bcachefs: Split out discard fastpath

Buckets usually can't be discarded until the transaction that made them
empty has been committed in the journal.

Tracing has indicated that we're queuing the discard worker excessively,
only for it to skip over many buckets that are still waiting on a
journal commit, discarding only one or two buckets per iteration.

We want to switch to only queuing the discard worker after a journal
flush write, but there's an important optimization we need to preserve:
if a bucket becomes empty and it was never committed in the journal
while it was in use, we want to discard it and reuse it right away -
since overwriting it before the previous writes are flushed from the
device cache eans those writes only cost bus bandwidth.

So, this patch implements a fast path for buckets that can be discarded
right away. We need new locking between the two discard workers; the new
list of buckets being discarded provides that locking.

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

1 files changed, 5 insertions, 1 deletions

diff --git a/fs/bcachefs/bcachefs.h b/fs/bcachefs/bcachefs.h
index 4d04e9c04dc3..13b8a16c18dc 100644
--- a/fs/bcachefs/bcachefs.h
+++ b/fs/bcachefs/bcachefs.h
@@ -708,6 +708,7 @@ struct btree_trans_buf {
 	x(reflink)							\
 	x(fallocate)							\
 	x(discard)							\
+	x(discard_fast)							\
 	x(invalidate)							\
 	x(delete_dead_snapshots)					\
 	x(snapshot_delete_pagecache)					\
@@ -943,8 +944,11 @@ struct bch_fs {
 	unsigned		write_points_nr;
 
 	struct buckets_waiting_for_journal buckets_waiting_for_journal;
-	struct work_struct	discard_work;
 	struct work_struct	invalidate_work;
+	struct work_struct	discard_work;
+	struct mutex		discard_buckets_in_flight_lock;
+	DARRAY(struct bpos)	discard_buckets_in_flight;
+	struct work_struct	discard_fast_work;
 
 	/* GARBAGE COLLECTION */
 	struct task_struct	*gc_thread;