bcachefs: Allocator now copes with unaligned buckets

We had a buggy release of bcachefs-tools that wasn't properly aligning
bucket sizes.

We can't ask users to reformat - and it's easy to teach the

bcachefs: Allocator now copes with unaligned buckets

We had a buggy release of bcachefs-tools that wasn't properly aligning
bucket sizes.

We can't ask users to reformat - and it's easy to teach the allocator to
make sure writes are properly aligned.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: EIO cleanup

Replace these with proper private error codes, so that when we get an
error message we're not sifting through the entire codebase to see where
it came from.

Signed-off-by: Ken

bcachefs: EIO cleanup

Replace these with proper private error codes, so that when we get an
error message we're not sifting through the entire codebase to see where
it came from.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: Bail out early on alloc_nowait data updates

If a data update doesn't want to block on allocations (promotes, self
healing on read error) - check if the allocation would fail before
kicking

bcachefs: Bail out early on alloc_nowait data updates

If a data update doesn't want to block on allocations (promotes, self
healing on read error) - check if the allocation would fail before
kicking off the data update and calling into the write path.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: dev_alloc_list.devs -> dev_alloc_list.data

This lets us use darray macros on dev_alloc_list (and it will become a
darray eventually, when we increase the maximum number of devices).

Signe

bcachefs: dev_alloc_list.devs -> dev_alloc_list.data

This lets us use darray macros on dev_alloc_list (and it will become a
darray eventually, when we increase the maximum number of devices).

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: Kill bch2_bucket_alloc_new_fs()

The early-early allocation path, bch2_bucket_alloc_new_fs(), is no
longer needed - and inconsistencies around new_fs_bucket_idx have been a
frequent source

bcachefs: Kill bch2_bucket_alloc_new_fs()

The early-early allocation path, bch2_bucket_alloc_new_fs(), is no
longer needed - and inconsistencies around new_fs_bucket_idx have been a
frequent source of bugs.

Reported-by: [email protected]
Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: fix prototype to bch2_alloc_sectors_start_trans()

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: Make allocator stuck timeout configurable, ratelimit messages

Limit these messages to once every 2 minutes to avoid spamming logs;
with multiple devices the output can be quite significant

bcachefs: Make allocator stuck timeout configurable, ratelimit messages

Limit these messages to once every 2 minutes to avoid spamming logs;
with multiple devices the output can be quite significant.

Also, up the default timeout to 30 seconds from 10 seconds.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: Improved allocator debugging for ec

chasing down a device removal deadlock with erasure coding

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: bch2_btree_reserve_cache_to_text()

Add a pretty printer so the btree reserve cache can be seen in sysfs; as
it pins open_buckets we need it for tracking down open_buckets issues.

Signed-o

bcachefs: bch2_btree_reserve_cache_to_text()

Add a pretty printer so the btree reserve cache can be seen in sysfs; as
it pins open_buckets we need it for tracking down open_buckets issues.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: ob_dev()

Wrapper around bch2_dev_have_ref() for open_buckets; we do guarantee
that the device an open_bucket points to exists.

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: bch2_print_allocator_stuck()

If we block on the allocator for more than 10 seconds, print out some
useful debugging info.

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: plumb data_type into bch2_bucket_alloc_trans()

prep work for making the allocator try to keep btree nodes within the
existing member info btree allocated bitmap

Signed-off-by: Kent Overst

bcachefs: plumb data_type into bch2_bucket_alloc_trans()

prep work for making the allocator try to keep btree nodes within the
existing member info btree allocated bitmap

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: member helper cleanups

Some renaming for better consistency

bch2_member_exists -> bch2_member_alive
bch2_dev_exists -> bch2_member_exists
bch2_dev_exsits2 -> bch2_dev_exists
bch_dev_lock

bcachefs: member helper cleanups

Some renaming for better consistency

bch2_member_exists -> bch2_member_alive
bch2_dev_exists -> bch2_member_exists
bch2_dev_exsits2 -> bch2_dev_exists
bch_dev_locked -> bch2_dev_locked
bch_dev_bkey_exists -> bch2_dev_bkey_exists

new helper - bch2_dev_safe

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: sb-members.c

Split out a new file for bch_sb_field_members - we'll likely want to
move more code here in the future.

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: Rename enum alloc_reserve -> bch_watermark

This is prep work for consolidating with JOURNAL_WATERMARK.

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: New erasure coding shutdown path

This implements a new shutdown path for erasure coding, which is needed
for the upcoming BCH_WRITE_WAIT_FOR_EC write path.

The process is:
- Cancel new s

bcachefs: New erasure coding shutdown path

This implements a new shutdown path for erasure coding, which is needed
for the upcoming BCH_WRITE_WAIT_FOR_EC write path.

The process is:
- Cancel new stripes being built up
- Close out/cancel open buckets on write points or the partial list
that are for stripes
- Shutdown rebalance/copygc
- Then wait for in flight new stripes to finish

With BCH_WRITE_WAIT_FOR_EC, move ops will be waiting on stripes to fill
up before they complete; the new ec shutdown path is needed for shutting
down copygc/rebalance without deadlocking.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: Rework open bucket partial list allocation

Now, any open_bucket can go on the partial list: allocating from the
partial list has been moved to its own dedicated function,
open_bucket_add_b

bcachefs: Rework open bucket partial list allocation

Now, any open_bucket can go on the partial list: allocating from the
partial list has been moved to its own dedicated function,
open_bucket_add_bucets() -> bucket_alloc_set_partial().

In particular, this means that erasure coded buckets can safely go on
the partial list; the new location works with the "allocate an ec bucket
first, then the rest" logic.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: bch2_open_bucket_to_text()

Factor out a common helper

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: Erasure coding now uses bch2_bucket_alloc_trans

This code predates plumbing btree_trans through the bucket allocation
path: switching to it fixes a deadlock due to using multiple btree_tra

bcachefs: Erasure coding now uses bch2_bucket_alloc_trans

This code predates plumbing btree_trans through the bucket allocation
path: switching to it fixes a deadlock due to using multiple btree_trans
at the same time, which we never want to do.

Signed-off-by: Kent Overstreet <[email protected]>

show more ...

bcachefs: Better inlining in core write path

Provide inline versions of some allocation functions
- bch2_alloc_sectors_done_inlined()
- bch2_alloc_sectors_append_ptrs_inlined()

and use them in th

bcachefs: Better inlining in core write path

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 <[email protected]>

show more ...

bcachefs: Kill bch2_alloc_sectors_start()

Only used in one place, just inline it there.

Signed-off-by: Kent Overstreet <[email protected]>

bcachefs: Kill allocator threads & freelists

Now that we have new persistent data structures for the allocator, this
patch converts the allocator to use them.

Now, foreground bucket allocation uses

bcachefs: Kill allocator threads & freelists

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 <[email protected]>

show more ...

bcachefs: Freespace, need_discard btrees

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

bcachefs: Freespace, need_discard btrees

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 <[email protected]>

show more ...

bcachefs: Run btree updates after write out of write_point

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 u

bcachefs: Run btree updates after write out of write_point

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 <[email protected]>

show more ...

bcachefs: x-macroize alloc_reserve enum

This makes an array of strings available, like our other enums.

Signed-off-by: Kent Overstreet <[email protected]>