From 3e880fb5e4bb6a012035e3edd0586ee2817c2e24 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Fri, 7 Jan 2011 17:49:19 +1100 Subject: [PATCH] fs: use fast counters for vfs caches percpu_counter library generates quite nasty code, so unless you need to dynamically allocate counters or take fast approximate value, a simple per cpu set of counters is much better. The percpu_counter can never be made to work as well, because it has an indirection from pointer to percpu memory, and it can't use direct this_cpu_inc interfaces because it doesn't use static PER_CPU data, so code will always be worse. In the fastpath, it is the difference between this: incl %gs:nr_dentry # nr_dentry and this: movl percpu_counter_batch(%rip), %edx # percpu_counter_batch, movl $1, %esi #, movq $nr_dentry, %rdi #, call __percpu_counter_add # (plus I clobber registers) __percpu_counter_add: pushq %rbp # movq %rsp, %rbp #, subq $32, %rsp #, movq %rbx, -24(%rbp) #, movq %r12, -16(%rbp) #, movq %r13, -8(%rbp) #, movq %rdi, %rbx # fbc, fbc #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP incl -8124(%rax) # .preempt_count movq 32(%rdi), %r12 # .counters, tcp_ptr__ #APP # 78 "lib/percpu_counter.c" 1 add %gs:this_cpu_off, %r12 # this_cpu_off, tcp_ptr__ # 0 "" 2 #NO_APP movslq (%r12),%r13 #* tcp_ptr__, tmp73 movslq %edx,%rax # batch, batch addq %rsi, %r13 # amount, count cmpq %rax, %r13 # batch, count jge .L27 #, negl %edx # tmp76 movslq %edx,%rdx # tmp76, tmp77 cmpq %rdx, %r13 # tmp77, count jg .L28 #, .L27: movq %rbx, %rdi # fbc, call _raw_spin_lock # addq %r13, 8(%rbx) # count, .count movq %rbx, %rdi # fbc, movl $0, (%r12) #,* tcp_ptr__ call _raw_spin_unlock # .L29: #APP # 216 "/home/npiggin/usr/src/linux-2.6/arch/x86/include/asm/thread_info.h" 1 movq %gs:kernel_stack,%rax #, pfo_ret__ # 0 "" 2 #NO_APP decl -8124(%rax) # .preempt_count movq -8136(%rax), %rax #, D.14625 testb $8, %al #, D.14625 jne .L32 #, .L31: movq -24(%rbp), %rbx #, movq -16(%rbp), %r12 #, movq -8(%rbp), %r13 #, leave ret .p2align 4,,10 .p2align 3 .L28: movl %r13d, (%r12) # count,* jmp .L29 # .L32: call preempt_schedule # .p2align 4,,6 jmp .L31 # .size __percpu_counter_add, .-__percpu_counter_add .p2align 4,,15 Signed-off-by: Nick Piggin --- fs/dcache.c | 19 +++++++++++++------ fs/inode.c | 17 ++++++++++------- 2 files changed, 23 insertions(+), 13 deletions(-) diff --git a/fs/dcache.c b/fs/dcache.c index f62ba90bce91..b2cb2662ca00 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -67,13 +67,22 @@ struct dentry_stat_t dentry_stat = { .age_limit = 45, }; -static struct percpu_counter nr_dentry __cacheline_aligned_in_smp; +static DEFINE_PER_CPU(unsigned int, nr_dentry); #if defined(CONFIG_SYSCTL) && defined(CONFIG_PROC_FS) +static int get_nr_dentry(void) +{ + int i; + int sum = 0; + for_each_possible_cpu(i) + sum += per_cpu(nr_dentry, i); + return sum < 0 ? 0 : sum; +} + int proc_nr_dentry(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - dentry_stat.nr_dentry = percpu_counter_sum_positive(&nr_dentry); + dentry_stat.nr_dentry = get_nr_dentry(); return proc_dointvec(table, write, buffer, lenp, ppos); } #endif @@ -93,7 +102,7 @@ static void __d_free(struct rcu_head *head) */ static void d_free(struct dentry *dentry) { - percpu_counter_dec(&nr_dentry); + this_cpu_dec(nr_dentry); if (dentry->d_op && dentry->d_op->d_release) dentry->d_op->d_release(dentry); @@ -981,7 +990,7 @@ struct dentry *d_alloc(struct dentry * parent, const struct qstr *name) list_add(&dentry->d_u.d_child, &parent->d_subdirs); spin_unlock(&dcache_lock); - percpu_counter_inc(&nr_dentry); + this_cpu_inc(nr_dentry); return dentry; } @@ -2418,8 +2427,6 @@ static void __init dcache_init(void) { int loop; - percpu_counter_init(&nr_dentry, 0); - /* * A constructor could be added for stable state like the lists, * but it is probably not worth it because of the cache nature diff --git a/fs/inode.c b/fs/inode.c index efc43979709f..5a0a898f55d1 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -102,13 +102,17 @@ static DECLARE_RWSEM(iprune_sem); */ struct inodes_stat_t inodes_stat; -static struct percpu_counter nr_inodes __cacheline_aligned_in_smp; +static DEFINE_PER_CPU(unsigned int, nr_inodes); static struct kmem_cache *inode_cachep __read_mostly; -static inline int get_nr_inodes(void) +static int get_nr_inodes(void) { - return percpu_counter_sum_positive(&nr_inodes); + int i; + int sum = 0; + for_each_possible_cpu(i) + sum += per_cpu(nr_inodes, i); + return sum < 0 ? 0 : sum; } static inline int get_nr_inodes_unused(void) @@ -118,9 +122,9 @@ static inline int get_nr_inodes_unused(void) int get_nr_dirty_inodes(void) { + /* not actually dirty inodes, but a wild approximation */ int nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; - } /* @@ -222,7 +226,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode) inode->i_fsnotify_mask = 0; #endif - percpu_counter_inc(&nr_inodes); + this_cpu_inc(nr_inodes); return 0; out: @@ -264,7 +268,7 @@ void __destroy_inode(struct inode *inode) if (inode->i_default_acl && inode->i_default_acl != ACL_NOT_CACHED) posix_acl_release(inode->i_default_acl); #endif - percpu_counter_dec(&nr_inodes); + this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); @@ -1646,7 +1650,6 @@ void __init inode_init(void) SLAB_MEM_SPREAD), init_once); register_shrinker(&icache_shrinker); - percpu_counter_init(&nr_inodes, 0); /* Hash may have been set up in inode_init_early */ if (!hashdist)