From: Harshad Shirwadkar <[email protected]>
This patch series supersedes the patch "ext4: remove journal barrier
during fast commit" sent in Feb 2022.
This patch series reworks the fast commit's commit path to improve
overall performance of the commit path. Following optimizations have
been added in this series:
* Avoid having to lock the journal throughout the fast commit.
* Remove tracking of open handles per inode.
With the changes introduced in this patch series, now the commit path
for fast commits is as follows:
[1] Lock the journal by calling jbd2_journal_lock_updates. This
ensures that all the exsiting handles finish and no new handles
can start.
[2] Mark all the fast commit eligible inodes as undergoing fast commit
by setting "EXT4_STATE_FC_COMMITTING" state.
[3] Unlock the journal by calling jbd2_journal_unlock_updates. This allows
starting of new handles. If new handles try to start an update on
any of the inodes that are being committed, ext4_fc_track_inode()
will block until those inodes have finished the fast commit.
[4] Submit data buffers of all the committing inodes.
[5] Wait for [4] to complete.
[6] Commit all the directory entry updates in the fast commit space.
[7] Commit all the changed inodes in the fast commit space and clear
"EXT4_STATE_FC_COMMITTING" for all the inodes.
[8] Write tail tag to ensure atomicity of commits.
(The above flow has been documented in the code as well)
I verified that the patch series introduces no regressions in "quick"
and "log" groups when "fast_commit" feature is enabled.
Signed-off-by: Harshad Shirwadkar <[email protected]>
Harshad Shirwadkar (5):
ext4: convert i_fc_lock to spinlock
ext4: drop i_fc_updates from inode fc info
ext4: for committing inode, make ext4_fc_track_inode wait
ext4: rework fast commit commit path
ext4: update code documentation
fs/ext4/ext4.h | 12 +--
fs/ext4/ext4_jbd2.c | 12 +++
fs/ext4/ext4_jbd2.h | 13 +--
fs/ext4/fast_commit.c | 228 ++++++++++++++++++++----------------------
fs/ext4/inode.c | 3 +-
fs/ext4/super.c | 2 +-
fs/jbd2/journal.c | 2 -
7 files changed, 134 insertions(+), 138 deletions(-)
--
2.35.1.616.g0bdcbb4464-goog
From: Harshad Shirwadkar <[email protected]>
The new logic introduced in this series does not require tracking number
of active handles open on an inode. So, drop it.
Signed-off-by: Harshad Shirwadkar <[email protected]>
---
fs/ext4/ext4.h | 5 ----
fs/ext4/fast_commit.c | 58 +------------------------------------------
2 files changed, 1 insertion(+), 62 deletions(-)
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index fb6d65f1176f..6861a3127a42 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1059,9 +1059,6 @@ struct ext4_inode_info {
/* End of lblk range that needs to be committed in this fast commit */
ext4_lblk_t i_fc_lblk_len;
- /* Number of ongoing updates on this inode */
- atomic_t i_fc_updates;
-
/* Fast commit wait queue for this inode */
wait_queue_head_t i_fc_wait;
@@ -2930,8 +2927,6 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
-void ext4_fc_start_update(struct inode *inode);
-void ext4_fc_stop_update(struct inode *inode);
void ext4_fc_del(struct inode *inode);
bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
void ext4_fc_replay_cleanup(struct super_block *sb);
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 4f2caf6f987c..a589fc415dbe 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -201,7 +201,6 @@ void ext4_fc_init_inode(struct inode *inode)
INIT_LIST_HEAD(&ei->i_fc_list);
INIT_LIST_HEAD(&ei->i_fc_dilist);
init_waitqueue_head(&ei->i_fc_wait);
- atomic_set(&ei->i_fc_updates, 0);
}
/* This function must be called with sbi->s_fc_lock held. */
@@ -229,50 +228,6 @@ __releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
finish_wait(wq, &wait.wq_entry);
}
-/*
- * Inform Ext4's fast about start of an inode update
- *
- * This function is called by the high level call VFS callbacks before
- * performing any inode update. This function blocks if there's an ongoing
- * fast commit on the inode in question.
- */
-void ext4_fc_start_update(struct inode *inode)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
-
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
- return;
-
-restart:
- spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- if (list_empty(&ei->i_fc_list))
- goto out;
-
- if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
- ext4_fc_wait_committing_inode(inode);
- goto restart;
- }
-out:
- atomic_inc(&ei->i_fc_updates);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
-}
-
-/*
- * Stop inode update and wake up waiting fast commits if any.
- */
-void ext4_fc_stop_update(struct inode *inode)
-{
- struct ext4_inode_info *ei = EXT4_I(inode);
-
- if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
- (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
- return;
-
- if (atomic_dec_and_test(&ei->i_fc_updates))
- wake_up_all(&ei->i_fc_wait);
-}
-
/*
* Remove inode from fast commit list. If the inode is being committed
* we wait until inode commit is done.
@@ -939,18 +894,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
spin_lock(&sbi->s_fc_lock);
list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
- while (atomic_read(&ei->i_fc_updates)) {
- DEFINE_WAIT(wait);
-
- prepare_to_wait(&ei->i_fc_wait, &wait,
- TASK_UNINTERRUPTIBLE);
- if (atomic_read(&ei->i_fc_updates)) {
- spin_unlock(&sbi->s_fc_lock);
- schedule();
- spin_lock(&sbi->s_fc_lock);
- }
- finish_wait(&ei->i_fc_wait, &wait);
- }
+
spin_unlock(&sbi->s_fc_lock);
ret = jbd2_submit_inode_data(ei->jinode);
if (ret)
--
2.35.1.616.g0bdcbb4464-goog
On Tue 08-03-22 02:51:09, Harshad Shirwadkar wrote:
> From: Harshad Shirwadkar <[email protected]>
>
> The new logic introduced in this series does not require tracking number
> of active handles open on an inode. So, drop it.
>
> Signed-off-by: Harshad Shirwadkar <[email protected]>
OK, but this patch needs to go towards the end of the series. Otherwise
fastcommit would be broken in the middle of the series which is nasty (e.g.
for bisection).
Honza
> ---
> fs/ext4/ext4.h | 5 ----
> fs/ext4/fast_commit.c | 58 +------------------------------------------
> 2 files changed, 1 insertion(+), 62 deletions(-)
>
> diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
> index fb6d65f1176f..6861a3127a42 100644
> --- a/fs/ext4/ext4.h
> +++ b/fs/ext4/ext4.h
> @@ -1059,9 +1059,6 @@ struct ext4_inode_info {
> /* End of lblk range that needs to be committed in this fast commit */
> ext4_lblk_t i_fc_lblk_len;
>
> - /* Number of ongoing updates on this inode */
> - atomic_t i_fc_updates;
> -
> /* Fast commit wait queue for this inode */
> wait_queue_head_t i_fc_wait;
>
> @@ -2930,8 +2927,6 @@ void __ext4_fc_track_create(handle_t *handle, struct inode *inode,
> void ext4_fc_track_create(handle_t *handle, struct dentry *dentry);
> void ext4_fc_track_inode(handle_t *handle, struct inode *inode);
> void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handle);
> -void ext4_fc_start_update(struct inode *inode);
> -void ext4_fc_stop_update(struct inode *inode);
> void ext4_fc_del(struct inode *inode);
> bool ext4_fc_replay_check_excluded(struct super_block *sb, ext4_fsblk_t block);
> void ext4_fc_replay_cleanup(struct super_block *sb);
> diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
> index 4f2caf6f987c..a589fc415dbe 100644
> --- a/fs/ext4/fast_commit.c
> +++ b/fs/ext4/fast_commit.c
> @@ -201,7 +201,6 @@ void ext4_fc_init_inode(struct inode *inode)
> INIT_LIST_HEAD(&ei->i_fc_list);
> INIT_LIST_HEAD(&ei->i_fc_dilist);
> init_waitqueue_head(&ei->i_fc_wait);
> - atomic_set(&ei->i_fc_updates, 0);
> }
>
> /* This function must be called with sbi->s_fc_lock held. */
> @@ -229,50 +228,6 @@ __releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
> finish_wait(wq, &wait.wq_entry);
> }
>
> -/*
> - * Inform Ext4's fast about start of an inode update
> - *
> - * This function is called by the high level call VFS callbacks before
> - * performing any inode update. This function blocks if there's an ongoing
> - * fast commit on the inode in question.
> - */
> -void ext4_fc_start_update(struct inode *inode)
> -{
> - struct ext4_inode_info *ei = EXT4_I(inode);
> -
> - if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
> - (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
> - return;
> -
> -restart:
> - spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
> - if (list_empty(&ei->i_fc_list))
> - goto out;
> -
> - if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
> - ext4_fc_wait_committing_inode(inode);
> - goto restart;
> - }
> -out:
> - atomic_inc(&ei->i_fc_updates);
> - spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
> -}
> -
> -/*
> - * Stop inode update and wake up waiting fast commits if any.
> - */
> -void ext4_fc_stop_update(struct inode *inode)
> -{
> - struct ext4_inode_info *ei = EXT4_I(inode);
> -
> - if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
> - (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
> - return;
> -
> - if (atomic_dec_and_test(&ei->i_fc_updates))
> - wake_up_all(&ei->i_fc_wait);
> -}
> -
> /*
> * Remove inode from fast commit list. If the inode is being committed
> * we wait until inode commit is done.
> @@ -939,18 +894,7 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
> spin_lock(&sbi->s_fc_lock);
> list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
> ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
> - while (atomic_read(&ei->i_fc_updates)) {
> - DEFINE_WAIT(wait);
> -
> - prepare_to_wait(&ei->i_fc_wait, &wait,
> - TASK_UNINTERRUPTIBLE);
> - if (atomic_read(&ei->i_fc_updates)) {
> - spin_unlock(&sbi->s_fc_lock);
> - schedule();
> - spin_lock(&sbi->s_fc_lock);
> - }
> - finish_wait(&ei->i_fc_wait, &wait);
> - }
> +
> spin_unlock(&sbi->s_fc_lock);
> ret = jbd2_submit_inode_data(ei->jinode);
> if (ret)
> --
> 2.35.1.616.g0bdcbb4464-goog
>
--
Jan Kara <[email protected]>
SUSE Labs, CR
From: Harshad Shirwadkar <[email protected]>
This patch updates code documentation to reflect the commit path changes
made in this series.
Signed-off-by: Harshad Shirwadkar <[email protected]>
---
fs/ext4/fast_commit.c | 36 ++++++++++++++++++++++--------------
1 file changed, 22 insertions(+), 14 deletions(-)
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index 831bb21dcb4f..c4e15898fbd4 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -49,14 +49,21 @@
* that need to be committed during a fast commit in another in memory queue of
* inodes. During the commit operation, we commit in the following order:
*
- * [1] Lock inodes for any further data updates by setting COMMITTING state
- * [2] Submit data buffers of all the inodes
- * [3] Wait for [2] to complete
- * [4] Commit all the directory entry updates in the fast commit space
- * [5] Commit all the changed inode structures
- * [6] Write tail tag (this tag ensures the atomicity, please read the following
+ * [1] Lock the journal by calling jbd2_journal_lock_updates. This ensures that
+ * all the exsiting handles finish and no new handles can start.
+ * [2] Mark all the fast commit eligible inodes as undergoing fast commit
+ * by setting "EXT4_STATE_FC_COMMITTING" state.
+ * [3] Unlock the journal by calling jbd2_journal_unlock_updates. This allows
+ * starting of new handles. If new handles try to start an update on
+ * any of the inodes that are being committed, ext4_fc_track_inode()
+ * will block until those inodes have finished the fast commit.
+ * [4] Submit data buffers of all the committing inodes.
+ * [5] Wait for [4] to complete.
+ * [6] Commit all the directory entry updates in the fast commit space.
+ * [7] Commit all the changed inodes in the fast commit space and clear
+ * "EXT4_STATE_FC_COMMITTING" for these inodes.
+ * [8] Write tail tag (this tag ensures the atomicity, please read the following
* section for more details).
- * [7] Wait for [4], [5] and [6] to complete.
*
* All the inode updates must call ext4_fc_start_update() before starting an
* update. If such an ongoing update is present, fast commit waits for it to
@@ -142,6 +149,13 @@
* similarly. Thus, by converting a non-idempotent procedure into a series of
* idempotent outcomes, fast commits ensured idempotence during the replay.
*
+ * Locking
+ * -------
+ * sbi->s_fc_lock protects the fast commit inodes queue and the fast commit
+ * dentry queue. ei->i_fc_lock protects the fast commit related info in a given
+ * inode. Most of the code avoids acquiring both the locks, but if one must do
+ * that then sbi->s_fc_lock must be acquired before ei->i_fc_lock.
+ *
* TODOs
* -----
*
@@ -156,13 +170,7 @@
* fast commit recovery even if that area is invalidated by later full
* commits.
*
- * 1) Fast commit's commit path locks the entire file system during fast
- * commit. This has significant performance penalty. Instead of that, we
- * should use ext4_fc_start/stop_update functions to start inode level
- * updates from ext4_journal_start/stop. Once we do that we can drop file
- * system locking during commit path.
- *
- * 2) Handle more ineligible cases.
+ * 1) Handle more ineligible cases.
*/
#include <trace/events/ext4.h>
--
2.35.1.616.g0bdcbb4464-goog
From: Harshad Shirwadkar <[email protected]>
This patch reworks fast commit's commit path to remove locking the
journal for the entire duration of a fast commit. Instead, we only lock
the journal while marking all the eligible inodes as "committing". This
allows handles to make progress in parallel with the fast commit.
Signed-off-by: Harshad Shirwadkar <[email protected]>
---
fs/ext4/fast_commit.c | 79 ++++++++++++++++++++++---------------------
fs/jbd2/journal.c | 2 --
2 files changed, 41 insertions(+), 40 deletions(-)
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index d69bf53bef21..831bb21dcb4f 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -203,31 +203,6 @@ void ext4_fc_init_inode(struct inode *inode)
init_waitqueue_head(&ei->i_fc_wait);
}
-/* This function must be called with sbi->s_fc_lock held. */
-static void ext4_fc_wait_committing_inode(struct inode *inode)
-__releases(&EXT4_SB(inode->i_sb)->s_fc_lock)
-{
- wait_queue_head_t *wq;
- struct ext4_inode_info *ei = EXT4_I(inode);
-
-#if (BITS_PER_LONG < 64)
- DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_state_flags,
- EXT4_STATE_FC_COMMITTING);
-#else
- DEFINE_WAIT_BIT(wait, &ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
- wq = bit_waitqueue(&ei->i_flags,
- EXT4_STATE_FC_COMMITTING);
-#endif
- lockdep_assert_held(&EXT4_SB(inode->i_sb)->s_fc_lock);
- prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
- spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
- schedule();
- finish_wait(wq, &wait.wq_entry);
-}
-
/*
* Remove inode from fast commit list. If the inode is being committed
* we wait until inode commit is done.
@@ -242,20 +217,30 @@ void ext4_fc_del(struct inode *inode)
(EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
return;
-restart:
spin_lock(&EXT4_SB(inode->i_sb)->s_fc_lock);
if (list_empty(&ei->i_fc_list) && list_empty(&ei->i_fc_dilist)) {
spin_unlock(&EXT4_SB(inode->i_sb)->s_fc_lock);
return;
}
- if (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
- ext4_fc_wait_committing_inode(inode);
- goto restart;
- }
-
- if (!list_empty(&ei->i_fc_list))
- list_del_init(&ei->i_fc_list);
+ /*
+ * Since ext4_fc_del is called from ext4_evict_inode while having a
+ * handle open, there is no need for us to wait here even if a fast
+ * commit is going on. That is because, if this inode is being
+ * committed, ext4_mark_inode_dirty would have waited for inode commit
+ * operation to finish before we come here. So, by the time we come
+ * here, inode's EXT4_STATE_FC_COMMITTING would have been cleared. So,
+ * we shouldn't see EXT4_STATE_FC_COMMITTING to be set on this inode
+ * here.
+ *
+ * We may come here without any handles open in the "no_delete" case of
+ * ext4_evict_inode as well. However, if that happens, we first mark the
+ * file system as fast commit ineligible anyway. So, even in that case,
+ * it is okay to remove the inode from the fc list.
+ */
+ WARN_ON(ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)
+ && !ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE));
+ list_del_init(&ei->i_fc_list);
/*
* Since this inode is getting removed, let's also remove all FC
@@ -278,8 +263,6 @@ void ext4_fc_del(struct inode *inode)
fc_dentry->fcd_name.len > DNAME_INLINE_LEN)
kfree(fc_dentry->fcd_name.name);
kmem_cache_free(ext4_fc_dentry_cachep, fc_dentry);
-
- return;
}
/*
@@ -926,8 +909,6 @@ static int ext4_fc_submit_inode_data_all(journal_t *journal)
spin_lock(&sbi->s_fc_lock);
list_for_each_entry(ei, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
- ext4_set_inode_state(&ei->vfs_inode, EXT4_STATE_FC_COMMITTING);
-
spin_unlock(&sbi->s_fc_lock);
ret = jbd2_submit_inode_data(ei->jinode);
if (ret)
@@ -1044,6 +1025,18 @@ static int ext4_fc_perform_commit(journal_t *journal)
int ret = 0;
u32 crc = 0;
+ /* Lock the journal */
+ jbd2_journal_lock_updates(journal);
+ spin_lock(&sbi->s_fc_lock);
+ list_for_each_entry(iter, &sbi->s_fc_q[FC_Q_MAIN], i_fc_list) {
+ spin_lock(&iter->i_fc_lock);
+ ext4_set_inode_state(&iter->vfs_inode,
+ EXT4_STATE_FC_COMMITTING);
+ spin_unlock(&iter->i_fc_lock);
+ }
+ spin_unlock(&sbi->s_fc_lock);
+ jbd2_journal_unlock_updates(journal);
+
ret = ext4_fc_submit_inode_data_all(journal);
if (ret)
return ret;
@@ -1094,6 +1087,14 @@ static int ext4_fc_perform_commit(journal_t *journal)
ret = ext4_fc_write_inode(inode, &crc);
if (ret)
goto out;
+ spin_lock(&iter->i_fc_lock);
+ ext4_clear_inode_state(inode, EXT4_STATE_FC_COMMITTING);
+ spin_unlock(&iter->i_fc_lock);
+#if (BITS_PER_LONG < 64)
+ wake_up_bit(&iter->i_state_flags, EXT4_STATE_FC_COMMITTING);
+#else
+ wake_up_bit(&iter->i_flags, EXT4_STATE_FC_COMMITTING);
+#endif
spin_lock(&sbi->s_fc_lock);
}
spin_unlock(&sbi->s_fc_lock);
@@ -1227,13 +1228,15 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
spin_lock(&sbi->s_fc_lock);
list_for_each_entry_safe(iter, iter_n, &sbi->s_fc_q[FC_Q_MAIN],
i_fc_list) {
- list_del_init(&iter->i_fc_list);
+ spin_lock(&iter->i_fc_lock);
ext4_clear_inode_state(&iter->vfs_inode,
EXT4_STATE_FC_COMMITTING);
+ spin_unlock(&iter->i_fc_lock);
if (iter->i_sync_tid <= tid)
ext4_fc_reset_inode(&iter->vfs_inode);
/* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
smp_mb();
+ list_del_init(&iter->i_fc_list);
#if (BITS_PER_LONG < 64)
wake_up_bit(&iter->i_state_flags, EXT4_STATE_FC_COMMITTING);
#else
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index c2cf74b01ddb..06b885628b1c 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -757,7 +757,6 @@ int jbd2_fc_begin_commit(journal_t *journal, tid_t tid)
}
journal->j_flags |= JBD2_FAST_COMMIT_ONGOING;
write_unlock(&journal->j_state_lock);
- jbd2_journal_lock_updates(journal);
return 0;
}
@@ -769,7 +768,6 @@ EXPORT_SYMBOL(jbd2_fc_begin_commit);
*/
static int __jbd2_fc_end_commit(journal_t *journal, tid_t tid, bool fallback)
{
- jbd2_journal_unlock_updates(journal);
if (journal->j_fc_cleanup_callback)
journal->j_fc_cleanup_callback(journal, 0, tid);
write_lock(&journal->j_state_lock);
--
2.35.1.616.g0bdcbb4464-goog
From: Harshad Shirwadkar <[email protected]>
If the inode that's being requested to track using ext4_fc_track_inode
is being committed, then wait until the inode finishes the commit.
Signed-off-by: Harshad Shirwadkar <[email protected]>
---
fs/ext4/ext4_jbd2.c | 12 ++++++++++++
fs/ext4/ext4_jbd2.h | 13 ++++---------
fs/ext4/fast_commit.c | 33 +++++++++++++++++++++++++++++++++
fs/ext4/inode.c | 3 ++-
4 files changed, 51 insertions(+), 10 deletions(-)
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index 3477a16d08ae..7fa301b0a35a 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -106,6 +106,18 @@ handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
GFP_NOFS, type, line);
}
+handle_t *__ext4_journal_start(struct inode *inode, unsigned int line,
+ int type, int blocks, int rsv_blocks,
+ int revoke_creds)
+{
+ handle_t *handle = __ext4_journal_start_sb(inode->i_sb, line,
+ type, blocks, rsv_blocks,
+ revoke_creds);
+ if (ext4_handle_valid(handle) && !IS_ERR(handle))
+ ext4_fc_track_inode(handle, inode);
+ return handle;
+}
+
int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle)
{
struct super_block *sb;
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index db2ae4a2b38d..e408622fe896 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -302,6 +302,10 @@ static inline int ext4_trans_default_revoke_credits(struct super_block *sb)
return ext4_free_metadata_revoke_credits(sb, 8);
}
+handle_t *__ext4_journal_start(struct inode *inode, unsigned int line,
+ int type, int blocks, int rsv_blocks,
+ int revoke_creds);
+
#define ext4_journal_start_sb(sb, type, nblocks) \
__ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0, \
ext4_trans_default_revoke_credits(sb))
@@ -318,15 +322,6 @@ static inline int ext4_trans_default_revoke_credits(struct super_block *sb)
__ext4_journal_start((inode), __LINE__, (type), (blocks), 0, \
(revoke_creds))
-static inline handle_t *__ext4_journal_start(struct inode *inode,
- unsigned int line, int type,
- int blocks, int rsv_blocks,
- int revoke_creds)
-{
- return __ext4_journal_start_sb(inode->i_sb, line, type, blocks,
- rsv_blocks, revoke_creds);
-}
-
#define ext4_journal_stop(handle) \
__ext4_journal_stop(__func__, __LINE__, (handle))
diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
index a589fc415dbe..d69bf53bef21 100644
--- a/fs/ext4/fast_commit.c
+++ b/fs/ext4/fast_commit.c
@@ -506,8 +506,14 @@ static int __track_inode(struct inode *inode, void *arg, bool update)
return 0;
}
+/*
+ * Track inode as part of the next fast commit. If the inode is being
+ * committed, this function will wait for the commit to finish.
+ */
void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+ wait_queue_head_t *wq;
int ret;
if (S_ISDIR(inode->i_mode))
@@ -519,6 +525,33 @@ void ext4_fc_track_inode(handle_t *handle, struct inode *inode)
return;
}
+ if (!test_opt2(inode->i_sb, JOURNAL_FAST_COMMIT) ||
+ (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY))
+ return;
+
+ spin_lock(&ei->i_fc_lock);
+ while (ext4_test_inode_state(inode, EXT4_STATE_FC_COMMITTING)) {
+#if (BITS_PER_LONG < 64)
+ DEFINE_WAIT_BIT(wait, &ei->i_state_flags,
+ EXT4_STATE_FC_COMMITTING);
+ wq = bit_waitqueue(&ei->i_state_flags,
+ EXT4_STATE_FC_COMMITTING);
+#else
+ DEFINE_WAIT_BIT(wait, &ei->i_flags,
+ EXT4_STATE_FC_COMMITTING);
+ wq = bit_waitqueue(&ei->i_flags,
+ EXT4_STATE_FC_COMMITTING);
+#endif
+
+ prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+ spin_unlock(&ei->i_fc_lock);
+
+ schedule();
+ finish_wait(wq, &wait.wq_entry);
+ spin_lock(&ei->i_fc_lock);
+ }
+ spin_unlock(&ei->i_fc_lock);
+
ret = ext4_fc_track_template(handle, inode, __track_inode, NULL, 1);
trace_ext4_fc_track_inode(inode, ret);
}
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 531a94f48637..7a01f5bd377c 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -629,6 +629,7 @@ int ext4_map_blocks(handle_t *handle, struct inode *inode,
* with create == 1 flag.
*/
down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_fc_track_inode(handle, inode);
/*
* We need to check for EXT4 here because migrate
@@ -5690,7 +5691,6 @@ int ext4_mark_iloc_dirty(handle_t *handle,
put_bh(iloc->bh);
return -EIO;
}
- ext4_fc_track_inode(handle, inode);
if (IS_I_VERSION(inode))
inode_inc_iversion(inode);
@@ -5727,6 +5727,7 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
brelse(iloc->bh);
iloc->bh = NULL;
}
+ ext4_fc_track_inode(handle, inode);
}
ext4_std_error(inode->i_sb, err);
return err;
--
2.35.1.616.g0bdcbb4464-goog