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>

This behavior dates from the early, early days of bcache, and upon
further delving appears to not make any sense. The shrinker only works
in terms of 'objects' of unknown size; normalizing to pages only had the
effect of changing the batch size, which we could do directly - if we
wanted; we probably don't. Normalizing to pages meant our batch size was
very small, which seems to have been keeping us from doing as much
shrinking as we should be under heavy memory pressure; this patch
appears to alleviate some OOMs we've been seeing.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

mark_stripe_bucket() was busted; it was using @new unitialized.

Also, clean up all the gc mark functions, and convert them to the same
style.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

This neatly avoids bugs where we fail partway through initializing a new
filesystem, if we just don't write out partly-initialized state.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

With printbufs, it's now easy to build up multi-line log messages and
emit them with one call, which is good because it prevents multiple
multi-line log messages from getting Interspersed in the log buffer;
this patch also improves the formatting and converts it to latest style.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Trivial cleanup.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

In a few places we were passing a variable to pr_buf() for the format
string - oops.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

This switches struct bucket to using a lock, instead of cmpxchg. And now
that the protected members no longer need to fit into a u64, we can
expand the sector counts to 32 bits.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

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>

This is one of the last steps in getting rid of the main in-memory
bucket array.

This changes bch2_dev_usage_update() to take bkey_alloc_unpacked instead
of bucket_mark, and for the places where we are in fact working with
bucket_mark and don't have bkey_alloc_unpacked, we add a wrapper that
takes bucket_mark and converts to bkey_alloc_unpacked.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

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 introduces a new alloc key which doesn't use varints. Soon we'll be
adding backpointers and storing them in alloc keys, which means our
pack/unpack workflow for alloc keys won't really work - we'll need to be
mutating alloc keys in place.

Instead of bch2_alloc_unpack(), we now have bch2_alloc_to_v4() that
converts older types of alloc keys to v4 if needed.
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>

A new empty key type, to be used when using a btree as a set.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Add a new superblock field which represents journal buckets as ranges:
also move code for the superblock journal fields to journal_sb.c.

This also reworks the code for resizing the journal to write the new
superblock before using the new journal buckets, and thus be a bit
safer.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

In the write path, after the write to the block device(s) complete we
have to punt to process context to do the btree update.

Instead of using the work item embedded in op->cl, this patch switches
to a per write-point work item. This helps with two different issues:

 - lock contention: btree updates to the same writepoint will (usually)
   be updating the same alloc keys
 - context switch overhead: when we're bottlenecked on btree updates,
   having a thread (running out of a work item) checking the write point
   for completed ops is cheaper than queueing up a new work item and
   waking up a kworker.

In an arbitrary benchmark, 4k random writes with fio running inside a
VM, this patch resulted in a 10% improvement in total iops.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This simplifies the logic in bch2_btree_update_start() a bit, handling
the unlock/block logic more locally.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

Since journal reclaim -> btree key cache flushing may require the
allocation of new btree nodes, it has an implicit dependency on copygc
in order to make forward progress - so we should avoid blocking copygc
unless the journal is really close to full.

This introduces watermarks to replace our single MAY_GET_UNRESERVED bit
in the journal, and adds a watermark for copygc and plumbs it through.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

We don't actually want copygc allocations to be nowait - an allocation
for copygc might fail and then later succeed due to a bucket needing to
wait on journal commit, or to be discarded.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

When bch2_journal_pin_set() is updating an existing pin, we shouldn't
call bch2_journal_reclaim_fast() after dropping the old pin and before
dropping the new pin - that could reclaim the entry we're trying to pin.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

This makes an array of strings available, like our other enums.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>

For backpointers, we'll need to delete old backpointers before adding
new backpointers - otherwise we'll run into spurious duplicate
backpointer errors.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

For backpointers, we need to switch the order triggers are run in: we
need to run triggers for deletions/overwrites before triggers for
inserts.

To avoid breaking the reflink triggers, this patch moves deleting of
indirect extents with refcount=0 to their triggers, instead of doing it
when we update those keys.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Print bucket:offset when the filesystem is online; this makes debugging
easier when correlating with alloc updates.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Add a new helper for logging messages to the journal - a new debugging
tool, an alternative to trace_printk().
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

This fixes a bug where __bch2_btree_node_update_key() wasn't clearing
should_be_locked, leading to bch2_btree_path_traverse() always failing -
all callers of btree_path_make_mut() want should_be_locked cleared, so
do it there.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

bch2_btree_iter_next_node() was mucking with other btree_path state
without setting path->update to be consistent with the fact that the
path is very much no longer uptodate - oops.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

We weren't properly catching errors from snapshot_live() - oops.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

bch2_journal_space_available -> bch2_journal_halt() self deadlocks on
journal lock; work around this by dropping/retaking journal lock before
we call bch2_fatal_error().
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

When deleting an entry from a heap that was at entry h->used - 1, we'd
end up calling heap_sift() on an entry outside the heap - the entry we
just removed - which would end up re-adding it to the heap and deleting
something we didn't want to delete. Oops...
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

This tells the compiler to check printf format strings, and catches a
few bugs.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

We've been seeing a very strange bug where journal flush & reclaim delay
end up getting inexplicably zeroed, in the superblock. We're now
validating all the options in bch2_validate_super(), and 0 is no longer
a valid value for those options, but we need to be careful not to
prevent people's filesystems from mounting because of the new
validation.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>

Something funny is going on with the new code for restoring the journal
write point, and it's hard to reproduce.

We do want to debug this because resuming writing to the journal in the
wrong spot could be something serious. For now, replace the assertion
with an error message and revert to old behaviour when it happens.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>