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>
This commit is contained in:
Jan Kara 2016-04-24 00:56:07 -04:00 committed by Theodore Ts'o
parent 3957ef53a5
commit 41617e1a8d
6 changed files with 38 additions and 9 deletions

View File

@ -362,7 +362,8 @@ static inline int ext4_journal_force_commit(journal_t *journal)
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;
}

View File

@ -219,6 +219,8 @@ static int journal_submit_data_buffers(journal_t *journal,
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 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
/* 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);

View File

@ -94,7 +94,8 @@ EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
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);

View File

@ -2462,7 +2462,8 @@ void jbd2_journal_refile_buffer(journal_t *journal, struct journal_head *jh)
/*
* 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 @@ int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
* 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 @@ done:
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

View File

@ -619,7 +619,7 @@ static inline int ocfs2_calc_tree_trunc_credits(struct super_block *sb,
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,

View File

@ -403,11 +403,19 @@ static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
/* 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
@ -1270,7 +1278,8 @@ extern int jbd2_journal_clear_err (journal_t *);
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);