In zoned btrfs a region that was once written then freed is not usable
until we reset the underlying zone. So we need to distinguish such
unusable space from usable free space.
Therefore we need to introduce the "zone_unusable" field to the block
group structure, and "bytes_zone_unusable" to the space_info structure to
track the unusable space.
Pinned bytes are always reclaimed to the unusable space. But, when an
allocated region is returned before using e.g., the block group becomes
read-only between allocation time and reservation time, we can safely
return the region to the block group. For the situation, this commit
introduces "btrfs_add_free_space_unused". This behaves the same as
btrfs_add_free_space() on regular btrfs. On zoned btrfs, it rewinds the
allocation offset.
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
fs/btrfs/block-group.c | 39 ++++++++++++++-------
fs/btrfs/block-group.h | 1 +
fs/btrfs/extent-tree.c | 10 +++++-
fs/btrfs/free-space-cache.c | 67 +++++++++++++++++++++++++++++++++++++
fs/btrfs/free-space-cache.h | 2 ++
fs/btrfs/space-info.c | 13 ++++---
fs/btrfs/space-info.h | 4 ++-
fs/btrfs/sysfs.c | 2 ++
fs/btrfs/zoned.c | 24 +++++++++++++
fs/btrfs/zoned.h | 3 ++
10 files changed, 146 insertions(+), 19 deletions(-)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index 7c210aa5f25f..487511e3f000 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -1001,12 +1001,17 @@ 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->bytes_zone_unusable -=
+ block_group->zone_unusable;
block_group->space_info->disk_total -= block_group->length * factor;
spin_unlock(&block_group->space_info->lock);
@@ -1150,7 +1155,7 @@ 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
@@ -1863,12 +1868,20 @@ static int read_one_block_group(struct btrfs_fs_info *info,
}
/*
- * Check for two cases, either we are full, and therefore don't need
- * to bother with the caching work since we won't find any space, or we
- * are empty, and we can just add all the space in and be done with it.
- * This saves us _a_lot_ of time, particularly in the full case.
+ * For zoned btrfs, space after the allocation offset is the only
+ * free space for a block group. So, we don't need any caching
+ * work. btrfs_calc_zone_unusable() will set the amount of free
+ * space and zone_unusable space.
+ *
+ * For regular btrfs, check for two cases, either we are full, and
+ * therefore don't need to bother with the caching work since we
+ * won't find any space, or we are empty, and we can just add all
+ * the space in and be done with it. This saves us _a_lot_ of
+ * time, particularly in the full case.
*/
- if (cache->length == cache->used) {
+ if (btrfs_is_zoned(info)) {
+ btrfs_calc_zone_unusable(cache);
+ } else if (cache->length == cache->used) {
cache->last_byte_to_unpin = (u64)-1;
cache->cached = BTRFS_CACHE_FINISHED;
btrfs_free_excluded_extents(cache);
@@ -1887,7 +1900,8 @@ 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;
@@ -1943,7 +1957,7 @@ static int fill_dummy_bgs(struct btrfs_fs_info *fs_info)
break;
}
btrfs_update_space_info(fs_info, bg->flags, em->len, em->len,
- 0, &space_info);
+ 0, 0, &space_info);
bg->space_info = space_info;
link_block_group(bg);
@@ -2185,7 +2199,7 @@ 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);
@@ -2293,7 +2307,8 @@ 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 9d026ab1768d..0f3c62c561bc 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 30b1a630dc2f..071a521927e6 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
@@ -2725,6 +2726,9 @@ fetch_cluster_info(struct btrfs_fs_info *fs_info,
{
struct btrfs_free_cluster *ret = NULL;
+ if (btrfs_is_zoned(fs_info))
+ return NULL;
+
