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>
