jbd2: introduce jbd2_inode dirty range scoping

Currently both journal_submit_inode_data_buffers() and
journal_finish_inode_data_buffers() operate on the entire address space
of each of the inodes associated with a given journal entry.  The
consequence of this is that if we have an inode where we are constantly
appending dirty pages we can end up waiting for an indefinite amount of
time in journal_finish_inode_data_buffers() while we wait for all the
pages under writeback to be written out.

The easiest way to cause this type of workload is do just dd from
/dev/zero to a file until it fills the entire filesystem.  This can
cause journal_finish_inode_data_buffers() to wait for the duration of
the entire dd operation.

We can improve this situation by scoping each of the inode dirty ranges
associated with a given transaction.  We do this via the jbd2_inode
structure so that the scoping is contained within jbd2 and so that it
follows the lifetime and locking rules for that structure.

This allows us to limit the writeback & wait in
journal_submit_inode_data_buffers() and
journal_finish_inode_data_buffers() respectively to the dirty range for
a given struct jdb2_inode, keeping us from waiting forever if the inode
in question is still being appended to.

Signed-off-by: Ross Zwisler <zwisler@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: stable@vger.kernel.org

1 files changed, 22 insertions, 0 deletions

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 5c04181b7c6d..0e0393e7f41a 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -451,6 +451,22 @@ struct jbd2_inode {
 	 * @i_flags: Flags of inode [j_list_lock]
 	 */
 	unsigned long i_flags;
+
+	/**
+	 * @i_dirty_start:
+	 *
+	 * Offset in bytes where the dirty range for this inode starts.
+	 * [j_list_lock]
+	 */
+	loff_t i_dirty_start;
+
+	/**
+	 * @i_dirty_end:
+	 *
+	 * Inclusive offset in bytes where the dirty range for this inode
+	 * ends. [j_list_lock]
+	 */
+	loff_t i_dirty_end;
 };
 
 struct jbd2_revoke_table_s;
@@ -1397,6 +1413,12 @@ extern int	   jbd2_journal_force_commit(journal_t *);
 extern int	   jbd2_journal_force_commit_nested(journal_t *);
 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_inode_ranged_write(handle_t *handle,
+			struct jbd2_inode *inode, loff_t start_byte,
+			loff_t length);
+extern int	   jbd2_journal_inode_ranged_wait(handle_t *handle,
+			struct jbd2_inode *inode, loff_t start_byte,
+			loff_t length);
 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);