bcachefs: Disk space accounting rewrite

Main part of the disk accounting rewrite.

This is a wholesale rewrite of the existing disk space accounting, which
relies on percepu counters that are sharded by journal buffer, and
rolled up and added to each journal write.

With the new scheme, every set of counters is a distinct key in the
accounting btree; this fixes scaling limitations of the old scheme,
where counters took up space in each journal entry and required multiple
percpu counters.

Now, in memory accounting requires a single set of percpu counters - not
multiple for each in flight journal buffer - and in the future we'll
probably also have counters that don't use in memory percpu counters,
they're not strictly required.

An accounting update is now a normal btree update, using the btree write
buffer path. At transaction commit time, we apply accounting updates to
the in memory counters, which are percpu counters indexed in an
eytzinger tree by the accounting key.

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

1 files changed, 15 insertions, 11 deletions

diff --git a/fs/bcachefs/ec.c b/fs/bcachefs/ec.c
index 83e279d41829..819d61b9ab83 100644
--- a/fs/bcachefs/ec.c
+++ b/fs/bcachefs/ec.c
@@ -13,6 +13,7 @@
 #include "btree_write_buffer.h"
 #include "buckets.h"
 #include "checksum.h"
+#include "disk_accounting.h"
 #include "disk_groups.h"
 #include "ec.h"
 #include "error.h"
@@ -302,7 +303,7 @@ static int mark_stripe_bucket(struct btree_trans *trans,
 		ret = __mark_stripe_bucket(trans, ca, s, ptr_idx, deleting, bucket, &new, flags);
 		if (!ret) {
 			alloc_to_bucket(g, new);
-			bch2_dev_usage_update(c, ca, &old, &new, 0, true);
+			bch2_dev_usage_update(c, ca, &old, &new);
 		}
 		bucket_unlock(g);
 err_unlock:
@@ -384,21 +385,25 @@ int bch2_trigger_stripe(struct btree_trans *trans,
 			new_s->nr_redundant	!= old_s->nr_redundant));
 
 		if (new_s) {
-			s64 sectors = le16_to_cpu(new_s->sectors);
+			s64 sectors = (u64) le16_to_cpu(new_s->sectors) * new_s->nr_redundant;
 
-			struct bch_replicas_padded r;
-			bch2_bkey_to_replicas(&r.e, new);
-			int ret = bch2_update_replicas_list(trans, &r.e, sectors * new_s->nr_redundant);
+			struct disk_accounting_pos acc = {
+				.type = BCH_DISK_ACCOUNTING_replicas,
+			};
+			bch2_bkey_to_replicas(&acc.replicas, new);
+			int ret = bch2_disk_accounting_mod(trans, &acc, &sectors, 1);
 			if (ret)
 				return ret;
 		}
 
 		if (old_s) {
-			s64 sectors = -((s64) le16_to_cpu(old_s->sectors));
+			s64 sectors = -((s64) le16_to_cpu(old_s->sectors)) * old_s->nr_redundant;
 
-			struct bch_replicas_padded r;
-			bch2_bkey_to_replicas(&r.e, old);
-			int ret = bch2_update_replicas_list(trans, &r.e, sectors * old_s->nr_redundant);
+			struct disk_accounting_pos acc = {
+				.type = BCH_DISK_ACCOUNTING_replicas,
+			};
+			bch2_bkey_to_replicas(&acc.replicas, old);
+			int ret = bch2_disk_accounting_mod(trans, &acc, &sectors, 1);
 			if (ret)
 				return ret;
 		}
@@ -481,8 +486,7 @@ int bch2_trigger_stripe(struct btree_trans *trans,
 			return ret;
 
 		ret = bch2_update_replicas(c, new, &m->r.e,
-				      ((s64) m->sectors * m->nr_redundant),
-				      0, true);
+				      ((s64) m->sectors * m->nr_redundant));
 		if (ret) {
 			struct printbuf buf = PRINTBUF;