->nr_bytes = atomic_read(&objcg->nr_charged_bytes) + ? atomic_xchg(&objcg->nr_charged_bytes, 0) : 0; + allow_uncharge = true; /* Allow uncharge when objcg changes */ } stock->nr_bytes += nr_bytes; - if (stock->nr_bytes > PAGE_SIZE) - drain_obj_stock(stock); + if (allow_uncharge && (stock->nr_bytes > PAGE_SIZE)) { + nr_pages = stock->nr_bytes >> PAGE_SHIFT; + stock->nr_bytes &= (PAGE_SIZE - 1); + } local_irq_restore(flags); + + if (nr_pages) + obj_cgroup_uncharge_pages(objcg, nr_pages); } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) @@ -3188,14 +3197,27 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) return 0; /* - * In theory, memcg->nr_charged_bytes can have enough + * In theory, objcg->nr_charged_bytes can have enough * pre-charged bytes to satisfy the allocation. However, - * flushing memcg->nr_charged_bytes requires two atomic - * operations, and memcg->nr_charged_bytes can't be big, - * so it's better to ignore it and try grab some new pages. - * memcg->nr_charged_bytes will be flushed in - * refill_obj_stock(), called from this function or - * independently later. + * flushing objcg->nr_charged_bytes requires two atomic + * operations, and objcg->nr_charged_bytes can't be big. + * The shared objcg->nr_charged_bytes can also become a + * performance bottleneck if all tasks of the same memcg are + * trying to update it. So it's better to ignore it and try + * grab some new pages. The stock's nr_bytes will be flushed to + * objcg->nr_charged_bytes later on when objcg changes. + * + * The stock's nr_bytes may contain enough pre-charged bytes + * to allow one less page from being charged, but we can't rely + * on the pre-charged bytes not being changed outside of + * consume_obj_stock() or refill_obj_stock(). So ignore those + * pre-charged bytes as well when charging pages. To avoid a + * page uncharge right after a page charge, we set the + * allow_uncharge flag to false when calling refill_obj_stock() + * to temporarily allow the pre-charged bytes to exceed the page + * size limit. The maximum reachable value of the pre-charged + * bytes is (sizeof(object) + PAGE_SIZE - 2) if there is no data + * race. */ nr_pages = size >> PAGE_SHIFT; nr_bytes = size & (PAGE_SIZE - 1); @@ -3205,14 +3227,14 @@ int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size) ret = obj_cgroup_charge_pages(objcg, gfp, nr_pages); if (!ret && nr_bytes) - refill_obj_stock(objcg, PAGE_SIZE - nr_bytes); + refill_obj_stock(objcg, PAGE_SIZE - nr_bytes, false); return ret; } void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size) { - refill_obj_stock(objcg, size); + refill_obj_stock(objcg, size, true); } #endif /* CONFIG_MEMCG_KMEM */ -- 2.39.5