btrfs: avoid long stall when dropping a non-shared large subvolume

Commit 011b46c30476 ("btrfs: skip subtree scan if it's too high to avoid
low stall in btrfs_commit_transaction()") introduced a mechanism to skip
large subtree during snapshot dropping.

But even for a subvolume without any shared tree blocks, we can still
queue quite a lot of qgroup records into one transaction, and cause a
long qgroup related stall.

So also add a check against the subvolume root level, to determine if we
need to mark qgroup inconsistent.

Reviewed-by: Boris Burkov <boris@bur.io>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

3 files changed, 29 insertions, 0 deletions

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index d6a4390ee34a..a0d5ab03aae2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6315,6 +6315,16 @@ int btrfs_drop_snapshot(struct btrfs_root *root, bool update_ref, bool for_reloc
 	set_bit(BTRFS_ROOT_DELETING, &root->state);
 	unfinished_drop = test_bit(BTRFS_ROOT_UNFINISHED_DROP, &root->state);
 
+	/*
+	 * For subvolume dropping, check if the subvolume is large enough so
+	 * that we need to mark qgroup inconsistent to avoid long qgroup stall.
+	 *
+	 * Even for a subvolume without any snapshot, there can still be
+	 * a lot of qgroup records queued into one transaction.
+	 */
+	if (!for_reloc)
+		btrfs_qgroup_check_tree_drop(fs_info, rootid,
+					     btrfs_header_level(root->node));
 	if (btrfs_disk_key_objectid(&root_item->drop_progress) == 0) {
 		level = btrfs_header_level(root->node);
 		path->nodes[level] = btrfs_lock_root_node(root);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e01b31aa0b1b..05e35eb126dc 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2748,6 +2748,24 @@ walk_down:
 	return 0;
 }
 
+void btrfs_qgroup_check_tree_drop(struct btrfs_fs_info *fs_info, u64 rootid, u8 level)
+{
+	u8 drop_subtree_thres;
+
+	if (btrfs_qgroup_mode(fs_info) != BTRFS_QGROUP_MODE_FULL)
+		return;
+
+	if (!btrfs_is_fstree(rootid))
+		return;
+
+	spin_lock(&fs_info->qgroup_lock);
+	drop_subtree_thres = fs_info->qgroup_drop_subtree_thres;
+	spin_unlock(&fs_info->qgroup_lock);
+
+	if (level >= drop_subtree_thres)
+		qgroup_mark_inconsistent(fs_info, "subtree level reached threshold");
+}
+
 static void qgroup_iterator_nested_add(struct list_head *head, struct btrfs_qgroup *qgroup)
 {
 	if (!list_empty(&qgroup->nested_iterator))
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 090ba5367872..c64b26b09c22 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -376,6 +376,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level);
+void btrfs_qgroup_check_tree_drop(struct btrfs_fs_info *fs_info, u64 rootid, u8 level);
 int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 				u64 num_bytes, struct ulist *old_roots,
 				struct ulist *new_roots);