On Thu, Dec 11, 2008 at 11:40:07PM +0100, Eric Dumazet wrote:
> Goal of this patch is to not touch inode_lock for socket/pipes/anonfd
> inodes allocation/freeing.
>
> SINGLE dentries are attached to inodes that dont need to be linked
> in a list of inodes, being "inode_in_use" or "sb->s_inodes"
> As inode_lock was taken only to protect these lists, we avoid taking it
> as well.
>
> Using iput_single() from dput_single() avoids taking inode_lock
> at freeing time.
>
> This patch has a very noticeable effect, because we avoid dirtying of
> three contended cache lines in new_inode(), and five cache lines in iput()
>
> ("socketallocbench -n 8" result : from 19.9s to 3.01s)
Nice!
Acked-by: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
> Signed-off-by: Eric Dumazet <dada1@xxxxxxxxxxxxx>
> ---
> fs/anon_inodes.c | 2 +-
> fs/dcache.c | 2 +-
> fs/inode.c | 29 ++++++++++++++++++++---------
> fs/pipe.c | 2 +-
> include/linux/fs.h | 12 +++++++++++-
> net/socket.c | 2 +-
> 6 files changed, 35 insertions(+), 14 deletions(-)
>
> diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
> index 8bf83cb..89fd36d 100644
> --- a/fs/anon_inodes.c
> +++ b/fs/anon_inodes.c
> @@ -125,7 +125,7 @@ EXPORT_SYMBOL_GPL(anon_inode_getfd);
> */
> static struct inode *anon_inode_mkinode(void)
> {
> - struct inode *inode = new_inode(anon_inode_mnt->mnt_sb);
> + struct inode *inode = new_inode_single(anon_inode_mnt->mnt_sb);
>
> if (!inode)
> return ERR_PTR(-ENOMEM);
> diff --git a/fs/dcache.c b/fs/dcache.c
> index af3bfb3..3363853 100644
> --- a/fs/dcache.c
> +++ b/fs/dcache.c
> @@ -231,7 +231,7 @@ static void dput_single(struct dentry *dentry)
> return;
> inode = dentry->d_inode;
> if (inode)
> - iput(inode);
> + iput_single(inode);
> d_free(dentry);
> }
>
> diff --git a/fs/inode.c b/fs/inode.c
> index dc8e72a..0fdfe1b 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -221,6 +221,13 @@ void destroy_inode(struct inode *inode)
> kmem_cache_free(inode_cachep, (inode));
> }
>
> +void iput_single(struct inode *inode)
> +{
> + if (atomic_dec_and_test(&inode->i_count)) {
> + destroy_inode(inode);
> + percpu_counter_dec(&nr_inodes);
> + }
> +}
>
> /*
> * These are initializations that only need to be done
> @@ -587,8 +594,9 @@ static int last_ino_get(void)
> #endif
>
> /**
> - * new_inode - obtain an inode
> + * __new_inode - obtain an inode
> * @sb: superblock
> + * @single: if true, dont link new inode in a list
> *
> * Allocates a new inode for given superblock. The default gfp_mask
> * for allocations related to inode->i_mapping is GFP_HIGHUSER_PAGECACHE.
> @@ -598,7 +606,7 @@ static int last_ino_get(void)
> * newly created inode's mapping
> *
> */
> -struct inode *new_inode(struct super_block *sb)
> +struct inode *__new_inode(struct super_block *sb, int single)
> {
> /*
> * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW
> @@ -607,22 +615,25 @@ struct inode *new_inode(struct super_block *sb)
> */
> struct inode * inode;
>
> - spin_lock_prefetch(&inode_lock);
> -
> inode = alloc_inode(sb);
> if (inode) {
> percpu_counter_inc(&nr_inodes);
> inode->i_state = 0;
> inode->i_ino = last_ino_get();
> - spin_lock(&inode_lock);
> - list_add(&inode->i_list, &inode_in_use);
> - list_add(&inode->i_sb_list, &sb->s_inodes);
> - spin_unlock(&inode_lock);
> + if (single) {
> + INIT_LIST_HEAD(&inode->i_list);
> + INIT_LIST_HEAD(&inode->i_sb_list);
> + } else {
> + spin_lock(&inode_lock);
> + list_add(&inode->i_list, &inode_in_use);
> + list_add(&inode->i_sb_list, &sb->s_inodes);
> + spin_unlock(&inode_lock);
> + }
> }
> return inode;
> }
>
> -EXPORT_SYMBOL(new_inode);
> +EXPORT_SYMBOL(__new_inode);
>
> void unlock_new_inode(struct inode *inode)
> {
> diff --git a/fs/pipe.c b/fs/pipe.c
> index 4de6dd5..8c51a0d 100644
> --- a/fs/pipe.c
> +++ b/fs/pipe.c
> @@ -865,7 +865,7 @@ static struct dentry_operations pipefs_dentry_operations = {
>
> static struct inode * get_pipe_inode(void)
> {
> - struct inode *inode = new_inode(pipe_mnt->mnt_sb);
> + struct inode *inode = new_inode_single(pipe_mnt->mnt_sb);
> struct pipe_inode_info *pipe;
>
> if (!inode)
> diff --git a/include/linux/fs.h b/include/linux/fs.h
> index a789346..a702d81 100644
> --- a/include/linux/fs.h
> +++ b/include/linux/fs.h
> @@ -1899,7 +1899,17 @@ extern void __iget(struct inode * inode);
> extern void iget_failed(struct inode *);
> extern void clear_inode(struct inode *);
> extern void destroy_inode(struct inode *);
> -extern struct inode *new_inode(struct super_block *);
> +extern struct inode *__new_inode(struct super_block *, int);
> +static inline struct inode *new_inode(struct super_block *sb)
> +{
> + return __new_inode(sb, 0);
> +}
> +static inline struct inode *new_inode_single(struct super_block *sb)
> +{
> + return __new_inode(sb, 1);
> +}
> +extern void iput_single(struct inode *);
> +
> extern int should_remove_suid(struct dentry *);
> extern int file_remove_suid(struct file *);
>
> diff --git a/net/socket.c b/net/socket.c
> index 353c928..4017409 100644
> --- a/net/socket.c
> +++ b/net/socket.c
> @@ -464,7 +464,7 @@ static struct socket *sock_alloc(void)
> struct inode *inode;
> struct socket *sock;
>
> - inode = new_inode(sock_mnt->mnt_sb);
> + inode = new_inode_single(sock_mnt->mnt_sb);
> if (!inode)
> return NULL;
>
> --
> To unsubscribe from this list: send the line "unsubscribe netdev" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe kernel-testers" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
