@@ -6293,7 +6293,7 @@ static int check_type_with_root(u64 rootid, u8 key_type)
goto err;
break;
case BTRFS_BLOCK_GROUP_ITEM_KEY:
- if (btrfs_fs_incompat(gfs_info, EXTENT_TREE_V2)) {
+ if (btrfs_fs_compat_ro(gfs_info, BLOCK_GROUP_TREE)) {
if (rootid != BTRFS_BLOCK_GROUP_TREE_OBJECTID)
goto err;
} else if (rootid != BTRFS_EXTENT_TREE_OBJECTID) {
@@ -9071,10 +9071,6 @@ again:
ret = load_super_root(&normal_trees, gfs_info->chunk_root);
if (ret < 0)
goto out;
- ret = load_super_root(&normal_trees, gfs_info->block_group_root);
- if (ret < 0)
- goto out;
-
ret = parse_tree_roots(&normal_trees, &dropping_trees);
if (ret < 0)
goto out;
@@ -9574,7 +9570,7 @@ again:
* If we are extent tree v2 then we can reint the block group root as
* well.
*/
- if (btrfs_fs_incompat(gfs_info, EXTENT_TREE_V2)) {
+ if (btrfs_fs_compat_ro(gfs_info, BLOCK_GROUP_TREE)) {
ret = btrfs_fsck_reinit_root(trans, gfs_info->block_group_root);
if (ret) {
fprintf(stderr, "block group initialization failed\n");
@@ -172,6 +172,14 @@ static const struct btrfs_feature runtime_features[] = {
VERSION_TO_STRING2(safe, 4,9),
VERSION_TO_STRING2(default, 5,15),
.desc = "free space tree (space_cache=v2)"
+ }, {
+ .name = "block-group-tree",
+ .flag = BTRFS_RUNTIME_FEATURE_BLOCK_GROUP_TREE,
+ .sysfs_name = "block_group_tree",
+ VERSION_TO_STRING2(compat, 6,0),
+ VERSION_NULL(safe),
+ VERSION_NULL(default),
+ .desc = "block group tree to reduce mount time"
},
/* Keep this one last */
{
@@ -45,6 +45,8 @@
#define BTRFS_RUNTIME_FEATURE_QUOTA (1ULL << 0)
#define BTRFS_RUNTIME_FEATURE_FREE_SPACE_TREE (1ULL << 1)
+#define BTRFS_RUNTIME_FEATURE_BLOCK_GROUP_TREE (1ULL << 2)
+
void btrfs_list_all_fs_features(u64 mask_disallowed);
void btrfs_list_all_runtime_features(u64 mask_disallowed);
@@ -479,6 +479,12 @@ BUILD_ASSERT(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE);
*/
#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID (1ULL << 1)
+/*
+ * Save all block group items into a dedicated block group tree, to greatly
+ * reduce mount time for large fs.
+ */
+#define BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE (1ULL << 5)
+
#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0)
#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1)
#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2)
@@ -508,7 +514,8 @@ BUILD_ASSERT(sizeof(struct btrfs_super_block) == BTRFS_SUPER_INFO_SIZE);
*/
#define BTRFS_FEATURE_COMPAT_RO_SUPP \
(BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE | \
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID)
+ BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID| \
+ BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE)
#if EXPERIMENTAL
#define BTRFS_FEATURE_INCOMPAT_SUPP \
@@ -1203,7 +1203,7 @@ static int load_important_roots(struct btrfs_fs_info *fs_info,
backup = sb->super_roots + index;
}
- if (!btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
+ if (!btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) {
free(fs_info->block_group_root);
fs_info->block_group_root = NULL;
goto tree_root;
@@ -1256,7 +1256,7 @@ int btrfs_setup_all_roots(struct btrfs_fs_info *fs_info, u64 root_tree_bytenr,
if (ret)
return ret;
- if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2)) {
+ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE)) {
ret = find_and_setup_root(root, fs_info,
BTRFS_BLOCK_GROUP_TREE_OBJECTID,
fs_info->block_group_root);
@@ -232,7 +232,7 @@ int btrfs_global_root_insert(struct btrfs_fs_info *fs_info,
static inline struct btrfs_root *btrfs_block_group_root(
struct btrfs_fs_info *fs_info)
{
- if (btrfs_fs_incompat(fs_info, EXTENT_TREE_V2))
+ if (btrfs_fs_compat_ro(fs_info, BLOCK_GROUP_TREE))
return fs_info->block_group_root;
return btrfs_extent_root(fs_info, 0);
}
@@ -1668,6 +1668,7 @@ struct readable_flag_entry {
static struct readable_flag_entry compat_ro_flags_array[] = {
DEF_COMPAT_RO_FLAG_ENTRY(FREE_SPACE_TREE),
DEF_COMPAT_RO_FLAG_ENTRY(FREE_SPACE_TREE_VALID),
+ DEF_COMPAT_RO_FLAG_ENTRY(BLOCK_GROUP_TREE),
};
static const int compat_ro_flags_num = sizeof(compat_ro_flags_array) /
sizeof(struct readable_flag_entry);
@@ -1754,9 +1755,7 @@ static void print_readable_compat_ro_flag(u64 flag)
*/
return __print_readable_flag(flag, compat_ro_flags_array,
compat_ro_flags_num,
- BTRFS_FEATURE_COMPAT_RO_SUPP |
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE |
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID);
+ BTRFS_FEATURE_COMPAT_RO_SUPP);
}
static void print_readable_incompat_flag(u64 flag)
@@ -75,6 +75,8 @@ static int btrfs_create_tree_root(int fd, struct btrfs_mkfs_config *cfg,
int blk;
int i;
u8 uuid[BTRFS_UUID_SIZE];
+ bool block_group_tree = !!(cfg->runtime_features &
+ BTRFS_RUNTIME_FEATURE_BLOCK_GROUP_TREE);
memset(buf->data + sizeof(struct btrfs_header), 0,
cfg->nodesize - sizeof(struct btrfs_header));
@@ -101,6 +103,9 @@ static int btrfs_create_tree_root(int fd, struct btrfs_mkfs_config *cfg,
if (blk == MKFS_ROOT_TREE || blk == MKFS_CHUNK_TREE)
continue;
+ if (!block_group_tree && blk == MKFS_BLOCK_GROUP_TREE)
+ continue;
+
btrfs_set_root_bytenr(&root_item, cfg->blocks[blk]);
btrfs_set_disk_key_objectid(&disk_key,
reference_root_table[blk]);
@@ -216,7 +221,8 @@ static int create_block_group_tree(int fd, struct btrfs_mkfs_config *cfg,
memset(buf->data + sizeof(struct btrfs_header), 0,
cfg->nodesize - sizeof(struct btrfs_header));
- write_block_group_item(buf, 0, bg_offset, bg_size, bg_used, 0,
+ write_block_group_item(buf, 0, bg_offset, bg_size, bg_used,
+ BTRFS_FIRST_CHUNK_TREE_OBJECTID,
cfg->leaf_data_size -
sizeof(struct btrfs_block_group_item));
btrfs_set_header_bytenr(buf, cfg->blocks[MKFS_BLOCK_GROUP_TREE]);
@@ -357,6 +363,7 @@ int make_btrfs(int fd, struct btrfs_mkfs_config *cfg)
u32 array_size;
u32 item_size;
u64 total_used = 0;
+ u64 ro_flags = 0;
int skinny_metadata = !!(cfg->features &
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA);
u64 num_bytes;
@@ -365,6 +372,8 @@ int make_btrfs(int fd, struct btrfs_mkfs_config *cfg)
bool add_block_group = true;
bool free_space_tree = !!(cfg->runtime_features &
BTRFS_RUNTIME_FEATURE_FREE_SPACE_TREE);
+ bool block_group_tree = !!(cfg->runtime_features &
+ BTRFS_RUNTIME_FEATURE_BLOCK_GROUP_TREE);
bool extent_tree_v2 = !!(cfg->features &
BTRFS_FEATURE_INCOMPAT_EXTENT_TREE_V2);
@@ -372,8 +381,13 @@ int make_btrfs(int fd, struct btrfs_mkfs_config *cfg)
sizeof(enum btrfs_mkfs_block) * ARRAY_SIZE(default_blocks));
blocks_nr = ARRAY_SIZE(default_blocks);
- /* Extent tree v2 needs an extra block for block group tree.*/
- if (extent_tree_v2) {
+ /*
+ * Add one new block for block group tree.
+ * And for block group tree, we don't need to add block group item
+ * into extent tree, the item will be handled in block group tree
+ * initialization.
+ */
+ if (block_group_tree) {
mkfs_blocks_add(blocks, &blocks_nr, MKFS_BLOCK_GROUP_TREE);
add_block_group = false;
}
@@ -433,12 +447,15 @@ int make_btrfs(int fd, struct btrfs_mkfs_config *cfg)
btrfs_set_super_cache_generation(&super, -1);
btrfs_set_super_incompat_flags(&super, cfg->features);
if (free_space_tree) {
- u64 ro_flags = BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE |
- BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID;
+ ro_flags |= (BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE |
+ BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE_VALID);
- btrfs_set_super_compat_ro_flags(&super, ro_flags);
btrfs_set_super_cache_generation(&super, 0);
}
+ if (block_group_tree)
+ ro_flags |= BTRFS_FEATURE_COMPAT_RO_BLOCK_GROUP_TREE;
+ btrfs_set_super_compat_ro_flags(&super, ro_flags);
+
if (extent_tree_v2)
btrfs_set_super_nr_global_roots(&super, 1);
@@ -695,7 +712,7 @@ int make_btrfs(int fd, struct btrfs_mkfs_config *cfg)
goto out;
}
- if (extent_tree_v2) {
+ if (block_group_tree) {
ret = create_block_group_tree(fd, cfg, buf,
system_group_offset,
system_group_size, total_used);
@@ -299,7 +299,8 @@ static int recow_roots(struct btrfs_trans_handle *trans,
ret = __recow_root(trans, info->dev_root);
if (ret)
return ret;
- if (btrfs_fs_incompat(info, EXTENT_TREE_V2)) {
+
+ if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) {
ret = __recow_root(trans, info->block_group_root);
if (ret)
return ret;
Block group tree feature is completely a standalone feature, and it has been over 5 years before the initial introduction to solve the long mount time. I don't really want to waste another 5 years waiting for a feature which may or may not work, but definitely not properly reviewed for its preparation patches. So this patch will separate the block group tree feature into a standalone compat RO feature. There is a catch, in mkfs create_block_group_tree(), current tree-checker only accepts block group item with valid chunk_objectid, but the existing code from extent-tree-v2 didn't properly initialize it. This patch will also fix above mentioned problem so kernel can mount it correctly. Now mkfs/fsck should be able to handle the fs with block group tree. Signed-off-by: Qu Wenruo <wqu@suse.com> --- check/main.c | 8 ++------ common/fsfeatures.c | 8 ++++++++ common/fsfeatures.h | 2 ++ kernel-shared/ctree.h | 9 ++++++++- kernel-shared/disk-io.c | 4 ++-- kernel-shared/disk-io.h | 2 +- kernel-shared/print-tree.c | 5 ++--- mkfs/common.c | 31 ++++++++++++++++++++++++------- mkfs/main.c | 3 ++- 9 files changed, 51 insertions(+), 21 deletions(-)