diff mbox series

[1/5] btrfs: use inode_logged() at need_log_inode()

Message ID 29350541f39b3bac1636b8e9772c7303923813eb.1684320689.git.fdmanana@suse.com (mailing list archive)
State New, archived
Headers show
Series btrfs: some minor log tree updates | expand

Commit Message

Filipe Manana May 17, 2023, 11:02 a.m. UTC
From: Filipe Manana <fdmanana@suse.com>

At need_log_inode() we directly check the ->logged_trans field of the
given inode to check if it was previously logged in the transaction, with
the goal of skipping logging the inode again when it's not necessary.
The ->logged_trans field in not persisted in the inode item or elsewhere,
it's only stored in memory (struct btrfs_inode), so it's transient and
lost once the inode is evicted and then loaded again. Once an inode is
loaded, we are conservative and set ->logged_trans to 0, which may mean
that either the inode was never logged in the current transaction or it
was logged but evicted before being loaded again.

Instead of checking the inode's ->logged_trans field directly, we can
use instead the helper inode_logged(), which will really check if the
inode was logged before in the current transaction in case we have a
->logged_trans field with a value of 0. This will prevent unnecessarily
logging an inode when it's not needed, and in some cases preventing a
transaction commit, in case the logging requires a fallback to a
transaction commit. The following test script shows a scenario where
due to eviction we fallback a transaction commit when trying to fsync
a file that was renamed:

  $ cat test.sh
  #!/bin/bash

  DEV=/dev/nullb0
  MNT=/mnt/nullb0

  num_init_files=10000
  num_new_files=10000

  mkfs.btrfs -f $DEV
  mount -o ssd $DEV $MNT

  mkdir $MNT/testdir
  for ((i = 1; i <= $num_init_files; i++)); do
      echo -n > $MNT/testdir/file_$i
  done

  echo -n > $MNT/testdir/foo

  sync

  # Add some files so that there's more work in the transaction other
  # than just renaming file foo.
  for ((i = 1; i <= $num_new_files; i++)); do
      echo -n > $MNT/testdir/new_file_$i
  done

  # Fsync the directory first.
  xfs_io -c "fsync" $MNT/testdir

  # Rename file foo.
  mv $MNT/testdir/foo $MNT/testdir/bar

  # Now triggger eviction of the test directory's inode.
  # Once loaded again, it will have logged_trans set to 0 and
  # last_unlink_trans set to the current transaction.
  echo 2 > /proc/sys/vm/drop_caches

  # Fsync file bar (ex-foo).
  # Before the patch the fsync would result in a transaction commit
  # because the inode for file bar has last_unlink_trans set to the
  # current transaction, so it will attempt to log the parent directory
  # as well, which will fallback to a full transaction commit because
  # it also has its last_unlink_trans set to the current transaction,
  # due to the inode eviction.
  start=$(date +%s%N)
  xfs_io -c "fsync" $MNT/testdir/bar
  end=$(date +%s%N)
  dur=$(( (end - start) / 1000000 ))

  echo "file fsync took: $dur milliseconds"

  umount $MNT

Before this patch:  fsync took 22 milliseconds
After this patch:   fsync took  8 milliseconds

Signed-off-by: Filipe Manana <fdmanana@suse.com>
---
 fs/btrfs/tree-log.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9b212e8c70cc..ccdfe1d95572 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3252,7 +3252,7 @@  int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
  * Returns 1 if the inode was logged before in the transaction, 0 if it was not,
  * and < 0 on error.
  */
-static int inode_logged(struct btrfs_trans_handle *trans,
+static int inode_logged(const struct btrfs_trans_handle *trans,
 			struct btrfs_inode *inode,
 			struct btrfs_path *path_in)
 {
@@ -5303,7 +5303,7 @@  static int btrfs_check_ref_name_override(struct extent_buffer *eb,
  * multiple times when multiple tasks have joined the same log transaction.
  */
 static bool need_log_inode(const struct btrfs_trans_handle *trans,
-			   const struct btrfs_inode *inode)
+			   struct btrfs_inode *inode)
 {
 	/*
 	 * If a directory was not modified, no dentries added or removed, we can
@@ -5321,7 +5321,7 @@  static bool need_log_inode(const struct btrfs_trans_handle *trans,
 	 * logged_trans will be 0, in which case we have to fully log it since
 	 * logged_trans is a transient field, not persisted.
 	 */
-	if (inode->logged_trans == trans->transid &&
+	if (inode_logged(trans, inode, NULL) == 1 &&
 	    !test_bit(BTRFS_INODE_COPY_EVERYTHING, &inode->runtime_flags))
 		return false;