[PATCH] Use __read_mostly on some hot fs variables

I discovered on oprofile hunting on a SMP platform that dentry lookups were
slowed down because d_hash_mask, d_hash_shift and dentry_hashtable were in
a cache line that contained inodes_stat.  So each time inodes_stats is
changed by a cpu, other cpus have to refill their cache line.

This patch moves some variables to the __read_mostly section, in order to
avoid false sharing.  RCU dentry lookups can go full speed.

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

fs/bio.c

@@ -30,7 +30,7 @@
 
 #define BIO_POOL_SIZE 256
 
-static kmem_cache_t *bio_slab;
+static kmem_cache_t *bio_slab __read_mostly;
 
 #define BIOVEC_NR_POOLS 6
 
@@ -39,7 +39,7 @@ static kmem_cache_t *bio_slab;
  * basically we just need to survive
  */
 #define BIO_SPLIT_ENTRIES 8	
-mempool_t *bio_split_pool;
+mempool_t *bio_split_pool __read_mostly;
 
 struct biovec_slab {
 	int nr_vecs;

fs/block_dev.c

@@ -234,7 +234,7 @@ static int block_fsync(struct file *filp, struct dentry *dentry, int datasync)
  */
 
 static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(bdev_lock);
-static kmem_cache_t * bdev_cachep;
+static kmem_cache_t * bdev_cachep __read_mostly;
 
 static struct inode *bdev_alloc_inode(struct super_block *sb)
 {
@@ -308,7 +308,7 @@ static struct file_system_type bd_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-static struct vfsmount *bd_mnt;
+static struct vfsmount *bd_mnt __read_mostly;
 struct super_block *blockdev_superblock;
 
 void __init bdev_cache_init(void)

fs/dcache.c

@@ -36,7 +36,7 @@
 
 /* #define DCACHE_DEBUG 1 */
 
-int sysctl_vfs_cache_pressure = 100;
+int sysctl_vfs_cache_pressure __read_mostly = 100;
 EXPORT_SYMBOL_GPL(sysctl_vfs_cache_pressure);
 
  __cacheline_aligned_in_smp DEFINE_SPINLOCK(dcache_lock);
@@ -44,7 +44,7 @@ static seqlock_t rename_lock __cacheline_aligned_in_smp = SEQLOCK_UNLOCKED;
 
 EXPORT_SYMBOL(dcache_lock);
 
-static kmem_cache_t *dentry_cache; 
+static kmem_cache_t *dentry_cache __read_mostly;
 
 #define DNAME_INLINE_LEN (sizeof(struct dentry)-offsetof(struct dentry,d_iname))
 
@@ -59,9 +59,9 @@ static kmem_cache_t *dentry_cache;
 #define D_HASHBITS     d_hash_shift
 #define D_HASHMASK     d_hash_mask
 
-static unsigned int d_hash_mask;
-static unsigned int d_hash_shift;
-static struct hlist_head *dentry_hashtable;
+static unsigned int d_hash_mask __read_mostly;
+static unsigned int d_hash_shift __read_mostly;
+static struct hlist_head *dentry_hashtable __read_mostly;
 static LIST_HEAD(dentry_unused);
 
 /* Statistics gathering. */
@@ -1719,10 +1719,10 @@ static void __init dcache_init(unsigned long mempages)
 }
 
 /* SLAB cache for __getname() consumers */
-kmem_cache_t *names_cachep;
+kmem_cache_t *names_cachep __read_mostly;
 
 /* SLAB cache for file structures */
-kmem_cache_t *filp_cachep;
+kmem_cache_t *filp_cachep __read_mostly;
 
 EXPORT_SYMBOL(d_genocide);
 

fs/dcookies.c

@@ -38,9 +38,9 @@ struct dcookie_struct {
 
 static LIST_HEAD(dcookie_users);
 static DEFINE_MUTEX(dcookie_mutex);
-static kmem_cache_t * dcookie_cache;
-static struct list_head * dcookie_hashtable;
-static size_t hash_size;
+static kmem_cache_t *dcookie_cache __read_mostly;
+static struct list_head *dcookie_hashtable __read_mostly;
+static size_t hash_size __read_mostly;
 
 static inline int is_live(void)
 {

fs/dnotify.c

@@ -21,9 +21,9 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 
-int dir_notify_enable = 1;
+int dir_notify_enable __read_mostly = 1;
 
-static kmem_cache_t *dn_cache;
+static kmem_cache_t *dn_cache __read_mostly;
 
 static void redo_inode_mask(struct inode *inode)
 {

fs/eventpoll.c

@@ -281,13 +281,13 @@ static struct mutex epmutex;
 static struct poll_safewake psw;
 
 /* Slab cache used to allocate "struct epitem" */
-static kmem_cache_t *epi_cache;
+static kmem_cache_t *epi_cache __read_mostly;
 
 /* Slab cache used to allocate "struct eppoll_entry" */
-static kmem_cache_t *pwq_cache;
+static kmem_cache_t *pwq_cache __read_mostly;
 
 /* Virtual fs used to allocate inodes for eventpoll files */
-static struct vfsmount *eventpoll_mnt;
+static struct vfsmount *eventpoll_mnt __read_mostly;
 
 /* File callbacks that implement the eventpoll file behaviour */
 static struct file_operations eventpoll_fops = {

fs/fcntl.c

@@ -412,7 +412,7 @@ out:
 
 /* Table to convert sigio signal codes into poll band bitmaps */
 
-static long band_table[NSIGPOLL] = {
+static const long band_table[NSIGPOLL] = {
 	POLLIN | POLLRDNORM,			/* POLL_IN */
 	POLLOUT | POLLWRNORM | POLLWRBAND,	/* POLL_OUT */
 	POLLIN | POLLRDNORM | POLLMSG,		/* POLL_MSG */
@@ -531,7 +531,7 @@ int send_sigurg(struct fown_struct *fown)
 }
 
 static DEFINE_RWLOCK(fasync_lock);
-static kmem_cache_t *fasync_cache;
+static kmem_cache_t *fasync_cache __read_mostly;
 
 /*
  * fasync_helper() is used by some character device drivers (mainly mice)

fs/inode.c

@@ -56,8 +56,8 @@
 #define I_HASHBITS	i_hash_shift
 #define I_HASHMASK	i_hash_mask
 
-static unsigned int i_hash_mask;
-static unsigned int i_hash_shift;
+static unsigned int i_hash_mask __read_mostly;
+static unsigned int i_hash_shift __read_mostly;
 
 /*
  * Each inode can be on two separate lists. One is
@@ -73,7 +73,7 @@ static unsigned int i_hash_shift;
 
 LIST_HEAD(inode_in_use);
 LIST_HEAD(inode_unused);
-static struct hlist_head *inode_hashtable;
+static struct hlist_head *inode_hashtable __read_mostly;
 
 /*
  * A simple spinlock to protect the list manipulations.
@@ -98,7 +98,7 @@ static DEFINE_MUTEX(iprune_mutex);
  */
 struct inodes_stat_t inodes_stat;
 
-static kmem_cache_t * inode_cachep;
+static kmem_cache_t * inode_cachep __read_mostly;
 
 static struct inode *alloc_inode(struct super_block *sb)
 {

fs/inotify.c

@@ -39,15 +39,15 @@
 
 static atomic_t inotify_cookie;
 
-static kmem_cache_t *watch_cachep;
-static kmem_cache_t *event_cachep;
+static kmem_cache_t *watch_cachep __read_mostly;
+static kmem_cache_t *event_cachep __read_mostly;
 
-static struct vfsmount *inotify_mnt;
+static struct vfsmount *inotify_mnt __read_mostly;
 
 /* these are configurable via /proc/sys/fs/inotify/ */
-int inotify_max_user_instances;
-int inotify_max_user_watches;
-int inotify_max_queued_events;
+int inotify_max_user_instances __read_mostly;
+int inotify_max_user_watches __read_mostly;
+int inotify_max_queued_events __read_mostly;
 
 /*
  * Lock ordering:

fs/locks.c

@@ -142,7 +142,7 @@ int lease_break_time = 45;
 static LIST_HEAD(file_lock_list);
 static LIST_HEAD(blocked_list);
 
-static kmem_cache_t *filelock_cache;
+static kmem_cache_t *filelock_cache __read_mostly;
 
 /* Allocate an empty lock structure. */
 static struct file_lock *locks_alloc_lock(void)

fs/namespace.c

@@ -43,9 +43,9 @@ __cacheline_aligned_in_smp DEFINE_SPINLOCK(vfsmount_lock);
 
 static int event;
 
-static struct list_head *mount_hashtable;
+static struct list_head *mount_hashtable __read_mostly;
 static int hash_mask __read_mostly, hash_bits __read_mostly;
-static kmem_cache_t *mnt_cache;
+static kmem_cache_t *mnt_cache __read_mostly;
 static struct rw_semaphore namespace_sem;
 
 /* /sys/fs */

fs/pipe.c

@@ -675,7 +675,7 @@ fail_page:
 	return NULL;
 }
 
-static struct vfsmount *pipe_mnt;
+static struct vfsmount *pipe_mnt __read_mostly;
 static int pipefs_delete_dentry(struct dentry *dentry)
 {
 	return 1;