diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-02-21 21:00:39 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-02-21 21:00:39 +0300 |
commit | 6f3952cbe00b74739f540981d1afe84cd4dac879 (patch) | |
tree | 6dacecd7ea8dc06d985c7ea417391c1ae2aec574 /fs/btrfs/ctree.h | |
parent | f9d58de23152f2c16f326d7e014cfa2933b00304 (diff) | |
parent | 9d294a685fbcb256ce8c5f7fd88a7596d0f52a8a (diff) | |
download | linux-6f3952cbe00b74739f540981d1afe84cd4dac879.tar.xz |
Merge tag 'for-5.12-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
"This brings updates of space handling, performance improvements or bug
fixes. The subpage block size and zoned mode features have reached
state where they're usable but with limitations.
Performance or related:
- do not block on deleted block group mutex in the cleaner, avoids
some long stalls
- improved flushing: make it work better with ticket space
reservations and avoid excessive transaction commits in some
scenarios, slightly improves throughput for random write load
- preemptive background flushing: separate the logic from ticket
reservations, improve the accounting and decisions when to flush in
low space conditions
- less lock contention related to running delayed refs, let just one
thread do the flushing when there are many inside transaction
commit
- dbench workload improvements: avoid unnecessary work when logging
inodes, fewer fallbacks to transaction commit and thus less waiting
for it (+7% throughput, -20% latency)
Core:
- subpage block size
- currently read-only support
- refactor and generalize code where sectorsize is assumed to be
page size, add the subpage handling everywhere
- the read-write support is on the way, page sizes are still
limited to 4K or 64K
- zoned mode, first working version but with limitations
- SMR/ZBC/ZNS friendly allocation mode, utilizing the "no fixed
location for structures" and chunked allocation
- superblock as the only fixed data structure needs special
handling, uses 2 consecutive zones as a ring buffer
- tree-log support with a dedicated block group to avoid unordered
writes
- emulated zones on non-zoned devices
- not yet working
- all non-single block group profiles, requires more zone write
pointer synchronization between the multiple block groups
- fitrim due to dependency on space cache, can be implemented
Fixes:
- ref-verify: proper tree owner and node level tracking
- fix pinned byte accounting, causing some early ENOSPC now more
likely due to other changes in delayed refs
Other:
- error handling fixes and improvements
- more error injection points
- more function documentation
- more and updated tracepoints
- subset of W=1 checked by default
- update comments to allow more automatic kdoc parameter checks"
* tag 'for-5.12-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (144 commits)
btrfs: zoned: enable to mount ZONED incompat flag
btrfs: zoned: deal with holes writing out tree-log pages
btrfs: zoned: reorder log node allocation on zoned filesystem
btrfs: zoned: serialize log transaction on zoned filesystems
btrfs: zoned: extend zoned allocator to use dedicated tree-log block group
btrfs: split alloc_log_tree()
btrfs: zoned: relocate block group to repair IO failure in zoned filesystems
btrfs: zoned: enable relocation on a zoned filesystem
btrfs: zoned: support dev-replace in zoned filesystems
btrfs: zoned: implement copying for zoned device-replace
btrfs: zoned: implement cloning for zoned device-replace
btrfs: zoned: mark block groups to copy for device-replace
btrfs: zoned: do not use async metadata checksum on zoned filesystems
btrfs: zoned: wait for existing extents before truncating
btrfs: zoned: serialize metadata IO
btrfs: zoned: introduce dedicated data write path for zoned filesystems
btrfs: zoned: enable zone append writing for direct IO
btrfs: zoned: use ZONE_APPEND write for zoned mode
btrfs: save irq flags when looking up an ordered extent
btrfs: zoned: cache if block group is on a sequential zone
...
Diffstat (limited to 'fs/btrfs/ctree.h')
-rw-r--r-- | fs/btrfs/ctree.h | 19 |
1 files changed, 13 insertions, 6 deletions
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 4debdbdde2ab..3bc00aed13b2 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -298,7 +298,8 @@ struct btrfs_super_block { BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \ BTRFS_FEATURE_INCOMPAT_METADATA_UUID | \ - BTRFS_FEATURE_INCOMPAT_RAID1C34) + BTRFS_FEATURE_INCOMPAT_RAID1C34 | \ + BTRFS_FEATURE_INCOMPAT_ZONED) #define BTRFS_FEATURE_INCOMPAT_SAFE_SET \ (BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF) @@ -797,7 +798,7 @@ struct btrfs_fs_info { /* used to keep from writing metadata until there is a nice batch */ struct percpu_counter dirty_metadata_bytes; struct percpu_counter delalloc_bytes; - struct percpu_counter dio_bytes; + struct percpu_counter ordered_bytes; s32 dirty_metadata_batch; s32 delalloc_batch; @@ -933,6 +934,7 @@ struct btrfs_fs_info { /* Used to reclaim the metadata space in the background. */ struct work_struct async_reclaim_work; struct work_struct async_data_reclaim_work; + struct work_struct preempt_reclaim_work; spinlock_t unused_bgs_lock; struct list_head unused_bgs; @@ -974,6 +976,9 @@ 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; @@ -1104,7 +1109,7 @@ struct btrfs_root { u32 type; - u64 highest_objectid; + u64 free_objectid; struct btrfs_key defrag_progress; struct btrfs_key defrag_max; @@ -2740,6 +2745,7 @@ enum btrfs_flush_state { ALLOC_CHUNK_FORCE = 8, RUN_DELAYED_IPUTS = 9, COMMIT_TRANS = 10, + FORCE_COMMIT_TRANS = 11, }; int btrfs_subvolume_reserve_metadata(struct btrfs_root *root, @@ -3100,15 +3106,14 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans, u32 min_type); int btrfs_start_delalloc_snapshot(struct btrfs_root *root); -int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, u64 nr, +int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, long nr, bool in_reclaim_context); int btrfs_set_extent_delalloc(struct btrfs_inode *inode, u64 start, u64 end, unsigned int extra_bits, struct extent_state **cached_state); int btrfs_create_subvol_root(struct btrfs_trans_handle *trans, struct btrfs_root *new_root, - struct btrfs_root *parent_root, - u64 new_dirid); + struct btrfs_root *parent_root); void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state, unsigned *bits); void btrfs_clear_delalloc_extent(struct inode *inode, @@ -3119,6 +3124,8 @@ void btrfs_split_delalloc_extent(struct inode *inode, struct extent_state *orig, u64 split); int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio, unsigned long bio_flags); +bool btrfs_bio_fits_in_ordered_extent(struct page *page, struct bio *bio, + unsigned int size); void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end); vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf); int btrfs_readpage(struct file *file, struct page *page); |