From cdec2e4265dfa09490601b00aeabd8a8d4af30f0 Mon Sep 17 00:00:00 2001 From: KAMEZAWA Hiroyuki Date: Tue, 15 Dec 2009 16:47:08 -0800 Subject: [PATCH] memcg: coalesce charging via percpu storage This is a patch for coalescing access to res_counter at charging by percpu caching. At charge, memcg charges 64pages and remember it in percpu cache. Because it's cache, drain/flush if necessary. This version uses public percpu area. 2 benefits for using public percpu area. 1. Sum of stocked charge in the system is limited to # of cpus not to the number of memcg. This shows better synchonization. 2. drain code for flush/cpuhotplug is very easy (and quick) The most important point of this patch is that we never touch res_counter in fast path. The res_counter is system-wide shared counter which is modified very frequently. We shouldn't touch it as far as we can for avoiding false sharing. On x86-64 8cpu server, I tested overheads of memcg at page fault by running a program which does map/fault/unmap in a loop. Running a task per a cpu by taskset and see sum of the number of page faults in 60secs. [without memcg config] 40156968 page-faults # 0.085 M/sec ( +- 0.046% ) 27.67 cache-miss/faults [root cgroup] 36659599 page-faults # 0.077 M/sec ( +- 0.247% ) 31.58 cache miss/faults [in a child cgroup] 18444157 page-faults # 0.039 M/sec ( +- 0.133% ) 69.96 cache miss/faults [ + coalescing uncharge patch] 27133719 page-faults # 0.057 M/sec ( +- 0.155% ) 47.16 cache miss/faults [ + coalescing uncharge patch + this patch ] 34224709 page-faults # 0.072 M/sec ( +- 0.173% ) 34.69 cache miss/faults Changelog (since Oct/2): - updated comments - replaced get_cpu_var() with __get_cpu_var() if possible. - removed mutex for system-wide drain. adds a counter instead of it. - removed CONFIG_HOTPLUG_CPU Changelog (old): - rebased onto the latest mmotm - moved charge size check before __GFP_WAIT check for avoiding unnecesary - added asynchronous flush routine. - fixed bugs pointed out by Nishimura-san. [akpm@linux-foundation.org: tweak comments] [nishimura@mxp.nes.nec.co.jp: don't do INIT_WORK() repeatedly against the same work_struct] Signed-off-by: KAMEZAWA Hiroyuki Cc: Balbir Singh Signed-off-by: Daisuke Nishimura Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 162 ++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 156 insertions(+), 6 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index a730c91b8e69..6587f657d57c 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -38,6 +38,7 @@ #include #include #include +#include #include "internal.h" #include @@ -275,6 +276,7 @@ enum charge_type { static void mem_cgroup_get(struct mem_cgroup *mem); static void mem_cgroup_put(struct mem_cgroup *mem); static struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *mem); +static void drain_all_stock_async(void); static struct mem_cgroup_per_zone * mem_cgroup_zoneinfo(struct mem_cgroup *mem, int nid, int zid) @@ -1137,6 +1139,8 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem, victim = mem_cgroup_select_victim(root_mem); if (victim == root_mem) { loop++; + if (loop >= 1) + drain_all_stock_async(); if (loop >= 2) { /* * If we have not been able to reclaim @@ -1258,6 +1262,133 @@ done: unlock_page_cgroup(pc); } +/* + * size of first charge trial. "32" comes from vmscan.c's magic value. + * TODO: maybe necessary to use big numbers in big irons. + */ +#define CHARGE_SIZE (32 * PAGE_SIZE) +struct memcg_stock_pcp { + struct mem_cgroup *cached; /* this never be root cgroup */ + int charge; + struct work_struct work; +}; +static DEFINE_PER_CPU(struct memcg_stock_pcp, memcg_stock); +static atomic_t memcg_drain_count; + +/* + * Try to consume stocked charge on this cpu. If success, PAGE_SIZE is consumed + * from local stock and true is returned. If the stock is 0 or charges from a + * cgroup which is not current target, returns false. This stock will be + * refilled. + */ +static bool consume_stock(struct mem_cgroup *mem) +{ + struct memcg_stock_pcp *stock; + bool ret = true; + + stock = &get_cpu_var(memcg_stock); + if (mem == stock->cached && stock->charge) + stock->charge -= PAGE_SIZE; + else /* need to call res_counter_charge */ + ret = false; + put_cpu_var(memcg_stock); + return ret; +} + +/* + * Returns stocks cached in percpu to res_counter and reset cached information. + */ +static void drain_stock(struct memcg_stock_pcp *stock) +{ + struct mem_cgroup *old = stock->cached; + + if (stock->charge) { + res_counter_uncharge(&old->res, stock->charge); + if (do_swap_account) + res_counter_uncharge(&old->memsw, stock->charge); + } + stock->cached = NULL; + stock->charge = 0; +} + +/* + * This must be called under preempt disabled or must be called by + * a thread which is pinned to local cpu. + */ +static void drain_local_stock(struct work_struct *dummy) +{ + struct memcg_stock_pcp *stock = &__get_cpu_var(memcg_stock); + drain_stock(stock); +} + +/* + * Cache charges(val) which is from res_counter, to local per_cpu area. + * This will be consumed by consumt_stock() function, later. + */ +static void refill_stock(struct mem_cgroup *mem, int val) +{ + struct memcg_stock_pcp *stock = &get_cpu_var(memcg_stock); + + if (stock->cached != mem) { /* reset if necessary */ + drain_stock(stock); + stock->cached = mem; + } + stock->charge += val; + put_cpu_var(memcg_stock); +} + +/* + * Tries to drain stocked charges in other cpus. This function is asynchronous + * and just put a work per cpu for draining localy on each cpu. Caller can + * expects some charges will be back to res_counter later but cannot wait for + * it. + */ +static void drain_all_stock_async(void) +{ + int cpu; + /* This function is for scheduling "drain" in asynchronous way. + * The result of "drain" is not directly handled by callers. Then, + * if someone is calling drain, we don't have to call drain more. + * Anyway, WORK_STRUCT_PENDING check in queue_work_on() will catch if + * there is a race. We just do loose check here. + */ + if (atomic_read(&memcg_drain_count)) + return; + /* Notify other cpus that system-wide "drain" is running */ + atomic_inc(&memcg_drain_count); + get_online_cpus(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + schedule_work_on(cpu, &stock->work); + } + put_online_cpus(); + atomic_dec(&memcg_drain_count); + /* We don't wait for flush_work */ +} + +/* This is a synchronous drain interface. */ +static void drain_all_stock_sync(void) +{ + /* called when force_empty is called */ + atomic_inc(&memcg_drain_count); + schedule_on_each_cpu(drain_local_stock); + atomic_dec(&memcg_drain_count); +} + +static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb, + unsigned long action, + void *hcpu) +{ + int cpu = (unsigned long)hcpu; + struct memcg_stock_pcp *stock; + + if (action != CPU_DEAD) + return NOTIFY_OK; + stock = &per_cpu(memcg_stock, cpu); + drain_stock(stock); + return NOTIFY_OK; +} + /* * Unlike exported interface, "oom" parameter is added. if oom==true, * oom-killer can be invoked. @@ -1269,6 +1400,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, struct mem_cgroup *mem, *mem_over_limit; int nr_retries = MEM_CGROUP_RECLAIM_RETRIES; struct res_counter *fail_res; + int csize = CHARGE_SIZE; if (unlikely(test_thread_flag(TIF_MEMDIE))) { /* Don't account this! */ @@ -1293,23 +1425,25 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, return 0; VM_BUG_ON(css_is_removed(&mem->css)); + if (mem_cgroup_is_root(mem)) + goto done; while (1) { int ret = 0; unsigned long flags = 0; - if (mem_cgroup_is_root(mem)) - goto done; - ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res); + if (consume_stock(mem)) + goto charged; + + ret = res_counter_charge(&mem->res, csize, &fail_res); if (likely(!ret)) { if (!do_swap_account) break; - ret = res_counter_charge(&mem->memsw, PAGE_SIZE, - &fail_res); + ret = res_counter_charge(&mem->memsw, csize, &fail_res); if (likely(!ret)) break; /* mem+swap counter fails */ - res_counter_uncharge(&mem->res, PAGE_SIZE); + res_counter_uncharge(&mem->res, csize); flags |= MEM_CGROUP_RECLAIM_NOSWAP; mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw); @@ -1318,6 +1452,11 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, mem_over_limit = mem_cgroup_from_res_counter(fail_res, res); + /* reduce request size and retry */ + if (csize > PAGE_SIZE) { + csize = PAGE_SIZE; + continue; + } if (!(gfp_mask & __GFP_WAIT)) goto nomem; @@ -1347,6 +1486,9 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm, goto nomem; } } + if (csize > PAGE_SIZE) + refill_stock(mem, csize - PAGE_SIZE); +charged: /* * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. * if they exceeds softlimit. @@ -2469,6 +2611,7 @@ move_account: goto out; /* This is for making all *used* pages to be on LRU. */ lru_add_drain_all(); + drain_all_stock_sync(); ret = 0; for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { @@ -3183,11 +3326,18 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) /* root ? */ if (cont->parent == NULL) { + int cpu; enable_swap_cgroup(); parent = NULL; root_mem_cgroup = mem; if (mem_cgroup_soft_limit_tree_init()) goto free_out; + for_each_possible_cpu(cpu) { + struct memcg_stock_pcp *stock = + &per_cpu(memcg_stock, cpu); + INIT_WORK(&stock->work, drain_local_stock); + } + hotcpu_notifier(memcg_stock_cpu_callback, 0); } else { parent = mem_cgroup_from_cont(cont->parent); -- 2.20.1