btrfs: Delay block group auto removal to avoid interfering qgroups

index 51b5e2da708c..8241de81089a 100644
@@ -6354,6 +6354,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			spin_lock(&info->unused_bgs_lock);
 			if (list_empty(&cache->bg_list)) {
 				btrfs_get_block_group(cache);
+				trace_btrfs_add_unused_block_group(cache);
 				list_add_tail(&cache->bg_list,
 					      &info->unused_bgs);
 			}

@@ -10204,6 +10205,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 			/* Should always be true but just in case. */
 			if (list_empty(&cache->bg_list)) {
 				btrfs_get_block_group(cache);
+				trace_btrfs_add_unused_block_group(cache);
 				list_add_tail(&cache->bg_list,
 					      &info->unused_bgs);
 			}

@@ -10391,6 +10393,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	BUG_ON(!block_group);
 	BUG_ON(!block_group->ro);
 
+	trace_btrfs_remove_block_group(block_group);
 	/*
 	 * Free the reserved super bytes from this block group before
 	 * remove it.

@@ -10755,6 +10758,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 			 * the ro check in case balance is currently acting on
 			 * this block group.
 			 */
+			trace_btrfs_skip_unused_block_group(block_group);
 			spin_unlock(&block_group->lock);
 			up_write(&space_info->groups_sem);
 			goto next;

index 52b39a0924e9..a59005862010 100644
@@ -3984,6 +3984,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			spin_lock(&fs_info->unused_bgs_lock);
 			if (list_empty(&cache->bg_list)) {
 				btrfs_get_block_group(cache);
+				trace_btrfs_add_unused_block_group(cache);
 				list_add_tail(&cache->bg_list,
 					      &fs_info->unused_bgs);
 			}

48 lines not on this page · raw message

index 2771cc56a622..b19b673485fd 100644
@@ -2829,6 +2829,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       struct btrfs_fs_info *info, u64 start, u64 end);
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,

index 8241de81089a..f0d7e19feca7 100644
@@ -6350,16 +6350,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		 * dirty list to avoid races between cleaner kthread and space
 		 * cache writeout.
 		 */
-		if (!alloc && old_val == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
-		}
+		if (!alloc && old_val == 0)
+			btrfs_mark_bg_unused(cache);
 
 		btrfs_put_block_group(cache);
 		total -= num_bytes;

@@ -10201,15 +10193,8 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
 			inc_block_group_ro(cache, 1);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			/* Should always be true but just in case. */
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
+			ASSERT(list_empty(&cache->bg_list));
+			btrfs_mark_bg_unused(cache);
 		}
 	}
 

@@ -11133,3 +11118,16 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
 			       !atomic_read(&root->will_be_snapshotted));
 	}
 }
+
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (list_empty(&bg->bg_list)) {
+		btrfs_get_block_group(bg);
+		trace_btrfs_add_unused_block_group(bg);
+		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+}

index a59005862010..40086b47a65f 100644
@@ -3981,14 +3981,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    btrfs_block_group_used(&cache->item) == 0) {
 			spin_unlock(&cache->lock);
-			spin_lock(&fs_info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &fs_info->unused_bgs);
-			}
-			spin_unlock(&fs_info->unused_bgs_lock);
+			btrfs_mark_bg_unused(cache);
 		} else {
 			spin_unlock(&cache->lock);
 		}

index b19b673485fd..19d7532fa4cf 100644
@@ -2829,7 +2829,8 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       struct btrfs_fs_info *info, u64 start, u64 end);
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg,
+			  struct btrfs_trans_handle *trans);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,

index f0d7e19feca7..80e17bd99f8e 100644
@@ -6351,7 +6351,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		 * cache writeout.
 		 */
 		if (!alloc && old_val == 0)
-			btrfs_mark_bg_unused(cache);
+			btrfs_mark_bg_unused(cache, trans);
 
 		btrfs_put_block_group(cache);
 		total -= num_bytes;

@@ -10194,7 +10194,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 			inc_block_group_ro(cache, 1);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
 			ASSERT(list_empty(&cache->bg_list));
-			btrfs_mark_bg_unused(cache);
+			btrfs_mark_bg_unused(cache, NULL);
 		}
 	}
 

@@ -11119,15 +11119,41 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
 	}
 }
 
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+/*
+ * Get a block group cache and mark it as unused (if not already
+ * unused/deleted)
+ *
+ * NOTE:
+ * Since qgroup could search commit root at any time, we can't just
+ * delete the block group and its chunk mapping in current trans.
+ * So we record bgs to be deleted in trans->transaction and then
+ * queue them into fs_info->unused_bgs.
+ *
+ * @bg:		The block group cache
+ * @trans:	The trans handler
+ */
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg,
+			  struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = bg->fs_info;
 
 	spin_lock(&fs_info->unused_bgs_lock);
 	if (list_empty(&bg->bg_list)) {
+		/*
+		 * Get one reference, will be freed at btrfs_delete_unused_bgs()
+		 */
 		btrfs_get_block_group(bg);
 		trace_btrfs_add_unused_block_group(bg);
-		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+
+		/*
+		 * If we don't have a trans, it means we are at mount time.
+		 * It's completely fine to mark it ready to be deleted.
+		 */
+		if (!trans)
+			list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+		else
+			list_add_tail(&bg->bg_list,
+				      &trans->transaction->pending_unused_bgs);
 	}
 	spin_unlock(&fs_info->unused_bgs_lock);
 }

index 40086b47a65f..d9e2420da457 100644
@@ -3981,7 +3981,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    btrfs_block_group_used(&cache->item) == 0) {
 			spin_unlock(&cache->lock);
-			btrfs_mark_bg_unused(cache);
+			btrfs_mark_bg_unused(cache, NULL);
 		} else {
 			spin_unlock(&cache->lock);
 		}

index c944b4769e3c..5518215fc388 100644
@@ -264,6 +264,7 @@ static noinline int join_transaction(struct btrfs_fs_info *fs_info,
 
 	INIT_LIST_HEAD(&cur_trans->pending_snapshots);
 	INIT_LIST_HEAD(&cur_trans->pending_chunks);
+	INIT_LIST_HEAD(&cur_trans->pending_unused_bgs);
 	INIT_LIST_HEAD(&cur_trans->switch_commits);
 	INIT_LIST_HEAD(&cur_trans->dirty_bgs);
 	INIT_LIST_HEAD(&cur_trans->io_bgs);

@@ -2269,6 +2270,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	wake_up(&cur_trans->commit_wait);
 	clear_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
 
+	/* transaction is done, queue pending unused bgs to cleaner */
+	spin_lock(&fs_info->unused_bgs_lock);
+	list_splice_tail_init(&cur_trans->pending_unused_bgs,
+			      &fs_info->unused_bgs);
+	spin_unlock(&fs_info->unused_bgs_lock);
+
 	spin_lock(&fs_info->trans_lock);
 	list_del_init(&cur_trans->list);
 	spin_unlock(&fs_info->trans_lock);

index d8c0826bc2c7..9f160e1811f7 100644
@@ -57,6 +57,16 @@ struct btrfs_transaction {
 	struct list_head switch_commits;
 	struct list_head dirty_bgs;
 
+	/*
+	 * Unused block groups waiting to be deleted after current transaction.
+	 * Protected by fs_info->unused_bgs_lock.
+	 *
+	 * Since qgroup could search commit root, we can't delete unused block
+	 * group in the same trans when it get emptied, but delay it to next
+	 * transaction (or next mount if power loss happens)
+	 */
+	struct list_head pending_unused_bgs;
+
 	/*
 	 * There is no explicit lock which protects io_bgs, rather its
 	 * consistency is implied by the fact that all the sites which modify