@@ -379,6 +379,14 @@ int btrfs_scan_one_device(int fd, const char *path,
return ret;
}
+/* zone size is ensured to be power of 2 */
+static u64 btrfs_zone_align(struct btrfs_zone_info *zinfo, u64 val)
+{
+ if (zinfo && zinfo->zone_size)
+ return (val + zinfo->zone_size - 1) & ~(zinfo->zone_size - 1);
+ return val;
+}
+
/*
* find_free_dev_extent_start - find free space in the specified device
* @device: the device which we search the free space in
@@ -425,6 +433,7 @@ static int find_free_dev_extent_start(struct btrfs_device *device,
*/
min_search_start = max(root->fs_info->alloc_start, (u64)SZ_1M);
search_start = max(search_start, min_search_start);
+ search_start = btrfs_zone_align(&device->zinfo, search_start);
path = btrfs_alloc_path();
if (!path)
@@ -507,7 +516,8 @@ static int find_free_dev_extent_start(struct btrfs_device *device,
extent_end = key.offset + btrfs_dev_extent_length(l,
dev_extent);
if (extent_end > search_start)
- search_start = extent_end;
+ search_start = btrfs_zone_align(&device->zinfo,
+ extent_end);
next:
path->slots[0]++;
cond_resched();
@@ -560,6 +570,9 @@ static int btrfs_alloc_dev_extent(struct btrfs_trans_handle *trans,
struct extent_buffer *leaf;
struct btrfs_key key;
+ /* Align to zone for a zoned block device */
+ *start = btrfs_zone_align(&device->zinfo, *start);
+
path = btrfs_alloc_path();
if (!path)
return -ENOMEM;
@@ -1030,9 +1043,15 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
btrfs_super_stripesize(info->super_copy));
}
- /* we don't want a chunk larger than 10% of the FS */
- percent_max = div_factor(btrfs_super_total_bytes(info->super_copy), 1);
- max_chunk_size = min(percent_max, max_chunk_size);
+ if (info->fs_devices->hmzoned) {
+ /* Zoned mode uses zone aligned chunks */
+ calc_size = info->fs_devices->zone_size;
+ max_chunk_size = calc_size * num_stripes;
+ } else {
+ /* we don't want a chunk larger than 10% of the FS */
+ percent_max = div_factor(btrfs_super_total_bytes(info->super_copy), 1);
+ max_chunk_size = min(percent_max, max_chunk_size);
+ }
again:
if (chunk_bytes_by_type(type, calc_size, num_stripes, sub_stripes) >
@@ -1112,7 +1131,9 @@ again:
*num_bytes = chunk_bytes_by_type(type, calc_size,
num_stripes, sub_stripes);
index = 0;
+ dev_offset = 0;
while(index < num_stripes) {
+ size_t zone_size = device->zinfo.zone_size;
struct btrfs_stripe *stripe;
BUG_ON(list_empty(&private_devs));
cur = private_devs.next;
@@ -1123,11 +1144,16 @@ again:
(index == num_stripes - 1))
list_move_tail(&device->dev_list, dev_list);
+ if (device->zinfo.zone_size)
+ calc_size = device->zinfo.zone_size;
+
ret = btrfs_alloc_dev_extent(trans, device, key.offset,
calc_size, &dev_offset, 0);
if (ret < 0)
goto out_chunk_map;
+ WARN_ON(zone_size && !IS_ALIGNED(dev_offset, zone_size));
+
device->bytes_used += calc_size;
ret = btrfs_update_device(trans, device);
if (ret < 0)
To facilitate support for zoned block devices in the extent buffer allocation, a zoned block device chunk is always aligned to a zone of the device. With this, the zone write pointer location simply becomes a hint to allocate new buffers. Signed-off-by: Naohiro Aota <naota@elisp.net> --- volumes.c | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-)