diff options
Diffstat (limited to 'fs/btrfs/space-info.c')
| -rw-r--r-- | fs/btrfs/space-info.c | 255 |
1 files changed, 184 insertions, 71 deletions
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index d5a9cd8a4fd8..d9087aa81b21 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 -#include "linux/spinlock.h" +#include <linux/spinlock.h> #include <linux/minmax.h> #include "misc.h" #include "ctree.h" @@ -14,6 +14,7 @@ #include "fs.h" #include "accessors.h" #include "extent-tree.h" +#include "zoned.h" /* * HOW DOES SPACE RESERVATION WORK @@ -49,11 +50,11 @@ * num_bytes we want to reserve. * * ->reserve - * space_info->bytes_may_reserve += num_bytes + * space_info->bytes_may_use += num_bytes * * ->extent allocation * Call btrfs_add_reserved_bytes() which does - * space_info->bytes_may_reserve -= num_bytes + * space_info->bytes_may_use -= num_bytes * space_info->bytes_reserved += extent_bytes * * ->insert reference @@ -127,6 +128,14 @@ * churn a lot and we can avoid making some extent tree modifications if we * are able to delay for as long as possible. * + * RESET_ZONES + * This state works only for the zoned mode. On the zoned mode, we cannot + * reuse once allocated then freed region until we reset the zone, due to + * the sequential write zone requirement. The RESET_ZONES state resets the + * zones of an unused block group and let us reuse the space. The reusing + * is faster than removing the block group and allocating another block + * group on the zones. + * * ALLOC_CHUNK * We will skip this the first time through space reservation, because of * overcommit and we don't want to have a lot of useless metadata space when @@ -225,19 +234,11 @@ void btrfs_update_space_info_chunk_size(struct btrfs_space_info *space_info, WRITE_ONCE(space_info->chunk_size, chunk_size); } -static int create_space_info(struct btrfs_fs_info *info, u64 flags) +static void init_space_info(struct btrfs_fs_info *info, + struct btrfs_space_info *space_info, u64 flags) { - - struct btrfs_space_info *space_info; - int i; - int ret; - - space_info = kzalloc(sizeof(*space_info), GFP_NOFS); - if (!space_info) - return -ENOMEM; - space_info->fs_info = info; - for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) + for (int i = 0; i < BTRFS_NR_RAID_TYPES; i++) INIT_LIST_HEAD(&space_info->block_groups[i]); init_rwsem(&space_info->groups_sem); spin_lock_init(&space_info->lock); @@ -248,9 +249,64 @@ static int create_space_info(struct btrfs_fs_info *info, u64 flags) 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 = BTRFS_SUB_GROUP_PRIMARY; if (btrfs_is_zoned(info)) space_info->bg_reclaim_threshold = BTRFS_DEFAULT_ZONED_RECLAIM_THRESH; +} + +static int create_space_info_sub_group(struct btrfs_space_info *parent, u64 flags, + enum btrfs_space_info_sub_group id, int index) +{ + struct btrfs_fs_info *fs_info = parent->fs_info; + struct btrfs_space_info *sub_group; + int ret; + + ASSERT(parent->subgroup_id == BTRFS_SUB_GROUP_PRIMARY); + ASSERT(id != BTRFS_SUB_GROUP_PRIMARY); + + sub_group = kzalloc(sizeof(*sub_group), GFP_NOFS); + if (!sub_group) + return -ENOMEM; + + init_space_info(fs_info, sub_group, flags); + parent->sub_group[index] = sub_group; + sub_group->parent = parent; + sub_group->subgroup_id = id; + + ret = btrfs_sysfs_add_space_info_type(fs_info, sub_group); + if (ret) { + kfree(sub_group); + parent->sub_group[index] = NULL; + } + return ret; +} + +static int create_space_info(struct btrfs_fs_info *info, u64 flags) +{ + + struct btrfs_space_info *space_info; + int ret = 0; + + space_info = kzalloc(sizeof(*space_info), GFP_NOFS); + if (!space_info) + return -ENOMEM; + + init_space_info(info, space_info, flags); + + if (btrfs_is_zoned(info)) { + if (flags & BTRFS_BLOCK_GROUP_DATA) + ret = create_space_info_sub_group(space_info, flags, + BTRFS_SUB_GROUP_DATA_RELOC, + 0); + else if (flags & BTRFS_BLOCK_GROUP_METADATA) + ret = create_space_info_sub_group(space_info, flags, + BTRFS_SUB_GROUP_TREELOG, + 0); + + if (ret) + return ret; + } ret = btrfs_sysfs_add_space_info_type(info, space_info); if (ret) @@ -303,31 +359,29 @@ out: void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info, struct btrfs_block_group *block_group) { - struct btrfs_space_info *found; + struct btrfs_space_info *space_info = block_group->space_info; int factor, index; factor = btrfs_bg_type_to_factor(block_group->flags); - found = btrfs_find_space_info(info, block_group->flags); - ASSERT(found); - spin_lock(&found->lock); - found->total_bytes += block_group->length; - found->disk_total += block_group->length * factor; - found->bytes_used += block_group->used; - found->disk_used += block_group->used * factor; - found->bytes_readonly += block_group->bytes_super; - btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable); + spin_lock(&space_info->lock); + space_info->total_bytes += block_group->length; + space_info->disk_total += block_group->length * factor; + space_info->bytes_used += block_group->used; + space_info->disk_used += block_group->used * factor; + space_info->bytes_readonly += block_group->bytes_super; + btrfs_space_info_update_bytes_zone_unusable(space_info, block_group->zone_unusable); if (block_group->length > 0) - found->full = 0; - btrfs_try_granting_tickets(info, found); - spin_unlock(&found->lock); + space_info->full = 0; + btrfs_try_granting_tickets(info, space_info); + spin_unlock(&space_info->lock); - block_group->space_info = found; + block_group->space_info = space_info; index = btrfs_bg_flags_to_raid_index(block_group->flags); - down_write(&found->groups_sem); - list_add_tail(&block_group->list, &found->block_groups[index]); - up_write(&found->groups_sem); + down_write(&space_info->groups_sem); + list_add_tail(&block_group->list, &space_info->block_groups[index]); + up_write(&space_info->groups_sem); } struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, @@ -489,9 +543,7 @@ again: if ((used + ticket->bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, ticket->bytes, flush)) { - btrfs_space_info_update_bytes_may_use(fs_info, - space_info, - ticket->bytes); + btrfs_space_info_update_bytes_may_use(space_info, ticket->bytes); remove_ticket(space_info, ticket); ticket->bytes = 0; space_info->tickets_id++; @@ -549,8 +601,9 @@ 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, @@ -805,7 +858,7 @@ static void flush_space(struct btrfs_fs_info *fs_info, ret = PTR_ERR(trans); break; } - ret = btrfs_chunk_alloc(trans, + ret = btrfs_chunk_alloc(trans, space_info, btrfs_get_alloc_profile(fs_info, space_info->flags), (state == ALLOC_CHUNK) ? CHUNK_ALLOC_NO_FORCE : CHUNK_ALLOC_FORCE); @@ -834,6 +887,9 @@ static void flush_space(struct btrfs_fs_info *fs_info, */ ret = btrfs_commit_current_transaction(root); break; + case RESET_ZONES: + ret = btrfs_reset_unused_block_groups(space_info, num_bytes); + break; default: ret = -ENOSPC; break; @@ -1073,22 +1129,19 @@ static bool maybe_fail_all_tickets(struct btrfs_fs_info *fs_info, return (tickets_id != space_info->tickets_id); } -/* - * This is for normal flushers, we can wait all goddamned day if we want to. We - * will loop and continuously try to flush as long as we are making progress. - * We count progress as clearing off tickets each time we have to loop. - */ -static void btrfs_async_reclaim_metadata_space(struct work_struct *work) +static void do_async_reclaim_metadata_space(struct btrfs_space_info *space_info) { - struct btrfs_fs_info *fs_info; - struct btrfs_space_info *space_info; + struct btrfs_fs_info *fs_info = space_info->fs_info; u64 to_reclaim; enum btrfs_flush_state flush_state; int commit_cycles = 0; u64 last_tickets_id; + enum btrfs_flush_state final_state; - fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work); - space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + if (btrfs_is_zoned(fs_info)) + final_state = RESET_ZONES; + else + final_state = COMMIT_TRANS; spin_lock(&space_info->lock); to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info); @@ -1141,7 +1194,7 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) if (flush_state == ALLOC_CHUNK_FORCE && !commit_cycles) flush_state++; - if (flush_state > COMMIT_TRANS) { + if (flush_state > final_state) { commit_cycles++; if (commit_cycles > 2) { if (maybe_fail_all_tickets(fs_info, space_info)) { @@ -1155,7 +1208,26 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work) } } spin_unlock(&space_info->lock); - } while (flush_state <= COMMIT_TRANS); + } while (flush_state <= final_state); +} + +/* + * This is for normal flushers, it can wait as much time as needed. We will + * loop and continuously try to flush as long as we are making progress. We + * count progress as clearing off tickets each time we have to loop. + */ +static void btrfs_async_reclaim_metadata_space(struct work_struct *work) +{ + struct btrfs_fs_info *fs_info; + struct btrfs_space_info *space_info; + + fs_info = container_of(work, struct btrfs_fs_info, async_reclaim_work); + space_info = btrfs_find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA); + do_async_reclaim_metadata_space(space_info); + for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) { + if (space_info->sub_group[i]) + do_async_reclaim_metadata_space(space_info->sub_group[i]); + } } /* @@ -1279,13 +1351,17 @@ static void btrfs_preempt_reclaim_metadata_space(struct work_struct *work) * If we are freeing inodes, we want to make sure all delayed iputs have * completed, because they could have been on an inode with i_nlink == 0, and * thus have been truncated and freed up space. But again this space is not - * immediately re-usable, it comes in the form of a delayed ref, which must be + * immediately reusable, it comes in the form of a delayed ref, which must be * run and then the transaction must be committed. * * COMMIT_TRANS * This is where we reclaim all of the pinned space generated by running the * iputs * + * RESET_ZONES + * This state works only for the zoned mode. We scan the unused block group + * list and reset the zones and reuse the block group. + * * ALLOC_CHUNK_FORCE * For data we start with alloc chunk force, however we could have been full * before, and then the transaction commit could have freed new block groups, @@ -1295,19 +1371,16 @@ static const enum btrfs_flush_state data_flush_states[] = { FLUSH_DELALLOC_FULL, RUN_DELAYED_IPUTS, COMMIT_TRANS, + RESET_ZONES, ALLOC_CHUNK_FORCE, }; -static void btrfs_async_reclaim_data_space(struct work_struct *work) +static void do_async_reclaim_data_space(struct btrfs_space_info *space_info) { - struct btrfs_fs_info *fs_info; - struct btrfs_space_info *space_info; + struct btrfs_fs_info *fs_info = space_info->fs_info; u64 last_tickets_id; enum btrfs_flush_state flush_state = 0; - fs_info = container_of(work, struct btrfs_fs_info, async_data_reclaim_work); - space_info = fs_info->data_sinfo; - spin_lock(&space_info->lock); if (list_empty(&space_info->tickets)) { space_info->flush = 0; @@ -1375,6 +1448,19 @@ aborted_fs: spin_unlock(&space_info->lock); } +static void btrfs_async_reclaim_data_space(struct work_struct *work) +{ + struct btrfs_fs_info *fs_info; + struct btrfs_space_info *space_info; + + fs_info = container_of(work, struct btrfs_fs_info, async_data_reclaim_work); + space_info = fs_info->data_sinfo; + do_async_reclaim_data_space(space_info); + for (int i = 0; i < BTRFS_SPACE_INFO_SUB_GROUP_MAX; i++) + if (space_info->sub_group[i]) + do_async_reclaim_data_space(space_info->sub_group[i]); +} + void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) { INIT_WORK(&fs_info->async_reclaim_work, btrfs_async_reclaim_metadata_space); @@ -1386,6 +1472,7 @@ void btrfs_init_async_reclaim_work(struct btrfs_fs_info *fs_info) static const enum btrfs_flush_state priority_flush_states[] = { FLUSH_DELAYED_ITEMS_NR, FLUSH_DELAYED_ITEMS, + RESET_ZONES, ALLOC_CHUNK, }; @@ -1399,6 +1486,7 @@ static const enum btrfs_flush_state evict_flush_states[] = { FLUSH_DELALLOC_FULL, ALLOC_CHUNK, COMMIT_TRANS, + RESET_ZONES, }; static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info, @@ -1488,8 +1576,7 @@ static void priority_reclaim_data_space(struct btrfs_fs_info *fs_info, spin_unlock(&space_info->lock); } -static void wait_reserve_ticket(struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, +static void wait_reserve_ticket(struct btrfs_space_info *space_info, struct reserve_ticket *ticket) { @@ -1547,7 +1634,7 @@ static int handle_reserve_ticket(struct btrfs_fs_info *fs_info, case BTRFS_RESERVE_FLUSH_DATA: case BTRFS_RESERVE_FLUSH_ALL: case BTRFS_RESERVE_FLUSH_ALL_STEAL: - wait_reserve_ticket(fs_info, space_info, ticket); + wait_reserve_ticket(space_info, ticket); break; case BTRFS_RESERVE_FLUSH_LIMIT: priority_reclaim_metadata_space(fs_info, space_info, ticket, @@ -1691,8 +1778,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, if (!pending_tickets && ((used + orig_bytes <= space_info->total_bytes) || btrfs_can_overcommit(fs_info, space_info, orig_bytes, flush))) { - btrfs_space_info_update_bytes_may_use(fs_info, space_info, - orig_bytes); + btrfs_space_info_update_bytes_may_use(space_info, orig_bytes); ret = 0; } @@ -1704,8 +1790,7 @@ static int __reserve_bytes(struct btrfs_fs_info *fs_info, if (ret && unlikely(flush == BTRFS_RESERVE_FLUSH_EMERGENCY)) { used = btrfs_space_info_used(space_info, false); if (used + orig_bytes <= space_info->total_bytes) { - btrfs_space_info_update_bytes_may_use(fs_info, space_info, - orig_bytes); + btrfs_space_info_update_bytes_may_use(space_info, orig_bytes); ret = 0; } } @@ -1817,10 +1902,10 @@ int btrfs_reserve_metadata_bytes(struct btrfs_fs_info *fs_info, * This will reserve bytes from the data space info. If there is not enough * space then we will attempt to flush space as specified by flush. */ -int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, +int btrfs_reserve_data_bytes(struct btrfs_space_info *space_info, u64 bytes, enum btrfs_reserve_flush_enum flush) { - struct btrfs_space_info *data_sinfo = fs_info->data_sinfo; + struct btrfs_fs_info *fs_info = space_info->fs_info; int ret; ASSERT(flush == BTRFS_RESERVE_FLUSH_DATA || @@ -1828,12 +1913,12 @@ int btrfs_reserve_data_bytes(struct btrfs_fs_info *fs_info, u64 bytes, flush == BTRFS_RESERVE_NO_FLUSH); ASSERT(!current->journal_info || flush != BTRFS_RESERVE_FLUSH_DATA); - ret = __reserve_bytes(fs_info, data_sinfo, bytes, flush); + ret = __reserve_bytes(fs_info, space_info, bytes, flush); if (ret == -ENOSPC) { trace_btrfs_space_reservation(fs_info, "space_info:enospc", - data_sinfo->flags, bytes, 1); + space_info->flags, bytes, 1); if (btrfs_test_opt(fs_info, ENOSPC_DEBUG)) - btrfs_dump_space_info(fs_info, data_sinfo, bytes, 0); + btrfs_dump_space_info(fs_info, space_info, bytes, 0); } return ret; } @@ -1984,8 +2069,7 @@ static bool is_reclaim_urgent(struct btrfs_space_info *space_info) return unalloc < data_chunk_size; } -static void do_reclaim_sweep(const struct btrfs_fs_info *fs_info, - struct btrfs_space_info *space_info, int raid) +static void do_reclaim_sweep(struct btrfs_space_info *space_info, int raid) { struct btrfs_block_group *bg; int thresh_pct; @@ -2081,6 +2165,35 @@ void btrfs_reclaim_sweep(const struct btrfs_fs_info *fs_info) if (!btrfs_should_periodic_reclaim(space_info)) continue; for (raid = 0; raid < BTRFS_NR_RAID_TYPES; raid++) - do_reclaim_sweep(fs_info, space_info, raid); + do_reclaim_sweep(space_info, raid); + } +} + +void btrfs_return_free_space(struct btrfs_space_info *space_info, u64 len) +{ + struct btrfs_fs_info *fs_info = space_info->fs_info; + struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv; + + lockdep_assert_held(&space_info->lock); + + /* Prioritize the global reservation to receive the freed space. */ + if (global_rsv->space_info != space_info) + goto grant; + + spin_lock(&global_rsv->lock); + if (!global_rsv->full) { + u64 to_add = min(len, global_rsv->size - global_rsv->reserved); + + global_rsv->reserved += to_add; + btrfs_space_info_update_bytes_may_use(space_info, to_add); + if (global_rsv->reserved >= global_rsv->size) + global_rsv->full = 1; + len -= to_add; } + spin_unlock(&global_rsv->lock); + +grant: + /* Add to any tickets we may have. */ + if (len) + btrfs_try_granting_tickets(fs_info, space_info); } |