[v8,16/41] btrfs: track unusable bytes for zones

Message ID	97c566b91d4cd1542a5c87a2a15137d325dedb7a.1601574234.git.naohiro.aota@wdc.com (mailing list archive)
State	New, archived
Headers	show Return-Path: <SRS0=iHD6=DI=vger.kernel.org=linux-btrfs-owner@kernel.org> IronPort-SDR: Nv9rBvCByaqDZRA6BDPVmlHpeDkAErIgCQEwbnRQ7CszOnDjGEmKc3dKxlbreWysNnGuC/zS+5 gnq2Rbhy8DvJ1fB7OLWPOOqpVTRLddaXWNK0hQApLLdUV+EMvpQf9Ltef5prmApRdzYV6cS5qr T1govyj2l9I6AsZt0cczGC+jJMih1KlLstybuZ0brXc1A0nYpc9VS6KyfeWfTGbOooDB1G3hCf 5Hy9EIVGMTH+X+SKk2IAKXdXlgUY3HmxXZ2f515x6+GP/m+lrmSAThscfsrtn7wRKW775FR1rh qYo= IronPort-SDR: qn7278Kf1RgpdNtdEQ7Z10VAl3zkmqLcI06i5HxtzhzQsAk6kvKzKpXq0QTT7NTVWm7NzlRHl9 R9qHR9jYaoUw== IronPort-SDR: qp3BV39J9Hwlraz8nMlWtUKnfv9ZW/ovlUrVeCuUKt/VZQI1rXcpuDXksDrAtybvDdbjUcjZuu R3mVGAgBk4VA== WDCIronportException: Internal From: Naohiro Aota <naohiro.aota@wdc.com> To: linux-btrfs@vger.kernel.org, dsterba@suse.com Cc: hare@suse.com, linux-fsdevel@vger.kernel.org, Naohiro Aota <naohiro.aota@wdc.com> Subject: [PATCH v8 16/41] btrfs: track unusable bytes for zones Date: Fri, 2 Oct 2020 03:36:23 +0900 Message-Id: <97c566b91d4cd1542a5c87a2a15137d325dedb7a.1601574234.git.naohiro.aota@wdc.com> In-Reply-To: <dece91bca322ce44bed19f2b0f460fa5ded2e512.1601574234.git.naohiro.aota@wdc.com> References: <dece91bca322ce44bed19f2b0f460fa5ded2e512.1601574234.git.naohiro.aota@wdc.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: bulk
Series	btrfs: zoned block device support \| expand [v8,00/41] btrfs: zoned block device support [v8,01/41] block: add bio_add_zone_append_page [v8,02/41] btrfs: introduce ZONED feature flag [v8,03/41] btrfs: Get zone information of zoned block devices [v8,04/41] btrfs: Check and enable ZONED mode [v8,05/41] btrfs: introduce max_zone_append_size [v8,06/41] btrfs: disallow space_cache in ZONED mode [v8,07/41] btrfs: disallow NODATACOW in ZONED mode [v8,08/41] btrfs: disable fallocate in ZONED mode [v8,09/41] btrfs: disallow mixed-bg in ZONED mode [v8,10/41] btrfs: disallow inode_cache in ZONED mode [v8,11/41] btrfs: implement log-structured superblock for ZONED mode [v8,12/41] btrfs: implement zoned chunk allocator [v8,13/41] btrfs: verify device extent is aligned to zone [v8,14/41] btrfs: load zone's alloction offset [v8,15/41] btrfs: emulate write pointer for conventional zones [v8,16/41] btrfs: track unusable bytes for zones [v8,17/41] btrfs: do sequential extent allocation in ZONED mode [v8,18/41] btrfs: reset zones of unused block groups [v8,19/41] btrfs: redirty released extent buffers in ZONED mode [v8,20/41] btrfs: extract page adding function [v8,21/41] btrfs: use bio_add_zone_append_page for zoned btrfs [v8,22/41] btrfs: handle REQ_OP_ZONE_APPEND as writing [v8,23/41] btrfs: split ordered extent when bio is sent [v8,24/41] btrfs: extend btrfs_rmap_block for specifying a device [v8,25/41] btrfs: use ZONE_APPEND write for ZONED btrfs [v8,26/41] btrfs: enable zone append writing for direct IO [v8,27/41] btrfs: introduce dedicated data write path for ZONED mode [v8,28/41] btrfs: serialize meta IOs on ZONED mode [v8,29/41] btrfs: wait existing extents before truncating [v8,30/41] btrfs: avoid async metadata checksum on ZONED mode [v8,31/41] btrfs: mark block groups to copy for device-replace [v8,32/41] btrfs: implement cloning for ZONED device-replace [v8,33/41] btrfs: implement copying for ZONED device-replace [v8,34/41] btrfs: support dev-replace in ZONED mode [v8,35/41] btrfs: enable relocation in ZONED mode [v8,36/41] btrfs: relocate block group to repair IO failure in ZONED [v8,37/41] btrfs: split alloc_log_tree() [v8,38/41] btrfs: extend zoned allocator to use dedicated tree-log block group [v8,39/41] btrfs: serialize log transaction on ZONED mode [v8,40/41] btrfs: reorder log node allocation [v8,41/41] btrfs: enable to mount ZONED incompat flag

diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 6de3d95ab9d9..e68e477d9160 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1080,12 +1080,15 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans, WARN_ON(block_group->space_info->total_bytes < block_group->length); WARN_ON(block_group->space_info->bytes_readonly - < block_group->length); + < block_group->length - block_group->zone_unusable); + WARN_ON(block_group->space_info->bytes_zone_unusable + < block_group->zone_unusable); WARN_ON(block_group->space_info->disk_total < block_group->length * factor); } block_group->space_info->total_bytes -= block_group->length; - block_group->space_info->bytes_readonly -= block_group->length; + block_group->space_info->bytes_readonly -= + (block_group->length - block_group->zone_unusable); block_group->space_info->disk_total -= block_group->length * factor; spin_unlock(&block_group->space_info->lock); @@ -1229,7 +1232,7 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force) } num_bytes = cache->length - cache->reserved - cache->pinned - - cache->bytes_super - cache->used; + cache->bytes_super - cache->zone_unusable - cache->used; /* * Data never overcommits, even in mixed mode, so do just the straight @@ -1973,6 +1976,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, btrfs_free_excluded_extents(cache); } + btrfs_calc_zone_unusable(cache); + ret = btrfs_add_block_group_cache(info, cache); if (ret) { btrfs_remove_free_space_cache(cache); @@ -1980,7 +1985,8 @@ static int read_one_block_group(struct btrfs_fs_info *info, } trace_btrfs_add_block_group(info, cache, 0); btrfs_update_space_info(info, cache->flags, cache->length, - cache->used, cache->bytes_super, &space_info); + cache->used, cache->bytes_super, + cache->zone_unusable, &space_info); cache->space_info = space_info; @@ -2217,7 +2223,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used, */ trace_btrfs_add_block_group(fs_info, cache, 1); btrfs_update_space_info(fs_info, cache->flags, size, bytes_used, - cache->bytes_super, &cache->space_info); + cache->bytes_super, 0, &cache->space_info); btrfs_update_global_block_rsv(fs_info); link_block_group(cache); @@ -2325,7 +2331,8 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache) spin_lock(&cache->lock); if (!--cache->ro) { num_bytes = cache->length - cache->reserved - - cache->pinned - cache->bytes_super - cache->used; + cache->pinned - cache->bytes_super - + cache->zone_unusable - cache->used; sinfo->bytes_readonly -= num_bytes; list_del_init(&cache->ro_list); } diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index 14e3043c9ce7..5be47f4bfea7 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -189,6 +189,7 @@ struct btrfs_block_group { * allocation. This is used only with ZONED mode enabled. */ u64 alloc_offset; + u64 zone_unusable; }; static inline u64 btrfs_block_group_end(struct btrfs_block_group *block_group) diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 3b21fee13e77..051e61f16cbe 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -34,6 +34,7 @@ #include "block-group.h" #include "discard.h" #include "rcu-string.h" +#include "zoned.h" #undef SCRAMBLE_DELAYED_REFS @@ -2807,9 +2808,11 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, cache = btrfs_lookup_block_group(fs_info, start); BUG_ON(!cache); /* Logic error */ - cluster = fetch_cluster_info(fs_info, - cache->space_info, - &empty_cluster); + if (!btrfs_fs_incompat(fs_info, ZONED)) + cluster = fetch_cluster_info(fs_info, + cache->space_info, + &empty_cluster); + empty_cluster <<= 1; } @@ -2846,7 +2849,11 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info, space_info->max_extent_size = 0; percpu_counter_add_batch(&space_info->total_bytes_pinned, -len, BTRFS_TOTAL_BYTES_PINNED_BATCH); - if (cache->ro) { + if (btrfs_fs_incompat(fs_info, ZONED)) { + /* need reset before reusing in zoned Block Group */ + space_info->bytes_zone_unusable += len; + readonly = true; + } else if (cache->ro) { space_info->bytes_readonly += len; readonly = true; } diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index af0013d3df63..65dd1538692a 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -2467,6 +2467,8 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, int ret = 0; u64 filter_bytes = bytes; + ASSERT(!btrfs_fs_incompat(fs_info, ZONED)); + info = kmem_cache_zalloc(btrfs_free_space_cachep, GFP_NOFS); if (!info) return -ENOMEM; @@ -2524,11 +2526,44 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, return ret; } +int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, + u64 bytenr, u64 size, bool used) +{ + struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl; + u64 offset = bytenr - block_group->start; + u64 to_free, to_unusable; + + spin_lock(&ctl->tree_lock); + if (!used) + to_free = size; + else if (offset >= block_group->alloc_offset) + to_free = size; + else if (offset + size <= block_group->alloc_offset) + to_free = 0; + else + to_free = offset + size - block_group->alloc_offset; + to_unusable = size - to_free; + + ctl->free_space += to_free; + block_group->zone_unusable += to_unusable; + spin_unlock(&ctl->tree_lock); + if (!used) { + spin_lock(&block_group->lock); + block_group->alloc_offset -= size; + spin_unlock(&block_group->lock); + } + return 0; +} + int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size) { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_fs_incompat(block_group->fs_info, ZONED)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2537,6 +2572,16 @@ int btrfs_add_free_space(struct btrfs_block_group *block_group, bytenr, size, trim_state); } +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size) +{ + if (btrfs_fs_incompat(block_group->fs_info, ZONED)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + false); + + return btrfs_add_free_space(block_group, bytenr, size); +} + /* * This is a subtle distinction because when adding free space back in general, * we want it to be added as untrimmed for async. But in the case where we add @@ -2547,6 +2592,10 @@ int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, { enum btrfs_trim_state trim_state = BTRFS_TRIM_STATE_UNTRIMMED; + if (btrfs_fs_incompat(block_group->fs_info, ZONED)) + return __btrfs_add_free_space_zoned(block_group, bytenr, size, + true); + if (btrfs_test_opt(block_group->fs_info, DISCARD_SYNC) || btrfs_test_opt(block_group->fs_info, DISCARD_ASYNC)) trim_state = BTRFS_TRIM_STATE_TRIMMED; @@ -2564,6 +2613,9 @@ int btrfs_remove_free_space(struct btrfs_block_group *block_group, int ret; bool re_search = false; + if (btrfs_fs_incompat(block_group->fs_info, ZONED)) + return 0; + spin_lock(&ctl->tree_lock); again: diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h index e3d5e0ad8f8e..7081216257a8 100644 --- a/fs/btrfs/free-space-cache.h +++ b/fs/btrfs/free-space-cache.h @@ -114,8 +114,12 @@ int __btrfs_add_free_space(struct btrfs_fs_info *fs_info, struct btrfs_free_space_ctl *ctl, u64 bytenr, u64 size, enum btrfs_trim_state trim_state); +int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group, + u64 bytenr, u64 size, bool used); int btrfs_add_free_space(struct btrfs_block_group *block_group, u64 bytenr, u64 size); +int btrfs_add_free_space_unused(struct btrfs_block_group *block_group, + u64 bytenr, u64 size); int btrfs_add_free_space_async_trimmed(struct btrfs_block_group *block_group, u64 bytenr, u64 size); int btrfs_remove_free_space(struct btrfs_block_group *block_group, diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c index 64099565ab8f..bbbf3c1412a4 100644 --- a/fs/btrfs/space-info.c +++ b/fs/btrfs/space-info.c @@ -163,6 +163,7 @@ u64 __pure btrfs_space_info_used(struct btrfs_space_info *s_info, ASSERT(s_info); return s_info->bytes_used + s_info->bytes_reserved + s_info->bytes_pinned + s_info->bytes_readonly + + s_info->bytes_zone_unusable + (may_use_included ? s_info->bytes_may_use : 0); } @@ -257,7 +258,7 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info) void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info) { struct btrfs_space_info *found; @@ -273,6 +274,7 @@ void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, found->bytes_used += bytes_used; found->disk_used += bytes_used * factor; found->bytes_readonly += bytes_readonly; + found->bytes_zone_unusable += bytes_zone_unusable; if (total_bytes > 0) found->full = 0; btrfs_try_granting_tickets(info, found); @@ -422,10 +424,10 @@ static void __btrfs_dump_space_info(struct btrfs_fs_info *fs_info, info->total_bytes - btrfs_space_info_used(info, true), info->full ? "" : "not "); btrfs_info(fs_info, - "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu", + "space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu zone_unusable=%llu", info->total_bytes, info->bytes_used, info->bytes_pinned, info->bytes_reserved, info->bytes_may_use, - info->bytes_readonly); + info->bytes_readonly, info->bytes_zone_unusable); DUMP_BLOCK_RSV(fs_info, global_block_rsv); DUMP_BLOCK_RSV(fs_info, trans_block_rsv); @@ -454,9 +456,10 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info, list_for_each_entry(cache, &info->block_groups[index], list) { spin_lock(&cache->lock); btrfs_info(fs_info, - "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %s", + "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu zone_unusable %s", cache->start, cache->length, cache->used, cache->pinned, - cache->reserved, cache->ro ? "[readonly]" : ""); + cache->reserved, cache->zone_unusable, + cache->ro ? "[readonly]" : ""); spin_unlock(&cache->lock); btrfs_dump_free_space(cache, bytes); } diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h index 5646393b928c..ee003ffba956 100644 --- a/fs/btrfs/space-info.h +++ b/fs/btrfs/space-info.h @@ -17,6 +17,8 @@ struct btrfs_space_info { u64 bytes_may_use; /* number of bytes that may be used for delalloc/allocations */ u64 bytes_readonly; /* total bytes that are read only */ + u64 bytes_zone_unusable; /* total bytes that are unusable until + resetting the device zone */ u64 max_extent_size; /* This will hold the maximum extent size of the space info if we had an ENOSPC in the @@ -119,7 +121,7 @@ DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned"); int btrfs_init_space_info(struct btrfs_fs_info *fs_info); void btrfs_update_space_info(struct btrfs_fs_info *info, u64 flags, u64 total_bytes, u64 bytes_used, - u64 bytes_readonly, + u64 bytes_readonly, u64 bytes_zone_unusable, struct btrfs_space_info **space_info); struct btrfs_space_info *btrfs_find_space_info(struct btrfs_fs_info *info, u64 flags); diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c index 828006020bbd..ea679803da9b 100644 --- a/fs/btrfs/sysfs.c +++ b/fs/btrfs/sysfs.c @@ -635,6 +635,7 @@ SPACE_INFO_ATTR(bytes_pinned); SPACE_INFO_ATTR(bytes_reserved); SPACE_INFO_ATTR(bytes_may_use); SPACE_INFO_ATTR(bytes_readonly); +SPACE_INFO_ATTR(bytes_zone_unusable); SPACE_INFO_ATTR(disk_used); SPACE_INFO_ATTR(disk_total); BTRFS_ATTR(space_info, total_bytes_pinned, @@ -648,6 +649,7 @@ static struct attribute *space_info_attrs[] = { BTRFS_ATTR_PTR(space_info, bytes_reserved), BTRFS_ATTR_PTR(space_info, bytes_may_use), BTRFS_ATTR_PTR(space_info, bytes_readonly), + BTRFS_ATTR_PTR(space_info, bytes_zone_unusable), BTRFS_ATTR_PTR(space_info, disk_used), BTRFS_ATTR_PTR(space_info, disk_total), BTRFS_ATTR_PTR(space_info, total_bytes_pinned), diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c index 3f65da0c4942..266daf7d60b7 100644 --- a/fs/btrfs/zoned.c +++ b/fs/btrfs/zoned.c @@ -995,3 +995,25 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache) return ret; } + +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) +{ + u64 unusable, free; + + if (!btrfs_fs_incompat(cache->fs_info, ZONED)) + return; + + WARN_ON(cache->bytes_super != 0); + unusable = cache->alloc_offset - cache->used; + free = cache->length - cache->alloc_offset; + /* we only need ->free_space in ALLOC_SEQ BGs */ + cache->last_byte_to_unpin = (u64)-1; + cache->cached = BTRFS_CACHE_FINISHED; + cache->free_space_ctl->free_space = free; + cache->zone_unusable = unusable; + /* + * Should not have any excluded extents. Just + * in case, though. + */ + btrfs_free_excluded_extents(cache); +} diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h index 3e05a526f0fa..ab048176a397 100644 --- a/fs/btrfs/zoned.h +++ b/fs/btrfs/zoned.h @@ -46,6 +46,7 @@ int btrfs_reset_device_zone(struct btrfs_device *device, u64 physical, u64 length, u64 *bytes); int btrfs_ensure_empty_zones(struct btrfs_device *device, u64 start, u64 size); int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache); +void btrfs_calc_zone_unusable(struct btrfs_block_group *cache); #else /* CONFIG_BLK_DEV_ZONED */ static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone) @@ -111,6 +112,7 @@ static inline int btrfs_load_block_group_zone_info( { return 0; } +static inline void btrfs_calc_zone_unusable(struct btrfs_block_group *cache) { } #endif static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)

[v8,16/41] btrfs: track unusable bytes for zones

Commit Message

Patch