UBIFS: optimize deletions

Every time anything is deleted, UBIFS writes the deletion inode
node twice - once in 'ubifs_jnl_update()' and the second time in
'ubifs_jnl_write_inode()'. However, the second write is not needed
if no commit happened after 'ubifs_jnl_update()'. This patch
checke that condition and avoids writing the deletion inode for
the second time.

Signed-off-by: Artem Bityutskiy <Artem.Bityutskiy@nokia.com>

diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 3bc3fc9..0bcee7d 100644 (file)
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -604,6 +604,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
                        release_head(c, BASEHD);
                        goto out_finish;
                }
+               ui->del_cmtno = c->cmt_no;
        }
 
        err = write_head(c, BASEHD, dent, len, &lnum, &dent_offs, sync);
@@ -820,6 +821,64 @@ out_free:
        return err;
 }
 
+/**
+ * ubifs_jnl_write_inode - delete an inode.
+ * @c: UBIFS file-system description object
+ * @inode: inode to delete
+ *
+ * This function deletes inode @inode which includes removing it from orphans,
+ * deleting it from TNC and, in some cases, writing a deletion inode to the
+ * journal.
+ *
+ * When regular file inodes are unlinked or a directory inode is removed, the
+ * 'ubifs_jnl_update()' function write corresponding deletion inode and
+ * direntry to the media, and adds the inode to orphans. After this, when the
+ * last reference to this inode has been dropped, this function is called. In
+ * general, it has to write one more deletion inode to the media, because if
+ * a commit happened between 'ubifs_jnl_update()' and
+ * 'ubifs_jnl_delete_inode()', the deletion inode is not in the journal
+ * anymore, and in fact it might be not on the flash anymore, becouse it might
+ * have been garbage-collected already. And for optimization reasond UBIFS does
+ * not read the orphan area if it has been unmounted cleanly, so it would have
+ * no indication in the journal that there is a deleted inode which has to be
+ * removed from TNC.
+ *
+ * However, if there was no commit between 'ubifs_jnl_update()' and
+ * 'ubifs_jnl_delete_inode()', then there is no need to write the deletion
+ * inode to the media for the second time. And this is quite typical case.
+ *
+ * This function returns zero in case of success and a negative error code in
+ * case of failure.
+ */
+int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode)
+{
+       int err;
+       struct ubifs_inode *ui = ubifs_inode(inode);
+
+       ubifs_assert(inode->i_nlink == 0);
+
+       if (ui->del_cmtno != c->cmt_no)
+               /* A commit happened for sure */
+               return ubifs_jnl_write_inode(c, inode);
+
+       down_read(&c->commit_sem);
+       /*
+        * Check commit number again, because the first test has been done
+        * without @c->commit_sem, so a commit might have happened.
+        */
+       if (ui->del_cmtno != c->cmt_no) {
+               up_read(&c->commit_sem);
+               return ubifs_jnl_write_inode(c, inode);
+       }
+
+       ubifs_delete_orphan(c, inode->i_ino);
+       err = ubifs_tnc_remove_ino(c, inode->i_ino);
+       if (err)
+               ubifs_ro_mode(c, err);
+       up_read(&c->commit_sem);
+       return err;
+}
+
 /**
  * ubifs_jnl_rename - rename a directory entry.
  * @c: UBIFS file-system description object
@@ -928,6 +987,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
                        release_head(c, BASEHD);
                        goto out_finish;
                }
+               new_ui->del_cmtno = c->cmt_no;
        }
 
        err = write_head(c, BASEHD, dent, len, &lnum, &offs, sync);

diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index d5d64ae..77b2883 100644 (file)
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -350,13 +350,15 @@ static void ubifs_delete_inode(struct inode *inode)
                goto out;
 
        ui->ui_size = inode->i_size = 0;
-       err = ubifs_jnl_write_inode(c, inode);
+       err = ubifs_jnl_delete_inode(c, inode);
        if (err)
                /*
                 * Worst case we have a lost orphan inode wasting space, so a
                 * simple error message is ok here.
                 */
-               ubifs_err("can't write inode %lu, error %d", inode->i_ino, err);
+               ubifs_err("can't delete inode %lu, error %d",
+                         inode->i_ino, err);
+
 out:
        if (ui->dirty)
                ubifs_release_dirty_inode_budget(c, ui);

diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 1ee3ae4..8ce0770 100644 (file)
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -323,6 +323,8 @@ struct ubifs_gced_idx_leb {
  * struct ubifs_inode - UBIFS in-memory inode description.
  * @vfs_inode: VFS inode description object
  * @creat_sqnum: sequence number at time of creation
+ * @del_cmtno: commit number corresponding to the time the inode was deleted,
+ *             protected by @c->commit_sem;
  * @xattr_size: summarized size of all extended attributes in bytes
  * @xattr_cnt: count of extended attributes this inode has
  * @xattr_names: sum of lengths of all extended attribute names belonging to
@@ -373,7 +375,10 @@ struct ubifs_gced_idx_leb {
  */
 struct ubifs_inode {
        struct inode vfs_inode;
-       unsigned long long creat_sqnum;
+       union {
+               unsigned long long creat_sqnum;
+               unsigned long long del_cmtno;
+       };
        unsigned int xattr_size;
        unsigned int xattr_cnt;
        unsigned int xattr_names;
@@ -780,7 +785,7 @@ struct ubifs_compressor {
 /**
  * struct ubifs_budget_req - budget requirements of an operation.
  *
- * @fast: non-zero if the budgeting should try to aquire budget quickly and
+ * @fast: non-zero if the budgeting should try to acquire budget quickly and
  *        should not try to call write-back
  * @recalculate: non-zero if @idx_growth, @data_growth, and @dd_growth fields
  *               have to be re-calculated
@@ -865,7 +870,7 @@ struct ubifs_mount_opts {
  * struct ubifs_info - UBIFS file-system description data structure
  * (per-superblock).
  * @vfs_sb: VFS @struct super_block object
- * @bdi: backing device info object to make VFS happy and disable readahead
+ * @bdi: backing device info object to make VFS happy and disable read-ahead
  *
  * @highest_inum: highest used inode number
  * @vfs_gen: VFS inode generation counter
@@ -1407,6 +1412,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 int ubifs_jnl_write_data(struct ubifs_info *c, const struct inode *inode,
                         const union ubifs_key *key, const void *buf, int len);
 int ubifs_jnl_write_inode(struct ubifs_info *c, const struct inode *inode);
+int ubifs_jnl_delete_inode(struct ubifs_info *c, const struct inode *inode);
 int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
                     const struct dentry *old_dentry,
                     const struct inode *new_dir,