diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index e0f071f6b5a7..63d197724519 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -86,6 +86,20 @@ btrfs_work_owner(struct btrfs_work *work)
 	return work->wq->fs_info;
 }
 
+bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq)
+{
+	/*
+	 * We could compare wq->normal->pending with num_online_cpus()
+	 * to support "thresh == NO_THRESHOLD" case, but it requires
+	 * moving up atomic_inc/dec in thresh_queue/exec_hook. Let's
+	 * postpone it until someone needs the support of that case.
+	 */
+	if (wq->normal->thresh == NO_THRESHOLD)
+		return false;
+
+	return atomic_read(&wq->normal->pending) > wq->normal->thresh * 2;
+}
+
 BTRFS_WORK_HELPER(worker_helper);
 BTRFS_WORK_HELPER(delalloc_helper);
 BTRFS_WORK_HELPER(flush_delalloc_helper);
diff --git a/fs/btrfs/async-thread.h b/fs/btrfs/async-thread.h
index 8e52484cd461..1f9597355c9d 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -84,4 +84,5 @@ void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
 void btrfs_set_work_high_priority(struct btrfs_work *work);
 struct btrfs_fs_info *btrfs_work_owner(struct btrfs_work *work);
 struct btrfs_fs_info *btrfs_workqueue_owner(struct __btrfs_workqueue *wq);
+bool btrfs_workqueue_normal_congested(struct btrfs_workqueue *wq);
 #endif
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index be007c1b5592..80982a83c9fd 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1353,7 +1353,8 @@ release_path:
 	total_done++;
 
 	btrfs_release_prepared_delayed_node(delayed_node);
-	if (async_work->nr == 0 || total_done < async_work->nr)
+	if ((async_work->nr == 0 && total_done < BTRFS_DELAYED_WRITEBACK) ||
+	    total_done < async_work->nr)
 		goto again;
 
 free_path:
@@ -1369,7 +1370,8 @@ static int btrfs_wq_run_delayed_node(struct btrfs_delayed_root *delayed_root,
 {
 	struct btrfs_async_delayed_work *async_work;
 
-	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND)
+	if (atomic_read(&delayed_root->items) < BTRFS_DELAYED_BACKGROUND ||
+	    btrfs_workqueue_normal_congested(fs_info->delayed_workers))
 		return 0;
 
 	async_work = kmalloc(sizeof(*async_work), GFP_NOFS);