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
|
#ifndef _FS_CEPH_OSDMAP_H
#define _FS_CEPH_OSDMAP_H
#include <linux/rbtree.h>
#include <linux/ceph/types.h>
#include <linux/ceph/decode.h>
#include <linux/ceph/ceph_fs.h>
#include <linux/crush/crush.h>
/*
* The osd map describes the current membership of the osd cluster and
* specifies the mapping of objects to placement groups and placement
* groups to (sets of) osds. That is, it completely specifies the
* (desired) distribution of all data objects in the system at some
* point in time.
*
* Each map version is identified by an epoch, which increases monotonically.
*
* The map can be updated either via an incremental map (diff) describing
* the change between two successive epochs, or as a fully encoded map.
*/
struct ceph_pg {
uint64_t pool;
uint32_t seed;
};
#define CEPH_POOL_FLAG_HASHPSPOOL 1
struct ceph_pg_pool_info {
struct rb_node node;
s64 id;
u8 type;
u8 size;
u8 crush_ruleset;
u8 object_hash;
u32 pg_num, pgp_num;
int pg_num_mask, pgp_num_mask;
u64 flags;
char *name;
};
struct ceph_object_locator {
s64 pool;
};
struct ceph_pg_mapping {
struct rb_node node;
struct ceph_pg pgid;
int len;
int osds[];
};
struct ceph_osdmap {
struct ceph_fsid fsid;
u32 epoch;
u32 mkfs_epoch;
struct ceph_timespec created, modified;
u32 flags; /* CEPH_OSDMAP_* */
u32 max_osd; /* size of osd_state, _offload, _addr arrays */
u8 *osd_state; /* CEPH_OSD_* */
u32 *osd_weight; /* 0 = failed, 0x10000 = 100% normal */
struct ceph_entity_addr *osd_addr;
struct rb_root pg_temp;
struct rb_root pg_pools;
u32 pool_max;
/* the CRUSH map specifies the mapping of placement groups to
* the list of osds that store+replicate them. */
struct crush_map *crush;
};
static inline int ceph_osd_is_up(struct ceph_osdmap *map, int osd)
{
return (osd < map->max_osd) && (map->osd_state[osd] & CEPH_OSD_UP);
}
static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag)
{
return map && (map->flags & flag);
}
extern char *ceph_osdmap_state_str(char *str, int len, int state);
static inline struct ceph_entity_addr *ceph_osd_addr(struct ceph_osdmap *map,
int osd)
{
if (osd >= map->max_osd)
return NULL;
return &map->osd_addr[osd];
}
static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
{
__u8 version;
if (!ceph_has_room(p, end, 1 + 8 + 4 + 4)) {
pr_warning("incomplete pg encoding");
return -EINVAL;
}
version = ceph_decode_8(p);
if (version > 1) {
pr_warning("do not understand pg encoding %d > 1",
(int)version);
return -EINVAL;
}
pgid->pool = ceph_decode_64(p);
pgid->seed = ceph_decode_32(p);
*p += 4; /* skip deprecated preferred value */
return 0;
}
extern struct ceph_osdmap *osdmap_decode(void **p, void *end);
extern struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
struct ceph_osdmap *map,
struct ceph_messenger *msgr);
extern void ceph_osdmap_destroy(struct ceph_osdmap *map);
/* calculate mapping of a file extent to an object */
extern int ceph_calc_file_object_mapping(struct ceph_file_layout *layout,
u64 off, u64 len,
u64 *bno, u64 *oxoff, u64 *oxlen);
/* calculate mapping of object to a placement group */
extern int ceph_calc_ceph_pg(struct ceph_pg *pg, const char *oid,
struct ceph_osdmap *osdmap, uint64_t pool);
extern int ceph_calc_pg_acting(struct ceph_osdmap *osdmap,
struct ceph_pg pgid,
int *acting);
extern int ceph_calc_pg_primary(struct ceph_osdmap *osdmap,
struct ceph_pg pgid);
extern const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id);
extern int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name);
#endif
|
