diff options
| author | Kent Overstreet <kent.overstreet@linux.dev> | 2024-01-10 23:47:04 -0500 |
|---|---|---|
| committer | Kent Overstreet <kent.overstreet@linux.dev> | 2024-01-21 06:01:45 -0500 |
| commit | 57f2d2097603fea102330e8cfe6be4a8db24809e (patch) | |
| tree | 60436cd28c9f83ba432873e0af1a48e2e71002cb | |
| parent | 5b14ce35af901853e91e186f34e71f31b08b4e0a (diff) | |
bcachefs: Reduce would_deadlock restarts
We don't have to take locks in any particular ordering - we'll make
forward progress just fine - but if we try to stick to an ordering, it
can help to avoid excessive would_deadlock transaction restarts.
This tweaks the reflink path to take extents btree locks in the right
order.
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
| -rw-r--r-- | fs/bcachefs/reflink.c | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/fs/bcachefs/reflink.c b/fs/bcachefs/reflink.c index 607010917421..98255aa64e22 100644 --- a/fs/bcachefs/reflink.c +++ b/fs/bcachefs/reflink.c @@ -486,6 +486,13 @@ s64 bch2_remap_range(struct bch_fs *c, bch2_btree_iter_set_snapshot(&dst_iter, dst_snapshot); + if (dst_inum.inum < src_inum.inum) { + /* Avoid some lock cycle transaction restarts */ + ret = bch2_btree_iter_traverse(&dst_iter); + if (ret) + continue; + } + dst_done = dst_iter.pos.offset - dst_start.offset; src_want = POS(src_start.inode, src_start.offset + dst_done); bch2_btree_iter_set_pos(&src_iter, src_want); |