Provide inline versions of some allocation functions
- bch2_alloc_sectors_done_inlined()
- bch2_alloc_sectors_append_ptrs_inlined()
and use them in the core IO path.
Also, inline bch2_extent_update_i_size_sectors() and
bch2_bkey_append_ptr().
In the core write path, function call overhead matters - every function
call is a jump to a new location and a potential cache miss.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This separates out the slowpath into a separate function, and inlines
bch2_alloc_v4_mut into bch2_trans_start_alloc_update(), the main place
it's called.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
When we need to add more replicas to an extent, it might be the case
that we already have a replica on every device, but some of them are
cached.
This patch fixes a bug where we'd spin on that extent because the write
path fails to find a device we can allocate from: we allow allocating
from devices that already have cached replicas on them, and change
bch2_data_update_index_update() to drop the cached replica if needed.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
When errors=panic, we need to dump transaction updates before calling
bch2_inconsistent_error().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We now have bch2_trans_inconsistent() which generically does the same
thing - dumps pending btree transaction updates.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Old inode formats don't have all the fields of the current inode format:
when unpacking inodes in the current format we can thus skip zeroing out
the destination buffer, but that doesn't work on for the old formats.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
In debug mode, we now track where btree iterators and paths are
initialized/allocated - helpful in tracking down btree path overflows.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This is something we need to do more widely: instead of bothering with
GFP_NOIO/GFP_NOFS, if we need to allocate memory while holding locks:
- first attempt the allocation with GFP_NOWAIT
- if that fails, drop btree locks with bch2_trans_unlock(), then
retry with GFP_KERNEL.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We need to take a ref on a path while we're traversing it: this fixes a
bug with paths getting reused while being traversed, in the key cache
fill code.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
The btree node read path has the ability to kick off an asynchronous
btree node rewrite if we saw and corrected an error. Previously this was
only used for errors that caused one of the replicas to be unusable -
this patch plumbs it through to all error paths, so that normal fsck
errors can be corrected.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This patch
- Adds a mechanism for queuing up journal entries prior to the journal
being started, which will be used for early journal log messages
- Adds bch2_fs_log_msg() and improves bch2_trans_log_msg(), which now
take format strings. bch2_fs_log_msg() can be used before or after
the journal has been started, and will use the appropriate mechanism.
- Deletes the now obsolete bch2_journal_log_msg()
- And adds more log messages to the recovery path - messages for
journal/filesystem started, journal entries being blacklisted, and
journal replay starting/finishing.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
With CONFIG_FORTIFY_SOURCE, the compiler attempts to warn about mempcys
that extend past struct field boundaries. This results in some spurious
warnings where we use embedded variable length structs, this patch
switches to unsafe_mecpy() to fix the warnings.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
It's now legal for the pin fifo to be empty, which means this code needs
to be updated in order to not hit an assert.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
While a btree transaction is running, we hold a SRCU read lock on the
btree key cache that prevents btree key cache keys from being freed -
this is so that relock() operations won't access freed memory.
The downside of this is that long running btree transactions prevent
memory from being freed from the key cache. This adds a check in
bch2_trans_begin() - if the transaction has been running longer than 1
second, drop and retake the SRCU read lock and zero out pointers to
unlock key cache paths.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Add a few easy unlikely() optimizations. These are mainly worthwhile
because the compiler will (usually) put the branch-not-taken path at the
end of the function, meaning better icache utilization.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This introduces some new conveniences, to help cut down on boilerplate:
- bch2_trans_kmalloc_nomemzero() - performance optimiation
- bch2_bkey_make_mut()
- bch2_bkey_get_mut()
- bch2_bkey_get_mut_typed()
- bch2_bkey_alloc()
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
If it so happens that we crash while dirty, meaning we don't have the
superblock clean section, and we erroneously mark a journal entry we
wrote as blacklisted, we won't be able to recover.
This patch fixes this by adding a fallback: if we've got no superblock
clean section, and no non-ignored journal entries, we try the most
recent ignored journal entry.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We weren't resetting filesystem & device usage when restarting gc, which
was spotted when free bucket counters overflowed - whoops.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Previously, we were journalling extra_journal_entries (which is used for
new btree roots, and irreversably mutates system state) before calling
bch2_trans_fs_usage_apply(), which can fail - whoops.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
When we started stashing the key being overwritten in
btree_insert_entry, this introduced a typical iterator invalidation
problem, triggered by btree node splits or resorts.
Previously, dealt with this by unconditionally re-validating those
stashed pointers in the transaction commit path. This patch gets rid of
that by doing it only when needed, in bch2_trans_node_add() or
bch2_trans_node_reinit_iter().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We shouldn't be overloading standard error codes now that we have
provisions for bcachefs-specific errorcodes: this patch converts super.c
and super-io.c to per error site errcodes, with a bit of cleanup.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This isn't actually an error condition, this just indicates a normal
shutdown - no reason for these to be in the log.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
bch2_btree_iter_peek_upto() in snapshots mode may need to keep a
btree_path for the insert position, not just the position of the key
we're returning. The code was incorrectly assuming this would be in the
same btree node - we were missing a bch2_btree_path_traverse() call.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
bch2_journal_keys_peek_upto() was comparing against btree_id & level
incorrectly - fix this by using __journal_key_cmp().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This fixes a (harmless) broken invariant in __bch2_btree_path_set_pos():
iterators to interior nodes should point to the first non whiteout.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This just cleans up and simplifies the code that decides where to resume
writing in the journal - when the code was originally written we weren't
saving the precise location of every journal write found.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
On startup, we need to ensure the first journal entry written is a flush
write: after a clean shutdown we generally don't read the journal, which
means we might be overwriting whatever was there previously, and there
must always be at least one flush entry in the journal or recovery will
fail.
Found by fstests generic/388.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This tweaks the recovery and journal paths so that we don't error out
before we need to: the list_journal command should work, even if we
wouldn't be able to replay successfully.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We weren't setting path->uptodate before calling
bch2_btree_key_cache_fill() - which causes __bch2_btree_path_upgrade()
to fail.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This switches btree_key_cache_fill() to use a btree iterator, not a
btree path, so that it can search for keys in previous snapshots.
We also add another iterator flag, BTREE_ITER_KEY_CACHE_FILL, to avoid
recursion back into the key cache.
This will allow us to re-enable the key cache for inodes in the next
patch.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
There was no reason for this to be a separate helper - we always want
the relock call that btree_trans_peek_key_cache() did.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
When we start using the key cache for inodes again, it'll be possible
for bch2_btree_path_peek_slot() to return a key in a different snapshot
with a key cache path.
This isn't what we want when triggers are checking what they're
overwriting, so introduce a new helper for the commit path.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This patch introduces
- bpos_eq()
- bpos_lt()
- bpos_le()
- bpos_gt()
- bpos_ge()
and equivalent replacements for bkey_cmp().
Looking at the generated assembly these could probably be improved
further, but we already see a significant code size improvement with
this patch.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Add a new bcachefs-specific magic number for the superblock, instead of
continuing to use the old bcache magic number3
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Extent overwrite used to be handled differently, underneath the
journaling layer and within the core btree code. This imposed
restrictions on bkey packing/packed formats, which no longer apply.
This patch deletes those restrictions.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- Ensure we print an error message if necessary.
Ideally we'd return the precise error code to userspace and leave
printing the error message to the userspace tool, but we haven't
decided to make our private error codes ABI-stable yet.
- Return standard error code to userspace
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Btree nodes shouldn't have their accessed bit set when entering the
btree cache by being read in from disk - this fixes linear scans
thrashing the cache.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Move the actual slowpath off into a new function -
bch2_time_stats_clear_buffer() - and inline
bch2_time_stats_update_one().
Alo, use the new inlined update functions from mean_and_variance.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
When flags & btree_id are constants, we can constant fold the entire
calculation of the actual iterator flags - and the whole thing becomes
small enough to inline.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This drops some unneeded references to JOURNAL_REPLAY_DONE in c->flags:
we're already mirroring it in btree_trans, we just weren't using it
consistently.
We may want to do this with more flags:
btree_iter.c: unsigned nr = test_bit(BCH_FS_STARTED, &c->flags)
btree_update_leaf.c: if (unlikely(!test_bit(BCH_FS_MAY_GO_RW, &c->flags))) {
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
It turns out the *_defined entries of bch_io_opts are only used in one
place - in the xattr get path - and there we immediately convert to a
bch_opts struct, which also has the *_defined entries.
This patch changes bch2_inode_opts_to_opts() to go directly from
bch_inode_unpacked to bch_opts, which is a minor simplification and will
also let us slim down struct bch_io_opts in another patch.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This provides an inlined version of bch2_subvolume_get() and uses it in
bch2_subvolume_get_snapshot(), since this is the version that's used all
over the place and in fast paths (e.g. IO paths).
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This is only called in two places, and when it's used we use it in a
tight loop - it's definitely worth inlining.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This just removes a redundant comparison - there's more work we could do
here to remove some redundant copying.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Standard splitting out of the slow path from the fast path of a
function. We may follow this up in another patch with inlining the fast
path into btree_iter.c.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
If the last journal write didn't complete sucessfully due to a torn
write, we'll detect it as a checksum error. In that case, we should just
pretend that journal entry was never written.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Print out the journal entries we read and will replay as soon as
possible - if we get an error walidating keys it's helpful to know where
it was in the journal.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
It turns out we need bch2_extent_trim_atomi() even when we're deleting
extents one at a time because it's possible for one reflink_p to
reference arbitrarily many reflink_v extents. This doesn't normally
happen, but the data move path can fragment existing extents in the
background.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
b->write_type needs to be set atomically with setting the
btree_node_need_write flag, so move it into b->flags.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- Centralize format strings in bcachefs.h
- Add bch2_fmt_inum_offset() and related helpers
- Switch error messages for inodes to also print out the offset, in
bytes
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Warnings ought to always have a format string/log message - makes them
considerably more useful.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Previously, when we exited from the loop body with a break statement
_ret wouldn't have been assigned to yet, and we could spuriously return
a transaction restart error.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This improves the bkey_format calculation when splitting btree nodes.
Previously, we'd use a format calculated for the original node for the
lower of the two new nodes.
This was particularly bad on sequential insertions, where we iteratively
split the last btree node, whos format has to include KEY_MAX.
Now, we calculate formats precisely for the keys the two new nodes will
contain. This also should make splitting a bit more efficient, since
we're only copying keys once (from the original node to the new node,
instead of new node, replacement node, then upper split).
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This switches where we take quota reservations to be per bch_wirte_op
instead of per dio_write, so we can drop the quota reservation in the
same place as we call i_sectors_acct(), and only take/release
ei_quota_lock once.
In the future we'd like ei_quota_lock to not be a mutex, so that we can
avoid punting to process context before deliving write completions in
nocow mode.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
The genradix code can handle multiple threads trying to allocate at the
same time - we don't need the genradix_ptr_alloc() call to happen under
a lock.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This fixes a regression from percpu freedlists in the btree key cache
code: in a rare error path, we were immediately freeing a bkey_cached
that had been used before and should've waited for an SRCU barrier.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
These were wrappers around atomic operations that verified that the
counter wasn't negative, but they're dead code - delete.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- Marking a non-static function as inline doesn't actually work and is
now causing problems - drop that
- Introduce BCACHEFS_LOG_PREFIX for when we want to prefix log messages
with bcachefs (filesystem name)
- Userspace doesn't have real percpu variables (maybe we can get this
fixed someday), put an #ifdef around bch2_disk_reservation_add()
fastpath
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We have a unique lock used for controlling adding to the pagecache: the
lock has two states, where both states are shared - the lock may be held
multiple times for either state - but not both states at the same time.
This is exactly what we need for nocow mode locking, so this patch pulls
it out of fs.c into its own file.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
BCH_WRITE_FLUSH is a write flag that causes a journal flush. It's only
used in the direct IO path, and this will allow for some consolidation
with the regular fsync path, which will help with the upcoming nocow
mode.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- factor out more slowpath code into non-inline function
- use bch2_print_string_as_lines(), so our error message doesn't get
truncated
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
btree_path_copy() doesn't need to call
bch2_btree_path_check_sort_fast() - the newly allocated path will always
be in the correct position, post copy; also delete some redundant
branches from __bch2_btree_path_make_mut().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- Don't call into bch2_encrypt_bio() when we're not encrypting
- Pull slowpath out of trans_lock_write()
- Make sure bc2h_trans_journal_res_get() gets inlined.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- With BCH_WRITE_SYNC, we no longer need the completion in struct
dio_write
- Pull out bch2_dio_write_copy_iov() into a separate non-inline
function, it's code that doesn't run in the common case
- Copy mapping and inode pointers into dio_write, avoiding pointer
chasing at the start of bch2_dio_write_loop()
- kthread_use_mm() is not needed in the common case; move it into
bch2_dio_write_loop_async()
- factor out various helpers from bch2_dio_write_loop() and rework
control flow for better icache utilization
Other small optimizations:
- bch2_keylist_free() is only used in one place, at the end of the
bch2_write() path - drop the reinit
- in bch2_disk_reservation_put(), check if res->sectors is nonzero
before touching c->online_reserved, since that will likely be a cache
miss
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
bcachefs: More DIO write path optimization
Better code prefetching (?)
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This adds a new flag for the write path, BCH_WRITE_SYNC, and switches
the O_DIRECT write path to use it when we're not running asynchronously.
It runs the btree update after the write in the original thread's
context instead of a kworker, cutting context switches in half.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This factors out a properly-documented helper for deciding when we want
to sort a btree node with MAX_BSETS bsets down to a single bset.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This replaces sysfs btree_avg_write_size with btree_write_stats, which
now breaks out statistics by the source of the btree write.
Btree writes that are too small are a source of inefficiency, and
excessive btree resort overhead - this will let us see what's causing
them.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
