btrfs: qgroup: Delay subtree scan to reduce overhead

index 9301b3ad9217..7e74bf42f2db 100644
@@ -581,17 +581,14 @@ static void init_delayed_ref_head(struct btrfs_delayed_ref_head *head_ref,
 	RB_CLEAR_NODE(&head_ref->href_node);
 	head_ref->processing = 0;
 	head_ref->total_ref_mod = count_mod;
-	head_ref->qgroup_reserved = 0;
-	head_ref->qgroup_ref_root = 0;
 	spin_lock_init(&head_ref->lock);
 	mutex_init(&head_ref->mutex);
 
 	if (qrecord) {
 		if (ref_root && reserved) {
-			head_ref->qgroup_ref_root = ref_root;
-			head_ref->qgroup_reserved = reserved;
+			qrecord->data_rsv = reserved;
+			qrecord->data_rsv_refroot = ref_root;
 		}
-
 		qrecord->bytenr = bytenr;
 		qrecord->num_bytes = num_bytes;
 		qrecord->old_roots = NULL;

@@ -630,10 +627,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 	existing = htree_insert(&delayed_refs->href_root,
 				&head_ref->href_node);
 	if (existing) {
-		WARN_ON(qrecord && head_ref->qgroup_ref_root
-			&& head_ref->qgroup_reserved
-			&& existing->qgroup_ref_root
-			&& existing->qgroup_reserved);
 		update_existing_head_ref(delayed_refs, existing, head_ref,
 					 old_ref_mod);
 		/*

@@ -745,7 +738,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
 	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
+		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
 			kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);

@@ -836,7 +829,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
 	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
+		record = kzalloc(sizeof(*record), GFP_NOFS);
 		if (!record) {
 			kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
 			kmem_cache_free(btrfs_delayed_ref_head_cachep,

index 8e20c5cb5404..09e242159acf 100644
@@ -102,17 +102,6 @@ struct btrfs_delayed_ref_head {
 	 */
 	int ref_mod;
 
-	/*
-	 * For qgroup reserved space freeing.
-	 *
-	 * ref_root and reserved will be recorded after
-	 * BTRFS_ADD_DELAYED_EXTENT is called.
-	 * And will be used to free reserved qgroup space at
-	 * run_delayed_refs() time.
-	 */
-	u64 qgroup_ref_root;
-	u64 qgroup_reserved;
-
 	/*
 	 * when a new extent is allocated, it is just reserved in memory
 	 * The actual extent isn't inserted into the extent allocation tree

index a1febf155747..6cf4070fd45f 100644
@@ -2497,9 +2497,6 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	/* Also free its reserved qgroup space */
-	btrfs_qgroup_free_delayed_ref(fs_info, head->qgroup_ref_root,
-				      head->qgroup_reserved);
 	btrfs_delayed_ref_unlock(head);
 	btrfs_put_delayed_ref_head(head);
 	return 0;

index 45868fd76209..0a66f619103d 100644
@@ -1540,12 +1540,18 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 		parent_node = *p;
 		entry = rb_entry(parent_node, struct btrfs_qgroup_extent_record,
 				 node);
-		if (bytenr < entry->bytenr)
+		if (bytenr < entry->bytenr) {
 			p = &(*p)->rb_left;
-		else if (bytenr > entry->bytenr)
+		} else if (bytenr > entry->bytenr) {
 			p = &(*p)->rb_right;
-		else
+		} else {
+			if (record->data_rsv && !entry->data_rsv) {
+				entry->data_rsv = record->data_rsv;
+				entry->data_rsv_refroot =
+					record->data_rsv_refroot;
+			}
 			return 1;
+		}
 	}
 
 	rb_link_node(&record->node, parent_node, p);

@@ -1591,7 +1597,7 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
 	    || bytenr == 0 || num_bytes == 0)
 		return 0;
-	record = kmalloc(sizeof(*record), gfp_flag);
+	record = kzalloc(sizeof(*record), gfp_flag);
 	if (!record)
 		return -ENOMEM;
 

@@ -2570,6 +2576,11 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 					goto cleanup;
 			}
 
+			/* Free the reserved data space */
+			btrfs_qgroup_free_refroot(fs_info,
+					record->data_rsv_refroot,
+					record->data_rsv,
+					BTRFS_QGROUP_RSV_DATA);
 			/*
 			 * Use SEQ_LAST as time_seq to do special search, which
 			 * doesn't lock tree or delayed_refs and search current

index d8f78f5ab854..fd26fddacd90 100644
@@ -45,6 +45,17 @@ struct btrfs_qgroup_extent_record {
 	struct rb_node node;
 	u64 bytenr;
 	u64 num_bytes;
+
+	/*
+	 * For qgroup reserved data space freeing.
+	 *
+	 * @data_rsv_refroot and @data_rsv will be recorded after
+	 * BTRFS_ADD_DELAYED_EXTENT is called.
+	 * And will be used to free reserved qgroup space at
+	 * transaction commit time.
+	 */
+	u32 data_rsv;		/* reserved data space needs to be freed */
+	u64 data_rsv_refroot;	/* which root the reserved data belongs to */
 	struct ulist *old_roots;
 };
 

@@ -252,15 +263,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type);
-static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
-						 u64 ref_root, u64 num_bytes)
-{
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
-		return;
-	trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes);
-	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes,
-				  BTRFS_QGROUP_RSV_DATA);
-}
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,

index 8568946f491d..3a5d2581bffd 100644
@@ -1510,35 +1510,6 @@ DEFINE_EVENT(btrfs__qgroup_rsv_data, btrfs_qgroup_release_data,
 	TP_ARGS(inode, start, len, reserved, op)
 );
 
-DECLARE_EVENT_CLASS(btrfs__qgroup_delayed_ref,
-
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 u64 ref_root, u64 reserved),
-
-	TP_ARGS(fs_info, ref_root, reserved),
-
-	TP_STRUCT__entry_btrfs(
-		__field(	u64,		ref_root	)
-		__field(	u64,		reserved	)
-	),
-
-	TP_fast_assign_btrfs(fs_info,
-		__entry->ref_root	= ref_root;
-		__entry->reserved	= reserved;
-	),
-
-	TP_printk_btrfs("root=%llu reserved=%llu op=free",
-		  __entry->ref_root, __entry->reserved)
-);
-
-DEFINE_EVENT(btrfs__qgroup_delayed_ref, btrfs_qgroup_free_delayed_ref,
-
-	TP_PROTO(const struct btrfs_fs_info *fs_info,
-		 u64 ref_root, u64 reserved),
-
-	TP_ARGS(fs_info, ref_root, reserved)
-);
-
 DECLARE_EVENT_CLASS(btrfs_qgroup_extent,
 	TP_PROTO(const struct btrfs_fs_info *fs_info,
 		 const struct btrfs_qgroup_extent_record *rec),

index 7e74bf42f2db..2fc7936a377f 100644
@@ -604,12 +604,10 @@ static noinline struct btrfs_delayed_ref_head *
 add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		     struct btrfs_delayed_ref_head *head_ref,
 		     struct btrfs_qgroup_extent_record *qrecord,
-		     int action, int *qrecord_inserted_ret,
-		     int *old_ref_mod, int *new_ref_mod)
+		     int action, int *old_ref_mod, int *new_ref_mod)
 {
 	struct btrfs_delayed_ref_head *existing;
 	struct btrfs_delayed_ref_root *delayed_refs;
-	int qrecord_inserted = 0;
 
 	delayed_refs = &trans->transaction->delayed_refs;
 

@@ -618,8 +616,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		if (btrfs_qgroup_trace_extent_nolock(trans->fs_info,
 					delayed_refs, qrecord))
 			kfree(qrecord);
-		else
-			qrecord_inserted = 1;
 	}
 
 	trace_add_delayed_ref_head(trans->fs_info, head_ref, action);

@@ -645,8 +641,6 @@ add_delayed_ref_head(struct btrfs_trans_handle *trans,
 		atomic_inc(&delayed_refs->num_entries);
 		trans->delayed_ref_updates++;
 	}
-	if (qrecord_inserted_ret)
-		*qrecord_inserted_ret = qrecord_inserted;
 	if (new_ref_mod)
 		*new_ref_mod = head_ref->total_ref_mod;
 

@@ -720,7 +714,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
-	int qrecord_inserted;
 	bool is_system = (ref_root == BTRFS_CHUNK_TREE_OBJECTID);
 	int ret;
 	u8 ref_type;

@@ -769,8 +762,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	 * the spin lock
 	 */
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
-					action, &qrecord_inserted,
-					old_ref_mod, new_ref_mod);
+					action, old_ref_mod, new_ref_mod);
 
 	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);

@@ -781,9 +773,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	if (ret > 0)
 		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
 
-	if (qrecord_inserted)
-		btrfs_qgroup_trace_extent_post(fs_info, record);
-
 	return 0;
 }
 

@@ -801,7 +790,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
-	int qrecord_inserted;
 	int ret;
 	u8 ref_type;
 

@@ -850,8 +838,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	 * the spin lock
 	 */
 	head_ref = add_delayed_ref_head(trans, head_ref, record,
-					action, &qrecord_inserted,
-					old_ref_mod, new_ref_mod);
+					action, old_ref_mod, new_ref_mod);
 
 	ret = insert_delayed_ref(trans, delayed_refs, head_ref, &ref->node);
 	spin_unlock(&delayed_refs->lock);

@@ -862,9 +849,6 @@ int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 	if (ret > 0)
 		kmem_cache_free(btrfs_delayed_data_ref_cachep, ref);
 
-
-	if (qrecord_inserted)
-		return btrfs_qgroup_trace_extent_post(fs_info, record);
 	return 0;
 }
 

@@ -889,7 +873,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 	spin_lock(&delayed_refs->lock);
 
 	add_delayed_ref_head(trans, head_ref, NULL, BTRFS_UPDATE_DELAYED_HEAD,
-			     NULL, NULL, NULL);
+			     NULL, NULL);
 
 	spin_unlock(&delayed_refs->lock);
 	return 0;

index 0a66f619103d..8729492ac10f 100644
@@ -1559,33 +1559,6 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
-				   struct btrfs_qgroup_extent_record *qrecord)
-{
-	struct ulist *old_root;
-	u64 bytenr = qrecord->bytenr;
-	int ret;
-
-	ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root, false);
-	if (ret < 0) {
-		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-		btrfs_warn(fs_info,
-"error accounting new delayed refs extent (err code: %d), quota inconsistent",
-			ret);
-		return 0;
-	}
-
-	/*
-	 * Here we don't need to get the lock of
-	 * trans->transaction->delayed_refs, since inserted qrecord won't
-	 * be deleted, only qrecord->node may be modified (new qrecord insert)
-	 *
-	 * So modifying qrecord->old_roots is safe here
-	 */
-	qrecord->old_roots = old_root;
-	return 0;
-}
-
 int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 			      u64 num_bytes, gfp_t gfp_flag)
 {

@@ -1609,11 +1582,9 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 	spin_lock(&delayed_refs->lock);
 	ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, record);
 	spin_unlock(&delayed_refs->lock);
-	if (ret > 0) {
+	if (ret > 0)
 		kfree(record);
-		return 0;
-	}
-	return btrfs_qgroup_trace_extent_post(fs_info, record);
+	return 0;
 }
 
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,

@@ -2563,11 +2534,7 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 		trace_btrfs_qgroup_account_extents(fs_info, record);
 
 		if (!ret) {
-			/*
-			 * Old roots should be searched when inserting qgroup
-			 * extent record
-			 */
-			if (WARN_ON(!record->old_roots)) {
+			if (!record->old_roots) {
 				/* Search commit root to find old_roots */
 				ret = btrfs_find_all_roots(NULL, fs_info,
 						record->bytenr, 0,

index fd26fddacd90..a4de5065de4b 100644
@@ -174,8 +174,7 @@ struct btrfs_delayed_extent_op;
  * Inform qgroup to trace one dirty extent, its info is recorded in @record.
  * So qgroup can account it at transaction committing time.
  *
- * No lock version, caller must acquire delayed ref lock and allocated memory,
- * then call btrfs_qgroup_trace_extent_post() after exiting lock context.
+ * No lock version, caller must acquire delayed ref lock and allocate memory,
  *
  * Return 0 for success insert
  * Return >0 for existing record, caller can free @record safely.

@@ -186,37 +185,12 @@ int btrfs_qgroup_trace_extent_nolock(
 		struct btrfs_delayed_ref_root *delayed_refs,
 		struct btrfs_qgroup_extent_record *record);
 
-/*
- * Post handler after qgroup_trace_extent_nolock().
- *
- * NOTE: Current qgroup does the expensive backref walk at transaction
- * committing time with TRANS_STATE_COMMIT_DOING, this blocks incoming
- * new transaction.
- * This is designed to allow btrfs_find_all_roots() to get correct new_roots
- * result.
- *
- * However for old_roots there is no need to do backref walk at that time,
- * since we search commit roots to walk backref and result will always be
- * correct.
- *
- * Due to the nature of no lock version, we can't do backref there.
- * So we must call btrfs_qgroup_trace_extent_post() after exiting
- * spinlock context.
- *
- * TODO: If we can fix and prove btrfs_find_all_roots() can get correct result
- * using current root, then we can move all expensive backref walk out of
- * transaction committing, but not now as qgroup accounting will be wrong again.
- */
-int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
-				   struct btrfs_qgroup_extent_record *qrecord);
-
 /*
  * Inform qgroup to trace one dirty extent, specified by @bytenr and
  * @num_bytes.
  * So qgroup can account it at commit trans time.
  *
- * Better encapsulated version, with memory allocation and backref walk for
- * commit roots.
+ * Better encapsulated version, with memory allocation
  * So this can sleep.
  *
  * Return 0 if the operation is done.

index 80953528572d..2c33506bdaaa 100644
@@ -1149,6 +1149,7 @@ struct btrfs_subvolume_writers {
 #define BTRFS_ROOT_FORCE_COW		6
 #define BTRFS_ROOT_MULTI_LOG_TASKS	7
 #define BTRFS_ROOT_DIRTY		8
+#define BTRFS_ROOT_DEAD_RELOC_TREE	9
 
 /*
  * in ram representation of the tree.  extent_root is used for all allocations

180 lines not on this page · raw message

index 8729492ac10f..e9ca73a7fa48 100644
@@ -1988,6 +1988,60 @@ static int qgroup_trace_new_subtree_blocks(struct btrfs_trans_handle* trans,
 	return ret;
 }
 
+static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
+				struct extent_buffer *src_eb,
+				struct extent_buffer *dst_eb,
+				u64 last_snapshot, bool trace_leaf)
+{
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_path *dst_path = NULL;
+	int level;
+	int ret;
+
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+		return 0;
+
+	/* Wrong parameter order */
+	if (btrfs_header_generation(src_eb) > btrfs_header_generation(dst_eb)) {
+		btrfs_err_rl(fs_info,
+		"%s: bad parameter order, src_gen=%llu dst_gen=%llu", __func__,
+			     btrfs_header_generation(src_eb),
+			     btrfs_header_generation(dst_eb));
+		return -EUCLEAN;
+	}
+
+	if (!extent_buffer_uptodate(src_eb) ||
+	    !extent_buffer_uptodate(dst_eb)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	level = btrfs_header_level(dst_eb);
+	dst_path = btrfs_alloc_path();
+	if (!dst_path) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	/* For dst_path */
+	extent_buffer_get(dst_eb);
+	dst_path->nodes[level] = dst_eb;
+	dst_path->slots[level] = 0;
+	dst_path->locks[level] = 0;
+
+	/* Do the generation aware breadth-first search */
+	ret = qgroup_trace_new_subtree_blocks(trans, src_eb, dst_path, level,
+					      level, last_snapshot, trace_leaf);
+	if (ret < 0)
+		goto out;
+	ret = 0;
+
+out:
+	btrfs_free_path(dst_path);
+	if (ret < 0)
+		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
+	return ret;
+}
+
 /*
  * Inform qgroup to trace subtree swap used in balance.
  *

@@ -2013,14 +2067,12 @@ int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 				u64 last_snapshot)
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_path *dst_path = NULL;
 	struct btrfs_key first_key;
 	struct extent_buffer *src_eb = NULL;
 	struct extent_buffer *dst_eb = NULL;
 	bool trace_leaf = false;
 	u64 child_gen;
 	u64 child_bytenr;
-	int level;
 	int ret;
 
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))

@@ -2071,22 +2123,9 @@ int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	level = btrfs_header_level(dst_eb);
-	dst_path = btrfs_alloc_path();
-	if (!dst_path) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	/* For dst_path */
-	extent_buffer_get(dst_eb);
-	dst_path->nodes[level] = dst_eb;
-	dst_path->slots[level] = 0;
-	dst_path->locks[level] = 0;
-
-	/* Do the generation-aware breadth-first search */
-	ret = qgroup_trace_new_subtree_blocks(trans, src_eb, dst_path, level,
-					      level, last_snapshot, trace_leaf);
+	/* Do the generation aware breadth-first search */
+	ret = qgroup_trace_subtree_swap(trans, src_eb, dst_eb, last_snapshot,
+					trace_leaf);
 	if (ret < 0)
 		goto out;
 	ret = 0;

@@ -2094,9 +2133,6 @@ int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 out:
 	free_extent_buffer(src_eb);
 	free_extent_buffer(dst_eb);
-	btrfs_free_path(dst_path);
-	if (ret < 0)
-		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 	return ret;
 }
 

index 2c33506bdaaa..e32fcf211c8a 100644
@@ -1151,6 +1151,17 @@ struct btrfs_subvolume_writers {
 #define BTRFS_ROOT_DIRTY		8
 #define BTRFS_ROOT_DEAD_RELOC_TREE	9
 
+/*
+ * Record swapped tree blocks of a file/subvolume tree for delayed subtree
+ * trace code. For detail check comment in fs/btrfs/qgroup.c.
+ */
+struct btrfs_qgroup_swapped_blocks {
+	spinlock_t lock;
+	struct rb_root blocks[BTRFS_MAX_LEVEL];
+	/* RM_EMPTY_ROOT() of above blocks[] */
+	bool swapped;
+};
+
 /*
  * in ram representation of the tree.  extent_root is used for all allocations
  * and for the extent tree extent_root root.

@@ -1275,6 +1286,8 @@ struct btrfs_root {
 	u64 qgroup_meta_rsv_pertrans;
 	u64 qgroup_meta_rsv_prealloc;
 
+	struct btrfs_qgroup_swapped_blocks swapped_blocks;
+
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	u64 alloc_bytenr;
 #endif

index b0ab41da91d1..bd37c3ee2fa9 100644
@@ -1204,6 +1204,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->anon_dev = 0;
 
 	spin_lock_init(&root->root_item_lock);
+	btrfs_qgroup_init_swapped_blocks(&root->swapped_blocks);
 }
 
 static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info,

133 lines not on this page · raw message

121 lines not on this page · raw message

index 6f1f11b5d8f6..9b78c8fff40f 100644
@@ -1913,6 +1913,13 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc,
 		if (ret < 0)
 			break;
 
+		btrfs_node_key_to_cpu(parent, &first_key, slot);
+		ret = btrfs_qgroup_add_swapped_blocks(trans, dest,
+				rc->block_group, parent, slot,
+				path->nodes[level], path->slots[level],
+				last_snapshot);
+		if (ret < 0)
+			break;
 		/*
 		 * swap blocks in fs tree and reloc tree.
 		 */

index d1eeef9ec5da..7a8b6a60ab18 100644
@@ -122,6 +122,7 @@ static noinline void switch_commit_roots(struct btrfs_transaction *trans)
 		if (is_fstree(root->root_key.objectid))
 			btrfs_unpin_free_ino(root);
 		clear_btree_io_tree(&root->dirty_log_pages);
+		btrfs_qgroup_clean_swapped_blocks(root);
 	}
 
 	/* We can free old roots now. */

index 539901fb5165..f4b1f73ecb71 100644
@@ -12,6 +12,7 @@
 #include "transaction.h"
 #include "print-tree.h"
 #include "locking.h"
+#include "qgroup.h"
 
 static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_path *path, int level);

@@ -1462,6 +1463,13 @@ noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
 		btrfs_set_lock_blocking(parent);
 	btrfs_set_lock_blocking(buf);
 
+	/*
+	 * Before CoWing this block for later modification, check if it's
+	 * the subtree root and do the delayed subtree trace if needed.
+	 *
+	 * Also We don't care about the error, as it's handled internally.
+	 */
+	btrfs_qgroup_trace_subtree_after_cow(trans, root, buf);
 	ret = __btrfs_cow_block(trans, root, buf, parent,
 				 parent_slot, cow_ret, search_start, 0);
 

90 lines not on this page · raw message

index 17fa8f7bd5b3..57c0d5b6cb9e 100644
@@ -400,4 +400,6 @@ int btrfs_qgroup_add_swapped_blocks(struct btrfs_trans_handle *trans,
 		struct extent_buffer *file_parent, int file_slot,
 		struct extent_buffer *reloc_parent, int reloc_slot,
 		u64 last_snapshot);
+int btrfs_qgroup_trace_subtree_after_cow(struct btrfs_trans_handle *trans,
+		struct btrfs_root *root, struct extent_buffer *eb);
 #endif

index 9b78c8fff40f..a5e9754243f4 100644
@@ -1904,16 +1904,12 @@ int replace_path(struct btrfs_trans_handle *trans, struct reloc_control *rc,
 		 *    If not traced, we will leak data numbers
 		 * 2) Fs subtree
 		 *    If not traced, we will double count old data
-		 *    and tree block numbers, if current trans doesn't free
-		 *    data reloc tree inode.
+		 *
+		 * We don't scan the subtree right now, but only record
+		 * the swapped tree blocks.
+		 * The real subtree rescan is delayed until we have new
+		 * CoW on the subtree root node before transaction commit.
 		 */
-		ret = btrfs_qgroup_trace_subtree_swap(trans, rc->block_group,
-				parent, slot, path->nodes[level],
-				path->slots[level], last_snapshot);
-		if (ret < 0)
-			break;
-
-		btrfs_node_key_to_cpu(parent, &first_key, slot);
 		ret = btrfs_qgroup_add_swapped_blocks(trans, dest,
 				rc->block_group, parent, slot,
 				path->nodes[level], path->slots[level],

index 8a4be3b9779b..c21e1bfeb467 100644
@@ -2042,100 +2042,6 @@ static int qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-/*
- * Inform qgroup to trace subtree swap used in balance.
- *
- * Unlike btrfs_qgroup_trace_subtree(), this function will only trace
- * new tree blocks whose generation is equal to (or larger than) @last_snapshot.
- *
- * Will go down the tree block pointed by @dst_eb (pointed by @dst_parent and
- * @dst_slot), and find any tree blocks whose generation is at @last_snapshot,
- * and then go down @src_eb (pointed by @src_parent and @src_slot) to find
- * the conterpart of the tree block, then mark both tree blocks as qgroup dirty,
- * and skip all tree blocks whose generation is smaller than last_snapshot.
- *
- * This would skip tons of tree blocks of original btrfs_qgroup_trace_subtree(),
- * which could be the cause of very slow balance if the file tree is large.
- *
- * @src_parent, @src_slot: pointer to src (file tree) eb.
- * @dst_parent, @dst_slot: pointer to dst (reloc tree) eb.
- */
-int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
-				struct btrfs_block_group_cache *bg_cache,
-				struct extent_buffer *src_parent, int src_slot,
-				struct extent_buffer *dst_parent, int dst_slot,
-				u64 last_snapshot)
-{
-	struct btrfs_fs_info *fs_info = trans->fs_info;
-	struct btrfs_key first_key;
-	struct extent_buffer *src_eb = NULL;
-	struct extent_buffer *dst_eb = NULL;
-	bool trace_leaf = false;
-	u64 child_gen;
-	u64 child_bytenr;
-	int ret;
-
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
-		return 0;
-
-	/* Check parameter order */
-	if (btrfs_node_ptr_generation(src_parent, src_slot) >
-	    btrfs_node_ptr_generation(dst_parent, dst_slot)) {
-		btrfs_err_rl(fs_info,
-		"%s: bad parameter order, src_gen=%llu dst_gen=%llu", __func__,
-			btrfs_node_ptr_generation(src_parent, src_slot),
-			btrfs_node_ptr_generation(dst_parent, dst_slot));
-		return -EUCLEAN;
-	}
-
-	/*
-	 * Only trace leaf if we're relocating data block groups, this could
-	 * reduce tons of data extents tracing for meta/sys bg relocation.
-	 */
-	if (bg_cache->flags & BTRFS_BLOCK_GROUP_DATA)
-		trace_leaf = true;
-	/* Read out real @src_eb, pointed by @src_parent and @src_slot */
-	child_bytenr = btrfs_node_blockptr(src_parent, src_slot);
-	child_gen = btrfs_node_ptr_generation(src_parent, src_slot);
-	btrfs_node_key_to_cpu(src_parent, &first_key, src_slot);
-
-	src_eb = read_tree_block(fs_info, child_bytenr, child_gen,
-			btrfs_header_level(src_parent) - 1, &first_key);
-	if (IS_ERR(src_eb)) {
-		ret = PTR_ERR(src_eb);
-		goto out;
-	}
-
-	/* Read out real @dst_eb, pointed by @src_parent and @src_slot */
-	child_bytenr = btrfs_node_blockptr(dst_parent, dst_slot);
-	child_gen = btrfs_node_ptr_generation(dst_parent, dst_slot);
-	btrfs_node_key_to_cpu(dst_parent, &first_key, dst_slot);
-
-	dst_eb = read_tree_block(fs_info, child_bytenr, child_gen,
-			btrfs_header_level(dst_parent) - 1, &first_key);
-	if (IS_ERR(dst_eb)) {
-		ret = PTR_ERR(dst_eb);
-		goto out;
-	}
-
-	if (!extent_buffer_uptodate(src_eb) || !extent_buffer_uptodate(dst_eb)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* Do the generation aware breadth-first search */
-	ret = qgroup_trace_subtree_swap(trans, src_eb, dst_eb, last_snapshot,
-					trace_leaf);
-	if (ret < 0)
-		goto out;
-	ret = 0;
-
-out:
-	free_extent_buffer(src_eb);
-	free_extent_buffer(dst_eb);
-	return ret;
-}
-
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level)

index 57c0d5b6cb9e..d7a9d2dce8c8 100644
@@ -301,12 +301,6 @@ 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);
-
-int btrfs_qgroup_trace_subtree_swap(struct btrfs_trans_handle *trans,
-				struct btrfs_block_group_cache *bg_cache,
-				struct extent_buffer *src_parent, int src_slot,
-				struct extent_buffer *dst_parent, int dst_slot,
-				u64 last_snapshot);
 int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 				u64 num_bytes, struct ulist *old_roots,
 				struct ulist *new_roots);