diff options
author | Kirill A. Shutemov <kirill.shutemov@linux.intel.com> | 2012-09-25 21:33:07 -0400 |
---|---|---|
committer | Al Viro <viro@zeniv.linux.org.uk> | 2012-10-02 21:35:55 -0400 |
commit | 8c0a85377048b64c880e76ec7368904fe46d0b94 (patch) | |
tree | 12e075f4159e88b09a89e35866017f82f80bcc7d /fs/ext2 | |
parent | 99621b44aa194eab594e1f17217231c02b519211 (diff) |
fs: push rcu_barrier() from deactivate_locked_super() to filesystems
There's no reason to call rcu_barrier() on every
deactivate_locked_super(). We only need to make sure that all delayed rcu
free inodes are flushed before we destroy related cache.
Removing rcu_barrier() from deactivate_locked_super() affects some fast
paths. E.g. on my machine exit_group() of a last process in IPC
namespace takes 0.07538s. rcu_barrier() takes 0.05188s of that time.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Diffstat (limited to 'fs/ext2')
-rw-r--r-- | fs/ext2/super.c | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/fs/ext2/super.c b/fs/ext2/super.c index af74d9e27b71..6c205d0c565b 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c | |||
@@ -206,6 +206,11 @@ static int init_inodecache(void) | |||
206 | 206 | ||
207 | static void destroy_inodecache(void) | 207 | static void destroy_inodecache(void) |
208 | { | 208 | { |
209 | /* | ||
210 | * Make sure all delayed rcu free inodes are flushed before we | ||
211 | * destroy cache. | ||
212 | */ | ||
213 | rcu_barrier(); | ||
209 | kmem_cache_destroy(ext2_inode_cachep); | 214 | kmem_cache_destroy(ext2_inode_cachep); |
210 | } | 215 | } |
211 | 216 | ||