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 <jack@suse.cz>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5f58462..f1c940b 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -362,7 +362,8 @@
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;
}
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2ad98d6..7007809 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -219,6 +219,8 @@
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);
@@ -256,6 +258,8 @@
/* 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);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 435f0b2..b31852f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -94,7 +94,8 @@
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);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 67c1038..be56c8c 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2462,7 +2462,8 @@
/*
* 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;
@@ -2487,12 +2488,14 @@
* 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;
@@ -2523,6 +2526,17 @@
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);
+}
+
/*
* File truncate and transaction commit interact with each other in a
* non-trivial way. If a transaction writing data block A is
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index f4cd3c3..497a4171 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -619,7 +619,7 @@
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,