From 4331f7d339ee0b54603344b9d13662a9c022540c Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Wed, 21 Mar 2012 16:34:26 -0700 Subject: [PATCH] memcg: fix performance of mem_cgroup_begin_update_page_stat() mem_cgroup_begin_update_page_stat() should be very fast because it's called very frequently. Now, it needs to look up page_cgroup and its memcg....this is slow. This patch adds a global variable to check "any memcg is moving or not". With this, the caller doesn't need to visit page_cgroup and memcg. Here is a test result. A test program makes page faults onto a file, MAP_SHARED and makes each page's page_mapcount(page) > 1, and free the range by madvise() and page fault again. This program causes 26214400 times of page fault onto a file(size was 1G.) and shows shows the cost of mem_cgroup_begin_update_page_stat(). Before this patch for mem_cgroup_begin_update_page_stat() [kamezawa@bluextal test]$ time ./mmap 1G real 0m21.765s user 0m5.999s sys 0m15.434s 27.46% mmap mmap [.] reader 21.15% mmap [kernel.kallsyms] [k] page_fault 9.17% mmap [kernel.kallsyms] [k] filemap_fault 2.96% mmap [kernel.kallsyms] [k] __do_fault 2.83% mmap [kernel.kallsyms] [k] __mem_cgroup_begin_update_page_stat After this patch [root@bluextal test]# time ./mmap 1G real 0m21.373s user 0m6.113s sys 0m15.016s In usual path, calls to __mem_cgroup_begin_update_page_stat() goes away. Note: we may be able to remove this optimization in future if we can get pointer to memcg directly from struct page. [akpm@linux-foundation.org: don't return a void] Signed-off-by: KAMEZAWA Hiroyuki Acked-by: Greg Thelen Acked-by: Johannes Weiner Cc: Michal Hocko Cc: KOSAKI Motohiro Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 ++++- mm/memcontrol.c | 9 ++++++++- 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index bf7ae01fc93..f94efd2f6c2 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -144,6 +144,8 @@ static inline bool mem_cgroup_disabled(void) void __mem_cgroup_begin_update_page_stat(struct page *page, bool *locked, unsigned long *flags); +extern atomic_t memcg_moving; + static inline void mem_cgroup_begin_update_page_stat(struct page *page, bool *locked, unsigned long *flags) { @@ -151,7 +153,8 @@ static inline void mem_cgroup_begin_update_page_stat(struct page *page, return; rcu_read_lock(); *locked = false; - return __mem_cgroup_begin_update_page_stat(page, locked, flags); + if (atomic_read(&memcg_moving)) + __mem_cgroup_begin_update_page_stat(page, locked, flags); } void __mem_cgroup_end_update_page_stat(struct page *page, diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0e13b2aeea6..eb1004f207b 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1306,8 +1306,13 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg) * rcu_read_unlock() * start move here. */ + +/* for quick checking without looking up memcg */ +atomic_t memcg_moving __read_mostly; + static void mem_cgroup_start_move(struct mem_cgroup *memcg) { + atomic_inc(&memcg_moving); atomic_inc(&memcg->moving_account); synchronize_rcu(); } @@ -1318,8 +1323,10 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) * Now, mem_cgroup_clear_mc() may call this function with NULL. * We check NULL in callee rather than caller. */ - if (memcg) + if (memcg) { + atomic_dec(&memcg_moving); atomic_dec(&memcg->moving_account); + } } /*