This splits btree_iter into two components: btree_iter is now the
externally visible componont, and it points to a btree_path which is now
reference counted.
This means we no longer have to clone iterators up front if they might
be mutated - btree_path can be shared by multiple iterators, and cloned
if an iterator would mutate a shared btree_path. This will help us use
iterators more efficiently, as well as slimming down the main long lived
state in btree_trans, and significantly cleans up the logic for iterator
lifetimes.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
The implementation of prefetch_four_cachelines should use ifdef
CONFIG_X86_64 to conditionally compile x86_64 asm.
Signed-off-by: Dan Robertson <dan@dlrobertson.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
fs/bcachefs/bset.c edited prefetch macro to add clang support
fs/bcachefs/btree_iter.c bugfix: initialize iter->real_pos in bch2_btree_iter_init for later use
fs/bcachefs/io.c bugfix: eliminated undefined behavior (negative bitshift)
fs/bcachefs/buckets.c bugfix: invert sign to handle 64bit abs()
Signed-off-by: Brett Holman <bpholman5@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Since we now ensure a btree node's max key fits in its packed format,
this isn't needed for the reasons it used to be - and, it was being used
inconsistently.
Also reorder struct btree a bit for performance, and kill some dead
code.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This patch starts treating the bpos.snapshot field like part of the key
in the btree code:
* bpos_successor() and bpos_predecessor() now include the snapshot field
* Keys in btrees that will be using snapshots (extents, inodes, dirents
and xattrs) now always have their snapshot field set to U32_MAX
The btree iterator code gets a new flag, BTREE_ITER_ALL_SNAPSHOTS, that
determines whether we're iterating over keys in all snapshots or not -
internally, this controlls whether bkey_(successor|predecessor)
increment/decrement the snapshot field, or only the higher bits of the
key.
We add a new member to struct btree_iter, iter->snapshot: when
BTREE_ITER_ALL_SNAPSHOTS is not set, iter->pos.snapshot should always
equal iter->snapshot, which will be 0 for btrees that don't use
snapshots, and alsways U32_MAX for btrees that will use snapshots
(until we enable snapshot creation).
This patch also introduces a new metadata version number, and compat
code for reading from/writing to older versions - this isn't a forced
upgrade (yet).
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
With snapshots, we're going to need to differentiate between comparisons
that should and shouldn't include the snapshot field. bpos_cmp is now
the comparison function that does include the snapshot field, used by
core btree code.
Upper level filesystem code generally does _not_ want to compare against
the snapshot field - that code wants keys to compare as equal even when
one of them is in an ancestor snapshot.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Since we now make sure to always generate packed bkey formats that can
pack the min_key of a btree node, this path should actually never
happen.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We weren't packing the min/max keys, which was a major oversight and
completely disabled generating bkey_floats for adjacent nodes.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Bkey noops were introduced to deal with trimming inline data extents in
place in the btree: if the u64s field of a bkey was 0, that u64 was a
noop and we'd start looking for the next bkey immediately after it.
But extent handling has been lifted above the btree - we no longer
modify existing extents in place in the btree, and the compatibilty code
for old style extent btree nodes is gone, so we can completely drop this
code.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
KEY_TYPE_discard used to be used for extent whiteouts, but when handling
over overlapping extents was lifted above the core btree code it became
unused. This patch updates various code to reflect that.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This is a fast path - also, lift out the checks/init for min/max key.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
perhaps a bit silly, but some debug assertions we want to add need const
propagated a bit more.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
It's not used much anymore, the module paramter interface is better.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
More aggressively checking iterator invariants, and fixing the resulting
bugs. Also greatly simplifying iter_next() and iter_next_slot() - they
were hyper optimized before, but the optimizations were getting too
brittle.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
It's used in the write path when the bset isn't in the btree node
buffer.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
The insert path had an optimization to short circuit lookup
table/iterator fixups when overwriting an existing key with the same
size value - but it was incorrect when other key fields
(size/version) were changing. This is important for the upcoming rework
to have extent updates use the same insert path as regular keys.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- Rework some of the helper comparison functions for consistency
- Currently trying to refactor all the logic that's different for
extents in the btree iterator code. The main difference is that for non
extents we search for a key greater than or equal to the search key,
while for extents we search for a key strictly greater than the search
key (iter->pos).
So that logic is now handled by btree_iter_search_key(), which computes
the real search key based on iter->pos and whether or not we're
searching for a key >= or > iter->pos.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We were calling __btree_node_key_to_offset() on a key that wasn't in the
btree node.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
For upcoming inline data extents, we're going to need to be able to
shorten the value of existing bkeys in the btree - and to make that work
we're going to be able to need to pad out the space the value previously
took up with something.
This patch changes the various code that iterates over bkeys to handle
k->u64s == 0 as meaning "skip the next 8 bytes".
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
The previous optimizations means using 32 bit mantissas are now a net
loss - having bkey_float be only 4 bytes is good for prefetching.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This is basically equivalent to the original strategy of falling back to
checking against the original key when the original key and previous key
didn't differ in the required bits - except, now we only fall back when
the search key doesn't differ in the required bits, which ends up being
a bit faster.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
The assumption underlying BFLOAT_FAILED_PREV was wrong; the comparison
we're doing in bset_search_tree() doesn't have to tell the pivot apart
from the previous key, it just has to tell if search is definitely
greater than or equal to the pivot.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This makes prefetching for the linear search at the end of the lookup
much more effective, and is a couple percent speedup.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Improve a few paper cuts that've shown up during profiling.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
bch2_btree_node_iter_prev_filter() tried to be smart about iterating
backwards when skipping over whiteouts/discards - but unfortunately,
doing so can leave the node iterator in an inconsistent state; the sane
solution is to just always iterate backwards one key at a time.
But we compact btree nodes when more than a quarter of the keys are
whiteouts/discards, so the optimization wasn't buying us that much
anyways.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
userspace allocators don't align allocations as nicely as kernel
allocators, which meant that in some cases we weren't allocating big
enough bvec arrays - just make the calculations more rigorous and
explicit to fix it.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This lifts the restriction that 0 size extents must not overlap with
other extents, which means we can now sort extents and non extents the
same way, and will let us simplify a bunch of other stuff as well.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Initially forked from drivers/md/bcache, bcachefs is a new copy-on-write
filesystem with every feature you could possibly want.
Website: https://bcachefs.org
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
