summaryrefslogtreecommitdiff
path: root/fs/bcachefs/disk_accounting.h
blob: 4ea6c8a092bc11d75e77209f7b42ed86aeee1361 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _BCACHEFS_DISK_ACCOUNTING_H
#define _BCACHEFS_DISK_ACCOUNTING_H

#include "eytzinger.h"
#include "sb-members.h"

static inline void bch2_u64s_neg(u64 *v, unsigned nr)
{
	for (unsigned i = 0; i < nr; i++)
		v[i] = -v[i];
}

static inline unsigned bch2_accounting_counters(const struct bkey *k)
{
	return bkey_val_u64s(k) - offsetof(struct bch_accounting, d) / sizeof(u64);
}

static inline void bch2_accounting_neg(struct bkey_s_accounting a)
{
	bch2_u64s_neg(a.v->d, bch2_accounting_counters(a.k));
}

static inline bool bch2_accounting_key_is_zero(struct bkey_s_c_accounting a)
{
	for (unsigned i = 0;  i < bch2_accounting_counters(a.k); i++)
		if (a.v->d[i])
			return false;
	return true;
}

static inline void bch2_accounting_accumulate(struct bkey_i_accounting *dst,
					      struct bkey_s_c_accounting src)
{
	EBUG_ON(dst->k.u64s != src.k->u64s);

	for (unsigned i = 0; i < bch2_accounting_counters(&dst->k); i++)
		dst->v.d[i] += src.v->d[i];
	if (bversion_cmp(dst->k.bversion, src.k->bversion) < 0)
		dst->k.bversion = src.k->bversion;
}

static inline void fs_usage_data_type_to_base(struct bch_fs_usage_base *fs_usage,
					      enum bch_data_type data_type,
					      s64 sectors)
{
	switch (data_type) {
	case BCH_DATA_btree:
		fs_usage->btree		+= sectors;
		break;
	case BCH_DATA_user:
	case BCH_DATA_parity:
		fs_usage->data		+= sectors;
		break;
	case BCH_DATA_cached:
		fs_usage->cached	+= sectors;
		break;
	default:
		break;
	}
}

static inline void bpos_to_disk_accounting_pos(struct disk_accounting_pos *acc, struct bpos p)
{
	acc->_pad = p;
#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
	bch2_bpos_swab(&acc->_pad);
#endif
}

static inline struct bpos disk_accounting_pos_to_bpos(struct disk_accounting_pos *k)
{
	struct bpos ret = k->_pad;

#if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__
	bch2_bpos_swab(&ret);
#endif
	return ret;
}

int bch2_disk_accounting_mod(struct btree_trans *, struct disk_accounting_pos *,
			     s64 *, unsigned, bool);
int bch2_mod_dev_cached_sectors(struct btree_trans *, unsigned, s64, bool);

int bch2_accounting_validate(struct bch_fs *, struct bkey_s_c, enum bch_validate_flags);
void bch2_accounting_key_to_text(struct printbuf *, struct disk_accounting_pos *);
void bch2_accounting_to_text(struct printbuf *, struct bch_fs *, struct bkey_s_c);
void bch2_accounting_swab(struct bkey_s);

#define bch2_bkey_ops_accounting ((struct bkey_ops) {	\
	.key_validate	= bch2_accounting_validate,	\
	.val_to_text	= bch2_accounting_to_text,	\
	.swab		= bch2_accounting_swab,		\
	.min_val_size	= 8,				\
})

int bch2_accounting_update_sb(struct btree_trans *);

static inline int accounting_pos_cmp(const void *_l, const void *_r)
{
	const struct bpos *l = _l, *r = _r;

	return bpos_cmp(*l, *r);
}

enum bch_accounting_mode {
	BCH_ACCOUNTING_normal,
	BCH_ACCOUNTING_gc,
	BCH_ACCOUNTING_read,
};

int bch2_accounting_mem_insert(struct bch_fs *, struct bkey_s_c_accounting, enum bch_accounting_mode);
void bch2_accounting_mem_gc(struct bch_fs *);

/*
 * Update in memory counters so they match the btree update we're doing; called
 * from transaction commit path
 */
static inline int bch2_accounting_mem_mod_locked(struct btree_trans *trans,
						 struct bkey_s_c_accounting a,
						 enum bch_accounting_mode mode)
{
	struct bch_fs *c = trans->c;
	struct bch_accounting_mem *acc = &c->accounting;
	struct disk_accounting_pos acc_k;
	bpos_to_disk_accounting_pos(&acc_k, a.k->p);
	bool gc = mode == BCH_ACCOUNTING_gc;

	EBUG_ON(gc && !acc->gc_running);

	if (acc_k.type == BCH_DISK_ACCOUNTING_inum)
		return 0;

	if (mode == BCH_ACCOUNTING_normal) {
		switch (acc_k.type) {
		case BCH_DISK_ACCOUNTING_persistent_reserved:
			trans->fs_usage_delta.reserved += acc_k.persistent_reserved.nr_replicas * a.v->d[0];
			break;
		case BCH_DISK_ACCOUNTING_replicas:
			fs_usage_data_type_to_base(&trans->fs_usage_delta, acc_k.replicas.data_type, a.v->d[0]);
			break;
		case BCH_DISK_ACCOUNTING_dev_data_type:
			rcu_read_lock();
			struct bch_dev *ca = bch2_dev_rcu(c, acc_k.dev_data_type.dev);
			if (ca) {
				this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].buckets, a.v->d[0]);
				this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].sectors, a.v->d[1]);
				this_cpu_add(ca->usage->d[acc_k.dev_data_type.data_type].fragmented, a.v->d[2]);
			}
			rcu_read_unlock();
			break;
		}
	}

	unsigned idx;

	while ((idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]),
				      accounting_pos_cmp, &a.k->p)) >= acc->k.nr) {
		int ret = bch2_accounting_mem_insert(c, a, mode);
		if (ret)
			return ret;
	}

	struct accounting_mem_entry *e = &acc->k.data[idx];

	EBUG_ON(bch2_accounting_counters(a.k) != e->nr_counters);

	for (unsigned i = 0; i < bch2_accounting_counters(a.k); i++)
		this_cpu_add(e->v[gc][i], a.v->d[i]);
	return 0;
}

static inline int bch2_accounting_mem_add(struct btree_trans *trans, struct bkey_s_c_accounting a, bool gc)
{
	percpu_down_read(&trans->c->mark_lock);
	int ret = bch2_accounting_mem_mod_locked(trans, a, gc ? BCH_ACCOUNTING_gc : BCH_ACCOUNTING_normal);
	percpu_up_read(&trans->c->mark_lock);
	return ret;
}

static inline void bch2_accounting_mem_read_counters(struct bch_accounting_mem *acc,
						     unsigned idx, u64 *v, unsigned nr, bool gc)
{
	memset(v, 0, sizeof(*v) * nr);

	if (unlikely(idx >= acc->k.nr))
		return;

	struct accounting_mem_entry *e = &acc->k.data[idx];

	nr = min_t(unsigned, nr, e->nr_counters);

	for (unsigned i = 0; i < nr; i++)
		v[i] = percpu_u64_get(e->v[gc] + i);
}

static inline void bch2_accounting_mem_read(struct bch_fs *c, struct bpos p,
					    u64 *v, unsigned nr)
{
	struct bch_accounting_mem *acc = &c->accounting;
	unsigned idx = eytzinger0_find(acc->k.data, acc->k.nr, sizeof(acc->k.data[0]),
				       accounting_pos_cmp, &p);

	bch2_accounting_mem_read_counters(acc, idx, v, nr, false);
}

int bch2_fs_replicas_usage_read(struct bch_fs *, darray_char *);
int bch2_fs_accounting_read(struct bch_fs *, darray_char *, unsigned);
void bch2_fs_accounting_to_text(struct printbuf *, struct bch_fs *);

int bch2_gc_accounting_start(struct bch_fs *);
int bch2_gc_accounting_done(struct bch_fs *);

int bch2_accounting_read(struct bch_fs *);

int bch2_dev_usage_remove(struct bch_fs *, unsigned);
int bch2_dev_usage_init(struct bch_dev *, bool);

void bch2_verify_accounting_clean(struct bch_fs *c);

void bch2_accounting_gc_free(struct bch_fs *);
void bch2_fs_accounting_exit(struct bch_fs *);

#endif /* _BCACHEFS_DISK_ACCOUNTING_H */