From 815744d75152078cde5391fc1e3c2d4424323fb6 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Thu, 13 Jun 2019 15:55:46 -0700 Subject: mm: memcontrol: don't batch updates of local VM stats and events The kernel test robot noticed a 26% will-it-scale pagefault regression from commit 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty"). This appears to be caused by bouncing the additional cachelines from the new hierarchical statistics counters. We can fix this by getting rid of the batched local counters instead. Originally, there were *only* group-local counters, and they were fully maintained per cpu. A reader of a stats file high up in the cgroup tree would have to walk the entire subtree and collect each level's per-cpu counters to get the recursive view. This was prohibitively expensive, and so we switched to per-cpu batched updates of the local counters during a983b5ebee57 ("mm: memcontrol: fix excessive complexity in memory.stat reporting"), reducing the complexity from nr_subgroups * nr_cpus to nr_subgroups. With growing machines and cgroup trees, the tree walk itself became too expensive for monitoring top-level groups, and this is when the culprit patch added hierarchy counters on each cgroup level. When the per-cpu batch size would be reached, both the local and the hierarchy counters would get batch-updated from the per-cpu delta simultaneously. This makes local and hierarchical counter reads blazingly fast, but it unfortunately makes the write-side too cache line intense. Since local counter reads were never a problem - we only centralized them to accelerate the hierarchy walk - and use of the local counters are becoming rarer due to replacement with hierarchical views (ongoing rework in the page reclaim and workingset code), we can make those local counters unbatched per-cpu counters again. The scheme will then be as such: when a memcg statistic changes, the writer will: - update the local counter (per-cpu) - update the batch counter (per-cpu). If the batch is full: - spill the batch into the group's atomic_t - spill the batch into all ancestors' atomic_ts - empty out the batch counter (per-cpu) when a local memcg counter is read, the reader will: - collect the local counter from all cpus when a hiearchy memcg counter is read, the reader will: - read the atomic_t We might be able to simplify this further and make the recursive counters unbatched per-cpu counters as well (batch upward propagation, but leave per-cpu collection to the readers), but that will require a more in-depth analysis and testing of all the callsites. Deal with the immediate regression for now. Link: http://lkml.kernel.org/r/20190521151647.GB2870@cmpxchg.org Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty") Signed-off-by: Johannes Weiner Reported-by: kernel test robot Tested-by: kernel test robot Cc: Michal Hocko Cc: Shakeel Butt Cc: Roman Gushchin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 26 ++++++++++++++++++-------- 1 file changed, 18 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index edf9e8f32d70..1dcb763bb610 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -117,9 +117,12 @@ struct memcg_shrinker_map { struct mem_cgroup_per_node { struct lruvec lruvec; + /* Legacy local VM stats */ + struct lruvec_stat __percpu *lruvec_stat_local; + + /* Subtree VM stats (batched updates) */ struct lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; - atomic_long_t lruvec_stat_local[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; @@ -265,17 +268,18 @@ struct mem_cgroup { atomic_t moving_account; struct task_struct *move_lock_task; - /* memory.stat */ + /* Legacy local VM stats and events */ + struct memcg_vmstats_percpu __percpu *vmstats_local; + + /* Subtree VM stats and events (batched updates) */ struct memcg_vmstats_percpu __percpu *vmstats_percpu; MEMCG_PADDING(_pad2_); atomic_long_t vmstats[MEMCG_NR_STAT]; - atomic_long_t vmstats_local[MEMCG_NR_STAT]; - atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; - atomic_long_t vmevents_local[NR_VM_EVENT_ITEMS]; + /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; @@ -567,7 +571,11 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { - long x = atomic_long_read(&memcg->vmstats_local[idx]); + long x = 0; + int cpu; + + for_each_possible_cpu(cpu) + x += per_cpu(memcg->vmstats_local->stat[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; @@ -641,13 +649,15 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; - long x; + long x = 0; + int cpu; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); - x = atomic_long_read(&pn->lruvec_stat_local[idx]); + for_each_possible_cpu(cpu) + x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; -- cgit v1.2.3