Btrfs: Metadata reservation for orphan inodes

diff -urp 2/fs/btrfs/btrfs_inode.h 3/fs/btrfs/btrfs_inode.h
@@ -151,6 +151,7 @@ struct btrfs_inode {
 	 * of these.
 	 */
 	unsigned ordered_data_close:1;
+	unsigned orphan_meta_reserved:1;
 	unsigned dummy_inode:1;
 
 	/*

diff -urp 2/fs/btrfs/ctree.h 3/fs/btrfs/ctree.h
@@ -1068,7 +1068,6 @@ struct btrfs_root {
 	int ref_cows;
 	int track_dirty;
 	int in_radix;
-	int clean_orphans;
 
 	u64 defrag_trans_start;
 	struct btrfs_key defrag_progress;

@@ -1082,8 +1081,11 @@ struct btrfs_root {
 
 	struct list_head root_list;
 
-	spinlock_t list_lock;
+	spinlock_t orphan_lock;
 	struct list_head orphan_list;
+	struct btrfs_block_rsv *orphan_block_rsv;
+	int orphan_item_inserted;
+	int orphan_cleanup_state;
 
 	spinlock_t inode_lock;
 	/* red-black tree that keeps track of in-memory inodes */

@@ -2079,6 +2081,9 @@ int btrfs_trans_reserve_metadata(struct 
 				int num_items, int *retries);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root);
+int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
+				  struct inode *inode);
+void btrfs_orphan_release_metadata(struct inode *inode);
 int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_pending_snapshot *pending);
 int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);

@@ -2403,6 +2408,13 @@ int btrfs_update_inode(struct btrfs_tran
 int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);
 int btrfs_orphan_del(struct btrfs_trans_handle *trans, struct inode *inode);
 void btrfs_orphan_cleanup(struct btrfs_root *root);
+void btrfs_orphan_pre_snapshot(struct btrfs_trans_handle *trans,
+				struct btrfs_pending_snapshot *pending,
+				u64 *bytes_to_reserve);
+void btrfs_orphan_post_snapshot(struct btrfs_trans_handle *trans,
+				struct btrfs_pending_snapshot *pending);
+void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
+			      struct btrfs_root *root);
 int btrfs_cont_expand(struct inode *inode, loff_t size);
 int btrfs_invalidate_inodes(struct btrfs_root *root);
 void btrfs_add_delayed_iput(struct inode *inode);

diff -urp 2/fs/btrfs/disk-io.c 3/fs/btrfs/disk-io.c
@@ -895,7 +895,8 @@ static int __setup_root(u32 nodesize, u3
 	root->ref_cows = 0;
 	root->track_dirty = 0;
 	root->in_radix = 0;
-	root->clean_orphans = 0;
+	root->orphan_item_inserted = 0;
+	root->orphan_cleanup_state = 0;
 
 	root->fs_info = fs_info;
 	root->objectid = objectid;

@@ -905,12 +906,13 @@ static int __setup_root(u32 nodesize, u3
 	root->in_sysfs = 0;
 	root->inode_tree = RB_ROOT;
 	root->block_rsv = NULL;
+	root->orphan_block_rsv = NULL;
 
 	INIT_LIST_HEAD(&root->dirty_list);
 	INIT_LIST_HEAD(&root->orphan_list);
 	INIT_LIST_HEAD(&root->root_list);
 	spin_lock_init(&root->node_lock);
-	spin_lock_init(&root->list_lock);
+	spin_lock_init(&root->orphan_lock);
 	spin_lock_init(&root->inode_lock);
 	spin_lock_init(&root->accounting_lock);
 	mutex_init(&root->objectid_mutex);

@@ -1194,19 +1196,23 @@ again:
 	if (root)
 		return root;
 
-	ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
-	if (ret == 0)
-		ret = -ENOENT;
-	if (ret < 0)
-		return ERR_PTR(ret);
-
 	root = btrfs_read_fs_root_no_radix(fs_info->tree_root, location);
 	if (IS_ERR(root))
 		return root;
 
-	WARN_ON(btrfs_root_refs(&root->root_item) == 0);
 	set_anon_super(&root->anon_super, NULL);
 
+	if (btrfs_root_refs(&root->root_item) == 0) {
+		ret = -ENOENT;
+		goto fail;
+	}
+
+	ret = btrfs_find_orphan_item(fs_info->tree_root, location->objectid);
+	if (ret < 0)
+		goto fail;
+	if (ret == 0)
+		root->orphan_item_inserted = 1;
+
 	ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
 	if (ret)
 		goto fail;

@@ -1215,10 +1221,9 @@ again:
 	ret = radix_tree_insert(&fs_info->fs_roots_radix,
 				(unsigned long)root->root_key.objectid,
 				root);
-	if (ret == 0) {
+	if (ret == 0)
 		root->in_radix = 1;
-		root->clean_orphans = 1;
-	}
+
 	spin_unlock(&fs_info->fs_roots_radix_lock);
 	radix_tree_preload_end();
 	if (ret) {

@@ -1989,6 +1994,9 @@ struct btrfs_root *open_ctree(struct sup
 	BUG_ON(ret);
 
 	if (!(sb->s_flags & MS_RDONLY)) {
+		ret = btrfs_cleanup_fs_roots(fs_info);
+		BUG_ON(ret);
+
 		ret = btrfs_recover_relocation(tree_root);
 		if (ret < 0) {
 			printk(KERN_WARNING

diff -urp 2/fs/btrfs/extent-tree.c 3/fs/btrfs/extent-tree.c
@@ -3625,6 +3625,34 @@ void btrfs_trans_release_metadata(struct
 	trans->bytes_reserved = 0;
 }
 
+int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
+				  struct inode *inode)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_block_rsv *src_rsv = get_block_rsv(trans, root);
+	struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
+
+	/*
+	 * one for deleting orphan item, one for updating inode and
+	 * two for calling btrfs_truncate_inode_items.
+	 *
+	 * btrfs_truncate_inode_items is a delete operation, it frees
+	 * more space than it uses in most cases. So two units of
+	 * metadata space should be enough for calling it many times.
+	 * If all of the metadata space is used, we can commit
+	 * transaction and use space it freed.
+	 */
+	u64 num_bytes = calc_trans_metadata_size(root, 4);
+	return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
+}
+
+void btrfs_orphan_release_metadata(struct inode *inode)
+{
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	u64 num_bytes = calc_trans_metadata_size(root, 4);
+	btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
+}
+
 int btrfs_snap_reserve_metadata(struct btrfs_trans_handle *trans,
 				struct btrfs_pending_snapshot *pending)
 {

431 lines not on this page · raw message

diff -urp 2/fs/btrfs/ioctl.c 3/fs/btrfs/ioctl.c
@@ -1296,10 +1296,12 @@ static noinline int btrfs_ioctl_snap_des
 	dest->root_item.drop_level = 0;
 	btrfs_set_root_refs(&dest->root_item, 0);
 
-	ret = btrfs_insert_orphan_item(trans,
-				root->fs_info->tree_root,
-				dest->root_key.objectid);
-	BUG_ON(ret);
+	if (!xchg(&dest->orphan_item_inserted, 1)) {
+		ret = btrfs_insert_orphan_item(trans,
+					root->fs_info->tree_root,
+					dest->root_key.objectid);
+		BUG_ON(ret);
+	}
 
 	ret = btrfs_commit_transaction(trans, root);
 	BUG_ON(ret);

diff -urp 2/fs/btrfs/root-tree.c 3/fs/btrfs/root-tree.c
@@ -259,6 +259,8 @@ int btrfs_find_orphan_roots(struct btrfs
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
 	struct btrfs_key key;
+	struct btrfs_key root_key;
+	struct btrfs_root *root;
 	int err = 0;
 	int ret;
 

@@ -270,6 +272,9 @@ int btrfs_find_orphan_roots(struct btrfs
 	key.type = BTRFS_ORPHAN_ITEM_KEY;
 	key.offset = 0;
 
+	root_key.type = BTRFS_ROOT_ITEM_KEY;
+	root_key.offset = (u64)-1;
+
 	while (1) {
 		ret = btrfs_search_slot(NULL, tree_root, &key, path, 0, 0);
 		if (ret < 0) {

@@ -294,13 +299,25 @@ int btrfs_find_orphan_roots(struct btrfs
 		    key.type != BTRFS_ORPHAN_ITEM_KEY)
 			break;
 
-		ret = btrfs_find_dead_roots(tree_root, key.offset);
-		if (ret) {
+		root_key.objectid = key.offset;
+		key.offset++;
+
+		root = btrfs_read_fs_root_no_name(tree_root->fs_info,
+						  &root_key);
+		if (!IS_ERR(root))
+			continue;
+
+		ret = PTR_ERR(root);
+		if (ret != -ENOENT) {
 			err = ret;
 			break;
 		}
 
-		key.offset++;
+		ret = btrfs_find_dead_roots(tree_root, root_key.objectid);
+		if (ret) {
+			err = ret;
+			break;
+		}
 	}
 
 	btrfs_free_path(path);

diff -urp 2/fs/btrfs/super.c 3/fs/btrfs/super.c
@@ -693,11 +693,11 @@ static int btrfs_remount(struct super_bl
 		if (btrfs_super_log_root(&root->fs_info->super_copy) != 0)
 			return -EINVAL;
 
-		/* recover relocation */
-		ret = btrfs_recover_relocation(root);
+		ret = btrfs_cleanup_fs_roots(root->fs_info);
 		WARN_ON(ret);
 
-		ret = btrfs_cleanup_fs_roots(root->fs_info);
+		/* recover relocation */
+		ret = btrfs_recover_relocation(root);
 		WARN_ON(ret);
 
 		sb->s_flags &= ~MS_RDONLY;

diff -urp 2/fs/btrfs/transaction.c 3/fs/btrfs/transaction.c
@@ -675,6 +675,7 @@ static noinline int commit_fs_roots(stru
 
 			btrfs_free_log(trans, root);
 			btrfs_update_reloc_root(trans, root);
+			btrfs_orphan_commit_root(trans, root);
 
 			if (root->commit_root != root->node) {
 				switch_commit_root(root);

@@ -834,6 +835,8 @@ static noinline int create_pending_snaps
 	struct extent_buffer *tmp;
 	struct extent_buffer *old;
 	int ret;
+	int retries = 0;
+	u64 to_reserve = 0;
 	u64 index = 0;
 	u64 objectid;
 

@@ -849,6 +852,17 @@ static noinline int create_pending_snaps
 		goto fail;
 	}
 
+	btrfs_orphan_pre_snapshot(trans, pending, &to_reserve);
+
+	if (to_reserve > 0) {
+		ret = btrfs_block_rsv_add(trans, root, &pending->block_rsv,
+					  to_reserve, &retries);
+		if (ret) {
+			pending->error = ret;
+			goto fail;
+		}
+	}
+
 	key.objectid = objectid;
 	key.offset = (u64)-1;
 	key.type = BTRFS_ROOT_ITEM_KEY;

@@ -908,6 +922,8 @@ static noinline int create_pending_snaps
 	key.offset = (u64)-1;
 	pending->snap = btrfs_read_fs_root_no_name(root->fs_info, &key);
 	BUG_ON(IS_ERR(pending->snap));
+
+	btrfs_orphan_post_snapshot(trans, pending);
 fail:
 	kfree(new_root_item);
 	btrfs_block_rsv_release(root, &pending->block_rsv, (u64)-1);