| Age | Commit message (Collapse) | Author |
|---|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
We're hunting for an open_bucket leak, add an assertion to help track it
down: also, we can't use the bch_fs after dropping our write ref to it.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Six locks do lock handoff via the wakeup path: the thread doing the
wakeup also takes the lock on behalf of the waiter, which means the
waiter only has to look at its waitlist entry, and doesn't have to touch
the lock cacheline while another thread is using it.
Linus noticed that this needs a real barrier, which this patch fixes.
Also add a comment for the should_sleep_fn() error path.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: linux-bcachefs@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This will be used when we need to re-hash a directory tree when setting
flags.
It is not possible to have concurrent btree_trans on a thread.
Signed-off-by: Joshua Ashton <joshua@froggi.es>
|
|
Now we also print the open_buckets owned by each write_point - this is
to help with debugging a shutdown hang.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
We were failing to upgrade to the latest compatible version - whoops.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This fixes the replicas_write_errors test: the patch
bcachefs: mark journal replicas before journal write submission
partially fixed replicas marking for the journal, but it broke the case
where one replica failed - this patch re-adds marking after the journal
write completes, when we know how many replicas succeeded.
Additionally, we do not consider it a fsck error when the very last
journal entry is not correctly marked, since there is an inherent race
there.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
I've been observing workloads where IPIs due to wakeups in
aio_complete() are ~15% of total CPU time in the profile. Most of those
wakeups are unnecessary when completion batching is in use in
io_getevents().
This plumbs min_nr through via the wait eventry, so that aio_complete()
can avoid doing unnecessary wakeups.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Benjamin LaHaise <bcrl@kvack.org
Cc: linux-aio@kvack.org
Cc: linux-fsdevel@vger.kernel.org
|
|
These counters should help us debug OOM issues.
Signed-off-by: Daniel Hill <daniel@gluo.nz>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
When mounted with nodataio, add the NOSUBMIT iomap flag to all data
mappings passed into the iomap layer. This causes iomap to skip all
data I/O submission and thus facilitates metadata only performance
testing.
For experimental use only. Only tested insofar as fsstress runs for
a few minutes without blowing up.
Signed-off-by: Brian Foster <bfoster@redhat.com>
|
|
Implement a quick and dirty hack to skip data I/O submission on a
specified mapping. The iomap layer will still perform every step up
through constructing the bio as if it will be submitted, but instead
invokes completion on the bio directly from submit context. The
purpose of this is to facilitate filesystem metadata performance
testing without the overhead of actual data I/O.
Note that this may be dangerous in current form in that folios are
not explicitly zeroed where they otherwise wouldn't be, so whatever
previous data exists in a folio prior to being added to a read bio
is mapped into pagecache for the file.
Signed-off-by: Brian Foster <bfoster@redhat.com>
|
|
Because scalability of the global inode_hash_lock really, really
sucks.
32-way concurrent create on a couple of different filesystems
before:
- 52.13% 0.04% [kernel] [k] ext4_create
- 52.09% ext4_create
- 41.03% __ext4_new_inode
- 29.92% insert_inode_locked
- 25.35% _raw_spin_lock
- do_raw_spin_lock
- 24.97% __pv_queued_spin_lock_slowpath
- 72.33% 0.02% [kernel] [k] do_filp_open
- 72.31% do_filp_open
- 72.28% path_openat
- 57.03% bch2_create
- 56.46% __bch2_create
- 40.43% inode_insert5
- 36.07% _raw_spin_lock
- do_raw_spin_lock
35.86% __pv_queued_spin_lock_slowpath
4.02% find_inode
Convert the inode hash table to a RCU-aware hash-bl table just like
the dentry cache. Note that we need to store a pointer to the
hlist_bl_head the inode has been added to in the inode so that when
it comes to unhash the inode we know what list to lock. We need to
do this because the hash value that is used to hash the inode is
generated from the inode itself - filesystems can provide this
themselves so we have to either store the hash or the head pointer
in the inode to be able to find the right list head for removal...
Same workload after:
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
|
|
In preparation for changing the inode hash table implementation.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This promotes mean_and_variance from bcachefs to lib/math, so it can be
used by other things.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Ideally we would disallow multiple btree_trans being initialized within
the same process - and hopefully we will at some point, the stack usage
is excessive - but for now there are a couple places where we do this:
- transaction commit error path -> journal reclaim - btree key cache
flush
- move data path -> do_pending_writes -> write path -> bucket
allocation (in the near future when bucket allocation switches to
using a freespace btree)
In order to avoid deadlocking the first btree_trans must have been
unlocked with bch2_trans_unlock() before using the second btree_trans -
this patch adds an assertion to bch2_trans_init() that verifies that
this has been done when lockdep is enabled.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This asserts (when lockdep is enabled) that btree locks aren't held when
exiting a btree_trans.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
|
|
Split out a new file from recovery.c for managing the list of keys we
read from the journal: before journal replay finishes the btree iterator
code needs to be able to iterate over and return keys from the journal
as well, so there's a fair bit of code here.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Pull code for bch_sb_field_clean out into its own file.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
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 <kent.overstreet@linux.dev>
|
|
We now have
btree_trans_commit.c
btree_update.c
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
fs-io.c is too big - time for some reorganization
- fs-dio.c: direct io
- fs-pagecache.c: pagecache data structures (bch_folio), utility code
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
On old kernels, kmalloc() may return an allocation that's not naturally
aligned - this resulted in a bug where we allocated a bio with not
enough biovecs. Fix this by using buf_pages().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This fixes a bug where we were already passing bkey_invalid_flags
around, but treating the parameter as just read/write - so the compat
code wasn't being run correctly.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Awhile back, we changed bkey_format generation to ensure that the packed
representation could never represent fields larger than the unpacked
representation.
This was to ensure that bkey_packed_successor() always gave a sensible
result, but in the current code bkey_packed_successor() is only used in
a debug assertion - not for anything important.
This kills the requirement that we've gotten rid of those weird bkey
formats, and instead changes the assertion to check if we're dealing
with an old weird bkey format.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
our debug mode assertions in bkey.c haven't been getting run, whoops
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Add error messages when we fail to lookup an inode, and also add a few
missing bch2_err_class() calls.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
We've observed significant lock thrashing on fstests generic/083 in
fallocate, due to dropping and retaking btree locks when checking the
pagecache for data.
This adds a nonblocking mode to bch2_clamp_data_hole(), where we only
use folio_trylock(), and can thus be used safely while btree locks are
held - thus we only have to drop btree locks as a fallback, on actual
lock contention.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Error code wasn't being propagated correctly, change it to match
fsck_err()
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This fixes should_restart_for_topology_repair() - previously it was
returning false if the btree io path had already seleceted topology
repair to run, even if it hadn't run yet.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
UBSAN was complaining about a shift by 64 in set_inc_field().
This only happened when the value being shifted was 0, so in theory
should be harmless - a shift by 64 (or register width) should logically
give a result of 0, but CPUs will in practice leave the input unchanged
when the number of bits to shift by wraps - and since our input here is
0, the output is still what we want.
But, it's still undefined behaviour and we need our UBSAN output to be
clean, so it needs to be fixed.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
- add a to_text() method for bkey_format
- convert bch2_bkey_format_validate() to modern error message style,
where we pass a printbuf for the error string instead of returning a
static string
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Add a new bitset btree for inodes pending deletion; this means we no
longer have to scan the full inodes btree after an unclean shutdown.
Specifically, this adds:
- a trigger to update the deleted_inodes btree based on changes to the
inodes btree
- a new recovery pass
- and check_inodes is now only a fsck pass.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
A number of smallish fixes for overlapping extent repair, and (part of)
a new unit test. This fixes all the issues turned up by bhzhu203, in his
filesystem image from running mongodb + snapshots.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
We want to ensure that fsck actually fixed all the errors it found - the
second fsck run should be clean.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
