summaryrefslogtreecommitdiff
path: root/fs/bcachefs
AgeCommit message (Collapse)AuthorFilesLines
2023-10-23bcachefs: Btree write bufferKent Overstreet16-21/+677
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>
2023-10-23bcachefs: Go RW before check_alloc_info()Kent Overstreet4-29/+53
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>
2023-10-23bcachefs: Start copygc when first going read-writeKent Overstreet2-31/+42
In the distant past, it wasn't possible to start copygc until after journal replay had finished. Now, the btree iterator code overlays keys from the journal, so there's no reason not to start it earlier - and it solves a rare deadlock. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Kill trans->flagsKent Overstreet5-51/+50
Recursive transaction commits are occasionally necessary - in particular, for the upcoming btree write buffer's flush path. This avoids bugs due to trans->flags being accidentally mutated mid-commit, which can cause c->writes refcount leaks. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: trans->notrace_relock_failKent Overstreet4-2/+11
When we unlock in order to submit IO, the next relock event is likely to fail if submit_bio() blocked - we shouldn't those events in our _fail stats, since those are expected events and shouldn't cause test failures. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Debug mode for c->writes referencesKent Overstreet13-46/+168
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>
2023-10-23bcachefs: ec_stripe_delete_work() now takes ref on c->writesKent Overstreet3-8/+17
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix btree_node_write_blocked() not being clearedKent Overstreet1-0/+3
The btree_node_write_blocked bit was a later addition to this code, it only mirrors the state of the b->write_blocked list (empty or nonempty) - unfortunately, when it was added it wasn't correctly kept in sync - oops. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Switch a BUG_ON() to a panic()Kent Overstreet1-1/+4
This assert is popping - rarely - in the CI, this will help us track it down from the logs. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix btree_path_alloc()Kent Overstreet1-3/+8
We need to call bch2_trans_update_max_paths() before marking the new path as allocated, since we're not initializing it yet. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix memleak in replicas_table_update()Brett Holman1-7/+0
Signed-off-by: Brett Holman <bholman.devel@gmail.com> Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Use for_each_btree_key_upto() more consistentlyKent Overstreet11-81/+150
It's important that in BTREE_ITER_FILTER_SNAPSHOTS mode we always use peek_upto() and provide an end for the interval we're searching for - otherwise, when we hit the end of the inode the next inode be in a different subvolume and not have any keys in the current snapshot, and we'd iterate over arbitrarily many keys before returning one. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Don't call bch2_journal_pin_drop() under key cache lockKent Overstreet1-6/+8
This fixes a (harmless) lockdep splat, due to a lock order violation in the key cache exit path. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23six locks: Improved optimistic spinningKent Overstreet2-16/+39
This adds a threshold for the maximum spin time, similar to the rwsem code, and a flag to the lock itself indicating when we've spun too long so other threads also refrain from spinning. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Use six_lock_ip()Kent Overstreet6-15/+31
This uses the new _ip() interface to six locks and hooks it up to btree_path->ip_allocated, when available. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23six locks: Expose tracepoint IPKent Overstreet2-42/+82
This adds _ip variations of the various lock functions that allow an IP to be passed in, which is used by lockstat. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: bch2_trans_in_restart_error()Kent Overstreet3-13/+34
This replaces various BUG_ON() assertions with panics that tell us where the restart was done and the restart type. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Improve btree node read error pathKent Overstreet2-24/+42
This ensures that failure to read a btree node error is treated as a topology error, and returns the correct error so that the topology repair pass will be run. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix bch2_trans_reset_updates()Kent Overstreet6-32/+25
This should have been resetting trans->fs_usage_deltas as well. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Inline bch2_btree_path_traverse() fastpathKent Overstreet2-27/+17
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix hash_check_key()Kent Overstreet1-1/+1
On hash collision when we have to check for duplicates or incorrect hash value, we weren't specifying a snapshot ID to iterate with. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Don't emit tracepoints for expected eventsKent Overstreet1-2/+2
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Use trylock in bch2_prt_backtrace()Kent Overstreet1-4/+2
Easy workaround for a lockdep splat - and since bch2_prt_backtrace() is only used in debug code this is fine. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: bch2_inode_opts_get()Kent Overstreet6-51/+39
This improves io_opts() and makes it a non-inline function - it's big enough that it probably shouldn't be. Also, bch_io_opts no longer needs fields for whether options are defined, so we can slim it down a bit. We'd like to stop passing around the full bch_io_opts, but that'll be tricky because of bch2_rebalance_add_key(). Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix bch_alloc_to_text()Kent Overstreet1-1/+4
We weren't guarding against the alloc key having an invalid data type. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Better inlining in core write pathKent Overstreet5-66/+81
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>
2023-10-23bcachefs: Better inlining for bch2_alloc_to_v4_mutKent Overstreet8-201/+305
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>
2023-10-23bcachefs: Improve btree_reserve_get_fail tracepointKent Overstreet2-5/+10
Now we include the return code. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix bch2_bucket_alloc_early()Kent Overstreet1-1/+4
We were incorrectly retrying after a transaction restart. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Check for lru entries with time=0Kent Overstreet1-0/+6
These are invalid. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix rereplicate when we already have a cached pointerKent Overstreet1-2/+13
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>
2023-10-23bcachefs: Fix repair path in bch2_mark_reflink_p()Kent Overstreet1-8/+14
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Dump transaction updates before panicingKent Overstreet1-1/+1
When errors=panic, we need to dump transaction updates before calling bch2_inconsistent_error(). Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Kill fs_usage_apply_warn()Kent Overstreet1-31/+3
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>
2023-10-23bcachefs: debug: Fix some locking bugsKent Overstreet1-2/+2
This fixes a few error paths in debug code that lead to locks failing to be dropped. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Convert EAGAIN errors to private error codesKent Overstreet8-32/+24
More error code cleanup, for better error messages and debugability. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Convert EROFS errors to private error codesKent Overstreet12-17/+18
More error code improvements - this gets us more useful error messages. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix compat path for old inode formatsKent Overstreet1-0/+2
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>
2023-10-23bcachefs: bch2_trans_relock_notrace()Kent Overstreet3-1/+17
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: btree_iter->ip_allocatedKent Overstreet5-40/+78
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>
2023-10-23bcachefs: key cache: Don't hold btree locks while using GFP_RECLAIMKent Overstreet2-21/+51
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>
2023-10-23bcachefs: Improve bkey_cached_lock_for_evict()Kent Overstreet1-3/+2
We don't need a write lock to check if a key is dirty. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Fix bch2_btree_path_traverse_all()Kent Overstreet1-0/+3
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>
2023-10-23bcachefs: Delete a faulty assertionKent Overstreet1-5/+4
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Kill bch2_extent_trim_atomic() usageKent Overstreet2-23/+7
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Plumb saw_error through to btree_err()Kent Overstreet3-13/+18
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>
2023-10-23bcachefs: Convert btree_err() to a functionKent Overstreet1-49/+64
This makes the code more readable, and reduces text size by 8 kb. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: fix fsck errorKent Overstreet1-1/+1
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Make log message at startup a bit cleanerKent Overstreet1-7/+6
Don't print out opts= if no options have been specified. Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
2023-10-23bcachefs: Log more messages in the journalKent Overstreet9-67/+111
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>
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-16 13:10:31 +0300