| Age | Commit message (Collapse) | Author |
|---|
|
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This implements a new and improved __bch2_bkey_unpack_key() as suggested
by Eric Biggers; we use a postprocessing step to compute byte indexes
and masks, and then fetch each packed field with a simple fetch and
mask, which are now able to run in parallel.
This should provide roughly similar performance to the dynamically
generated bkey unpack functions dropped by the previous patch.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This patch makes no functional changes; we're just introducing a new
type to be used for a new and improved __bch2_bkey_unpack_key().
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
It uses vmalloc_exec, which will be removed.
Signed-off-by: Hristo Venev <hristo@venev.name>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
These deletes a bch2_trans_unlock() call from __bch2_move_data(). It was
redundant; bch2_move_extent() has the correct unlock call, and it was
buggy because when move_extent calls bch2_extent_drop_ptrs() we don't
want the transaction to be unlocked yet - this fixes a btree_iter.c
assertion.
Fixes https://github.com/koverstreet/bcachefs/issues/511.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Small performance optimization; an open coded loop is better than rep ;
movsq for small copies.
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
|
|
Originally, we used kmap() instead of kmap_atomic() for reading events
out of the completion ringbuffer because we're using copy_to_user(),
which can fault.
Now that kmap_local() is a thing, use that instead.
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>
|
|
This patch:
- Changes show_mem() to always report on slab usage
- Instead of reporting on all slabs, we only report on top 10 slabs,
and in sorted order
- Also reports on shrinkers, with the new shrinkers_to_text().
Shrinkers need to be included in OOM/allocation failure reporting
because they're responsible for memory reclaim - if a shrinker isn't
giving up its memory, we need to know which one and why.
More OOM reporting can be moved to show_mem.c and improved, this patch
is only a start.
New example output on OOM/memory allocation failure:
00177 Mem-Info:
00177 active_anon:13706 inactive_anon:32266 isolated_anon:16
00177 active_file:1653 inactive_file:1822 isolated_file:0
00177 unevictable:0 dirty:0 writeback:0
00177 slab_reclaimable:6242 slab_unreclaimable:11168
00177 mapped:3824 shmem:3 pagetables:1266 bounce:0
00177 kernel_misc_reclaimable:0
00177 free:4362 free_pcp:35 free_cma:0
00177 Node 0 active_anon:54824kB inactive_anon:129064kB active_file:6612kB inactive_file:7288kB unevictable:0kB isolated(anon):64kB isolated(file):0kB mapped:15296kB dirty:0kB writeback:0kB shmem:12kB writeback_tmp:0kB kernel_stack:3392kB pagetables:5064kB all_unreclaimable? no
00177 DMA free:2232kB boost:0kB min:88kB low:108kB high:128kB reserved_highatomic:0KB active_anon:2924kB inactive_anon:6596kB active_file:428kB inactive_file:384kB unevictable:0kB writepending:0kB present:15992kB managed:15360kB mlocked:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
00177 lowmem_reserve[]: 0 426 426 426
00177 DMA32 free:15092kB boost:5836kB min:8432kB low:9080kB high:9728kB reserved_highatomic:0KB active_anon:52196kB inactive_anon:122392kB active_file:6176kB inactive_file:7068kB unevictable:0kB writepending:0kB present:507760kB managed:441816kB mlocked:0kB bounce:0kB free_pcp:72kB local_pcp:0kB free_cma:0kB
00177 lowmem_reserve[]: 0 0 0 0
00177 DMA: 284*4kB (UM) 53*8kB (UM) 21*16kB (U) 11*32kB (U) 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 2248kB
00177 DMA32: 2765*4kB (UME) 375*8kB (UME) 57*16kB (UM) 5*32kB (U) 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 15132kB
00177 4656 total pagecache pages
00177 1031 pages in swap cache
00177 Swap cache stats: add 6572399, delete 6572173, find 488603/3286476
00177 Free swap = 509112kB
00177 Total swap = 2097148kB
00177 130938 pages RAM
00177 0 pages HighMem/MovableOnly
00177 16644 pages reserved
00177 Unreclaimable slab info:
00177 9p-fcall-cache total: 8.25 MiB active: 8.25 MiB
00177 kernfs_node_cache total: 2.15 MiB active: 2.15 MiB
00177 kmalloc-64 total: 2.08 MiB active: 2.07 MiB
00177 task_struct total: 1.95 MiB active: 1.95 MiB
00177 kmalloc-4k total: 1.50 MiB active: 1.50 MiB
00177 signal_cache total: 1.34 MiB active: 1.34 MiB
00177 kmalloc-2k total: 1.16 MiB active: 1.16 MiB
00177 bch_inode_info total: 1.02 MiB active: 922 KiB
00177 perf_event total: 1.02 MiB active: 1.02 MiB
00177 biovec-max total: 992 KiB active: 960 KiB
00177 Shrinkers:
00177 super_cache_scan: objects: 127
00177 super_cache_scan: objects: 106
00177 jbd2_journal_shrink_scan: objects: 32
00177 ext4_es_scan: objects: 32
00177 bch2_btree_cache_scan: objects: 8
00177 nr nodes: 24
00177 nr dirty: 0
00177 cannibalize lock: 0000000000000000
00177
00177 super_cache_scan: objects: 8
00177 super_cache_scan: objects: 1
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
show_mem.c is really mm specific, and the next patch in the series is
going to require mm/slab.h, so let's move it before doing more work on
it.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
|
|
The next step in this patch series for improving debugging of shrinker
related issues: keep counts of number of objects we request to free vs.
actually freed, and prints them in shrinker_to_text().
Shrinkers won't necessarily free all objects requested for a variety of
reasons, but if the two counts are wildly different something is likely
amiss.
Signed-off-by: Kent Overstreet <kent.overstreet@gmail.com>
|
|
This adds a new callback method to shrinkers which they can use to
describe anything relevant to memory reclaim about their internal state,
for example object dirtyness.
This uses the new printbufs to output to heap allocated strings, so that
the .to_text() methods can be used both for messages logged to the
console, and also sysfs/debugfs.
This patch also adds shrinkers_to_text(), which reports on the top 10
shrinkers - by object count - in sorted order, to be used in OOM
reporting.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This adds a seq_buf wrapper for string_get_size().
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 switching the VFS inode cache over the hlist_bl
lists, we nee dto be able to fake a list node that looks like it is
hased for correct operation of filesystems that don't directly use
the VFS indoe cache.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
|
|
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
|
|
|
|
A error check had a flipped conditional - whoops.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
bch2_replicas_gc_(start|end) is now only used for journal replicas
entries, which don't have bucket sector counts - so this code is
entirely dead and can be deleted.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
The journal write submission path marks the associated replica
entries for journal data in journal_write_done(), which is just
after journal write bio submission. This creates a small window
where journal entries might have been written out, but the
associated replica is not marked such that recovery does not know
that the associated device contains journal data.
Move the replica marking a bit earlier in the write path such that
recovery is guaranteed to recognize that the device contains journal
data in the event of a crash.
Signed-off-by: Brian Foster <bfoster@redhat.com>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Now that we can reliably designate and find the master subvolume out of
a tree of snapshots, we can finally make quotas work with snapshots:
That is - quotas will now _ignore_ snapshot subvolumes, and only be in
effect for the master (non snapshot) subvolume.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Add two new fields to bch_subvolume:
- otime: creation time
- parent: For snapshots, this is the id of the subvolume the snapshot
was created from
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This adds a new btree which gets us a persistent per-snapshot-tree
identifier.
- BTREE_ID_snapshot_trees
- KEY_TYPE_snapshot_tree
- bch_snapshot now has a field that points to a snapshot_tree
This is going to be used to designate one snapshot ID/subvolume out of a
given tree of snapshots as the "main" subvolume, so that we can do quota
accounting in that subvolume and not the rest.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Add a new helper for allocating a new slot in a btree.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
It's safe to call bch2_trans_update with a k/v pair where the value
hasn't been filled out, as long as the key part has been and the value
is filled out by transaction commit time.
This patch folds the bch2_trans_update() call into bch2_bkey_make_mut(),
eliminating a bit of boilerplate.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
It's safe to call bch2_trans_update with a k/v pair where the value
hasn't been filled out, as long as the key part has been and the value
is filled out by transaction commit time.
This patch folds the bch2_trans_update() call into bch2_bkey_get_mut(),
eliminating a bit of boilerplate.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
It's safe to call bch2_trans_update with a k/v pair where the value
hasn't been filled out, as long as the key part has been and the value
is filled out by transaction commit time.
This patch folds the bch2_trans_update() call into bch2_bkey_alloc(),
eliminating a bit of boilerplate.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
- bch2_bkey_get_mut() now handles types increasing in size, allocating
a buffer for the type's current size when necessary
- bch2_bkey_make_mut_typed()
- bch2_bkey_get_mut() now initializes the iterator, like
bch2_bkey_get_iter()
Also, refactor so that most of the code is in functions - now macros are
only used for wrappers.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
It's for doing updates - this is where it belongs, and next pathes will
be changing these helpers to use items from btree_update.h.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Introduce new helpers for a common pattern:
bch2_trans_iter_init();
bch2_btree_iter_peek_slot();
- bch2_bkey_get_iter_type() returns -ENOENT if it doesn't find a key of
the correct type
- bch2_bkey_get_val_typed() copies the val out of the btree to a
(typically stack allocated) variable; it handles the case where the
value in the btree is smaller than the current version of the type,
zeroing out the remainder.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This adds a new field to bkey_ops for the minimum size of the value,
which standardizes that check and also enforces the new rule (previously
done somewhat ad-hoc) that we can extend value types by adding new
fields on to the end.
To make that work we do _not_ initialize min_val_size with sizeof,
instead we initialize it to the size of the first version of those
values.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Change btree_update_flags to start after the last btree iterator flag,
so that we can pass both in the same flags argument.
This is needed for the upcoming bch2_bkey_get_mut() helper.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Brian Foster <bfoster@redhat.com>
|
|
When a device is removed from a bcachefs volume, the associated
content is removed from the various btrees. The alloc tree uses the
key cache, so when keys are removed the deletes exist in cache for a
period of time until reclaim comes along and flushes outstanding
updates.
When a device is re-added to the bcachefs volume, the add process
re-adds some of these previously deleted keys. When marking device
superblock locations on device add, the keys will likely refer to
some of the same alloc keys that were just removed. The memory
triggers for these key updates are responsible for further updates,
such as bch2_mark_alloc() calling into bch2_dev_usage_update() to
update per-device usage accounting.
When a new key is added to key cache, the trans update path also
flushes the key to the backing btree for coherency reasons for tree
walks.
With all of this context, if a device is removed and re-added
quickly enough such that some key deletes from the remove are still
pending a key cache flush, the trans update path can view this as
addition of a new key because the old key in the insert entry refers
to a deleted key. However the deleted cached key has not been filled
by absence of a btree key, but rather refers to an explicit deletion
of an existing key that occurred during device removal.
The trans update path adds a new update to flush the key and tags
the original (cached) update to skip running the memory triggers.
This results in running triggers on the non-cached update instead,
which in turn will perform accounting updates based on incoherent
values. For example, bch2_dev_usage_update() subtracts the the old
alloc key dirty sector count in the non-cached btree key from the
newly initialized (i.e. zeroed) per device counters, leading to
underflow and accounting corruption.
There are at least a few ways to avoid this problem, the simplest of
which may be to run triggers against the cached update rather than
the non-cached update. If the key only needs to be flushed when the
key is not present in the tree, however, then this still performs an
unnecessary update. We could potentially use the cached key dirty
state to determine whether the delete is a dirty, cached update vs.
a clean cache fill, but this may require transmitting key cache
dirty state across layers, which adds complexity and seems to be of
limited value. Instead, update flush_new_cached_update() to handle
this by simply checking for the key in the btree and only perform
the flush when a backing key is not present.
Signed-off-by: Brian Foster <bfoster@redhat.com>
|
|
This works around a "stack from too large" error.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
This patch deletes a .key_invalid check for btree pointers that only
applies to _very_ old on disk format versions, and potentially
complicates the upgrade process.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Improved test coverage.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
We had some bugs with setting/using first_this_inode in the inode
walker in the dirents/xattr code.
This patch changes to not clear first_this_inode until after
initializing the new hash info.
Also, we fix an error message to not print on transaction restart, and
add a comment to related fsck error code.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
|
With backpointers, it's now impossible for bch2_evacuate_bucket() to be
completely reliable: it can race with an extent being partially
overwritten or split, which needs a new write buffer flush for the
backpointer to be seen.
This shouldn't be a real issue in practice; the previous patch added a
new tracepoint so we'll be able to see more easily if it is.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
|
