| Message ID | 355f307dca7ea6da7db20038d46b3ef7a2cedd4f.1742364593.git.naohiro.aota@wdc.com (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | btrfs: zoned: split out space_info for dedicated block groups | expand |
On 19.03.25 07:17, Naohiro Aota wrote: > diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c > index 56c3aa0e7fe2..f5f0485d37b6 100644 > --- a/fs/btrfs/block-group.c > +++ b/fs/btrfs/block-group.c > @@ -4537,6 +4537,12 @@ 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); you could move the loop into check_removing_space_info(). As long as sub_groups don't have sub_groups the recursion won't be too bad for the kernel's stack constraints. > list_del(&space_info->list); > btrfs_sysfs_remove_space_info(space_info); > diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c > index c421161f4237..53eea3cd2bf3 100644 > --- a/fs/btrfs/space-info.c > +++ b/fs/btrfs/space-info.c > @@ -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 +267,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) > > init_space_info(info, space_info, flags); > > + if (btrfs_is_zoned(info)) { > + if (flags & BTRFS_BLOCK_GROUP_DATA) { > + struct btrfs_space_info *reloc = kzalloc(sizeof(*reloc), GFP_NOFS); > + > + if (!reloc) > + return -ENOMEM; I'd prefer: struct btrfs_space_info *reloc; reloc = kzalloc(sizeof(*reloc), GFP_NOFS); if (!reloc) return -ENOMEM; Also maybe add as the next patch also adds a case for METADATA, maybe factor that out into: if (btrfs_is_zoned(info)) { ret = btrfs_create_zone_sub_space_info(info); /* or create_sub_info_for_zoned? */ if (ret) return ret; } > + 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); > + } > + } > +
On Thu, Mar 20, 2025 at 04:11:27PM +0000, Johannes Thumshirn wrote: > > + if (flags & BTRFS_BLOCK_GROUP_DATA) { > > + struct btrfs_space_info *reloc = kzalloc(sizeof(*reloc), GFP_NOFS); > > + > > + if (!reloc) > > + return -ENOMEM; > > I'd prefer: > > struct btrfs_space_info *reloc; > > reloc = kzalloc(sizeof(*reloc), GFP_NOFS); > if (!reloc) > return -ENOMEM; Yes, only simple initializations should be in the declaration block, e.g. integer calculations or pointer operaions. Allocations should be always separated.
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 56c3aa0e7fe2..f5f0485d37b6 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -4537,6 +4537,12 @@ 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); diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index c421161f4237..53eea3cd2bf3 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -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 +267,22 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) init_space_info(info, space_info, flags); + if (btrfs_is_zoned(info)) { + if (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 +578,9 @@ 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, diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 7459b4eb99cd..64641885babd 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -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, diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index b9af74498b0c..92caa5d09e2f 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -1930,15 +1930,25 @@ 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: @@ -1958,7 +1968,7 @@ 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. This commit first introduces the relocation data sub-space_info, and the next commit will introduce tree-log sub-space_info. In the future, 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 | 22 ++++++++++++++++++++-- fs/btrfs/space-info.h | 8 ++++++++ fs/btrfs/sysfs.c | 16 +++++++++++++--- 4 files changed, 47 insertions(+), 5 deletions(-)