Btrfs: Add a leaf reference cache

Much of the IO done while dropping snapshots is done looking up leaves in the filesystem trees to see if they point to any extents and to drop the references on any extents found. This creates a cache so that IO isn't required. Signed-off-by: Chris Mason <chris.mason@oracle.com>
git-mirror · Sep 25, 2008 · 31153d8 · 31153d8
1 parent 3a115f5
commit 31153d8
Show file tree

Hide file tree

Showing 8 changed files with 476 additions and 33 deletions.
diff --git a/fs/btrfs/Makefile b/fs/btrfs/Makefile
@@ -6,7 +6,8 @@ btrfs-y := super.o ctree.o extent-tree.o print-tree.o root-tree.o dir-item.o \
 	   hash.o file-item.o inode-item.o inode-map.o disk-io.o \
 	   transaction.o bit-radix.o inode.o file.o tree-defrag.o \
 	   extent_map.o sysfs.o struct-funcs.o xattr.o ordered-data.o \
-	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o
+	   extent_io.o volumes.o async-thread.o ioctl.o locking.o orphan.o \
+	   ref-cache.o
 
 btrfs-$(CONFIG_FS_POSIX_ACL)	+= acl.o
 else

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
@@ -165,7 +165,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
 	btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN);
 
 	WARN_ON(btrfs_header_generation(buf) > trans->transid);
-	ret = btrfs_inc_ref(trans, new_root, buf);
+	ret = btrfs_inc_ref(trans, new_root, buf, 0);
 	kfree(new_root);
 
 	if (ret)
@@ -232,7 +232,7 @@ int __btrfs_cow_block(struct btrfs_trans_handle *trans,
 	WARN_ON(btrfs_header_generation(buf) > trans->transid);
 	if (btrfs_header_generation(buf) != trans->transid) {
 		different_trans = 1;
-		ret = btrfs_inc_ref(trans, root, buf);
+		ret = btrfs_inc_ref(trans, root, buf, 1);
 		if (ret)
 			return ret;
 	} else {

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
@@ -592,6 +592,10 @@ struct btrfs_fs_info {
 	u64 last_alloc;
 	u64 last_data_alloc;
 
+	spinlock_t ref_cache_lock;
+	u64 total_ref_cache_size;
+	u64 running_ref_cache_size;
+
 	u64 avail_data_alloc_bits;
 	u64 avail_metadata_alloc_bits;
 	u64 avail_system_alloc_bits;
@@ -613,6 +617,8 @@ struct btrfs_root {
 	spinlock_t node_lock;
 
 	struct extent_buffer *commit_root;
+	struct btrfs_leaf_ref_tree *ref_tree;
+
 	struct btrfs_root_item root_item;
 	struct btrfs_key root_key;
 	struct btrfs_fs_info *fs_info;
@@ -1430,7 +1436,7 @@ int btrfs_reserve_extent(struct btrfs_trans_handle *trans,
 				  u64 search_end, struct btrfs_key *ins,
 				  u64 data);
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf);
+		  struct extent_buffer *buf, int cache_ref);
 int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, u64 bytenr, u64 num_bytes,
 		      u64 root_objectid, u64 ref_generation,

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
@@ -716,6 +716,7 @@ static int __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
 	root->node = NULL;
 	root->inode = NULL;
 	root->commit_root = NULL;
+	root->ref_tree = NULL;
 	root->sectorsize = sectorsize;
 	root->nodesize = nodesize;
 	root->leafsize = leafsize;
@@ -1165,12 +1166,19 @@ static int transaction_kthread(void *arg)
 		vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
 		mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
+		printk("btrfs: total reference cache size %Lu\n",
+			root->fs_info->total_ref_cache_size);
+
 		mutex_lock(&root->fs_info->trans_mutex);
 		cur = root->fs_info->running_transaction;
 		if (!cur) {
 			mutex_unlock(&root->fs_info->trans_mutex);
 			goto sleep;
 		}
+
+		printk("btrfs: running reference cache size %Lu\n",
+			root->fs_info->running_ref_cache_size);
+
 		now = get_seconds();
 		if (now < cur->start_time || now - cur->start_time < 30) {
 			mutex_unlock(&root->fs_info->trans_mutex);
@@ -1233,6 +1241,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->hash_lock);
 	spin_lock_init(&fs_info->delalloc_lock);
 	spin_lock_init(&fs_info->new_trans_lock);
+	spin_lock_init(&fs_info->ref_cache_lock);
 
 	init_completion(&fs_info->kobj_unregister);
 	fs_info->tree_root = tree_root;
@@ -1699,6 +1708,11 @@ int close_ctree(struct btrfs_root *root)
 		printk("btrfs: at unmount delalloc count %Lu\n",
 		       fs_info->delalloc_bytes);
 	}
+	if (fs_info->total_ref_cache_size) {
+		printk("btrfs: at umount reference cache size %Lu\n",
+			fs_info->total_ref_cache_size);
+	}
+
 	if (fs_info->extent_root->node)
 		free_extent_buffer(fs_info->extent_root->node);
 

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
@@ -26,6 +26,7 @@
 #include "transaction.h"
 #include "volumes.h"
 #include "locking.h"
+#include "ref-cache.h"
 
 #define BLOCK_GROUP_DATA     EXTENT_WRITEBACK
 #define BLOCK_GROUP_METADATA EXTENT_UPTODATE
@@ -927,7 +928,7 @@ u32 btrfs_count_snapshots_in_path(struct btrfs_root *root,
 }
 
 int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		  struct extent_buffer *buf)
+		  struct extent_buffer *buf, int cache_ref)
 {
 	u64 bytenr;
 	u32 nritems;
@@ -937,6 +938,7 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	int level;
 	int ret;
 	int faili;
+	int nr_file_extents = 0;
 
 	if (!root->ref_cows)
 		return 0;
@@ -959,6 +961,9 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			if (disk_bytenr == 0)
 				continue;
 
+			if (buf != root->commit_root)
+				nr_file_extents++;
+
 			mutex_lock(&root->fs_info->alloc_mutex);
 			ret = __btrfs_inc_extent_ref(trans, root, disk_bytenr,
 				    btrfs_file_extent_disk_num_bytes(buf, fi),
@@ -988,6 +993,53 @@ int btrfs_inc_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			}
 		}
 	}
+	/* cache orignal leaf block's references */
+	if (level == 0 && cache_ref && buf != root->commit_root) {
+		struct btrfs_leaf_ref *ref;
+		struct btrfs_extent_info *info;
+
+		ref = btrfs_alloc_leaf_ref(nr_file_extents);
+		if (!ref) {
+			WARN_ON(1);
+			goto out;
+		}
+
+		btrfs_item_key_to_cpu(buf, &ref->key, 0);
+
+		ref->bytenr = buf->start;
+		ref->owner = btrfs_header_owner(buf);
+		ref->generation = btrfs_header_generation(buf);
+		ref->nritems = nr_file_extents;
+		info = ref->extents;
+
+		for (i = 0; nr_file_extents > 0 && i < nritems; i++) {
+			u64 disk_bytenr;
+			btrfs_item_key_to_cpu(buf, &key, i);
+			if (btrfs_key_type(&key) != BTRFS_EXTENT_DATA_KEY)
+				continue;
+			fi = btrfs_item_ptr(buf, i,
+					    struct btrfs_file_extent_item);
+			if (btrfs_file_extent_type(buf, fi) ==
+			    BTRFS_FILE_EXTENT_INLINE)
+				continue;
+			disk_bytenr = btrfs_file_extent_disk_bytenr(buf, fi);
+			if (disk_bytenr == 0)
+				continue;
+
+			info->bytenr = disk_bytenr;
+			info->num_bytes =
+				btrfs_file_extent_disk_num_bytes(buf, fi);
+			info->objectid = key.objectid;
+			info->offset = key.offset;
+			info++;
+		}
+
+		BUG_ON(!root->ref_tree);
+		ret = btrfs_add_leaf_ref(root, ref);
+		WARN_ON(ret);
+		btrfs_free_leaf_ref(ref);
+	}
+out:
 	return 0;
 fail:
 	WARN_ON(1);
@@ -2215,9 +2267,9 @@ struct extent_buffer *btrfs_alloc_free_block(struct btrfs_trans_handle *trans,
 	return buf;
 }
 
-static int noinline drop_leaf_ref(struct btrfs_trans_handle *trans,
-				  struct btrfs_root *root,
-				  struct extent_buffer *leaf)
+static int noinline drop_leaf_ref_no_cache(struct btrfs_trans_handle *trans,
+				  	   struct btrfs_root *root,
+					   struct extent_buffer *leaf)
 {
 	u64 leaf_owner;
 	u64 leaf_generation;
@@ -2266,6 +2318,30 @@ static int noinline drop_leaf_ref(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
+static int noinline drop_leaf_ref(struct btrfs_trans_handle *trans,
+				  	 struct btrfs_root *root,
+					 struct btrfs_leaf_ref *ref)
+{
+	int i;
+	int ret;
+	struct btrfs_extent_info *info = ref->extents;
+
+	mutex_unlock(&root->fs_info->alloc_mutex);
+	for (i = 0; i < ref->nritems; i++) {
+		mutex_lock(&root->fs_info->alloc_mutex);
+		ret = __btrfs_free_extent(trans, root,
+					info->bytenr, info->num_bytes,
+					ref->owner, ref->generation,
+					info->objectid, info->offset, 0);
+		mutex_unlock(&root->fs_info->alloc_mutex);
+		BUG_ON(ret);
+		info++;
+	}
+	mutex_lock(&root->fs_info->alloc_mutex);
+
+	return 0;
+}
+
 static void noinline reada_walk_down(struct btrfs_root *root,
 				     struct extent_buffer *node,
 				     int slot)
@@ -2341,6 +2417,7 @@ static int noinline walk_down_tree(struct btrfs_trans_handle *trans,
 	struct extent_buffer *next;
 	struct extent_buffer *cur;
 	struct extent_buffer *parent;
+	struct btrfs_leaf_ref *ref;
 	u32 blocksize;
 	int ret;
 	u32 refs;
@@ -2370,7 +2447,7 @@ static int noinline walk_down_tree(struct btrfs_trans_handle *trans,
 		    btrfs_header_nritems(cur))
 			break;
 		if (*level == 0) {
-			ret = drop_leaf_ref(trans, root, cur);
+			ret = drop_leaf_ref_no_cache(trans, root, cur);
 			BUG_ON(ret);
 			break;
 		}
@@ -2391,14 +2468,28 @@ static int noinline walk_down_tree(struct btrfs_trans_handle *trans,
 			BUG_ON(ret);
 			continue;
 		}
+
+		if (*level == 1) {
+			struct btrfs_key key;
+			btrfs_node_key_to_cpu(cur, &key, path->slots[*level]);
+			ref = btrfs_lookup_leaf_ref(root, &key);
+			if (ref) {
+				ret = drop_leaf_ref(trans, root, ref);
+				BUG_ON(ret);
+				btrfs_remove_leaf_ref(root, ref);
+				btrfs_free_leaf_ref(ref);
+				*level = 0;
+				break;
+			}
+		}
+
 		next = btrfs_find_tree_block(root, bytenr, blocksize);
 		if (!next || !btrfs_buffer_uptodate(next, ptr_gen)) {
 			free_extent_buffer(next);
 			mutex_unlock(&root->fs_info->alloc_mutex);
 
 			if (path->slots[*level] == 0)
 				reada_walk_down(root, cur, path->slots[*level]);
-
 			next = read_tree_block(root, bytenr, blocksize,
 					       ptr_gen);
 			cond_resched();
@@ -2435,17 +2526,19 @@ static int noinline walk_down_tree(struct btrfs_trans_handle *trans,
 	WARN_ON(*level >= BTRFS_MAX_LEVEL);
 
 	if (path->nodes[*level] == root->node) {
-		root_owner = root->root_key.objectid;
 		parent = path->nodes[*level];
+		bytenr = path->nodes[*level]->start;
 	} else {
 		parent = path->nodes[*level + 1];
-		root_owner = btrfs_header_owner(parent);
+		bytenr = btrfs_node_blockptr(parent, path->slots[*level + 1]);
 	}
 
+	blocksize = btrfs_level_size(root, *level);
+	root_owner = btrfs_header_owner(parent);
 	root_gen = btrfs_header_generation(parent);
-	ret = __btrfs_free_extent(trans, root, path->nodes[*level]->start,
-				path->nodes[*level]->len,
-				root_owner, root_gen, 0, 0, 1);
+
+	ret = __btrfs_free_extent(trans, root, bytenr, blocksize,
+				  root_owner, root_gen, 0, 0, 1);
 	free_extent_buffer(path->nodes[*level]);
 	path->nodes[*level] = NULL;
 	*level += 1;