@@ -509,8 +509,24 @@ void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
&ordered->flags));
- if (list_empty(&ordered->trans_list))
- list_add_tail(&ordered->trans_list, &trans->ordered);
+ /*
+ * If our ordered extent completed it means it updated the
+ * fs/subvol and csum trees already, so no need to make the
+ * current transaction's commit wait for it, as we end up
+ * holding memory unnecessarily and delaying the inode's iput
+ * until the transaction commit (we schedule an iput for the
+ * inode when the ordered extent's refcount drops to 0), which
+ * prevents it from being evictable until the transaction
+ * commits.
+ */
+ if (list_empty(&ordered->trans_list)) {
+ if (test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags))
+ btrfs_put_ordered_extent(ordered);
+ else
+ list_add_tail(&ordered->trans_list,
+ &trans->ordered);
+ }
+
spin_lock_irq(&log->log_extents_lock[index]);
}
spin_unlock_irq(&log->log_extents_lock[index]);
We don't need to attach ordered extents that have completed to the current transaction. Doing so only makes us hold memory for longer than necessary and delaying the iput of the inode until the transaction is committed (for each created ordered extent we do an igrab and then schedule an asynchronous iput when the ordered extent's reference count drops to 0), preventing the inode from being evictable until the transaction commits. Signed-off-by: Filipe Manana <fdmanana@suse.com> --- This applies on top of my previous patch titled: "Btrfs: fix data loss after concurrent fsyncs for files in the same subvol" fs/btrfs/ordered-data.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-)