This improves the nocow lock table so that hash table entries have
multiple locks, and locks specify which bucket they're for - i.e. we can
now resolve hash collisions.
This is important because the allocator has to skip buckets that are
locked in the nocow lock table, and previously hash collisions would
cause it to spuriously skip unlocked buckets.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
To improve mount times, add a btree for just bucket gens, 256 of them
per key: this means we'll have to scan drastically less metadata at
startup.
This adds
- trigger for keeping it in sync with the all btree
- initialization code, for filesystems from previous versions
- new path for reading bucket gens
- new fsck code
And a new on disk format version.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This adds support for nocow mode, where we do writes in-place when
possible. Patch components:
- New boolean filesystem and inode option, nocow: note that when nocow
is enabled, data checksumming and compression are implicitly disabled
- To prevent in-place writes from racing with data moves
(data_update.c) or bucket reuse (i.e. a bucket being reused and
re-allocated while a nocow write is in flight, we have a new locking
mechanism.
Buckets can be locked for either data update or data move, using a
fixed size hash table of two_state_shared locks. We don't have any
chaining, meaning updates and moves to different buckets that hash to
the same lock will wait unnecessarily - we'll want to watch for this
becoming an issue.
- The allocator path also needs to check for in-place writes in flight
to a given bucket before giving it out: thus we add another counter
to bucket_alloc_state so we can track this.
- Fsync now may need to issue cache flushes to block devices instead of
flushing the journal. We add a device bitmask to bch_inode_info,
ei_devs_need_flush, which tracks devices that need to have flushes
issued - note that this will lead to unnecessary flushes when other
codepaths have already issued flushes, we may want to replace this with
a sequence number.
- New nocow write path: look up extents, and if they're writable write
to them - otherwise fall back to the normal COW write path.
XXX: switch to sequence numbers instead of bitmask for devs needing
journal flush
XXX: ei_quota_lock being a mutex means bch2_nocow_write_done() needs to
run in process context - see if we can improve this
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This patch adds backpointers: we now have a reverse index from device
and offset on that device (specifically, offset within a bucket) back to
btree nodes and (non cached) data extents.
The first 40 backpointers within a bucket are stored in the alloc key;
after that backpointers spill over to the next backpointers btree. This
is to help avoid performance regressions from additional btree updates
on large streaming workloads.
This patch adds all the code for creating, checking and repairing
backpointers. The next patch in the series is going to use backpointers
for copygc - finally getting rid of the need to scan all extents to do
copygc.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This adds a new method of doing btree updates - a straight write buffer,
implemented as a flat fixed size array.
This is only useful when we don't need to read from the btree in order
to do the update, and when reading is infrequent - perfect for the LRU
btree.
This will make LRU btree updates fast enough that we'll be able to use
it for persistently indexing buckets by fragmentation, which will be a
massive boost to copygc performance.
Changes:
- A new btree_insert_type enum, for btree_insert_entries. Specifies
btree, btree key cache, or btree write buffer.
- bch2_trans_update_buffered(): updates via the btree write buffer
don't need a btree path, so we need a new update path.
- Transaction commit path changes:
The update to the btree write buffer both mutates global, and can
fail if there isn't currently room. Therefore we do all write buffer
updates in the transaction all at once, and also if it fails we have
to revert filesystem usage counter changes.
If there isn't room we flush the write buffer in the transaction
commit error path and retry.
- A new persistent option, for specifying the number of entries in the
write buffer.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
It's possible to do btree updates before going RW by adding them to the
list of updates for journal replay to do, but this is limited by what
fits in RAM. This patch switches the second alloc info phase to run
after going RW - btree_gc has already ensured the alloc btree itself is
correct - and tweaks the allocation path to deal with the potential
small inconsistencies.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This adds a debug mode where we split up the c->writes refcount into
distinct refcounts for every codepath that takes a reference, and adds
sysfs code to print the value of each ref.
This will make it easier to debug shutdown hangs due to refcount leaks.
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>
- 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>
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>
checkpatch.pl gives lots of warnings that we don't want - suggested
ignore list:
ASSIGN_IN_IF
UNSPECIFIED_INT - bcachefs coding style prefers single token type names
NEW_TYPEDEFS - typedefs are occasionally good
FUNCTION_ARGUMENTS - we prefer to look at functions in .c files
(hopefully with docbook documentation), not .h
file prototypes
MULTISTATEMENT_MACRO_USE_DO_WHILE
- we have _many_ x-macros and other macros where
we can't do this
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Now we store the transaction's fn idx in a local variable, instead of
redoing the lookup every time we call bch2_trans_init().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
- factor out fsck_err_get()
- if the "bcachefs (%s):" prefix has already been applied, don't
duplicate it
- convert to printbufs instead of static char arrays
- tidy up control flow a bit
- use bch2_print_string_as_lines(), to avoid messages getting truncated
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This removes an optimization that didn't actually save us any memory,
due to alignment, but did make the code more complicated than it needed
to be. We were also seeing a bug where journal_seq_base wasn't getting
correctly initailized, so hopefully it'll fix that too.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Since we've now got time_stats for lock hold times (per btree
transaction), we don't need this anymore.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Also, do some reorganizing/renaming, convert atomic counters in bch_fs
to persistent counters, and add a few missing counters.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This patch
- tracks maximum bch2_trans_kmalloc() memory used in btree_transaction_stats
- makes it available in debugfs
- switches bch2_trans_init() to using that for the amount of memory to
preallocate, instead of the parameter passed in
This drastically reduces transaction restarts, and means we no longer
need to track this in the source code.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We need a way to check if the machinery for handling btree_paths with in
a transaction is behaving reasonably, as it often has not been - we've
had bugs with transaction path overflows caused by duplicate paths and
plenty of other things.
This patch tracks, per transaction fn, the most btree paths ever
allocated by that transaction and makes it available in debugfs.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Going to be adding more things to this in the next patch.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We now record the length of time btree locks are held and expose this in debugfs.
Enabled via CONFIG_BCACHEFS_LOCK_TIME_STATS.
Signed-off-by: Daniel Hill <daniel@gluo.nz>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
fsck doesn't want to run while we're cleaning up deleted snapshots - if
that work needs to be done, we want it to have finished before fsck
runs, otherwise fsck will get confused when it finds multiple keys in
the same snapshot ID equivalence class (i.e. the mechanism that
snapshot deletion uses for cleaning up redundant keys).
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
move_ratelimit() now has a bool that specifies whether we want to
wait for copygc to finish.
When copygc is running, we're probably low on free buckets instead
of consuming the remaining buckets, we want to wait for copygc to
finish.
This should help with performance, and run away bucket fragmentation.
Signed-off-by: Daniel Hill <daniel@gluo.nz>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
btree updates before going RW are expensive if they're in random order,
since they use the list of keys for journal replay to insert, which is
just a gap buffer.
This patch improves the bucket invalidate path so that if
bch2_check_lrus() hasn't finished it only prints warnings instead of
doing an emergency shutdown, which means we can now set BCH_FS_MAY_GO_RW
before bch2_check_lrus().
Also, the filesystem state bits are reorganized a bit.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
This adds a new superblock field for persisting counters
and adds a sysfs interface in counters/ exposing these counters.
The superblock field is ignored by older versions letting us avoid
an on disk version bump.
Each sysfs file outputs a counter that tracks since filesystem
creation and a counter for the current mount session.
Signed-off-by: Daniel Hill <daniel@gluo.nz>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
We're seeing occasional firings of the assertion in the key cache
shutdown code that nr_dirty == 0, which means we must sometimes be doing
transaction commits after we've gone read only.
Cleanups & changes:
- BCH_FS_ALLOC_CLEAN renamed to BCH_FS_CLEAN_SHUTDOWN
- new helper bch2_btree_interior_updates_flush(), which returns true if
it had to wait
- bch2_btree_flush_writes() now also returns true if there were btree
writes in flight
- __bch2_fs_read_only now checks if btree writes were in flight in the
shutdown loop: btree write completion does a transaction update, to
update the pointer in the parent node
- assert that !BCH_FS_CLEAN_SHUTDOWN in __bch2_trans_commit
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
This option was useful when the replicas mechism was new and still being
debugged, but hasn't been used in ages - let's delete it.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Previously, the journal read path used a linked list for storing the
journal entries we read from disk. But there's been a bug that's been
causing journal_flush_delay to incorrectly be set to 0, leading to far
more journal entries than is normal being written out, which then means
filesystems are no longer able to start due to the O(n^2) behaviour of
inserting into/searching that linked list.
Fix this by switching to a radix tree.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Btree updates before we go RW work by inserting into the array of keys
that journal replay will insert - but inserting into a flat array is
O(n), meaning if btree_gc needs to update many alloc keys, we're O(n^2).
Fortunately, the updates btree_gc does happens in sequential order,
which means a gap buffer works nicely here - this patch implements a gap
buffer for journal keys.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
All code using the in-memory bucket array, excluding GC, has now been
converted to use the alloc btree directly - so we can finally delete it.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
In the old allocator code, preparing an existing empty bucket was part
of the same code path that invalidated buckets containing cached data.
In the new allocator code this is no longer the case: the main allocator
path finds empty buckets (via the new freespace btree), and can't
allocate buckets that contain cached data.
We now need a separate code path to invalidate buckets containing cached
data when we're low on empty buckets, which this patch implements. When
the number of free buckets decreases that triggers the new invalidate
path to run, which uses the LRU btree to pick cached data buckets to
invalidate until we're above our watermark.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
In the old allocator code, buckets would be discarded just prior to
being used - this made sense in bcache where we were discarding buckets
just after invalidating the cached data they contain, but in a
filesystem where we typically have more free space we want to be
discarding buckets when they become empty.
This patch implements the new behaviour - it checks the need_discard
btree for buckets awaiting discards, and then clears the appropriate
bit in the alloc btree, which moves the buckets to the freespace btree.
Additionally, discards are now enabled by default.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Now that we have new persistent data structures for the allocator, this
patch converts the allocator to use them.
Now, foreground bucket allocation uses the freespace btree to find
buckets to allocate, instead of popping buckets off the freelist.
The background allocator threads are no longer needed and are deleted,
as well as the allocator freelists. Now we only need background tasks
for invalidating buckets containing cached data (when we are low on
empty buckets), and for issuing discards.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This adds two new btrees for the upcoming allocator rewrite: an extents
btree of free buckets, and a btree for buckets awaiting discards.
We also add a new trigger for alloc keys to keep the new btrees up to
date, and a compatibility path to initialize them on existing
filesystems.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This implements new persistent LRUs, to be used for buckets containing
cached data, as well as stripes ordered by time when a block became
empty.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
In sysfs, files can only output at most PAGE_SIZE. This is a problem for
debug info that needs to list an arbitrary number of times, and because
of this limit some of our debug info has been terser and harder to read
than we'd like.
This patch moves info about journal pins and cached btree nodes to
debugfs, and greatly expands and improves the output we return.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
This improves __bch2_trans_commit - early in the recovery process, when
we're running btree_gc and before we want to go RW, it now uses
bch2_journal_key_insert() to add the update to the list of updates for
journal replay to do, instead of btree_gc having to use separate
interfaces depending on whether we're running at bringup or, later,
runtime.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
The old .debugcheck methods are no more and this just calls the .invalid
method, which doesn't add much since we already check that when doing
btree updates and when reading metadata in.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Like the previous patches, this converts bch2_gc_gens() to use the alloc
btree directly, and private arrays of generation numbers for its own
recalculation of oldest_gen.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
This changes the btree_gc code to only use the second bucket array, the
one dedicated to GC. On completion, it compares what's in its in memory
bucket array to the allocation information in the btree and writes it
directly, instead of updating the main in-memory bucket array and
writing that.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Add a new helper that returns true if the given btree ID uses the btree
key cache. This enables some new cleanups, since the helper can check
the options for whether caching is enabled on a given btree.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
We were double-freeing old_buckets and not freeing old_buckets_gens:
also, the code was supposed to free buckets, not old_buckets;
old_buckets is only needed because we have to use rcu_assign_pointer()
instead of swap(), and won't be set if we hit the error path.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
Implement a hash table, using cuckoo hashing, for empty buckets that are
waiting on a journal commit before they can be reused.
This replaces the journal_seq field of bucket_mark, and is part of
eventually getting rid of the in memory bucket array.
We may need to make bch2_bucket_needs_journal_commit() lockless, pending
profiling and testing.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
This reverts commit f95b61228efd04c9c158123da5827c96e9773b29.
It turns out, we're seeing filesystems in the wild end up with
blacklisted btree node bsets - this should not be happening, and until
we understand why and fix it we need to keep this code around.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
- Add a shim uuid_unparse_lower() in the kernel, since %pU doesn't work
in userspace
- We don't need to print the bcachefs: or the filesystem name prefix in
userspace
- Improve a few error messages
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>