This is the 1/3 patch to enable tree log on zoned filesystems.
The tree-log feature does not work on a zoned filesystem as is. Blocks for
a tree-log tree are allocated mixed with other metadata blocks and btrfs
writes and syncs the tree-log blocks to devices at the time of fsync(),
which has a different timing than a global transaction commit. As a
result, both writing tree-log blocks and writing other metadata blocks
become non-sequential writes that zoned filesystems must avoid.
Introduce a dedicated block group for tree-log blocks, so that tree-log
blocks and other metadata blocks can be separate write streams. As a
result, each write stream can now be written to devices separately.
"fs_info->treelog_bg" tracks the dedicated block group and btrfs assigns
"treelog_bg" on-demand on tree-log block allocation time.
This commit extends the zoned block allocator to use the block group.
Reviewed-by: Josef Bacik <josef@xxxxxxxxxxxxxx>
Signed-off-by: Johannes Thumshirn <johannes.thumshirn@xxxxxxx>
Signed-off-by: Naohiro Aota <naohiro.aota@xxxxxxx>
---
fs/btrfs/block-group.c | 2 ++
fs/btrfs/ctree.h | 2 ++
fs/btrfs/disk-io.c | 1 +
fs/btrfs/extent-tree.c | 75 +++++++++++++++++++++++++++++++++++++++---
fs/btrfs/zoned.h | 14 ++++++++
5 files changed, 90 insertions(+), 4 deletions(-)
diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
index f5e9f560ce6d..5064be59dac5 100644
--- a/fs/btrfs/block-group.c
+++ b/fs/btrfs/block-group.c
@@ -901,6 +901,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
btrfs_return_cluster_to_free_space(block_group, cluster);
spin_unlock(&cluster->refill_lock);
+ btrfs_clear_treelog_bg(block_group);
+
path = btrfs_alloc_path();
if (!path) {
ret = -ENOMEM;
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 1bb4f767966a..6f4b493625ef 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -976,6 +976,8 @@ struct btrfs_fs_info {
/* Max size to emit ZONE_APPEND write command */
u64 max_zone_append_size;
struct mutex zoned_meta_io_lock;
+ spinlock_t treelog_bg_lock;
+ u64 treelog_bg;
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d2fa92526b3b..84c6650d5ef7 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2787,6 +2787,7 @@ void btrfs_init_fs_info(struct btrfs_fs_info *fs_info)
spin_lock_init(&fs_info->super_lock);
spin_lock_init(&fs_info->buffer_lock);
spin_lock_init(&fs_info->unused_bgs_lock);
+ spin_lock_init(&fs_info->treelog_bg_lock);
rwlock_init(&fs_info->tree_mod_log_lock);
mutex_init(&fs_info->unused_bg_unpin_mutex);
mutex_init(&fs_info->delete_unused_bgs_mutex);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e2b2abc42295..f8e8c17e5624 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3497,6 +3497,9 @@ struct find_free_extent_ctl {
bool have_caching_bg;
bool orig_have_caching_bg;
+ /* Allocation is called for tree-log */
+ bool for_treelog;
+
/* RAID index, converted from flags */
int index;
@@ -3725,6 +3728,22 @@ static int do_allocation_clustered(struct btrfs_block_group *block_group,
return find_free_extent_unclustered(block_group, ffe_ctl);
}
+/*
+ * Tree-log block group locking
+ * ============================
+ *
+ * fs_info::treelog_bg_lock protects the fs_info::treelog_bg which
+ * indicates the starting address of a block group, which is reserved only
+ * for tree-log metadata.
+ *
+ * Lock nesting
+ * ============
+ *
+ * space_info::lock
+ * block_group::lock
+ * fs_info::treelog_bg_lock
+ */
+
/*
* Simple allocator for sequential only block group. It only allows sequential
* allocation. No need to play with trees. This function also reserves the
@@ -3734,23 +3753,54 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
struct find_free_extent_ctl *ffe_ctl,
struct btrfs_block_group **bg_ret)
{
+ struct btrfs_fs_info *fs_info = block_group->fs_info;
struct btrfs_space_info *space_info = block_group->space_info;
struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
u64 start = block_group->start;
u64 num_bytes = ffe_ctl->num_bytes;
u64 avail;
+ u64 bytenr = block_group->start;
+ u64 log_bytenr;
int ret = 0;
+ bool skip;
ASSERT(btrfs_is_zoned(block_group->fs_info));
+ /*
+ * Do not allow non-tree-log blocks in the dedicated tree-log block
+ * group, and vice versa.
+ */
+ spin_lock(&fs_info->treelog_bg_lock);
+ log_bytenr = fs_info->treelog_bg;
+ skip = log_bytenr && ((ffe_ctl->for_treelog && bytenr != log_bytenr) ||
+ (!ffe_ctl->for_treelog && bytenr == log_bytenr));
+ spin_unlock(&fs_info->treelog_bg_lock);
+ if (skip)
+ return 1;
+
spin_lock(&space_info->lock);
spin_lock(&block_group->lock);
+ spin_lock(&fs_info->treelog_bg_lock);
+
+ ASSERT(!ffe_ctl->for_treelog ||
+ block_group->start == fs_info->treelog_bg ||
+ fs_info->treelog_bg == 0);
if (block_group->ro) {
ret = 1;
goto out;
}
+ /*
+ * Do not allow currently using block group to be tree-log dedicated
+ * block group.
+ */
+ if (ffe_ctl->for_treelog && !fs_info->treelog_bg &&
+ (block_group->used || block_group->reserved)) {
+ ret = 1;
+ goto out;
+ }
+
avail = block_group->length - block_group->alloc_offset;
if (avail < num_bytes) {
if (ffe_ctl->max_extent_size < avail) {
@@ -3765,6 +3815,9 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
goto out;
}
+ if (ffe_ctl->for_treelog && !fs_info->treelog_bg)
+ fs_info->treelog_bg = block_group->start;
+
ffe_ctl->found_offset = start + block_group->alloc_offset;
block_group->alloc_offset += num_bytes;
spin_lock(&ctl->tree_lock);
@@ -3779,6 +3832,9 @@ static int do_allocation_zoned(struct btrfs_block_group *block_group,
ffe_ctl->search_start = ffe_ctl->found_offset;
out:
+ if (ret && ffe_ctl->for_treelog)
+ fs_info->treelog_bg = 0;
+ spin_unlock(&fs_info->treelog_bg_lock);
spin_unlock(&block_group->lock);
spin_unlock(&space_info->lock);
return ret;
@@ -4028,7 +4084,12 @@ static int prepare_allocation(struct btrfs_fs_info *fs_info,
return prepare_allocation_clustered(fs_info, ffe_ctl,
space_info, ins);
case BTRFS_EXTENT_ALLOC_ZONED:
- /* Nothing to do */
+ if (ffe_ctl->for_treelog) {
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (fs_info->treelog_bg)
+ ffe_ctl->hint_byte = fs_info->treelog_bg;
+ spin_unlock(&fs_info->treelog_bg_lock);
+ }
return 0;
default:
BUG();
@@ -4072,6 +4133,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
struct find_free_extent_ctl ffe_ctl = {0};
struct btrfs_space_info *space_info;
bool full_search = false;
+ bool for_treelog = root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID;
WARN_ON(num_bytes < fs_info->sectorsize);
@@ -4085,6 +4147,7 @@ static noinline int find_free_extent(struct btrfs_root *root,
ffe_ctl.orig_have_caching_bg = false;
ffe_ctl.found_offset = 0;
ffe_ctl.hint_byte = hint_byte_orig;
+ ffe_ctl.for_treelog = for_treelog;
ffe_ctl.policy = BTRFS_EXTENT_ALLOC_CLUSTERED;
/* For clustered allocation */
@@ -4159,8 +4222,11 @@ static noinline int find_free_extent(struct btrfs_root *root,
struct btrfs_block_group *bg_ret;
/* If the block group is read-only, we can skip it entirely. */
- if (unlikely(block_group->ro))
+ if (unlikely(block_group->ro)) {
+ if (for_treelog)
+ btrfs_clear_treelog_bg(block_group);
continue;
+ }
btrfs_grab_block_group(block_group, delalloc);
ffe_ctl.search_start = block_group->start;
@@ -4346,6 +4412,7 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
bool final_tried = num_bytes == min_alloc_size;
u64 flags;
int ret;
+ bool for_treelog = root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID;
flags = get_alloc_profile_by_root(root, is_data);
again:
@@ -4369,8 +4436,8 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
sinfo = btrfs_find_space_info(fs_info, flags);
btrfs_err(fs_info,
- "allocation failed flags %llu, wanted %llu",
- flags, num_bytes);
+ "allocation failed flags %llu, wanted %llu tree-log %d",
+ flags, num_bytes, for_treelog);
if (sinfo)
btrfs_dump_space_info(fs_info, sinfo,
num_bytes, 1);
diff --git a/fs/btrfs/zoned.h b/fs/btrfs/zoned.h
index 932ad9bc0de6..61e969652fe1 100644
--- a/fs/btrfs/zoned.h
+++ b/fs/btrfs/zoned.h
@@ -7,6 +7,7 @@
#include <linux/blkdev.h>
#include "volumes.h"
#include "disk-io.h"
+#include "block-group.h"
struct btrfs_zoned_device_info {
/*
@@ -290,4 +291,17 @@ static inline void btrfs_zoned_meta_io_unlock(struct btrfs_fs_info *fs_info)
mutex_unlock(&fs_info->zoned_meta_io_lock);
}
+static inline void btrfs_clear_treelog_bg(struct btrfs_block_group *bg)
+{
+ struct btrfs_fs_info *fs_info = bg->fs_info;
+
+ if (!btrfs_is_zoned(fs_info))
+ return;
+
+ spin_lock(&fs_info->treelog_bg_lock);
+ if (fs_info->treelog_bg == bg->start)
+ fs_info->treelog_bg = 0;
+ spin_unlock(&fs_info->treelog_bg_lock);
+}
+
#endif
--
2.30.0
