jbd2: add support for avoiding data writes during transaction commits

Currently when filesystem needs to make sure data is on permanent
storage before committing a transaction it adds inode to transaction's
inode list. During transaction commit, jbd2 writes back all dirty
buffers that have allocated underlying blocks and waits for the IO to
finish. However when doing writeback for delayed allocated data, we
allocate blocks and immediately submit the data. Thus asking jbd2 to
write dirty pages just unnecessarily adds more work to jbd2 possibly
writing back other redirtied blocks.

Add support to jbd2 to allow filesystem to ask jbd2 to only wait for
outstanding data writes before committing a transaction and thus avoid
unnecessary writes.

Signed-off-by: Jan Kara <[e-mail]>
Signed-off-by: Theodore Ts'o <[e-mail]>

fs/ext4/ext4_jbd2.h

···
 static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
 {
 	if (ext4_handle_valid(handle))
-		return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
+		return jbd2_journal_inode_add_write(handle,
+						    EXT4_I(inode)->jinode);
 	return 0;
 }
 

fs/jbd2/commit.c

···
 
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+		if (!(jinode->i_flags & JI_WRITE_DATA))
+			continue;
 		mapping = jinode->i_vfs_inode->i_mapping;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
···
 	/* For locking, see the comment in journal_submit_data_buffers() */
 	spin_lock(&journal->j_list_lock);
 	list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+		if (!(jinode->i_flags & JI_WAIT_DATA))
+			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
 		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);

fs/jbd2/journal.c

···
 EXPORT_SYMBOL(jbd2_journal_invalidatepage);
 EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
 EXPORT_SYMBOL(jbd2_journal_force_commit);
-EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_inode_add_write);
+EXPORT_SYMBOL(jbd2_journal_inode_add_wait);
 EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
 EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);

fs/jbd2/transaction.c

···
 /*
  * File inode in the inode list of the handle's transaction
  */
-int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
+static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
+				   unsigned long flags)
 {
 	transaction_t *transaction = handle->h_transaction;
 	journal_t *journal;
···
 	 * and if jinode->i_next_transaction == transaction, commit code
 	 * will only file the inode where we want it.
 	 */
-	if (jinode->i_transaction == transaction ||
-	    jinode->i_next_transaction == transaction)
+	if ((jinode->i_transaction == transaction ||
+	    jinode->i_next_transaction == transaction) &&
+	    (jinode->i_flags & flags) == flags)
 		return 0;
 
 	spin_lock(&journal->j_list_lock);
-
+	jinode->i_flags |= flags;
+	/* Is inode already attached where we need it? */
 	if (jinode->i_transaction == transaction ||
 	    jinode->i_next_transaction == transaction)
 		goto done;
···
 	spin_unlock(&journal->j_list_lock);
 
 	return 0;
+}
+
+int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode)
+{
+	return jbd2_journal_file_inode(handle, jinode,
+				       JI_WRITE_DATA | JI_WAIT_DATA);
+}
+
+int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode)
+{
+	return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA);
 }
 
 /*

fs/ocfs2/journal.h

···
 
 static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
 {
-	return jbd2_journal_file_inode(handle, &OCFS2_I(inode)->ip_jinode);
+	return jbd2_journal_inode_add_write(handle, &OCFS2_I(inode)->ip_jinode);
 }
 
 static inline int ocfs2_begin_ordered_truncate(struct inode *inode,

include/linux/jbd2.h

···
 
 /* Flags in jbd_inode->i_flags */
 #define __JI_COMMIT_RUNNING 0
-/* Commit of the inode data in progress. We use this flag to protect us from
+#define __JI_WRITE_DATA 1
+#define __JI_WAIT_DATA 2
+
+/*
+ * Commit of the inode data in progress. We use this flag to protect us from
  * concurrent deletion of inode. We cannot use reference to inode for this
  * since we cannot afford doing last iput() on behalf of kjournald
  */
 #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+/* Write allocated dirty buffers in this inode before commit */
+#define JI_WRITE_DATA (1 << __JI_WRITE_DATA)
+/* Wait for outstanding data writes for this inode before commit */
+#define JI_WAIT_DATA (1 << __JI_WAIT_DATA)
 
 /**
  * struct jbd_inode is the structure linking inodes in ordered mode
···
 extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
 extern int	   jbd2_journal_force_commit(journal_t *);
 extern int	   jbd2_journal_force_commit_nested(journal_t *);
-extern int	   jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int	   jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode);
+extern int	   jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode);
 extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
 				struct jbd2_inode *inode, loff_t new_size);
 extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);