linux/fs/bcachefs/disk_accounting_format.h

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHEFS_DISK_ACCOUNTING_FORMAT_H
#define _BCACHEFS_DISK_ACCOUNTING_FORMAT_H

#include "replicas_format.h"

/*
 * Disk accounting - KEY_TYPE_accounting - on disk format:
 *
 * Here, the key has considerably more structure than a typical key (bpos); an
 * accounting key is 'struct disk_accounting_pos', which is a union of bpos.
 *
 * More specifically: a key is just a muliword integer (where word endianness
 * matches native byte order), so we're treating bpos as an opaque 20 byte
 * integer and mapping bch_accounting_key to that.
 *
 * This is a type-tagged union of all our various subtypes; a disk accounting
 * key can be device counters, replicas counters, et cetera - it's extensible.
 *
 * The value is a list of u64s or s64s; the number of counters is specific to a
 * given accounting type.
 *
 * Unlike with other key types, updates are _deltas_, and the deltas are not
 * resolved until the update to the underlying btree, done by btree write buffer
 * flush or journal replay.
 *
 * Journal replay in particular requires special handling. The journal tracks a
 * range of entries which may possibly have not yet been applied to the btree
 * yet - it does not know definitively whether individual entries are dirty and
 * still need to be applied.
 *
 * To handle this, we use the version field of struct bkey, and give every
 * accounting update a unique version number - a total ordering in time; the
 * version number is derived from the key's position in the journal. Then
 * journal replay can compare the version number of the key from the journal
 * with the version number of the key in the btree to determine if a key needs
 * to be replayed.
 *
 * For this to work, we must maintain this strict time ordering of updates as
 * they are flushed to the btree, both via write buffer flush and via journal
 * replay. This has complications for the write buffer code while journal replay
 * is still in progress; the write buffer cannot flush any accounting keys to
 * the btree until journal replay has finished replaying its accounting keys, or
 * the (newer) version number of the keys from the write buffer will cause
 * updates from journal replay to be lost.
 */

struct bch_accounting { … };

#define BCH_ACCOUNTING_MAX_COUNTERS …

#define BCH_DATA_TYPES() …

enum bch_data_type { … };

static inline bool data_type_is_empty(enum bch_data_type type)
{ … }

static inline bool data_type_is_hidden(enum bch_data_type type)
{ … }

#define BCH_DISK_ACCOUNTING_TYPES() …

enum disk_accounting_type { … };

struct bch_nr_inodes { … };

struct bch_persistent_reserved { … };

struct bch_dev_data_type { … };

struct bch_dev_stripe_buckets { … };

struct bch_acct_compression { … };

struct bch_acct_snapshot { … };

struct bch_acct_btree { … };

struct disk_accounting_pos { … };

#endif /* _BCACHEFS_DISK_ACCOUNTING_FORMAT_H */