Btrfs: fix transaction throttling for delayed refs

Dave has this fs_mark script that can make btrfs abort with sufficient amount of
ram.  This is because with more ram we can keep more dirty metadata in cache
which in a round about way makes for many more pending delayed refs.  What
happens is we end up not throttling the transaction enough so when we go to
commit the transaction when we've completely filled the file system we'll
abort() because we use all of the space in the global reserve and we still have
delayed refs to run.  To fix this we need to make the delayed ref flushing and
the transaction throttling dependant upon the number of delayed refs that we
have instead of how much reserved space is left in the global reserve.  With
this patch we not only stop aborting transactions but we also get a smoother run
speed with fs_mark and it makes us about 10% faster.  Thanks,

Reported-by: David Sterba <dsterba@suse.cz>
Signed-off-by: Josef Bacik <jbacik@fusionio.com>

1 files changed, 10 insertions, 14 deletions

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index c11b7ef..c916ebd 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -615,10 +615,11 @@ void btrfs_throttle(struct btrfs_root *root)
 static int should_end_transaction(struct btrfs_trans_handle *trans,
 				  struct btrfs_root *root)
 {
-	int ret;
+	if (root->fs_info->global_block_rsv.space_info->full &&
+	    btrfs_should_throttle_delayed_refs(trans, root))
+		return 1;
 
-	ret = btrfs_block_rsv_check(root, &root->fs_info->global_block_rsv, 5);
-	return ret ? 1 : 0;
+	return !!btrfs_block_rsv_check(root, &root->fs_info->global_block_rsv, 5);
 }
 
 int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
@@ -649,7 +650,7 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 	struct btrfs_fs_info *info = root->fs_info;
-	int count = 0;
+	unsigned long cur = trans->delayed_ref_updates;
 	int lock = (trans->type != TRANS_JOIN_NOLOCK);
 	int err = 0;
 
@@ -678,17 +679,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 	if (!list_empty(&trans->new_bgs))
 		btrfs_create_pending_block_groups(trans, root);
 
-	while (count < 1) {
-		unsigned long cur = trans->delayed_ref_updates;
+	trans->delayed_ref_updates = 0;
+	if (btrfs_should_throttle_delayed_refs(trans, root)) {
+		cur = max_t(unsigned long, cur, 1);
 		trans->delayed_ref_updates = 0;
-		if (cur &&
-		    trans->transaction->delayed_refs.num_heads_ready > 64) {
-			trans->delayed_ref_updates = 0;
-			btrfs_run_delayed_refs(trans, root, cur);
-		} else {
-			break;
-		}
-		count++;
+		btrfs_run_delayed_refs(trans, root, cur);
 	}
 
 	btrfs_trans_release_metadata(trans, root);
@@ -1626,6 +1621,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	 * start sending their work down.
 	 */
 	cur_trans->delayed_refs.flushing = 1;
+	smp_wmb();
 
 	if (!list_empty(&trans->new_bgs))
 		btrfs_create_pending_block_groups(trans, root);