For metadata space on zoned btrfs, reaching ALLOC_CHUNK{,_FORCE} means we
don't have enough space left in the active_total_bytes. Before allocating a
new chunk, we can try to activate an existing block group in this case.
Also, allocating a chunk is not enough to grant a ticket for metadata space
on zoned btrfs. We need to activate the block group to increase the
active_total_bytes.
btrfs_zoned_activate_one_bg() implements the activation feature. It will
activate a block group by (maybe) finishing a block group. It will give up
activating a block group if it cannot finish any block group.
CC: stable@xxxxxxxxxxxxxxx # 5.16+
Fixes: afba2bc036b0 ("btrfs: zoned: implement active zone tracking")
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
fs/btrfs/space-info.c | 30 ++++++++++++++++++++++++
fs/btrfs/zoned.c | 53 +++++++++++++++++++++++++++++++++++++++++++
fs/btrfs/zoned.h | 10 ++++++++
3 files changed, 93 insertions(+)
diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
index 7183a8dc9b34..b99e3c32c07d 100644
--- a/fs/btrfs/space-info.c
+++ b/fs/btrfs/space-info.c
@@ -9,6 +9,7 @@
#include "ordered-data.h"
#include "transaction.h"
#include "block-group.h"
+#include "zoned.h"
/*
* HOW DOES SPACE RESERVATION WORK
@@ -724,6 +725,18 @@ static void flush_space(struct btrfs_fs_info *fs_info,
break;
case ALLOC_CHUNK:
case ALLOC_CHUNK_FORCE:
+ /*
+ * For metadata space on zoned btrfs, reaching here means we
+ * don't have enough space left in active_total_bytes. Try to
+ * activate a block group first, because we may have inactive
+ * block group already allocated.
+ */
+ ret = btrfs_zoned_activate_one_bg(fs_info, space_info, false);
+ if (ret < 0)
+ break;
+ else if (ret == 1)
+ break;
+
trans = btrfs_join_transaction(root);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
@@ -734,6 +747,23 @@ static void flush_space(struct btrfs_fs_info *fs_info,
(state == ALLOC_CHUNK) ? CHUNK_ALLOC_NO_FORCE :
CHUNK_ALLOC_FORCE);
btrfs_end_transaction(trans);
+
+ /*
+ * For metadata space on zoned btrfs, allocating a new chunk is
+ * not enough. We still need to activate the block group. Active
+ * the newly allocated block group by (maybe) finishing a block
+ * group.
+ */
+ if (ret == 1) {
+ ret = btrfs_zoned_activate_one_bg(fs_info, space_info, true);
+ /*
+ * Revert to the original ret regardless we could finish
+ * one block group or not.
+ */
+ if (ret >= 0)
+ ret = 1;
+ }
+
if (ret > 0 || ret == -ENOSPC)
ret = 0;
break;
diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
index 44a4b9e7dae9..67098f3fcd14 100644
--- a/fs/btrfs/zoned.c
+++ b/fs/btrfs/zoned.c
@@ -2225,3 +2225,56 @@ int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)
return ret < 0 ? ret : 1;
}
+
+int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info,
+ bool do_finish)
+{
+ struct btrfs_block_group *bg;
+ bool need_finish;
+ int index;
+
+ if (!btrfs_is_zoned(fs_info) || (space_info->flags & BTRFS_BLOCK_GROUP_DATA))
+ return 0;
+
+ /* No more block group to activate */
+ if (space_info->active_total_bytes == space_info->total_bytes)
+ return 0;
+
+ for (;;) {
+ int ret;
+
+ need_finish = false;
+ down_read(&space_info->groups_sem);
+ for (index = 0; index < BTRFS_NR_RAID_TYPES; index++) {
+ list_for_each_entry(bg, &space_info->block_groups[index], list) {
+ if (!spin_trylock(&bg->lock))
+ continue;
+ if (btrfs_zoned_bg_is_full(bg) || bg->zone_is_active) {
+ spin_unlock(&bg->lock);
+ continue;
+ }
+ spin_unlock(&bg->lock);
+
+ if (btrfs_zone_activate(bg)) {
+ up_read(&space_info->groups_sem);
+ return 1;
+ }
+
+ need_finish = true;
+ }
+ }
+ up_read(&space_info->groups_sem);
+
+ if (!do_finish || !need_finish)
+ break;
+
+ ret = btrfs_zone_finish_one_bg(fs_info);
+ if (ret == 0)
+ break;
+ if (ret < 0)
+ return ret;
+ }
+
+ return 0;
+}
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 329d28e2fd8d..f7b0b9035fd6 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -81,6 +81,8 @@ bool btrfs_zoned_should_reclaim(struct btrfs_fs_info *fs_info);
void btrfs_zoned_release_data_reloc_bg(struct btrfs_fs_info *fs_info, u64 logical,
u64 length);
int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info);
+int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info, bool do_finish);
#else /* CONFIG_BLK_DEV_ZONED */
static inline int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos,
struct blk_zone *zone)
@@ -256,6 +258,14 @@ static inline int btrfs_zone_finish_one_bg(struct btrfs_fs_info *fs_info)
return 1;
}
+static inline int btrfs_zoned_activate_one_bg(struct btrfs_fs_info *fs_info,
+ struct btrfs_space_info *space_info,
+ bool do_finish)
+{
+ /* Consider all the BGs are active */
+ return 0;
+}
+
#endif
static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
--
2.35.1
