jbd2: transaction reservation support

In some cases we cannot start a transaction because of locking
constraints and passing started transaction into those places is not
handy either because we could block transaction commit for too long.
Transaction reservation is designed to solve these issues.  It
reserves a handle with given number of credits in the journal and the
handle can be later attached to the running transaction without
blocking on commit or checkpointing.  Reserved handles do not block
transaction commit in any way, they only reduce maximum size of the
running transaction (because we have to always be prepared to
accomodate request for attaching reserved handle).
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

fs/ext4/ext4_jbd2.c

@@ -62,7 +62,7 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
 		ext4_abort(sb, "Detected aborted journal");
 		return ERR_PTR(-EROFS);
 	}
-	return jbd2__journal_start(journal, nblocks, GFP_NOFS, type, line);
+	return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, type, line);
 }
 
 int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)

fs/jbd2/commit.c

@@ -523,6 +523,12 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	 */
 	jbd2_journal_switch_revoke_table(journal);
 
+	/*
+	 * Reserved credits cannot be claimed anymore, free them
+	 */
+	atomic_sub(atomic_read(&journal->j_reserved_credits),
+		   &commit_transaction->t_outstanding_credits);
+
 	trace_jbd2_commit_flushing(journal, commit_transaction);
 	stats.run.rs_flushing = jiffies;
 	stats.run.rs_locked = jbd2_time_diff(stats.run.rs_locked,

fs/jbd2/journal.c

@@ -1030,6 +1030,7 @@ static journal_t * journal_init_common (void)
 	init_waitqueue_head(&journal->j_wait_done_commit);
 	init_waitqueue_head(&journal->j_wait_commit);
 	init_waitqueue_head(&journal->j_wait_updates);
+	init_waitqueue_head(&journal->j_wait_reserved);
 	mutex_init(&journal->j_barrier);
 	mutex_init(&journal->j_checkpoint_mutex);
 	spin_lock_init(&journal->j_revoke_lock);
@@ -1039,6 +1040,7 @@ static journal_t * journal_init_common (void)
 	journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
 	journal->j_min_batch_time = 0;
 	journal->j_max_batch_time = 15000; /* 15ms */
+	atomic_set(&journal->j_reserved_credits, 0);
 
 	/* The journal is marked for error until we succeed with recovery! */
 	journal->j_flags = JBD2_ABORT;

include/linux/jbd2.h

@@ -410,8 +410,15 @@ struct jbd2_revoke_table_s;
 
 struct jbd2_journal_handle
 {
-	/* Which compound transaction is this update a part of? */
-	transaction_t		*h_transaction;
+	union {
+		/* Which compound transaction is this update a part of? */
+		transaction_t	*h_transaction;
+		/* Which journal handle belongs to - used iff h_reserved set */
+		journal_t	*h_journal;
+	};
+
+	/* Handle reserved for finishing the logical operation */
+	handle_t		*h_rsv_handle;
 
 	/* Number of remaining buffers we are allowed to dirty: */
 	int			h_buffer_credits;
@@ -426,6 +433,7 @@ struct jbd2_journal_handle
 	/* Flags [no locking] */
 	unsigned int	h_sync:		1;	/* sync-on-close */
 	unsigned int	h_jdata:	1;	/* force data journaling */
+	unsigned int	h_reserved:	1;	/* handle with reserved credits */
 	unsigned int	h_aborted:	1;	/* fatal error on handle */
 	unsigned int	h_type:		8;	/* for handle statistics */
 	unsigned int	h_line_no:	16;	/* for handle statistics */
@@ -690,6 +698,7 @@ jbd2_time_diff(unsigned long start, unsigned long end)
  * @j_wait_done_commit: Wait queue for waiting for commit to complete
  * @j_wait_commit: Wait queue to trigger commit
  * @j_wait_updates: Wait queue to wait for updates to complete
+ * @j_wait_reserved: Wait queue to wait for reserved buffer credits to drop
  * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints
  * @j_head: Journal head - identifies the first unused block in the journal
  * @j_tail: Journal tail - identifies the oldest still-used block in the
@@ -703,6 +712,7 @@ jbd2_time_diff(unsigned long start, unsigned long end)
  *     journal
  * @j_fs_dev: Device which holds the client fs.  For internal journal this will
  *     be equal to j_dev
+ * @j_reserved_credits: Number of buffers reserved from the running transaction
  * @j_maxlen: Total maximum capacity of the journal region on disk.
  * @j_list_lock: Protects the buffer lists and internal buffer state.
  * @j_inode: Optional inode where we store the journal.  If present, all journal
@@ -801,6 +811,9 @@ struct journal_s
 	/* Wait queue to wait for updates to complete */
 	wait_queue_head_t	j_wait_updates;
 
+	/* Wait queue to wait for reserved buffer credits to drop */
+	wait_queue_head_t	j_wait_reserved;
+
 	/* Semaphore for locking against concurrent checkpoints */
 	struct mutex		j_checkpoint_mutex;
 
@@ -855,6 +868,9 @@ struct journal_s
 	/* Total maximum capacity of the journal region on disk. */
 	unsigned int		j_maxlen;
 
+	/* Number of buffers reserved from the running transaction */
+	atomic_t		j_reserved_credits;
+
 	/*
 	 * Protects the buffer lists and internal buffer state.
 	 */
@@ -1091,10 +1107,14 @@ static inline handle_t *journal_current_handle(void)
  */
 
 extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
-extern handle_t *jbd2__journal_start(journal_t *, int nblocks, gfp_t gfp_mask,
-				     unsigned int type, unsigned int line_no);
+extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks,
+				     gfp_t gfp_mask, unsigned int type,
+				     unsigned int line_no);
 extern int	 jbd2_journal_restart(handle_t *, int nblocks);
 extern int	 jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask);
+extern int	 jbd2_journal_start_reserved(handle_t *handle,
+				unsigned int type, unsigned int line_no);
+extern void	 jbd2_journal_free_reserved(handle_t *handle);
 extern int	 jbd2_journal_extend (handle_t *, int nblocks);
 extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
 extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);