@@ -619,6 +619,7 @@ struct btrfs_block_group_cache {
* zone.
*/
u64 alloc_offset;
+ struct mutex zone_io_lock;
};
/* delayed seq elem */
@@ -5532,6 +5532,7 @@ static int find_free_extent_seq(struct btrfs_block_group_cache *cache,
if (cache->alloc_type != BTRFS_ALLOC_SEQ)
return 1;
+ btrfs_hmzoned_data_io_lock(cache);
spin_lock(&space_info->lock);
spin_lock(&cache->lock);
@@ -5563,6 +5564,9 @@ static int find_free_extent_seq(struct btrfs_block_group_cache *cache,
out:
spin_unlock(&cache->lock);
spin_unlock(&space_info->lock);
+ /* if succeeds, unlock after submit_bio */
+ if (ret)
+ btrfs_hmzoned_data_io_unlock(cache);
return ret;
}
@@ -8104,6 +8108,7 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
btrfs_init_free_space_ctl(cache);
atomic_set(&cache->trimming, 0);
mutex_init(&cache->free_space_lock);
+ mutex_init(&cache->zone_io_lock);
btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);
cache->alloc_type = BTRFS_ALLOC_FIT;
@@ -39,6 +39,7 @@ int btrfs_hmzoned_check_metadata_space(struct btrfs_fs_info *fs_info);
void btrfs_redirty_list_add(struct btrfs_transaction *trans,
struct extent_buffer *eb);
void btrfs_free_redirty_list(struct btrfs_transaction *trans);
+void btrfs_hmzoned_data_io_unlock_at(struct inode *inode, u64 start, u64 len);
static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos)
{
@@ -140,4 +141,37 @@ static inline bool btrfs_check_super_location(struct btrfs_device *device,
!btrfs_dev_is_sequential(device, pos);
}
+
+static inline void btrfs_hmzoned_data_io_lock(
+ struct btrfs_block_group_cache *cache)
+{
+ /* No need to lock metadata BGs or non-sequential BGs */
+ if (!(cache->flags & BTRFS_BLOCK_GROUP_DATA) ||
+ cache->alloc_type != BTRFS_ALLOC_SEQ)
+ return;
+ mutex_lock(&cache->zone_io_lock);
+}
+
+static inline void btrfs_hmzoned_data_io_unlock(
+ struct btrfs_block_group_cache *cache)
+{
+ if (!(cache->flags & BTRFS_BLOCK_GROUP_DATA) ||
+ cache->alloc_type != BTRFS_ALLOC_SEQ)
+ return;
+ mutex_unlock(&cache->zone_io_lock);
+}
+
+static inline void btrfs_hmzoned_data_io_unlock_logical(
+ struct btrfs_fs_info *fs_info, u64 logical)
+{
+ struct btrfs_block_group_cache *cache;
+
+ if (!btrfs_fs_incompat(fs_info, HMZONED))
+ return;
+
+ cache = btrfs_lookup_block_group(fs_info, logical);
+ btrfs_hmzoned_data_io_unlock(cache);
+ btrfs_put_block_group(cache);
+}
+
#endif
@@ -48,6 +48,7 @@
#include "qgroup.h"
#include "dedupe.h"
#include "delalloc-space.h"
+#include "hmzoned.h"
struct btrfs_iget_args {
struct btrfs_key *location;
@@ -1279,6 +1280,39 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
return 0;
}
+static noinline int run_delalloc_hmzoned(struct inode *inode,
+ struct page *locked_page, u64 start,
+ u64 end, int *page_started,
+ unsigned long *nr_written)
+{
+ struct extent_map *em;
+ u64 logical;
+ int ret;
+
+ ret = cow_file_range(inode, locked_page, start, end,
+ end, page_started, nr_written, 0, NULL);
+ if (ret)
+ return ret;
+
+ if (*page_started)
+ return 0;
+
+ em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, end - start + 1,
+ 0);
+ ASSERT(em != NULL && em->block_start < EXTENT_MAP_LAST_BYTE);
+ logical = em->block_start;
+ free_extent_map(em);
+
+ __set_page_dirty_nobuffers(locked_page);
+ account_page_redirty(locked_page);
+ extent_write_locked_range(inode, start, end, WB_SYNC_ALL);
+ *page_started = 1;
+
+ btrfs_hmzoned_data_io_unlock_logical(btrfs_sb(inode->i_sb), logical);
+
+ return 0;
+}
+
static noinline int csum_exist_in_range(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes)
{
@@ -1645,17 +1679,24 @@ int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
int ret;
int force_cow = need_force_cow(inode, start, end);
unsigned int write_flags = wbc_to_write_flags(wbc);
+ int do_compress = inode_can_compress(inode) &&
+ inode_need_compress(inode, start, end);
+ int hmzoned = btrfs_fs_incompat(btrfs_sb(inode->i_sb), HMZONED);
if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATACOW && !force_cow) {
+ ASSERT(!hmzoned);
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 1, nr_written);
} else if (BTRFS_I(inode)->flags & BTRFS_INODE_PREALLOC && !force_cow) {
+ ASSERT(!hmzoned);
ret = run_delalloc_nocow(inode, locked_page, start, end,
page_started, 0, nr_written);
- } else if (!inode_can_compress(inode) ||
- !inode_need_compress(inode, start, end)) {
+ } else if (!do_compress && !hmzoned) {
ret = cow_file_range(inode, locked_page, start, end, end,
page_started, nr_written, 1, NULL);
+ } else if (!do_compress && hmzoned) {
+ ret = run_delalloc_hmzoned(inode, locked_page, start, end,
+ page_started, nr_written);
} else {
set_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
&BTRFS_I(inode)->runtime_flags);
To preserve sequential write pattern on the drives, we must serialize allocation and submit_bio. This commit add per-block group mutex "zone_io_lock" and find_free_extent_seq() hold the lock. The lock is kept even after returning from find_free_extent(). It is released when submiting IOs corresponding to the allocation is completed. Implementing such behavior under __extent_writepage_io is almost impossible because once pages are unlocked we are not sure when submiting IOs for an allocated region is finished or not. Instead, this commit add run_delalloc_hmzoned() to write out non-compressed data IOs at once using extent_write_locked_rage(). After the write, we can call btrfs_hmzoned_unlock_allocation() to unlock the block group for new allocation. Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> --- fs/btrfs/ctree.h | 1 + fs/btrfs/extent-tree.c | 5 +++++ fs/btrfs/hmzoned.h | 34 +++++++++++++++++++++++++++++++ fs/btrfs/inode.c | 45 ++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 83 insertions(+), 2 deletions(-)