diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 3ba140468f12635b096a92a5fa22a26306e5eaf7..e22fba272e4fdfbe0f93856cb2852c120e6516cb 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -135,6 +135,11 @@ struct btrfs_delayed_data_ref {
 	u64 offset;
 };
 
+enum btrfs_delayed_ref_flags {
+	/* Indicate that we are flushing delayed refs for the commit */
+	BTRFS_DELAYED_REFS_FLUSHING,
+};
+
 struct btrfs_delayed_ref_root {
 	/* head ref rbtree */
 	struct rb_root_cached href_root;
@@ -158,12 +163,7 @@ struct btrfs_delayed_ref_root {
 
 	u64 pending_csums;
 
-	/*
-	 * set when the tree is flushing before a transaction commit,
-	 * used by the throttling code to decide if new updates need
-	 * to be run right away
-	 */
-	int flushing;
+	unsigned long flags;
 
 	u64 run_delayed_start;
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 3bcb5444536ee2871682d9590a35e297aa479db5..1485f7722f479de4ab14354ab2742db25338c154 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -909,9 +909,8 @@ bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
 {
 	struct btrfs_transaction *cur_trans = trans->transaction;
 
-	smp_mb();
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START ||
-	    cur_trans->delayed_refs.flushing)
+	    test_bit(BTRFS_DELAYED_REFS_FLUSHING, &cur_trans->delayed_refs.flags))
 		return true;
 
 	return should_end_transaction(trans);
@@ -2043,23 +2042,22 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	btrfs_trans_release_metadata(trans);
 	trans->block_rsv = NULL;
 
-	/* make a pass through all the delayed refs we have so far
-	 * any runnings procs may add more while we are here
-	 */
-	ret = btrfs_run_delayed_refs(trans, 0);
-	if (ret) {
-		btrfs_end_transaction(trans);
-		return ret;
-	}
-
-	cur_trans = trans->transaction;
-
 	/*
-	 * set the flushing flag so procs in this transaction have to
-	 * start sending their work down.
+	 * We only want one transaction commit doing the flushing so we do not
+	 * waste a bunch of time on lock contention on the extent root node.
 	 */
-	cur_trans->delayed_refs.flushing = 1;
-	smp_wmb();
+	if (!test_and_set_bit(BTRFS_DELAYED_REFS_FLUSHING,
+			      &cur_trans->delayed_refs.flags)) {
+		/*
+		 * Make a pass through all the delayed refs we have so far.
+		 * Any running threads may add more while we are here.
+		 */
+		ret = btrfs_run_delayed_refs(trans, 0);
+		if (ret) {
+			btrfs_end_transaction(trans);
+			return ret;
+		}
+	}
 
 	btrfs_create_pending_block_groups(trans);