summaryrefslogtreecommitdiffstats
path: root/include/linux/ceph/rados.h
blob: de91fbdf127e64b343f3fc3530d6d7fb9bd4e59e (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
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
#ifndef CEPH_RADOS_H
#define CEPH_RADOS_H

/*
 * Data types for the Ceph distributed object storage layer RADOS
 * (Reliable Autonomic Distributed Object Store).
 */

#include <linux/ceph/msgr.h>

/*
 * osdmap encoding versions
 */
#define CEPH_OSDMAP_INC_VERSION     5
#define CEPH_OSDMAP_INC_VERSION_EXT 6
#define CEPH_OSDMAP_VERSION         5
#define CEPH_OSDMAP_VERSION_EXT     6

/*
 * fs id
 */
struct ceph_fsid {
	unsigned char fsid[16];
};

static inline int ceph_fsid_compare(const struct ceph_fsid *a,
				    const struct ceph_fsid *b)
{
	return memcmp(a, b, sizeof(*a));
}

/*
 * ino, object, etc.
 */
typedef __le64 ceph_snapid_t;
#define CEPH_SNAPDIR ((__u64)(-1))  /* reserved for hidden .snap dir */
#define CEPH_NOSNAP  ((__u64)(-2))  /* "head", "live" revision */
#define CEPH_MAXSNAP ((__u64)(-3))  /* largest valid snapid */

struct ceph_timespec {
	__le32 tv_sec;
	__le32 tv_nsec;
} __attribute__ ((packed));


/*
 * object layout - how objects are mapped into PGs
 */
#define CEPH_OBJECT_LAYOUT_HASH     1
#define CEPH_OBJECT_LAYOUT_LINEAR   2
#define CEPH_OBJECT_LAYOUT_HASHINO  3

/*
 * pg layout -- how PGs are mapped onto (sets of) OSDs
 */
#define CEPH_PG_LAYOUT_CRUSH  0
#define CEPH_PG_LAYOUT_HASH   1
#define CEPH_PG_LAYOUT_LINEAR 2
#define CEPH_PG_LAYOUT_HYBRID 3

#define CEPH_PG_MAX_SIZE      16  /* max # osds in a single pg */

/*
 * placement group.
 * we encode this into one __le64.
 */
struct ceph_pg {
	__le16 preferred; /* preferred primary osd */
	__le16 ps;        /* placement seed */
	__le32 pool;      /* object pool */
} __attribute__ ((packed));

/*
 * pg_pool is a set of pgs storing a pool of objects
 *
 *  pg_num -- base number of pseudorandomly placed pgs
 *
 *  pgp_num -- effective number when calculating pg placement.  this
 * is used for pg_num increases.  new pgs result in data being "split"
 * into new pgs.  for this to proceed smoothly, new pgs are intiially
 * colocated with their parents; that is, pgp_num doesn't increase
 * until the new pgs have successfully split.  only _then_ are the new
 * pgs placed independently.
 *
 *  lpg_num -- localized pg count (per device).  replicas are randomly
 * selected.
 *
 *  lpgp_num -- as above.
 */
#define CEPH_PG_TYPE_REP     1
#define CEPH_PG_TYPE_RAID4   2
#define CEPH_PG_POOL_VERSION 2
struct ceph_pg_pool {
	__u8 type;                /* CEPH_PG_TYPE_* */
	__u8 size;                /* number of osds in each pg */
	__u8 crush_ruleset;       /* crush placement rule */
	__u8 object_hash;         /* hash mapping object name to ps */
	__le32 pg_num, pgp_num;   /* number of pg's */
	__le32 lpg_num, lpgp_num; /* number of localized pg's */
	__le32 last_change;       /* most recent epoch changed */
	__le64 snap_seq;          /* seq for per-pool snapshot */
	__le32 snap_epoch;        /* epoch of last snap */
	__le32 num_snaps;
	__le32 num_removed_snap_intervals; /* if non-empty, NO per-pool snaps */
	__le64 auid;               /* who owns the pg */
} __attribute__ ((packed));

/*
 * stable_mod func is used to control number of placement groups.
 * similar to straight-up modulo, but produces a stable mapping as b
 * increases over time.  b is the number of bins, and bmask is the
 * containing power of 2 minus 1.
 *
 * b <= bmask and bmask=(2**n)-1
 * e.g., b=12 -> bmask=15, b=123 -> bmask=127
 */
static inline int ceph_stable_mod(int x, int b, int bmask)
{
	if ((x & bmask) < b)
		return x & bmask;
	else
		return x & (bmask >> 1);
}

/*
 * object layout - how a given object should be stored.
 */
struct ceph_object_layout {
	struct ceph_pg ol_pgid;   /* raw pg, with _full_ ps precision. */
	__le32 ol_stripe_unit;    /* for per-object parity, if any */
} __attribute__ ((packed));

/*
 * compound epoch+version, used by storage layer to serialize mutations
 */
struct ceph_eversion {
	__le32 epoch;
	__le64 version;
} __attribute__ ((packed));

/*
 * osd map bits
 */

/* status bits */
#define CEPH_OSD_EXISTS 1
#define CEPH_OSD_UP     2

/* osd weights.  fixed point value: 0x10000 == 1.0 ("in"), 0 == "out" */
#define CEPH_OSD_IN  0x10000
#define CEPH_OSD_OUT 0


/*
 * osd map flag bits
 */
#define CEPH_OSDMAP_NEARFULL (1<<0)  /* sync writes (near ENOSPC) */
#define CEPH_OSDMAP_FULL     (1<<1)  /* no data writes (ENOSPC) */
#define CEPH_OSDMAP_PAUSERD  (1<<2)  /* pause all reads */
#define CEPH_OSDMAP_PAUSEWR  (1<<3)  /* pause all writes */
#define CEPH_OSDMAP_PAUSEREC (1<<4)  /* pause recovery */

/*
 * osd ops
 */
#define CEPH_OSD_OP_MODE       0xf000
#define CEPH_OSD_OP_MODE_RD    0x1000
#define CEPH_OSD_OP_MODE_WR    0x2000
#define CEPH_OSD_OP_MODE_RMW   0x3000
#define CEPH_OSD_OP_MODE_SUB   0x4000

#define CEPH_OSD_OP_TYPE       0x0f00
#define CEPH_OSD_OP_TYPE_LOCK  0x0100
#define CEPH_OSD_OP_TYPE_DATA  0x0200
#define CEPH_OSD_OP_TYPE_ATTR  0x0300
#define CEPH_OSD_OP_TYPE_EXEC  0x0400
#define CEPH_OSD_OP_TYPE_PG    0x0500

enum {
	/** data **/
	/* read */
	CEPH_OSD_OP_READ      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 1,
	CEPH_OSD_OP_STAT      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 2,
	CEPH_OSD_OP_MAPEXT    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 3,

	/* fancy read */
	CEPH_OSD_OP_MASKTRUNC   = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 4,
	CEPH_OSD_OP_SPARSE_READ = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 5,

	CEPH_OSD_OP_NOTIFY    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 6,
	CEPH_OSD_OP_NOTIFY_ACK = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 7,

	/* versioning */
	CEPH_OSD_OP_ASSERT_VER = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 8,

	/* write */
	CEPH_OSD_OP_WRITE     = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 1,
	CEPH_OSD_OP_WRITEFULL = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 2,
	CEPH_OSD_OP_TRUNCATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 3,
	CEPH_OSD_OP_ZERO      = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 4,
	CEPH_OSD_OP_DELETE    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 5,

	/* fancy write */
	CEPH_OSD_OP_APPEND    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 6,
	CEPH_OSD_OP_STARTSYNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 7,
	CEPH_OSD_OP_SETTRUNC  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 8,
	CEPH_OSD_OP_TRIMTRUNC = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 9,

	CEPH_OSD_OP_TMAPUP  = CEPH_OSD_OP_MODE_RMW | CEPH_OSD_OP_TYPE_DATA | 10,
	CEPH_OSD_OP_TMAPPUT = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 11,
	CEPH_OSD_OP_TMAPGET = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_DATA | 12,

	CEPH_OSD_OP_CREATE  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 13,
	CEPH_OSD_OP_ROLLBACK= CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 14,

	CEPH_OSD_OP_WATCH   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_DATA | 15,

	/** attrs **/
	/* read */
	CEPH_OSD_OP_GETXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 1,
	CEPH_OSD_OP_GETXATTRS = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 2,
	CEPH_OSD_OP_CMPXATTR  = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_ATTR | 3,

	/* write */
	CEPH_OSD_OP_SETXATTR  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 1,
	CEPH_OSD_OP_SETXATTRS = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 2,
	CEPH_OSD_OP_RESETXATTRS = CEPH_OSD_OP_MODE_WR|CEPH_OSD_OP_TYPE_ATTR | 3,
	CEPH_OSD_OP_RMXATTR   = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_ATTR | 4,

	/** subop **/
	CEPH_OSD_OP_PULL            = CEPH_OSD_OP_MODE_SUB | 1,
	CEPH_OSD_OP_PUSH            = CEPH_OSD_OP_MODE_SUB | 2,
	CEPH_OSD_OP_BALANCEREADS    = CEPH_OSD_OP_MODE_SUB | 3,
	CEPH_OSD_OP_UNBALANCEREADS  = CEPH_OSD_OP_MODE_SUB | 4,
	CEPH_OSD_OP_SCRUB           = CEPH_OSD_OP_MODE_SUB | 5,
	CEPH_OSD_OP_SCRUB_RESERVE   = CEPH_OSD_OP_MODE_SUB | 6,
	CEPH_OSD_OP_SCRUB_UNRESERVE = CEPH_OSD_OP_MODE_SUB | 7,
	CEPH_OSD_OP_SCRUB_STOP      = CEPH_OSD_OP_MODE_SUB | 8,

	/** lock **/
	CEPH_OSD_OP_WRLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 1,
	CEPH_OSD_OP_WRUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 2,
	CEPH_OSD_OP_RDLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 3,
	CEPH_OSD_OP_RDUNLOCK  = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 4,
	CEPH_OSD_OP_UPLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 5,
	CEPH_OSD_OP_DNLOCK    = CEPH_OSD_OP_MODE_WR | CEPH_OSD_OP_TYPE_LOCK | 6,

	/** exec **/
	CEPH_OSD_OP_CALL    = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_EXEC | 1,

	/** pg **/
	CEPH_OSD_OP_PGLS      = CEPH_OSD_OP_MODE_RD | CEPH_OSD_OP_TYPE_PG | 1,
};

static inline int ceph_osd_op_type_lock(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_LOCK;
}
static inline int ceph_osd_op_type_data(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_DATA;
}
static inline int ceph_osd_op_type_attr(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_ATTR;
}
static inline int ceph_osd_op_type_exec(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_EXEC;
}
static inline int ceph_osd_op_type_pg(int op)
{
	return (op & CEPH_OSD_OP_TYPE) == CEPH_OSD_OP_TYPE_PG;
}

static inline int ceph_osd_op_mode_subop(int op)
{
	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_SUB;
}
static inline int ceph_osd_op_mode_read(int op)
{
	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_RD;
}
static inline int ceph_osd_op_mode_modify(int op)
{
	return (op & CEPH_OSD_OP_MODE) == CEPH_OSD_OP_MODE_WR;
}

/*
 * note that the following tmap stuff is also defined in the ceph librados.h
 * any modification here needs to be updated there
 */
#define CEPH_OSD_TMAP_HDR 'h'
#define CEPH_OSD_TMAP_SET 's'
#define CEPH_OSD_TMAP_RM  'r'

extern const char *ceph_osd_op_name(int op);


/*
 * osd op flags
 *
 * An op may be READ, WRITE, or READ|WRITE.
 */
enum {
	CEPH_OSD_FLAG_ACK = 1,          /* want (or is) "ack" ack */
	CEPH_OSD_FLAG_ONNVRAM = 2,      /* want (or is) "onnvram" ack */
	CEPH_OSD_FLAG_ONDISK = 4,       /* want (or is) "ondisk" ack */
	CEPH_OSD_FLAG_RETRY = 8,        /* resend attempt */
	CEPH_OSD_FLAG_READ = 16,        /* op may read */
	CEPH_OSD_FLAG_WRITE = 32,       /* op may write */
	CEPH_OSD_FLAG_ORDERSNAP = 64,   /* EOLDSNAP if snapc is out of order */
	CEPH_OSD_FLAG_PEERSTAT = 128,   /* msg includes osd_peer_stat */
	CEPH_OSD_FLAG_BALANCE_READS = 256,
	CEPH_OSD_FLAG_PARALLELEXEC = 512, /* execute op in parallel */
	CEPH_OSD_FLAG_PGOP = 1024,      /* pg op, no object */
	CEPH_OSD_FLAG_EXEC = 2048,      /* op may exec */
	CEPH_OSD_FLAG_EXEC_PUBLIC = 4096, /* op may exec (public) */
};

enum {
	CEPH_OSD_OP_FLAG_EXCL = 1,      /* EXCL object create */
};

#define EOLDSNAPC    ERESTART  /* ORDERSNAP flag set; writer has old snapc*/
#define EBLACKLISTED ESHUTDOWN /* blacklisted */

/* xattr comparison */
enum {
	CEPH_OSD_CMPXATTR_OP_NOP = 0,
	CEPH_OSD_CMPXATTR_OP_EQ  = 1,
	CEPH_OSD_CMPXATTR_OP_NE  = 2,
	CEPH_OSD_CMPXATTR_OP_GT  = 3,
	CEPH_OSD_CMPXATTR_OP_GTE = 4,
	CEPH_OSD_CMPXATTR_OP_LT  = 5,
	CEPH_OSD_CMPXATTR_OP_LTE = 6
};

enum {
	CEPH_OSD_CMPXATTR_MODE_STRING = 1,
	CEPH_OSD_CMPXATTR_MODE_U64    = 2
};

#define RADOS_NOTIFY_VER	1

/*
 * an individual object operation.  each may be accompanied by some data
 * payload
 */
struct ceph_osd_op {
	__le16 op;           /* CEPH_OSD_OP_* */
	__le32 flags;        /* CEPH_OSD_FLAG_* */
	union {
		struct {
			__le64 offset, length;
			__le64 truncate_size;
			__le32 truncate_seq;
		} __attribute__ ((packed)) extent;
		struct {
			__le32 name_len;
			__le32 value_len;
			__u8 cmp_op;       /* CEPH_OSD_CMPXATTR_OP_* */
			__u8 cmp_mode;     /* CEPH_OSD_CMPXATTR_MODE_* */
		} __attribute__ ((packed)) xattr;
		struct {
			__u8 class_len;
			__u8 method_len;
			__u8 argc;
			__le32 indata_len;
		} __attribute__ ((packed)) cls;
		struct {
			__le64 cookie, count;
		} __attribute__ ((packed)) pgls;
	        struct {
		        __le64 snapid;
	        } __attribute__ ((packed)) snap;
		struct {
			__le64 cookie;
			__le64 ver;
			__u8 flag;	/* 0 = unwatch, 1 = watch */
		} __attribute__ ((packed)) watch;
};
	__le32 payload_len;
} __attribute__ ((packed));

/*
 * osd request message header.  each request may include multiple
 * ceph_osd_op object operations.
 */
struct ceph_osd_request_head {
	__le32 client_inc;                 /* client incarnation */
	struct ceph_object_layout layout;  /* pgid */
	__le32 osdmap_epoch;               /* client's osdmap epoch */

	__le32 flags;

	struct ceph_timespec mtime;        /* for mutations only */
	struct ceph_eversion reassert_version; /* if we are replaying op */

	__le32 object_len;     /* length of object name */

	__le64 snapid;         /* snapid to read */
	__le64 snap_seq;       /* writer's snap context */
	__le32 num_snaps;

	__le16 num_ops;
	struct ceph_osd_op ops[];  /* followed by ops[], obj, ticket, snaps */
} __attribute__ ((packed));

struct ceph_osd_reply_head {
	__le32 client_inc;                /* client incarnation */
	__le32 flags;
	struct ceph_object_layout layout;
	__le32 osdmap_epoch;
	struct ceph_eversion reassert_version; /* for replaying uncommitted */

	__le32 result;                    /* result code */

	__le32 object_len;                /* length of object name */
	__le32 num_ops;
	struct ceph_osd_op ops[0];  /* ops[], object */
} __attribute__ ((packed));



#endif
OpenPOWER on IntegriCloud