From f90280d6b7963fa8925258ed66b4f567fe73dfea Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 17 Aug 2018 15:48:25 -0700 Subject: [PATCH] mm/vmscan.c: clear shrinker bit if there are no objects related to memcg To avoid further unneed calls of do_shrink_slab() for shrinkers, which already do not have any charged objects in a memcg, their bits have to be cleared. This patch introduces a lockless mechanism to do that without races without parallel list lru add. After do_shrink_slab() returns SHRINK_EMPTY the first time, we clear the bit and call it once again. Then we restore the bit, if the new return value is different. Note, that single smp_mb__after_atomic() in shrink_slab_memcg() covers two situations: 1)list_lru_add() shrink_slab_memcg list_add_tail() for_each_set_bit() <--- read bit do_shrink_slab() <--- missed list update (no barrier) set_bit() do_shrink_slab() <--- seen list update This situation, when the first do_shrink_slab() sees set bit, but it doesn't see list update (i.e., race with the first element queueing), is rare. So we don't add before the first call of do_shrink_slab() instead of this to do not slow down generic case. Also, it's need the second call as seen in below in (2). 2)list_lru_add() shrink_slab_memcg() list_add_tail() ... set_bit() ... ... for_each_set_bit() do_shrink_slab() do_shrink_slab() clear_bit() ... ... ... list_lru_add() ... list_add_tail() clear_bit() set_bit() do_shrink_slab() The barriers guarantee that the second do_shrink_slab() in the right side task sees list update if really cleared the bit. This case is drawn in the code comment. [Results/performance of the patchset] After the whole patchset applied the below test shows signify increase of performance: $echo 1 > /sys/fs/cgroup/memory/memory.use_hierarchy $mkdir /sys/fs/cgroup/memory/ct $echo 4000M > /sys/fs/cgroup/memory/ct/memory.kmem.limit_in_bytes $for i in `seq 0 4000`; do mkdir /sys/fs/cgroup/memory/ct/$i; echo $$ > /sys/fs/cgroup/memory/ct/$i/cgroup.procs; mkdir -p s/$i; mount -t tmpfs $i s/$i; touch s/$i/file; done Then, 5 sequential calls of drop caches: $time echo 3 > /proc/sys/vm/drop_caches 1)Before: 0.00user 13.78system 0:13.78elapsed 99%CPU 0.00user 5.59system 0:05.60elapsed 99%CPU 0.00user 5.48system 0:05.48elapsed 99%CPU 0.00user 8.35system 0:08.35elapsed 99%CPU 0.00user 8.34system 0:08.35elapsed 99%CPU 2)After 0.00user 1.10system 0:01.10elapsed 99%CPU 0.00user 0.00system 0:00.01elapsed 64%CPU 0.00user 0.01system 0:00.01elapsed 82%CPU 0.00user 0.00system 0:00.01elapsed 64%CPU 0.00user 0.01system 0:00.01elapsed 82%CPU The results show the performance increases at least in 548 times. Shakeel Butt tested this patchset with fork-bomb on his configuration: > I created 255 memcgs, 255 ext4 mounts and made each memcg create a > file containing few KiBs on corresponding mount. Then in a separate > memcg of 200 MiB limit ran a fork-bomb. > > I ran the "perf record -ag -- sleep 60" and below are the results: > > Without the patch series: > Samples: 4M of event 'cycles', Event count (approx.): 3279403076005 > + 36.40% fb.sh [kernel.kallsyms] [k] shrink_slab > + 18.97% fb.sh [kernel.kallsyms] [k] list_lru_count_one > + 6.75% fb.sh [kernel.kallsyms] [k] super_cache_count > + 0.49% fb.sh [kernel.kallsyms] [k] down_read_trylock > + 0.44% fb.sh [kernel.kallsyms] [k] mem_cgroup_iter > + 0.27% fb.sh [kernel.kallsyms] [k] up_read > + 0.21% fb.sh [kernel.kallsyms] [k] osq_lock > + 0.13% fb.sh [kernel.kallsyms] [k] shmem_unused_huge_count > + 0.08% fb.sh [kernel.kallsyms] [k] shrink_node_memcg > + 0.08% fb.sh [kernel.kallsyms] [k] shrink_node > > With the patch series: > Samples: 4M of event 'cycles', Event count (approx.): 2756866824946 > + 47.49% fb.sh [kernel.kallsyms] [k] down_read_trylock > + 30.72% fb.sh [kernel.kallsyms] [k] up_read > + 9.51% fb.sh [kernel.kallsyms] [k] mem_cgroup_iter > + 1.69% fb.sh [kernel.kallsyms] [k] shrink_node_memcg > + 1.35% fb.sh [kernel.kallsyms] [k] mem_cgroup_protected > + 1.05% fb.sh [kernel.kallsyms] [k] queued_spin_lock_slowpath > + 0.85% fb.sh [kernel.kallsyms] [k] _raw_spin_lock > + 0.78% fb.sh [kernel.kallsyms] [k] lruvec_lru_size > + 0.57% fb.sh [kernel.kallsyms] [k] shrink_node > + 0.54% fb.sh [kernel.kallsyms] [k] queue_work_on > + 0.46% fb.sh [kernel.kallsyms] [k] shrink_slab_memcg [ktkhai@virtuozzo.com: v9] Link: http://lkml.kernel.org/r/153112561772.4097.11011071937553113003.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/153063070859.1818.11870882950920963480.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Acked-by: Vladimir Davydov Tested-by: Shakeel Butt Cc: Al Viro Cc: Andrey Ryabinin Cc: Chris Wilson Cc: Greg Kroah-Hartman Cc: Guenter Roeck Cc: "Huang, Ying" Cc: Johannes Weiner Cc: Josef Bacik Cc: Li RongQing Cc: Matthew Wilcox Cc: Matthias Kaehlcke Cc: Mel Gorman Cc: Michal Hocko Cc: Minchan Kim Cc: Philippe Ombredanne Cc: Roman Gushchin Cc: Sahitya Tummala Cc: Stephen Rothwell Cc: Tetsuo Handa Cc: Thomas Gleixner Cc: Waiman Long Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 ++ mm/vmscan.c | 26 ++++++++++++++++++++++++-- 2 files changed, 26 insertions(+), 2 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 55c010a..6a92189 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -430,6 +430,8 @@ void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) rcu_read_lock(); map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map); + /* Pairs with smp mb in shrink_slab() */ + smp_mb__before_atomic(); set_bit(shrinker_id, map->map); rcu_read_unlock(); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 8199e1b..93fdd03 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -596,8 +596,30 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, continue; ret = do_shrink_slab(&sc, shrinker, priority); - if (ret == SHRINK_EMPTY) - ret = 0; + if (ret == SHRINK_EMPTY) { + clear_bit(i, map->map); + /* + * After the shrinker reported that it had no objects to + * free, but before we cleared the corresponding bit in + * the memcg shrinker map, a new object might have been + * added. To make sure, we have the bit set in this + * case, we invoke the shrinker one more time and reset + * the bit if it reports that it is not empty anymore. + * The memory barrier here pairs with the barrier in + * memcg_set_shrinker_bit(): + * + * list_lru_add() shrink_slab_memcg() + * list_add_tail() clear_bit() + * + * set_bit() do_shrink_slab() + */ + smp_mb__after_atomic(); + ret = do_shrink_slab(&sc, shrinker, priority); + if (ret == SHRINK_EMPTY) + ret = 0; + else + memcg_set_shrinker_bit(memcg, nid, i); + } freed += ret; if (rwsem_is_contended(&shrinker_rwsem)) { -- 2.7.4