btrfs: zoned: reserve data_reloc block group on mount
PATCH v4 1/1 btrfs: zoned: reserve data_reloc block group on mount
From: Johannes Thumshirn <[email protected]>
Create a block group dedicated for data relocation on mount of a zoned filesystem.
If there is already more than one empty DATA block group on mount, this one is picked for the data relocation block group, instead of a newly created one.
This is done to ensure, there is always space for performing garbage collection and the filesystem is not hitting ENOSPC under heavy overwrite workloads.
---
Changes to v3:
- Use jump label to only have search loop once (Filipe)
fs/btrfs/disk-io.c | 1 + fs/btrfs/zoned.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/zoned.h | 3 +++ 3 files changed, 65 insertions(+)
fs/btrfs/disk-io.c +1 -0
@@ -3562,6 +3562,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sysfs; } +btrfs_zoned_reserve_data_reloc_bg (fs_info);btrfs_free_zone_cache (fs_info);btrfs_check_active_zone_reservation (fs_info);
fs/btrfs/zoned.c +61 -0
73 lines not on this page · raw message
fs/btrfs/zoned.h +3 -0
@@ -88,6 +88,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical,void btrfs_schedule_zone_finish_bg (struct btrfs_block_group *bg,struct extent_buffer *eb);void btrfs_clear_data_reloc_bg (struct btrfs_block_group *bg); +void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info);void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info);bool btrfs_zoned_should_reclaim (const struct btrfs_fs_info *fs_info); void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
@@ -241,6 +242,8 @@ static inline void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,static inline void btrfs_clear_data_reloc_bg (struct btrfs_block_group *bg) { } +static inline void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info) { } +static inline void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info) { }static inline bool btrfs_zoned_should_reclaim (const struct btrfs_fs_info *fs_info)
Signature · 1 line
2.49.0
Quoted 9 lines · Johannes Thumshirn
From: Johannes Thumshirn <[email protected]>
Create a block group dedicated for data relocation on mount of a zoned filesystem.
If there is already more than one empty DATA block group on mount, this one is picked for the data relocation block group, instead of a newly created one.
Quoted 6 lines
This is done to ensure, there is always space for performing garbage collection and the filesystem is not hitting ENOSPC under heavy overwrite workloads.
Signed-off-by Johannes Thumshirn <[email protected]>Reviewed-by Filipe Manana <[email protected]>
Unfortunately this can result in a FS corruption if the accompanying mkfs patch is not applied.
I think it is, because I'm not waiting for the transaction to be written out in case we need to allocate a chunk. Therefor metadata on DUP can get out of sync somehow when one copy is on a sequential zone and one on a conventional zone.
Quoted 117 lines
fs/btrfs/disk-io.c | 1 + fs/btrfs/zoned.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/zoned.h | 3 +++ 3 files changed, 65 insertions(+)fs/btrfs/disk-io.c +1
-0@@ -3562,6 +3562,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sysfs; } +btrfs_zoned_reserve_data_reloc_bg (fs_info);btrfs_free_zone_cache (fs_info);btrfs_check_active_zone_reservation (fs_info);fs/btrfs/zoned.c +61
-0@@ -17,6 +17,7 @@#include "fs.h" #include "accessors.h" #include "bio.h" +#include "transaction.h" /* Maximum number of zones to report per blkdev_report_zones() call */ #define BTRFS_REPORT_NR_ZONES 4096@@ -2443,6 +2444,66 @@ void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)spin_unlock (&fs_info->relocation_bg_lock); } +void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info) +{ +struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; +struct btrfs_space_info *space_info = data_sinfo->sub_group[0 ]; +struct btrfs_trans_handle *trans; +struct btrfs_block_group *bg; +struct list_head *bg_list; +u64 alloc_flags; +bool initial = false; +bool did_chunk_alloc = false; +int index; +int ret; + +if (!btrfs_is_zoned (fs_info)) +return ; + +if (fs_info->data_reloc_bg) +return ; + +if (sb_rdonly (fs_info->sb)) +return ; + +ASSERT (space_info->subgroup_id ==BTRFS_SUB_GROUP_DATA_RELOC ); + alloc_flags =btrfs_get_alloc_profile (fs_info, space_info->flags); + index =btrfs_bg_flags_to_raid_index (alloc_flags); + + bg_list = &data_sinfo->block_groups[index]; +again: +list_for_each_entry (bg, bg_list, list) { +if (bg->used >0 ) +continue ; + +if (!initial) { + initial = true; +continue ; + } + + fs_info->data_reloc_bg = bg->start; +set_bit (BLOCK_GROUP_FLAG_ZONED_DATA_RELOC , &bg->runtime_flags); +btrfs_zone_activate (bg); + +return ; + } + +if (did_chunk_alloc) +return ; + + trans =btrfs_join_transaction (fs_info->tree_root); +if (IS_ERR (trans)) +return ; + + ret =btrfs_chunk_alloc (trans, space_info, alloc_flags,CHUNK_ALLOC_FORCE ); +btrfs_end_transaction (trans); +if (ret ==1 ) { + did_chunk_alloc = true; + bg_list = &space_info->block_groups[index]; + goto again; + } +} +void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info) {struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;fs/btrfs/zoned.h +3
-0@@ -88,6 +88,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical,void btrfs_schedule_zone_finish_bg (struct btrfs_block_group *bg,struct extent_buffer *eb);void btrfs_clear_data_reloc_bg (struct btrfs_block_group *bg); +void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info);void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info);bool btrfs_zoned_should_reclaim (const struct btrfs_fs_info *fs_info); void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,@@ -241,6 +242,8 @@ static inline void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,static inline void btrfs_clear_data_reloc_bg (struct btrfs_block_group *bg) { } +static inline void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info) { } +static inline void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info) { }static inline bool btrfs_zoned_should_reclaim (const struct btrfs_fs_info *fs_info)
Quoted 18 lines · Johannes Thumshirn
Quoted 9 lines · Johannes Thumshirn
From: Johannes Thumshirn <[email protected]>
Create a block group dedicated for data relocation on mount of a zoned filesystem.
If there is already more than one empty DATA block group on mount, this one is picked for the data relocation block group, instead of a newly created one.
Quoted 6 lines
This is done to ensure, there is always space for performing garbage collection and the filesystem is not hitting ENOSPC under heavy overwrite workloads.
Signed-off-by Johannes Thumshirn <[email protected]>Reviewed-by Filipe Manana <[email protected]>
Quoted 7 lines
Unfortunately this can result in a FS corruption if the accompanying mkfs patch is not applied.
I think it is, because I'm not waiting for the transaction to be written out in case we need to allocate a chunk. Therefor metadata on DUP can get out of sync somehow when one copy is on a sequential zone and one on a conventional zone.
Not familiar with the zone specific problems, but in order to use a new chunk, there's no need to commit a transaction.
And if for some weird reason that is a problem for the zoned case, how about committing the transaction after allocating the chunk? Does it still cause any issue?
Quoted 120 lines
Quoted 119 lines
fs/btrfs/disk-io.c | 1 + fs/btrfs/zoned.c | 61 ++++++++++++++++++++++++++++++++++++++++++++++ fs/btrfs/zoned.h | 3 +++ 3 files changed, 65 insertions(+)fs/btrfs/disk-io.c +1
-0@@ -3562,6 +3562,7 @@ int __cold open_ctree(struct super_block *sb, struct btrfs_fs_devices *fs_device goto fail_sysfs; } +btrfs_zoned_reserve_data_reloc_bg (fs_info);btrfs_free_zone_cache (fs_info);btrfs_check_active_zone_reservation (fs_info);fs/btrfs/zoned.c +61
-0@@ -17,6 +17,7 @@#include "fs.h" #include "accessors.h" #include "bio.h" +#include "transaction.h" /* Maximum number of zones to report per blkdev_report_zones() call */ #define BTRFS_REPORT_NR_ZONES 4096@@ -2443,6 +2444,66 @@ void btrfs_clear_data_reloc_bg(struct btrfs_block_group *bg)spin_unlock (&fs_info->relocation_bg_lock); } +void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info) +{ +struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; +struct btrfs_space_info *space_info = data_sinfo->sub_group[0 ]; +struct btrfs_trans_handle *trans; +struct btrfs_block_group *bg; +struct list_head *bg_list; +u64 alloc_flags; +bool initial = false; +bool did_chunk_alloc = false; +int index; +int ret; + +if (!btrfs_is_zoned (fs_info)) +return ; + +if (fs_info->data_reloc_bg) +return ; + +if (sb_rdonly (fs_info->sb)) +return ; + +ASSERT (space_info->subgroup_id ==BTRFS_SUB_GROUP_DATA_RELOC ); + alloc_flags =btrfs_get_alloc_profile (fs_info, space_info->flags); + index =btrfs_bg_flags_to_raid_index (alloc_flags); + + bg_list = &data_sinfo->block_groups[index]; +again: +list_for_each_entry (bg, bg_list, list) { +if (bg->used >0 ) +continue ; + +if (!initial) { + initial = true; +continue ; + } + + fs_info->data_reloc_bg = bg->start; +set_bit (BLOCK_GROUP_FLAG_ZONED_DATA_RELOC , &bg->runtime_flags); +btrfs_zone_activate (bg); + +return ; + } + +if (did_chunk_alloc) +return ; + + trans =btrfs_join_transaction (fs_info->tree_root); +if (IS_ERR (trans)) +return ; + + ret =btrfs_chunk_alloc (trans, space_info, alloc_flags,CHUNK_ALLOC_FORCE ); +btrfs_end_transaction (trans); +if (ret ==1 ) { + did_chunk_alloc = true; + bg_list = &space_info->block_groups[index]; + goto again; + } +} +void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info) {struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;fs/btrfs/zoned.h +3
-0@@ -88,6 +88,7 @@ void btrfs_zone_finish_endio(struct btrfs_fs_info *fs_info, u64 logical,void btrfs_schedule_zone_finish_bg (struct btrfs_block_group *bg,struct extent_buffer *eb);void btrfs_clear_data_reloc_bg (struct btrfs_block_group *bg); +void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info);void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info);bool btrfs_zoned_should_reclaim (const struct btrfs_fs_info *fs_info); void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,@@ -241,6 +242,8 @@ static inline void btrfs_schedule_zone_finish_bg(struct btrfs_block_group *bg,static inline void btrfs_clear_data_reloc_bg (struct btrfs_block_group *bg) { } +static inline void btrfs_zoned_reserve_data_reloc_bg (struct btrfs_fs_info *fs_info) { } +static inline void btrfs_free_zone_cache (struct btrfs_fs_info *fs_info) { }static inline bool btrfs_zoned_should_reclaim (const struct btrfs_fs_info *fs_info)
Quoted 28 lines · Filipe Manana
Quoted 18 lines · Johannes Thumshirn
Quoted 9 lines · Johannes Thumshirn
From: Johannes Thumshirn <[email protected]>
Create a block group dedicated for data relocation on mount of a zoned filesystem.
If there is already more than one empty DATA block group on mount, this one is picked for the data relocation block group, instead of a newly created one.
Quoted 6 lines
This is done to ensure, there is always space for performing garbage collection and the filesystem is not hitting ENOSPC under heavy overwrite workloads.
Signed-off-by Johannes Thumshirn <[email protected]>Reviewed-by Filipe Manana <[email protected]>Quoted 7 lines
Unfortunately this can result in a FS corruption if the accompanying mkfs patch is not applied.
I think it is, because I'm not waiting for the transaction to be written out in case we need to allocate a chunk. Therefor metadata on DUP can get out of sync somehow when one copy is on a sequential zone and one on a conventional zone.
Quoted 5 lines
Not familiar with the zone specific problems, but in order to use a new chunk, there's no need to commit a transaction.
And if for some weird reason that is a problem for the zoned case, how about committing the transaction after allocating the chunk? Does it still cause any issue?
AFAICT yes. And it's a very wired case that only happens on DUP metadata and the metadata bg has to be backed by a conventional and a sequential zone.
The problem is, every hypothesis I have how this could happen is invalidated by looking at the code. Basically what must happen is that more than one chunk is created backed by the same zone, which according to the code can't happen.