summaryrefslogtreecommitdiff
path: root/include/linux/ceph/osdmap.h
blob: 5e601975745f2b3e6513416cfaa3af87a9a9f11f (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
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
/* SPDX-License-Identifier: GPL-2.0 */
#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/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_SPG_NOSHARD	-1

struct ceph_spg {
	struct ceph_pg pgid;
	s8 shard;
};

int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs);
int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs);

#define CEPH_POOL_FLAG_HASHPSPOOL	(1ULL << 0) /* hash pg seed and pool id
						       together */
#define CEPH_POOL_FLAG_FULL		(1ULL << 1) /* pool is full */
#define CEPH_POOL_FLAG_FULL_QUOTA	(1ULL << 10) /* pool ran out of quota,
							will set FULL too */
#define CEPH_POOL_FLAG_NEARFULL		(1ULL << 11) /* pool is nearfull */

struct ceph_pg_pool_info {
	struct rb_node node;
	s64 id;
	u8 type; /* CEPH_POOL_TYPE_* */
	u8 size;
	u8 min_size;
	u8 crush_ruleset;
	u8 object_hash;
	u32 last_force_request_resend;
	u32 pg_num, pgp_num;
	int pg_num_mask, pgp_num_mask;
	s64 read_tier;
	s64 write_tier; /* wins for read+write ops */
	u64 flags; /* CEPH_POOL_FLAG_* */
	char *name;

	bool was_full;  /* for handle_one_map() */
};

static inline bool ceph_can_shift_osds(struct ceph_pg_pool_info *pool)
{
	switch (pool->type) {
	case CEPH_POOL_TYPE_REP:
		return true;
	case CEPH_POOL_TYPE_EC:
		return false;
	default:
		BUG();
	}
}

struct ceph_object_locator {
	s64 pool;
	struct ceph_string *pool_ns;
};

static inline void ceph_oloc_init(struct ceph_object_locator *oloc)
{
	oloc->pool = -1;
	oloc->pool_ns = NULL;
}

static inline bool ceph_oloc_empty(const struct ceph_object_locator *oloc)
{
	return oloc->pool == -1;
}

void ceph_oloc_copy(struct ceph_object_locator *dest,
		    const struct ceph_object_locator *src);
void ceph_oloc_destroy(struct ceph_object_locator *oloc);

/*
 * 51-char inline_name is long enough for all cephfs and all but one
 * rbd requests: <imgname> in "<imgname>.rbd"/"rbd_id.<imgname>" can be
 * arbitrarily long (~PAGE_SIZE).  It's done once during rbd map; all
 * other rbd requests fit into inline_name.
 *
 * Makes ceph_object_id 64 bytes on 64-bit.
 */
#define CEPH_OID_INLINE_LEN 52

/*
 * Both inline and external buffers have space for a NUL-terminator,
 * which is carried around.  It's not required though - RADOS object
 * names don't have to be NUL-terminated and may contain NULs.
 */
struct ceph_object_id {
	char *name;
	char inline_name[CEPH_OID_INLINE_LEN];
	int name_len;
};

#define __CEPH_OID_INITIALIZER(oid) { .name = (oid).inline_name }

#define CEPH_DEFINE_OID_ONSTACK(oid)				\
	struct ceph_object_id oid = __CEPH_OID_INITIALIZER(oid)

static inline void ceph_oid_init(struct ceph_object_id *oid)
{
	*oid = (struct ceph_object_id) __CEPH_OID_INITIALIZER(*oid);
}

static inline bool ceph_oid_empty(const struct ceph_object_id *oid)
{
	return oid->name == oid->inline_name && !oid->name_len;
}

void ceph_oid_copy(struct ceph_object_id *dest,
		   const struct ceph_object_id *src);
__printf(2, 3)
void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...);
__printf(3, 4)
int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp,
		     const char *fmt, ...);
void ceph_oid_destroy(struct ceph_object_id *oid);

struct ceph_pg_mapping {
	struct rb_node node;
	struct ceph_pg pgid;

	union {
		struct {
			int len;
			int osds[];
		} pg_temp, pg_upmap;
		struct {
			int osd;
		} primary_temp;
		struct {
			int len;
			int from_to[][2];
		} pg_upmap_items;
	};
};

struct ceph_osdmap {
	struct ceph_fsid fsid;
	u32 epoch;
	struct ceph_timespec created, modified;

	u32 flags;         /* CEPH_OSDMAP_* */

	u32 max_osd;       /* size of osd_state, _offload, _addr arrays */
	u32 *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 primary_temp;

	/* remap (post-CRUSH, pre-up) */
	struct rb_root pg_upmap;	/* PG := raw set */
	struct rb_root pg_upmap_items;	/* from -> to within raw set */

	u32 *osd_primary_affinity;

	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;

	struct mutex crush_workspace_mutex;
	void *crush_workspace;
};

static inline bool ceph_osd_exists(struct ceph_osdmap *map, int osd)
{
	return osd >= 0 && osd < map->max_osd &&
	       (map->osd_state[osd] & CEPH_OSD_EXISTS);
}

static inline bool ceph_osd_is_up(struct ceph_osdmap *map, int osd)
{
	return ceph_osd_exists(map, osd) &&
	       (map->osd_state[osd] & CEPH_OSD_UP);
}

static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd)
{
	return !ceph_osd_is_up(map, osd);
}

char *ceph_osdmap_state_str(char *str, int len, u32 state);
extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd);

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];
}

#define CEPH_PGID_ENCODING_LEN		(1 + 8 + 4 + 4)

static inline int ceph_decode_pgid(void **p, void *end, struct ceph_pg *pgid)
{
	__u8 version;

	if (!ceph_has_room(p, end, CEPH_PGID_ENCODING_LEN)) {
		pr_warn("incomplete pg encoding\n");
		return -EINVAL;
	}
	version = ceph_decode_8(p);
	if (version > 1) {
		pr_warn("do not understand pg encoding %d > 1\n",
			(int)version);
		return -EINVAL;
	}

	pgid->pool = ceph_decode_64(p);
	pgid->seed = ceph_decode_32(p);
	*p += 4;	/* skip deprecated preferred value */

	return 0;
}

struct ceph_osdmap *ceph_osdmap_alloc(void);
extern struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end);
struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end,
					     struct ceph_osdmap *map);
extern void ceph_osdmap_destroy(struct ceph_osdmap *map);

struct ceph_osds {
	int osds[CEPH_PG_MAX_SIZE];
	int size;
	int primary; /* id, NOT index */
};

static inline void ceph_osds_init(struct ceph_osds *set)
{
	set->size = 0;
	set->primary = -1;
}

void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src);

bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num,
		      u32 new_pg_num);
bool ceph_is_new_interval(const struct ceph_osds *old_acting,
			  const struct ceph_osds *new_acting,
			  const struct ceph_osds *old_up,
			  const struct ceph_osds *new_up,
			  int old_size,
			  int new_size,
			  int old_min_size,
			  int new_min_size,
			  u32 old_pg_num,
			  u32 new_pg_num,
			  bool old_sort_bitwise,
			  bool new_sort_bitwise,
			  bool old_recovery_deletes,
			  bool new_recovery_deletes,
			  const struct ceph_pg *pgid);
bool ceph_osds_changed(const struct ceph_osds *old_acting,
		       const struct ceph_osds *new_acting,
		       bool any_change);

void __ceph_object_locator_to_pg(struct ceph_pg_pool_info *pi,
				 const struct ceph_object_id *oid,
				 const struct ceph_object_locator *oloc,
				 struct ceph_pg *raw_pgid);
int ceph_object_locator_to_pg(struct ceph_osdmap *osdmap,
			      const struct ceph_object_id *oid,
			      const struct ceph_object_locator *oloc,
			      struct ceph_pg *raw_pgid);

void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap,
			       struct ceph_pg_pool_info *pi,
			       const struct ceph_pg *raw_pgid,
			       struct ceph_osds *up,
			       struct ceph_osds *acting);
bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap,
			      struct ceph_pg_pool_info *pi,
			      const struct ceph_pg *raw_pgid,
			      struct ceph_spg *spgid);
int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap,
			      const struct ceph_pg *raw_pgid);

extern struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map,
						    u64 id);

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);
u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id);

#endif