Messages in this thread Patch in this message | | | From | Chao Yu <> | Subject | [PATCH 2/2] f2fs: reduce region of f2fs_lock_op covered for better concurrency | Date | Tue, 24 Jun 2014 14:16:24 +0800 |
| |
In our rename process, region of f2fs_lock_op covered is too big as some of the code like f2fs_empty_dir/f2fs_find_entry are not needed to protect by this lock.
So in the extreme case like doing checkpoint when we rename old inode to exist inode in a large directory could cause lower concurrency.
Let's reduce the region of f2fs_lock_op to fix this.
Signed-off-by: Chao Yu <chao2.yu@samsung.com> --- fs/f2fs/namei.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-)
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c index f17e34c..143799d 100644 --- a/fs/f2fs/namei.c +++ b/fs/f2fs/namei.c @@ -394,8 +394,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, goto out_old; } - f2fs_lock_op(sbi); - if (new_inode) { err = -ENOTEMPTY; @@ -408,6 +406,8 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, if (!new_entry) goto out_dir; + f2fs_lock_op(sbi); + err = acquire_orphan_inode(sbi); if (err) goto put_out_dir; @@ -439,9 +439,13 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, update_inode_page(old_inode); update_inode_page(new_inode); } else { + f2fs_lock_op(sbi); + err = f2fs_add_link(new_dentry, old_inode); - if (err) + if (err) { + f2fs_unlock_op(sbi); goto out_dir; + } if (old_dir_entry) { inc_nlink(new_dir); @@ -475,6 +479,7 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry, return 0; put_out_dir: + f2fs_unlock_op(sbi); kunmap(new_page); f2fs_put_page(new_page, 0); out_dir: @@ -482,7 +487,6 @@ out_dir: kunmap(old_dir_page); f2fs_put_page(old_dir_page, 0); } - f2fs_unlock_op(sbi); out_old: kunmap(old_page); f2fs_put_page(old_page, 0); -- 1.7.9.5
| |