ceph: use i_release_count to indicate dir's completeness
Current ceph code tracks directory's completeness in two places.
ceph_readdir() checks i_release_count to decide if it can set the
I_COMPLETE flag in i_ceph_flags. All other places check the I_COMPLETE
flag. This indirection introduces locking complexity.
This patch adds a new variable i_complete_count to ceph_inode_info.
Set i_release_count's value to it when marking a directory complete.
By comparing the two variables, we know if a directory is complete
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 0c369ac..f02d82b 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -107,7 +107,7 @@
* falling back to a "normal" sync readdir if any dentries in the dir
* are dropped.
*
- * I_COMPLETE tells indicates we have all dentries in the dir. It is
+ * Complete dir indicates that we have all dentries in the dir. It is
* defined IFF we hold CEPH_CAP_FILE_SHARED (which will be revoked by
* the MDS if/when the directory is modified).
*/
@@ -198,8 +198,8 @@
filp->f_pos++;
/* make sure a dentry wasn't dropped while we didn't have parent lock */
- if (!ceph_i_test(dir, CEPH_I_COMPLETE)) {
- dout(" lost I_COMPLETE on %p; falling back to mds\n", dir);
+ if (!ceph_dir_is_complete(dir)) {
+ dout(" lost dir complete on %p; falling back to mds\n", dir);
err = -EAGAIN;
goto out;
}
@@ -258,7 +258,7 @@
if (filp->f_pos == 0) {
/* note dir version at start of readdir so we can tell
* if any dentries get dropped */
- fi->dir_release_count = ci->i_release_count;
+ fi->dir_release_count = atomic_read(&ci->i_release_count);
dout("readdir off 0 -> '.'\n");
if (filldir(dirent, ".", 1, ceph_make_fpos(0, 0),
@@ -284,7 +284,7 @@
if ((filp->f_pos == 2 || fi->dentry) &&
!ceph_test_mount_opt(fsc, NOASYNCREADDIR) &&
ceph_snap(inode) != CEPH_SNAPDIR &&
- (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
+ __ceph_dir_is_complete(ci) &&
__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1)) {
spin_unlock(&ci->i_ceph_lock);
err = __dcache_readdir(filp, dirent, filldir);
@@ -350,7 +350,8 @@
if (!req->r_did_prepopulate) {
dout("readdir !did_prepopulate");
- fi->dir_release_count--; /* preclude I_COMPLETE */
+ /* preclude from marking dir complete */
+ fi->dir_release_count--;
}
/* note next offset and last dentry name */
@@ -428,9 +429,9 @@
* the complete dir contents in our cache.
*/
spin_lock(&ci->i_ceph_lock);
- if (ci->i_release_count == fi->dir_release_count) {
+ if (atomic_read(&ci->i_release_count) == fi->dir_release_count) {
dout(" marking %p complete\n", inode);
- ci->i_ceph_flags |= CEPH_I_COMPLETE;
+ __ceph_dir_set_complete(ci, fi->dir_release_count);
ci->i_max_offset = filp->f_pos;
}
spin_unlock(&ci->i_ceph_lock);
@@ -605,7 +606,7 @@
fsc->mount_options->snapdir_name,
dentry->d_name.len) &&
!is_root_ceph_dentry(dir, dentry) &&
- (ci->i_ceph_flags & CEPH_I_COMPLETE) &&
+ __ceph_dir_is_complete(ci) &&
(__ceph_caps_issued_mask(ci, CEPH_CAP_FILE_SHARED, 1))) {
spin_unlock(&ci->i_ceph_lock);
dout(" dir %p complete, -ENOENT\n", dir);
@@ -909,7 +910,7 @@
*/
/* d_move screws up d_subdirs order */
- ceph_i_clear(new_dir, CEPH_I_COMPLETE);
+ ceph_dir_clear_complete(new_dir);
d_move(old_dentry, new_dentry);
@@ -1079,7 +1080,7 @@
if (IS_ROOT(dentry))
return;
- /* if we are not hashed, we don't affect I_COMPLETE */
+ /* if we are not hashed, we don't affect dir's completeness */
if (d_unhashed(dentry))
return;
@@ -1087,7 +1088,7 @@
* we hold d_lock, so d_parent is stable, and d_fsdata is never
* cleared until d_release
*/
- ceph_i_clear(dentry->d_parent->d_inode, CEPH_I_COMPLETE);
+ ceph_dir_clear_complete(dentry->d_parent->d_inode);
}
/*