@@ -4506,6 +4506,12 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
struct btrfs_space_info,
list);
+ for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) {
+ if (space_info->sub_group[i]) {
+ check_removing_space_info(space_info->sub_group[i]);
+ kfree(space_info->sub_group[i]);
+ }
+ }
check_removing_space_info(space_info);
list_del(&space_info->list);
btrfs_sysfs_remove_space_info(space_info);
@@ -249,6 +249,7 @@ static void init_space_info(struct btrfs_fs_info *info,
INIT_LIST_HEAD(&space_info->priority_tickets);
space_info->clamp = 1;
btrfs_update_space_info_chunk_size(space_info, calc_chunk_size(info, flags));
+ space_info->subgroup_id = SUB_GROUP_PRIMARY;
if (btrfs_is_zoned(info))
space_info->bg_reclaim_threshold = BTRFS_DEFAULT_ZONED_RECLAIM_THRESH;
@@ -266,6 +267,20 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags)
init_space_info(info, space_info, flags);
+ if (btrfs_is_zoned(info) && (flags & BTRFS_BLOCK_GROUP_DATA)) {
+ struct btrfs_space_info *reloc = kzalloc(sizeof(*reloc), GFP_NOFS);
+
+ if (!reloc)
+ return -ENOMEM;
+ init_space_info(info, reloc, flags);
+ space_info->sub_group[SUB_GROUP_DATA_RELOC] = reloc;
+ reloc->parent = space_info;
+ reloc->subgroup_id = SUB_GROUP_DATA_RELOC;
+
+ ret = btrfs_sysfs_add_space_info_type(info, reloc);
+ ASSERT(!ret);
+ }
+
ret = btrfs_sysfs_add_space_info_type(info, space_info);
if (ret)
return ret;
@@ -561,8 +576,9 @@ static void __btrfs_dump_space_info(const struct btrfs_fs_info *fs_info,
lockdep_assert_held(&info->lock);
/* The free space could be negative in case of overcommit */
- btrfs_info(fs_info, "space_info %s has %lld free, is %sfull",
- flag_str,
+ btrfs_info(fs_info,
+ "space_info %s (sub-group id %d) has %lld free, is %sfull",
+ flag_str, info->subgroup_id,
(s64)(info->total_bytes - btrfs_space_info_used(info, true)),
info->full ? "" : "not ");
btrfs_info(fs_info,
@@ -98,8 +98,16 @@ enum btrfs_flush_state {
RESET_ZONES = 12,
};
+enum btrfs_space_info_sub_group {
+ SUB_GROUP_DATA_RELOC = 0,
+ SUB_GROUP_PRIMARY = -1,
+};
+#define BTRFS_SPACE_INFO_SUB_GROUP_MAX 1
struct btrfs_space_info {
struct btrfs_fs_info *fs_info;
+ struct btrfs_space_info *parent;
+ struct btrfs_space_info *sub_group[BTRFS_SPACE_INFO_SUB_GROUP_MAX];
+ int subgroup_id;
spinlock_t lock;
u64 total_bytes; /* total bytes in the space,
@@ -1792,15 +1792,25 @@ void btrfs_sysfs_remove_space_info(struct btrfs_space_info *space_info)
kobject_put(&space_info->kobj);
}
-static const char *alloc_name(u64 flags)
+static const char *alloc_name(struct btrfs_space_info *space_info)
{
+ u64 flags = space_info->flags;
+
switch (flags) {
case BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA:
return "mixed";
case BTRFS_BLOCK_GROUP_METADATA:
return "metadata";
case BTRFS_BLOCK_GROUP_DATA:
- return "data";
+ switch (space_info->subgroup_id) {
+ case SUB_GROUP_PRIMARY:
+ return "data";
+ case SUB_GROUP_DATA_RELOC:
+ return "data-reloc";
+ default:
+ WARN_ON_ONCE(1);
+ return "data (unknown sub-group)";
+ }
case BTRFS_BLOCK_GROUP_SYSTEM:
return "system";
default:
@@ -1820,7 +1830,7 @@ int btrfs_sysfs_add_space_info_type(struct btrfs_fs_info *fs_info,
ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype,
fs_info->space_info_kobj, "%s",
- alloc_name(space_info->flags));
+ alloc_name(space_info));
if (ret) {
kobject_put(&space_info->kobj);
return ret;
Current code assumes we have only one space_info for each block group type (DATA, METADATA, and SYSTEM). We sometime needs multiple space_info to manage special block groups. One example is handling the data relocation block group for the zoned mode. That block group is dedicated for writing relocated data and we cannot allocate any regular extent from that block group, which is implemented in the zoned extent allocator. That block group still belongs to the normal data space_info. So, when all the normal data block groups are full and there are some free space in the dedicated block group, the space_info looks to have some free space, while it cannot allocate normal extent anymore. That results in a strange ENOSPC error. We need to have a space_info for the relocation data block group to represent the situation properly. This commit adds a basic infrastructure for having a "sub-group" of a space_info: creation and removing. A sub-group space_info belongs to one of the primary space_infos and has the same flags as its parent. Currently, the sub-group is only implemented for the relocation data space_info. In the future, we can also implement the space_info for the tree-log block group. Or, it could be useful to implement tiered storage for btrfs e.g, by implementing a sub-group space_info for block groups resides on a fast storage. Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> --- fs/btrfs/block-group.c | 6 ++++++ fs/btrfs/space-info.c | 20 ++++++++++++++++++-- fs/btrfs/space-info.h | 8 ++++++++ fs/btrfs/sysfs.c | 16 +++++++++++++--- 4 files changed, 45 insertions(+), 5 deletions(-)