diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index 9aba42b..a09264d 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -70,6 +70,20 @@
 	normal_work_helper(work);					\
 }
 
+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 ad4d064..8e1d657 100644
--- a/fs/btrfs/async-thread.h
+++ b/fs/btrfs/async-thread.h
@@ -80,4 +80,5 @@
 void btrfs_destroy_workqueue(struct btrfs_workqueue *wq);
 void btrfs_workqueue_set_max(struct btrfs_workqueue *wq, int max);
 void btrfs_set_work_high_priority(struct btrfs_work *work);
+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 02b934d..09fa5af 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1375,7 +1375,8 @@
 	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:
@@ -1391,7 +1392,8 @@
 {
 	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);