diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 11:34:19 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-05-07 11:34:19 -0700 |
commit | 9f2e3a53f7ec9ef55e9d01bc29a6285d291c151e (patch) | |
tree | c25b0eb20dac1a39a6b55c521b2658dcceb7d532 /fs/btrfs/delayed-ref.h | |
parent | 78438ce18f26dbcaa8993bb45d20ffb0cec3bc3e (diff) | |
parent | b1c16ac978fd40ae636e629bb69a652df7eebdc2 (diff) | |
download | linux-9f2e3a53f7ec9ef55e9d01bc29a6285d291c151e.tar.gz linux-9f2e3a53f7ec9ef55e9d01bc29a6285d291c151e.tar.bz2 linux-9f2e3a53f7ec9ef55e9d01bc29a6285d291c151e.zip |
Merge tag 'for-5.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux
Pull btrfs updates from David Sterba:
"This time the majority of changes are cleanups, though there's still a
number of changes of user interest.
User visible changes:
- better read time and write checks to catch errors early and before
writing data to disk (to catch potential memory corruption on data
that get checksummed)
- qgroups + metadata relocation: last speed up patch int the series
to address the slowness, there should be no overhead comparing
balance with and without qgroups
- FIEMAP ioctl does not start a transaction unnecessarily, this can
result in a speed up and less blocking due to IO
- LOGICAL_INO (v1, v2) does not start transaction unnecessarily, this
can speed up the mentioned ioctl and scrub as well
- fsync on files with many (but not too many) hardlinks is faster,
finer decision if the links should be fsynced individually or
completely
- send tries harder to find ranges to clone
- trim/discard will skip unallocated chunks that haven't been touched
since the last mount
Fixes:
- send flushes delayed allocation before start, otherwise it could
miss some changes in case of a very recent rw->ro switch of a
subvolume
- fix fallocate with qgroups that could lead to space accounting
underflow, reported as a warning
- trim/discard ioctl honours the requested range
- starting send and dedupe on a subvolume at the same time will let
only one of them succeed, this is to prevent changes that send
could miss due to dedupe; both operations are restartable
Core changes:
- more tree-checker validations, errors reported by fuzzing tools:
- device item
- inode item
- block group profiles
- tracepoints for extent buffer locking
- async cow preallocates memory to avoid errors happening too deep in
the call chain
- metadata reservations for delalloc reworked to better adapt in
many-writers/low-space scenarios
- improved space flushing logic for intense DIO vs buffered workloads
- lots of cleanups
- removed unused struct members
- redundant argument removal
- properties and xattrs
- extent buffer locking
- selftests
- use common file type conversions
- many-argument functions reduction"
* tag 'for-5.2-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/kdave/linux: (227 commits)
btrfs: Use kvmalloc for allocating compressed path context
btrfs: Factor out common extent locking code in submit_compressed_extents
btrfs: Set io_tree only once in submit_compressed_extents
btrfs: Replace clear_extent_bit with unlock_extent
btrfs: Make compress_file_range take only struct async_chunk
btrfs: Remove fs_info from struct async_chunk
btrfs: Rename async_cow to async_chunk
btrfs: Preallocate chunks in cow_file_range_async
btrfs: reserve delalloc metadata differently
btrfs: track DIO bytes in flight
btrfs: merge calls of btrfs_setxattr and btrfs_setxattr_trans in btrfs_set_prop
btrfs: delete unused function btrfs_set_prop_trans
btrfs: start transaction in xattr_handler_set_prop
btrfs: drop local copy of inode i_mode
btrfs: drop old_fsflags in btrfs_ioctl_setflags
btrfs: modify local copy of btrfs_inode flags
btrfs: drop useless inode i_flags copy and restore
btrfs: start transaction in btrfs_ioctl_setflags()
btrfs: export btrfs_set_prop
btrfs: refactor btrfs_set_props to validate externally
...
Diffstat (limited to 'fs/btrfs/delayed-ref.h')
-rw-r--r-- | fs/btrfs/delayed-ref.h | 122 |
1 files changed, 114 insertions, 8 deletions
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h index 70606da440aa..c18f93ea88ed 100644 --- a/fs/btrfs/delayed-ref.h +++ b/fs/btrfs/delayed-ref.h @@ -176,6 +176,83 @@ struct btrfs_delayed_ref_root { u64 qgroup_to_skip; }; +enum btrfs_ref_type { + BTRFS_REF_NOT_SET, + BTRFS_REF_DATA, + BTRFS_REF_METADATA, + BTRFS_REF_LAST, +}; + +struct btrfs_data_ref { + /* For EXTENT_DATA_REF */ + + /* Root which refers to this data extent */ + u64 ref_root; + + /* Inode which refers to this data extent */ + u64 ino; + + /* + * file_offset - extent_offset + * + * file_offset is the key.offset of the EXTENT_DATA key. + * extent_offset is btrfs_file_extent_offset() of the EXTENT_DATA data. + */ + u64 offset; +}; + +struct btrfs_tree_ref { + /* + * Level of this tree block + * + * Shared for skinny (TREE_BLOCK_REF) and normal tree ref. + */ + int level; + + /* + * Root which refers to this tree block. + * + * For TREE_BLOCK_REF (skinny metadata, either inline or keyed) + */ + u64 root; + + /* For non-skinny metadata, no special member needed */ +}; + +struct btrfs_ref { + enum btrfs_ref_type type; + int action; + + /* + * Whether this extent should go through qgroup record. + * + * Normally false, but for certain cases like delayed subtree scan, + * setting this flag can hugely reduce qgroup overhead. + */ + bool skip_qgroup; + + /* + * Optional. For which root is this modification. + * Mostly used for qgroup optimization. + * + * When unset, data/tree ref init code will populate it. + * In certain cases, we're modifying reference for a different root. + * E.g. COW fs tree blocks for balance. + * In that case, tree_ref::root will be fs tree, but we're doing this + * for reloc tree, then we should set @real_root to reloc tree. + */ + u64 real_root; + u64 bytenr; + u64 len; + + /* Bytenr of the parent tree block */ + u64 parent; + union { + struct btrfs_data_ref data_ref; + struct btrfs_tree_ref tree_ref; + }; +}; + extern struct kmem_cache *btrfs_delayed_ref_head_cachep; extern struct kmem_cache *btrfs_delayed_tree_ref_cachep; extern struct kmem_cache *btrfs_delayed_data_ref_cachep; @@ -184,6 +261,38 @@ extern struct kmem_cache *btrfs_delayed_extent_op_cachep; int __init btrfs_delayed_ref_init(void); void __cold btrfs_delayed_ref_exit(void); +static inline void btrfs_init_generic_ref(struct btrfs_ref *generic_ref, + int action, u64 bytenr, u64 len, u64 parent) +{ + generic_ref->action = action; + generic_ref->bytenr = bytenr; + generic_ref->len = len; + generic_ref->parent = parent; +} + +static inline void btrfs_init_tree_ref(struct btrfs_ref *generic_ref, + int level, u64 root) +{ + /* If @real_root not set, use @root as fallback */ + if (!generic_ref->real_root) + generic_ref->real_root = root; + generic_ref->tree_ref.level = level; + generic_ref->tree_ref.root = root; + generic_ref->type = BTRFS_REF_METADATA; +} + +static inline void btrfs_init_data_ref(struct btrfs_ref *generic_ref, + u64 ref_root, u64 ino, u64 offset) +{ + /* If @real_root not set, use @root as fallback */ + if (!generic_ref->real_root) + generic_ref->real_root = ref_root; + generic_ref->data_ref.ref_root = ref_root; + generic_ref->data_ref.ino = ino; + generic_ref->data_ref.offset = offset; + generic_ref->type = BTRFS_REF_DATA; +} + static inline struct btrfs_delayed_extent_op * btrfs_alloc_delayed_extent_op(void) { @@ -224,17 +333,14 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea } int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans, - u64 bytenr, u64 num_bytes, u64 parent, - u64 ref_root, int level, int action, + struct btrfs_ref *generic_ref, struct btrfs_delayed_extent_op *extent_op, int *old_ref_mod, int *new_ref_mod); int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans, - u64 bytenr, u64 num_bytes, - u64 parent, u64 ref_root, - u64 owner, u64 offset, u64 reserved, int action, - int *old_ref_mod, int *new_ref_mod); -int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info, - struct btrfs_trans_handle *trans, + struct btrfs_ref *generic_ref, + u64 reserved, int *old_ref_mod, + int *new_ref_mod); +int btrfs_add_delayed_extent_op(struct btrfs_trans_handle *trans, u64 bytenr, u64 num_bytes, struct btrfs_delayed_extent_op *extent_op); void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans, |