Blame view
net/ceph/osdmap.c
61.5 KB
b24413180 License cleanup: ... |
1 |
// SPDX-License-Identifier: GPL-2.0 |
f24e9980e ceph: OSD client |
2 |
|
3d14c5d2b ceph: factor out ... |
3 |
#include <linux/ceph/ceph_debug.h> |
5a0e3ad6a include cleanup: ... |
4 |
|
3d14c5d2b ceph: factor out ... |
5 |
#include <linux/module.h> |
5a0e3ad6a include cleanup: ... |
6 |
#include <linux/slab.h> |
f24e9980e ceph: OSD client |
7 |
#include <asm/div64.h> |
3d14c5d2b ceph: factor out ... |
8 9 10 11 12 |
#include <linux/ceph/libceph.h> #include <linux/ceph/osdmap.h> #include <linux/ceph/decode.h> #include <linux/crush/hash.h> #include <linux/crush/mapper.h> |
f24e9980e ceph: OSD client |
13 |
|
0bb05da2e libceph: osd_stat... |
14 |
char *ceph_osdmap_state_str(char *str, int len, u32 state) |
f24e9980e ceph: OSD client |
15 |
{ |
f24e9980e ceph: OSD client |
16 |
if (!len) |
1ec3911db libceph: fix unde... |
17 |
return str; |
f24e9980e ceph: OSD client |
18 |
|
1ec3911db libceph: fix unde... |
19 20 21 22 23 24 25 |
if ((state & CEPH_OSD_EXISTS) && (state & CEPH_OSD_UP)) snprintf(str, len, "exists, up"); else if (state & CEPH_OSD_EXISTS) snprintf(str, len, "exists"); else if (state & CEPH_OSD_UP) snprintf(str, len, "up"); else |
f24e9980e ceph: OSD client |
26 |
snprintf(str, len, "doesn't exist"); |
1ec3911db libceph: fix unde... |
27 |
|
f24e9980e ceph: OSD client |
28 29 30 31 |
return str; } /* maps */ |
95c961747 net: cleanup unsi... |
32 |
static int calc_bits_of(unsigned int t) |
f24e9980e ceph: OSD client |
33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
{ int b = 0; while (t) { t = t >> 1; b++; } return b; } /* * the foo_mask is the smallest value 2^n-1 that is >= foo. */ static void calc_pg_masks(struct ceph_pg_pool_info *pi) { |
4f6a7e5ee ceph: update supp... |
47 48 |
pi->pg_num_mask = (1 << calc_bits_of(pi->pg_num-1)) - 1; pi->pgp_num_mask = (1 << calc_bits_of(pi->pgp_num-1)) - 1; |
f24e9980e ceph: OSD client |
49 50 51 52 53 54 55 56 57 58 59 |
} /* * decode crush map */ static int crush_decode_uniform_bucket(void **p, void *end, struct crush_bucket_uniform *b) { dout("crush_decode_uniform_bucket %p to %p ", *p, end); ceph_decode_need(p, end, (1+b->h.size) * sizeof(u32), bad); |
c89136ea4 ceph: convert enc... |
60 |
b->item_weight = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 |
return 0; bad: return -EINVAL; } static int crush_decode_list_bucket(void **p, void *end, struct crush_bucket_list *b) { int j; dout("crush_decode_list_bucket %p to %p ", *p, end); b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->item_weights == NULL) return -ENOMEM; b->sum_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->sum_weights == NULL) return -ENOMEM; ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); for (j = 0; j < b->h.size; j++) { |
c89136ea4 ceph: convert enc... |
80 81 |
b->item_weights[j] = ceph_decode_32(p); b->sum_weights[j] = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
82 83 84 85 86 87 88 89 90 91 92 93 |
} return 0; bad: return -EINVAL; } static int crush_decode_tree_bucket(void **p, void *end, struct crush_bucket_tree *b) { int j; dout("crush_decode_tree_bucket %p to %p ", *p, end); |
82cd003a7 crush: fix a bug ... |
94 |
ceph_decode_8_safe(p, end, b->num_nodes, bad); |
f24e9980e ceph: OSD client |
95 96 97 98 99 |
b->node_weights = kcalloc(b->num_nodes, sizeof(u32), GFP_NOFS); if (b->node_weights == NULL) return -ENOMEM; ceph_decode_need(p, end, b->num_nodes * sizeof(u32), bad); for (j = 0; j < b->num_nodes; j++) |
c89136ea4 ceph: convert enc... |
100 |
b->node_weights[j] = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 |
return 0; bad: return -EINVAL; } static int crush_decode_straw_bucket(void **p, void *end, struct crush_bucket_straw *b) { int j; dout("crush_decode_straw_bucket %p to %p ", *p, end); b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->item_weights == NULL) return -ENOMEM; b->straws = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->straws == NULL) return -ENOMEM; ceph_decode_need(p, end, 2 * b->h.size * sizeof(u32), bad); for (j = 0; j < b->h.size; j++) { |
c89136ea4 ceph: convert enc... |
120 121 |
b->item_weights[j] = ceph_decode_32(p); b->straws[j] = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
122 123 124 125 126 |
} return 0; bad: return -EINVAL; } |
958a27658 crush: straw2 buc... |
127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
static int crush_decode_straw2_bucket(void **p, void *end, struct crush_bucket_straw2 *b) { int j; dout("crush_decode_straw2_bucket %p to %p ", *p, end); b->item_weights = kcalloc(b->h.size, sizeof(u32), GFP_NOFS); if (b->item_weights == NULL) return -ENOMEM; ceph_decode_need(p, end, b->h.size * sizeof(u32), bad); for (j = 0; j < b->h.size; j++) b->item_weights[j] = ceph_decode_32(p); return 0; bad: return -EINVAL; } |
5cf9c4a99 libceph, crush: p... |
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 |
static struct crush_choose_arg_map *alloc_choose_arg_map(void) { struct crush_choose_arg_map *arg_map; arg_map = kzalloc(sizeof(*arg_map), GFP_NOIO); if (!arg_map) return NULL; RB_CLEAR_NODE(&arg_map->node); return arg_map; } static void free_choose_arg_map(struct crush_choose_arg_map *arg_map) { if (arg_map) { int i, j; WARN_ON(!RB_EMPTY_NODE(&arg_map->node)); for (i = 0; i < arg_map->size; i++) { struct crush_choose_arg *arg = &arg_map->args[i]; for (j = 0; j < arg->weight_set_size; j++) kfree(arg->weight_set[j].weights); kfree(arg->weight_set); kfree(arg->ids); } kfree(arg_map->args); kfree(arg_map); } } DEFINE_RB_FUNCS(choose_arg_map, struct crush_choose_arg_map, choose_args_index, node); void clear_choose_args(struct crush_map *c) { while (!RB_EMPTY_ROOT(&c->choose_args)) { struct crush_choose_arg_map *arg_map = rb_entry(rb_first(&c->choose_args), struct crush_choose_arg_map, node); erase_choose_arg_map(&c->choose_args, arg_map); free_choose_arg_map(arg_map); } } static u32 *decode_array_32_alloc(void **p, void *end, u32 *plen) { u32 *a = NULL; u32 len; int ret; ceph_decode_32_safe(p, end, len, e_inval); if (len) { u32 i; a = kmalloc_array(len, sizeof(u32), GFP_NOIO); if (!a) { ret = -ENOMEM; goto fail; } ceph_decode_need(p, end, len * sizeof(u32), e_inval); for (i = 0; i < len; i++) a[i] = ceph_decode_32(p); } *plen = len; return a; e_inval: ret = -EINVAL; fail: kfree(a); return ERR_PTR(ret); } /* * Assumes @arg is zero-initialized. */ static int decode_choose_arg(void **p, void *end, struct crush_choose_arg *arg) { int ret; ceph_decode_32_safe(p, end, arg->weight_set_size, e_inval); if (arg->weight_set_size) { u32 i; arg->weight_set = kmalloc_array(arg->weight_set_size, sizeof(*arg->weight_set), GFP_NOIO); if (!arg->weight_set) return -ENOMEM; for (i = 0; i < arg->weight_set_size; i++) { struct crush_weight_set *w = &arg->weight_set[i]; w->weights = decode_array_32_alloc(p, end, &w->size); if (IS_ERR(w->weights)) { ret = PTR_ERR(w->weights); w->weights = NULL; return ret; } } } arg->ids = decode_array_32_alloc(p, end, &arg->ids_size); if (IS_ERR(arg->ids)) { ret = PTR_ERR(arg->ids); arg->ids = NULL; return ret; } return 0; e_inval: return -EINVAL; } static int decode_choose_args(void **p, void *end, struct crush_map *c) { struct crush_choose_arg_map *arg_map = NULL; u32 num_choose_arg_maps, num_buckets; int ret; ceph_decode_32_safe(p, end, num_choose_arg_maps, e_inval); while (num_choose_arg_maps--) { arg_map = alloc_choose_arg_map(); if (!arg_map) { ret = -ENOMEM; goto fail; } ceph_decode_64_safe(p, end, arg_map->choose_args_index, e_inval); arg_map->size = c->max_buckets; arg_map->args = kcalloc(arg_map->size, sizeof(*arg_map->args), GFP_NOIO); if (!arg_map->args) { ret = -ENOMEM; goto fail; } ceph_decode_32_safe(p, end, num_buckets, e_inval); while (num_buckets--) { struct crush_choose_arg *arg; u32 bucket_index; ceph_decode_32_safe(p, end, bucket_index, e_inval); if (bucket_index >= arg_map->size) goto e_inval; arg = &arg_map->args[bucket_index]; ret = decode_choose_arg(p, end, arg); if (ret) goto fail; |
c7ed1a4bf crush: assume wei... |
300 301 302 303 |
if (arg->ids_size && arg->ids_size != c->buckets[bucket_index]->size) goto e_inval; |
5cf9c4a99 libceph, crush: p... |
304 305 306 307 308 309 310 311 312 313 314 315 316 |
} insert_choose_arg_map(&c->choose_args, arg_map); } return 0; e_inval: ret = -EINVAL; fail: free_choose_arg_map(arg_map); return ret; } |
66a0e2d57 crush: remove mut... |
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 |
static void crush_finalize(struct crush_map *c) { __s32 b; /* Space for the array of pointers to per-bucket workspace */ c->working_size = sizeof(struct crush_work) + c->max_buckets * sizeof(struct crush_work_bucket *); for (b = 0; b < c->max_buckets; b++) { if (!c->buckets[b]) continue; switch (c->buckets[b]->alg) { default: /* * The base case, permutation variables and * the pointer to the permutation array. */ c->working_size += sizeof(struct crush_work_bucket); break; } /* Every bucket has a permutation array. */ c->working_size += c->buckets[b]->size * sizeof(__u32); } } |
f24e9980e ceph: OSD client |
342 343 344 |
static struct crush_map *crush_decode(void *pbyval, void *end) { struct crush_map *c; |
c2acfd95d libceph: set -EIN... |
345 |
int err; |
f24e9980e ceph: OSD client |
346 347 348 349 350 351 352 353 354 355 356 |
int i, j; void **p = &pbyval; void *start = pbyval; u32 magic; dout("crush_decode %p to %p len %d ", *p, end, (int)(end - *p)); c = kzalloc(sizeof(*c), GFP_NOFS); if (c == NULL) return ERR_PTR(-ENOMEM); |
5cf9c4a99 libceph, crush: p... |
357 |
c->choose_args = RB_ROOT; |
546f04ef7 libceph: support ... |
358 359 360 361 |
/* set tunables to default values */ c->choose_local_tries = 2; c->choose_local_fallback_tries = 5; c->choose_total_tries = 19; |
1604f488a libceph: for choo... |
362 |
c->chooseleaf_descend_once = 0; |
546f04ef7 libceph: support ... |
363 |
|
f24e9980e ceph: OSD client |
364 |
ceph_decode_need(p, end, 4*sizeof(u32), bad); |
c89136ea4 ceph: convert enc... |
365 |
magic = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
366 367 368 |
if (magic != CRUSH_MAGIC) { pr_err("crush_decode magic %x != current %x ", |
95c961747 net: cleanup unsi... |
369 |
(unsigned int)magic, (unsigned int)CRUSH_MAGIC); |
f24e9980e ceph: OSD client |
370 371 |
goto bad; } |
c89136ea4 ceph: convert enc... |
372 373 374 |
c->max_buckets = ceph_decode_32(p); c->max_rules = ceph_decode_32(p); c->max_devices = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
375 |
|
f24e9980e ceph: OSD client |
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 |
c->buckets = kcalloc(c->max_buckets, sizeof(*c->buckets), GFP_NOFS); if (c->buckets == NULL) goto badmem; c->rules = kcalloc(c->max_rules, sizeof(*c->rules), GFP_NOFS); if (c->rules == NULL) goto badmem; /* buckets */ for (i = 0; i < c->max_buckets; i++) { int size = 0; u32 alg; struct crush_bucket *b; ceph_decode_32_safe(p, end, alg, bad); if (alg == 0) { c->buckets[i] = NULL; continue; } dout("crush_decode bucket %d off %x %p to %p ", i, (int)(*p-start), *p, end); switch (alg) { case CRUSH_BUCKET_UNIFORM: size = sizeof(struct crush_bucket_uniform); break; case CRUSH_BUCKET_LIST: size = sizeof(struct crush_bucket_list); break; case CRUSH_BUCKET_TREE: size = sizeof(struct crush_bucket_tree); break; case CRUSH_BUCKET_STRAW: size = sizeof(struct crush_bucket_straw); break; |
958a27658 crush: straw2 buc... |
411 412 413 |
case CRUSH_BUCKET_STRAW2: size = sizeof(struct crush_bucket_straw2); break; |
f24e9980e ceph: OSD client |
414 415 416 417 418 419 420 421 422 |
default: goto bad; } BUG_ON(size == 0); b = c->buckets[i] = kzalloc(size, GFP_NOFS); if (b == NULL) goto badmem; ceph_decode_need(p, end, 4*sizeof(u32), bad); |
c89136ea4 ceph: convert enc... |
423 424 |
b->id = ceph_decode_32(p); b->type = ceph_decode_16(p); |
fb690390e ceph: make CRUSH ... |
425 426 |
b->alg = ceph_decode_8(p); b->hash = ceph_decode_8(p); |
c89136ea4 ceph: convert enc... |
427 428 |
b->weight = ceph_decode_32(p); b->size = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
429 430 431 432 433 434 435 436 |
dout("crush_decode bucket size %d off %x %p to %p ", b->size, (int)(*p-start), *p, end); b->items = kcalloc(b->size, sizeof(__s32), GFP_NOFS); if (b->items == NULL) goto badmem; |
f24e9980e ceph: OSD client |
437 438 439 |
ceph_decode_need(p, end, b->size*sizeof(u32), bad); for (j = 0; j < b->size; j++) |
c89136ea4 ceph: convert enc... |
440 |
b->items[j] = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
441 442 443 444 445 446 |
switch (b->alg) { case CRUSH_BUCKET_UNIFORM: err = crush_decode_uniform_bucket(p, end, (struct crush_bucket_uniform *)b); if (err < 0) |
c2acfd95d libceph: set -EIN... |
447 |
goto fail; |
f24e9980e ceph: OSD client |
448 449 450 451 452 |
break; case CRUSH_BUCKET_LIST: err = crush_decode_list_bucket(p, end, (struct crush_bucket_list *)b); if (err < 0) |
c2acfd95d libceph: set -EIN... |
453 |
goto fail; |
f24e9980e ceph: OSD client |
454 455 456 457 458 |
break; case CRUSH_BUCKET_TREE: err = crush_decode_tree_bucket(p, end, (struct crush_bucket_tree *)b); if (err < 0) |
c2acfd95d libceph: set -EIN... |
459 |
goto fail; |
f24e9980e ceph: OSD client |
460 461 462 463 464 |
break; case CRUSH_BUCKET_STRAW: err = crush_decode_straw_bucket(p, end, (struct crush_bucket_straw *)b); if (err < 0) |
c2acfd95d libceph: set -EIN... |
465 |
goto fail; |
f24e9980e ceph: OSD client |
466 |
break; |
958a27658 crush: straw2 buc... |
467 468 469 470 |
case CRUSH_BUCKET_STRAW2: err = crush_decode_straw2_bucket(p, end, (struct crush_bucket_straw2 *)b); if (err < 0) |
c2acfd95d libceph: set -EIN... |
471 |
goto fail; |
958a27658 crush: straw2 buc... |
472 |
break; |
f24e9980e ceph: OSD client |
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 |
} } /* rules */ dout("rule vec is %p ", c->rules); for (i = 0; i < c->max_rules; i++) { u32 yes; struct crush_rule *r; ceph_decode_32_safe(p, end, yes, bad); if (!yes) { dout("crush_decode NO rule %d off %x %p to %p ", i, (int)(*p-start), *p, end); c->rules[i] = NULL; continue; } dout("crush_decode rule %d off %x %p to %p ", i, (int)(*p-start), *p, end); /* len */ ceph_decode_32_safe(p, end, yes, bad); #if BITS_PER_LONG == 32 |
644866977 libceph: fix over... |
499 500 |
if (yes > (ULONG_MAX - sizeof(*r)) / sizeof(struct crush_rule_step)) |
f24e9980e ceph: OSD client |
501 502 503 504 505 506 507 508 509 510 511 512 513 |
goto bad; #endif r = c->rules[i] = kmalloc(sizeof(*r) + yes*sizeof(struct crush_rule_step), GFP_NOFS); if (r == NULL) goto badmem; dout(" rule %d is at %p ", i, r); r->len = yes; ceph_decode_copy_safe(p, end, &r->mask, 4, bad); /* 4 u8's */ ceph_decode_need(p, end, r->len*3*sizeof(u32), bad); for (j = 0; j < r->len; j++) { |
c89136ea4 ceph: convert enc... |
514 515 516 |
r->steps[j].op = ceph_decode_32(p); r->steps[j].arg1 = ceph_decode_32(p); r->steps[j].arg2 = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
517 518 |
} } |
278b1d709 libceph: ceph_dec... |
519 520 521 |
ceph_decode_skip_map(p, end, 32, string, bad); /* type_map */ ceph_decode_skip_map(p, end, 32, string, bad); /* name_map */ ceph_decode_skip_map(p, end, 32, string, bad); /* rule_name_map */ |
546f04ef7 libceph: support ... |
522 523 524 525 526 527 |
/* tunables */ ceph_decode_need(p, end, 3*sizeof(u32), done); c->choose_local_tries = ceph_decode_32(p); c->choose_local_fallback_tries = ceph_decode_32(p); c->choose_total_tries = ceph_decode_32(p); |
b9b519b78 crush: decode and... |
528 529 |
dout("crush decode tunable choose_local_tries = %d ", |
546f04ef7 libceph: support ... |
530 |
c->choose_local_tries); |
b9b519b78 crush: decode and... |
531 532 |
dout("crush decode tunable choose_local_fallback_tries = %d ", |
546f04ef7 libceph: support ... |
533 |
c->choose_local_fallback_tries); |
b9b519b78 crush: decode and... |
534 535 |
dout("crush decode tunable choose_total_tries = %d ", |
546f04ef7 libceph: support ... |
536 |
c->choose_total_tries); |
f24e9980e ceph: OSD client |
537 |
|
1604f488a libceph: for choo... |
538 539 |
ceph_decode_need(p, end, sizeof(u32), done); c->chooseleaf_descend_once = ceph_decode_32(p); |
b9b519b78 crush: decode and... |
540 541 |
dout("crush decode tunable chooseleaf_descend_once = %d ", |
1604f488a libceph: for choo... |
542 |
c->chooseleaf_descend_once); |
f140662f3 crush: decode and... |
543 544 |
ceph_decode_need(p, end, sizeof(u8), done); c->chooseleaf_vary_r = ceph_decode_8(p); |
b9b519b78 crush: decode and... |
545 546 |
dout("crush decode tunable chooseleaf_vary_r = %d ", |
f140662f3 crush: decode and... |
547 |
c->chooseleaf_vary_r); |
b9b519b78 crush: decode and... |
548 549 550 551 552 553 554 555 556 |
/* skip straw_calc_version, allowed_bucket_algs */ ceph_decode_need(p, end, sizeof(u8) + sizeof(u32), done); *p += sizeof(u8) + sizeof(u32); ceph_decode_need(p, end, sizeof(u8), done); c->chooseleaf_stable = ceph_decode_8(p); dout("crush decode tunable chooseleaf_stable = %d ", c->chooseleaf_stable); |
5cf9c4a99 libceph, crush: p... |
557 558 559 560 561 562 563 564 565 566 567 568 |
if (*p != end) { /* class_map */ ceph_decode_skip_map(p, end, 32, 32, bad); /* class_name */ ceph_decode_skip_map(p, end, 32, string, bad); /* class_bucket */ ceph_decode_skip_map_of_map(p, end, 32, 32, 32, bad); } if (*p != end) { err = decode_choose_args(p, end, c); if (err) |
c2acfd95d libceph: set -EIN... |
569 |
goto fail; |
5cf9c4a99 libceph, crush: p... |
570 |
} |
546f04ef7 libceph: support ... |
571 |
done: |
9afd30dbc libceph: fix crus... |
572 |
crush_finalize(c); |
f24e9980e ceph: OSD client |
573 574 575 576 577 578 |
dout("crush_decode success "); return c; badmem: err = -ENOMEM; |
c2acfd95d libceph: set -EIN... |
579 |
fail: |
f24e9980e ceph: OSD client |
580 581 582 583 |
dout("crush_decode fail %d ", err); crush_destroy(c); return ERR_PTR(err); |
c2acfd95d libceph: set -EIN... |
584 585 586 587 |
bad: err = -EINVAL; goto fail; |
f24e9980e ceph: OSD client |
588 |
} |
f984cb76c libceph: make pgi... |
589 |
int ceph_pg_compare(const struct ceph_pg *lhs, const struct ceph_pg *rhs) |
51042122d ceph: fix endian ... |
590 |
{ |
f984cb76c libceph: make pgi... |
591 |
if (lhs->pool < rhs->pool) |
5b191d991 libceph: decode i... |
592 |
return -1; |
f984cb76c libceph: make pgi... |
593 |
if (lhs->pool > rhs->pool) |
5b191d991 libceph: decode i... |
594 |
return 1; |
f984cb76c libceph: make pgi... |
595 |
if (lhs->seed < rhs->seed) |
51042122d ceph: fix endian ... |
596 |
return -1; |
f984cb76c libceph: make pgi... |
597 |
if (lhs->seed > rhs->seed) |
51042122d ceph: fix endian ... |
598 |
return 1; |
f984cb76c libceph: make pgi... |
599 |
|
51042122d ceph: fix endian ... |
600 601 |
return 0; } |
a02a946df libceph: respect ... |
602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 |
int ceph_spg_compare(const struct ceph_spg *lhs, const struct ceph_spg *rhs) { int ret; ret = ceph_pg_compare(&lhs->pgid, &rhs->pgid); if (ret) return ret; if (lhs->shard < rhs->shard) return -1; if (lhs->shard > rhs->shard) return 1; return 0; } |
a303bb0e5 libceph: introduc... |
617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 |
static struct ceph_pg_mapping *alloc_pg_mapping(size_t payload_len) { struct ceph_pg_mapping *pg; pg = kmalloc(sizeof(*pg) + payload_len, GFP_NOIO); if (!pg) return NULL; RB_CLEAR_NODE(&pg->node); return pg; } static void free_pg_mapping(struct ceph_pg_mapping *pg) { WARN_ON(!RB_EMPTY_NODE(&pg->node)); kfree(pg); } |
f984cb76c libceph: make pgi... |
635 636 637 638 |
/* * rbtree of pg_mapping for handling pg_temp (explicit mapping of pgid * to a set of osds) and primary_temp (explicit primary setting) */ |
ab75144be libceph: kill __{... |
639 640 |
DEFINE_RB_FUNCS2(pg_mapping, struct ceph_pg_mapping, pgid, ceph_pg_compare, RB_BYPTR, const struct ceph_pg *, node) |
8adc8b3d7 libceph: fix pg_t... |
641 |
|
f24e9980e ceph: OSD client |
642 |
/* |
4fc51be8f ceph: use rbtree ... |
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 |
* rbtree of pg pool info */ static int __insert_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *new) { struct rb_node **p = &root->rb_node; struct rb_node *parent = NULL; struct ceph_pg_pool_info *pi = NULL; while (*p) { parent = *p; pi = rb_entry(parent, struct ceph_pg_pool_info, node); if (new->id < pi->id) p = &(*p)->rb_left; else if (new->id > pi->id) p = &(*p)->rb_right; else return -EEXIST; } rb_link_node(&new->node, parent, p); rb_insert_color(&new->node, root); return 0; } |
4f6a7e5ee ceph: update supp... |
666 |
static struct ceph_pg_pool_info *__lookup_pg_pool(struct rb_root *root, u64 id) |
4fc51be8f ceph: use rbtree ... |
667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 |
{ struct ceph_pg_pool_info *pi; struct rb_node *n = root->rb_node; while (n) { pi = rb_entry(n, struct ceph_pg_pool_info, node); if (id < pi->id) n = n->rb_left; else if (id > pi->id) n = n->rb_right; else return pi; } return NULL; } |
ce7f6a279 libceph: add ceph... |
682 683 684 685 |
struct ceph_pg_pool_info *ceph_pg_pool_by_id(struct ceph_osdmap *map, u64 id) { return __lookup_pg_pool(&map->pg_pools, id); } |
72afc71ff libceph: define c... |
686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 |
const char *ceph_pg_pool_name_by_id(struct ceph_osdmap *map, u64 id) { struct ceph_pg_pool_info *pi; if (id == CEPH_NOPOOL) return NULL; if (WARN_ON_ONCE(id > (u64) INT_MAX)) return NULL; pi = __lookup_pg_pool(&map->pg_pools, (int) id); return pi ? pi->name : NULL; } EXPORT_SYMBOL(ceph_pg_pool_name_by_id); |
7669a2c95 ceph: lookup pool... |
701 702 703 704 705 706 707 708 709 710 711 712 |
int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) { struct rb_node *rbp; for (rbp = rb_first(&map->pg_pools); rbp; rbp = rb_next(rbp)) { struct ceph_pg_pool_info *pi = rb_entry(rbp, struct ceph_pg_pool_info, node); if (pi->name && strcmp(pi->name, name) == 0) return pi->id; } return -ENOENT; } |
3d14c5d2b ceph: factor out ... |
713 |
EXPORT_SYMBOL(ceph_pg_poolid_by_name); |
7669a2c95 ceph: lookup pool... |
714 |
|
2844a76a2 ceph: decode v5 o... |
715 716 717 718 719 720 |
static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) { rb_erase(&pi->node, root); kfree(pi->name); kfree(pi); } |
0f70c7eed libceph: rename _... |
721 |
static int decode_pool(void **p, void *end, struct ceph_pg_pool_info *pi) |
efd7576b2 ceph: fix pg pool... |
722 |
{ |
4f6a7e5ee ceph: update supp... |
723 724 725 726 727 728 729 730 |
u8 ev, cv; unsigned len, num; void *pool_end; ceph_decode_need(p, end, 2 + 4, bad); ev = ceph_decode_8(p); /* encoding version */ cv = ceph_decode_8(p); /* compat version */ if (ev < 5) { |
b9a678994 libceph: Convert ... |
731 732 |
pr_warn("got v %d < 5 cv %d of ceph_pg_pool ", ev, cv); |
4f6a7e5ee ceph: update supp... |
733 734 |
return -EINVAL; } |
17a13e402 libceph: follow {... |
735 |
if (cv > 9) { |
b9a678994 libceph: Convert ... |
736 737 |
pr_warn("got v %d cv %d > 9 of ceph_pg_pool ", ev, cv); |
4f6a7e5ee ceph: update supp... |
738 739 740 741 742 |
return -EINVAL; } len = ceph_decode_32(p); ceph_decode_need(p, end, len, bad); pool_end = *p + len; |
73a7e693f ceph: fix decodin... |
743 |
|
4f6a7e5ee ceph: update supp... |
744 745 746 747 |
pi->type = ceph_decode_8(p); pi->size = ceph_decode_8(p); pi->crush_ruleset = ceph_decode_8(p); pi->object_hash = ceph_decode_8(p); |
73a7e693f ceph: fix decodin... |
748 |
|
4f6a7e5ee ceph: update supp... |
749 750 751 752 753 754 755 756 757 758 759 760 761 762 |
pi->pg_num = ceph_decode_32(p); pi->pgp_num = ceph_decode_32(p); *p += 4 + 4; /* skip lpg* */ *p += 4; /* skip last_change */ *p += 8 + 4; /* skip snap_seq, snap_epoch */ /* skip snaps */ num = ceph_decode_32(p); while (num--) { *p += 8; /* snapid key */ *p += 1 + 1; /* versions */ len = ceph_decode_32(p); *p += len; |
73a7e693f ceph: fix decodin... |
763 |
} |
17a13e402 libceph: follow {... |
764 |
/* skip removed_snaps */ |
4f6a7e5ee ceph: update supp... |
765 766 767 768 769 |
num = ceph_decode_32(p); *p += num * (8 + 8); *p += 8; /* skip auid */ pi->flags = ceph_decode_64(p); |
17a13e402 libceph: follow {... |
770 771 772 |
*p += 4; /* skip crash_replay_interval */ if (ev >= 7) |
04812acf5 libceph: pi->min_... |
773 774 775 |
pi->min_size = ceph_decode_8(p); else pi->min_size = pi->size - pi->size / 2; |
17a13e402 libceph: follow {... |
776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 |
if (ev >= 8) *p += 8 + 8; /* skip quota_max_* */ if (ev >= 9) { /* skip tiers */ num = ceph_decode_32(p); *p += num * 8; *p += 8; /* skip tier_of */ *p += 1; /* skip cache_mode */ pi->read_tier = ceph_decode_64(p); pi->write_tier = ceph_decode_64(p); } else { pi->read_tier = -1; pi->write_tier = -1; } |
4f6a7e5ee ceph: update supp... |
794 |
|
04812acf5 libceph: pi->min_... |
795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 |
if (ev >= 10) { /* skip properties */ num = ceph_decode_32(p); while (num--) { len = ceph_decode_32(p); *p += len; /* key */ len = ceph_decode_32(p); *p += len; /* val */ } } if (ev >= 11) { /* skip hit_set_params */ *p += 1 + 1; /* versions */ len = ceph_decode_32(p); *p += len; *p += 4; /* skip hit_set_period */ *p += 4; /* skip hit_set_count */ } if (ev >= 12) *p += 4; /* skip stripe_width */ if (ev >= 13) { *p += 8; /* skip target_max_bytes */ *p += 8; /* skip target_max_objects */ *p += 4; /* skip cache_target_dirty_ratio_micro */ *p += 4; /* skip cache_target_full_ratio_micro */ *p += 4; /* skip cache_min_flush_age */ *p += 4; /* skip cache_min_evict_age */ } if (ev >= 14) { /* skip erasure_code_profile */ len = ceph_decode_32(p); *p += len; } |
8e48cf00c libceph: new pi->... |
833 834 835 836 |
/* * last_force_op_resend_preluminous, will be overridden if the * map was encoded with RESEND_ON_SPLIT */ |
04812acf5 libceph: pi->min_... |
837 838 839 840 |
if (ev >= 15) pi->last_force_request_resend = ceph_decode_32(p); else pi->last_force_request_resend = 0; |
8e48cf00c libceph: new pi->... |
841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 |
if (ev >= 16) *p += 4; /* skip min_read_recency_for_promote */ if (ev >= 17) *p += 8; /* skip expected_num_objects */ if (ev >= 19) *p += 4; /* skip cache_target_dirty_high_ratio_micro */ if (ev >= 20) *p += 4; /* skip min_write_recency_for_promote */ if (ev >= 21) *p += 1; /* skip use_gmt_hitset */ if (ev >= 22) *p += 1; /* skip fast_read */ if (ev >= 23) { *p += 4; /* skip hit_set_grade_decay_rate */ *p += 4; /* skip hit_set_search_last_n */ } if (ev >= 24) { /* skip opts */ *p += 1 + 1; /* versions */ len = ceph_decode_32(p); *p += len; } if (ev >= 25) pi->last_force_request_resend = ceph_decode_32(p); |
4f6a7e5ee ceph: update supp... |
873 874 875 876 |
/* ignore the rest */ *p = pool_end; calc_pg_masks(pi); |
73a7e693f ceph: fix decodin... |
877 878 879 880 |
return 0; bad: return -EINVAL; |
efd7576b2 ceph: fix pg pool... |
881 |
} |
0f70c7eed libceph: rename _... |
882 |
static int decode_pool_names(void **p, void *end, struct ceph_osdmap *map) |
2844a76a2 ceph: decode v5 o... |
883 884 |
{ struct ceph_pg_pool_info *pi; |
4f6a7e5ee ceph: update supp... |
885 886 |
u32 num, len; u64 pool; |
2844a76a2 ceph: decode v5 o... |
887 888 889 890 891 |
ceph_decode_32_safe(p, end, num, bad); dout(" %d pool names ", num); while (num--) { |
4f6a7e5ee ceph: update supp... |
892 |
ceph_decode_64_safe(p, end, pool, bad); |
2844a76a2 ceph: decode v5 o... |
893 |
ceph_decode_32_safe(p, end, len, bad); |
4f6a7e5ee ceph: update supp... |
894 895 |
dout(" pool %llu len %d ", pool, len); |
ad3b904c0 libceph: fix over... |
896 |
ceph_decode_need(p, end, len, bad); |
2844a76a2 ceph: decode v5 o... |
897 898 |
pi = __lookup_pg_pool(&map->pg_pools, pool); if (pi) { |
ad3b904c0 libceph: fix over... |
899 900 901 902 |
char *name = kstrndup(*p, len, GFP_NOFS); if (!name) return -ENOMEM; |
2844a76a2 ceph: decode v5 o... |
903 |
kfree(pi->name); |
ad3b904c0 libceph: fix over... |
904 905 906 |
pi->name = name; dout(" name is %s ", pi->name); |
2844a76a2 ceph: decode v5 o... |
907 908 909 910 911 912 913 914 915 916 917 918 |
} *p += len; } return 0; bad: return -EINVAL; } /* * osd map */ |
e5253a7bd libceph: allocate... |
919 920 921 922 923 924 925 926 927 928 929 930 |
struct ceph_osdmap *ceph_osdmap_alloc(void) { struct ceph_osdmap *map; map = kzalloc(sizeof(*map), GFP_NOIO); if (!map) return NULL; map->pg_pools = RB_ROOT; map->pool_max = -1; map->pg_temp = RB_ROOT; map->primary_temp = RB_ROOT; |
6f428df47 libceph: pg_upmap... |
931 932 |
map->pg_upmap = RB_ROOT; map->pg_upmap_items = RB_ROOT; |
743efcfff crush: merge work... |
933 |
mutex_init(&map->crush_workspace_mutex); |
e5253a7bd libceph: allocate... |
934 935 936 |
return map; } |
2844a76a2 ceph: decode v5 o... |
937 938 939 940 941 942 943 944 945 946 |
void ceph_osdmap_destroy(struct ceph_osdmap *map) { dout("osdmap_destroy %p ", map); if (map->crush) crush_destroy(map->crush); while (!RB_EMPTY_ROOT(&map->pg_temp)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->pg_temp), struct ceph_pg_mapping, node); |
ab75144be libceph: kill __{... |
947 948 |
erase_pg_mapping(&map->pg_temp, pg); free_pg_mapping(pg); |
2844a76a2 ceph: decode v5 o... |
949 |
} |
9686f94c8 libceph: primary_... |
950 951 952 953 |
while (!RB_EMPTY_ROOT(&map->primary_temp)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->primary_temp), struct ceph_pg_mapping, node); |
ab75144be libceph: kill __{... |
954 955 |
erase_pg_mapping(&map->primary_temp, pg); free_pg_mapping(pg); |
9686f94c8 libceph: primary_... |
956 |
} |
6f428df47 libceph: pg_upmap... |
957 958 959 960 961 962 963 964 965 966 967 968 969 970 |
while (!RB_EMPTY_ROOT(&map->pg_upmap)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->pg_upmap), struct ceph_pg_mapping, node); rb_erase(&pg->node, &map->pg_upmap); kfree(pg); } while (!RB_EMPTY_ROOT(&map->pg_upmap_items)) { struct ceph_pg_mapping *pg = rb_entry(rb_first(&map->pg_upmap_items), struct ceph_pg_mapping, node); rb_erase(&pg->node, &map->pg_upmap_items); kfree(pg); } |
2844a76a2 ceph: decode v5 o... |
971 972 973 974 975 976 977 978 979 |
while (!RB_EMPTY_ROOT(&map->pg_pools)) { struct ceph_pg_pool_info *pi = rb_entry(rb_first(&map->pg_pools), struct ceph_pg_pool_info, node); __remove_pg_pool(&map->pg_pools, pi); } kfree(map->osd_state); kfree(map->osd_weight); kfree(map->osd_addr); |
2cfa34f2d libceph: primary_... |
980 |
kfree(map->osd_primary_affinity); |
66a0e2d57 crush: remove mut... |
981 |
kfree(map->crush_workspace); |
2844a76a2 ceph: decode v5 o... |
982 983 984 985 |
kfree(map); } /* |
4d60351f9 libceph: switch o... |
986 987 988 |
* Adjust max_osd value, (re)allocate arrays. * * The new elements are properly initialized. |
2844a76a2 ceph: decode v5 o... |
989 990 991 |
*/ static int osdmap_set_max_osd(struct ceph_osdmap *map, int max) { |
0bb05da2e libceph: osd_stat... |
992 |
u32 *state; |
2844a76a2 ceph: decode v5 o... |
993 |
u32 *weight; |
4d60351f9 libceph: switch o... |
994 995 |
struct ceph_entity_addr *addr; int i; |
2844a76a2 ceph: decode v5 o... |
996 |
|
4d60351f9 libceph: switch o... |
997 |
state = krealloc(map->osd_state, max*sizeof(*state), GFP_NOFS); |
589506f1e libceph: fix a us... |
998 999 1000 |
if (!state) return -ENOMEM; map->osd_state = state; |
4d60351f9 libceph: switch o... |
1001 |
weight = krealloc(map->osd_weight, max*sizeof(*weight), GFP_NOFS); |
589506f1e libceph: fix a us... |
1002 1003 1004 |
if (!weight) return -ENOMEM; map->osd_weight = weight; |
4d60351f9 libceph: switch o... |
1005 |
|
589506f1e libceph: fix a us... |
1006 1007 |
addr = krealloc(map->osd_addr, max*sizeof(*addr), GFP_NOFS); if (!addr) |
2844a76a2 ceph: decode v5 o... |
1008 |
return -ENOMEM; |
589506f1e libceph: fix a us... |
1009 |
map->osd_addr = addr; |
2844a76a2 ceph: decode v5 o... |
1010 |
|
4d60351f9 libceph: switch o... |
1011 |
for (i = map->max_osd; i < max; i++) { |
589506f1e libceph: fix a us... |
1012 1013 1014 |
map->osd_state[i] = 0; map->osd_weight[i] = CEPH_OSD_OUT; memset(map->osd_addr + i, 0, sizeof(*map->osd_addr)); |
2844a76a2 ceph: decode v5 o... |
1015 |
} |
2cfa34f2d libceph: primary_... |
1016 1017 1018 1019 1020 1021 1022 |
if (map->osd_primary_affinity) { u32 *affinity; affinity = krealloc(map->osd_primary_affinity, max*sizeof(*affinity), GFP_NOFS); if (!affinity) return -ENOMEM; |
589506f1e libceph: fix a us... |
1023 |
map->osd_primary_affinity = affinity; |
2cfa34f2d libceph: primary_... |
1024 1025 |
for (i = map->max_osd; i < max; i++) |
589506f1e libceph: fix a us... |
1026 1027 |
map->osd_primary_affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; |
2cfa34f2d libceph: primary_... |
1028 |
} |
2844a76a2 ceph: decode v5 o... |
1029 |
map->max_osd = max; |
4d60351f9 libceph: switch o... |
1030 |
|
2844a76a2 ceph: decode v5 o... |
1031 1032 |
return 0; } |
1b6a78b5b libceph: add osdm... |
1033 1034 |
static int osdmap_set_crush(struct ceph_osdmap *map, struct crush_map *crush) { |
66a0e2d57 crush: remove mut... |
1035 |
void *workspace; |
743efcfff crush: merge work... |
1036 |
size_t work_size; |
66a0e2d57 crush: remove mut... |
1037 |
|
1b6a78b5b libceph: add osdm... |
1038 1039 |
if (IS_ERR(crush)) return PTR_ERR(crush); |
743efcfff crush: merge work... |
1040 1041 1042 1043 |
work_size = crush_work_size(crush, CEPH_PG_MAX_SIZE); dout("%s work_size %zu bytes ", __func__, work_size); workspace = kmalloc(work_size, GFP_NOIO); |
66a0e2d57 crush: remove mut... |
1044 1045 1046 1047 1048 |
if (!workspace) { crush_destroy(crush); return -ENOMEM; } crush_init_workspace(crush, workspace); |
1b6a78b5b libceph: add osdm... |
1049 1050 |
if (map->crush) crush_destroy(map->crush); |
66a0e2d57 crush: remove mut... |
1051 |
kfree(map->crush_workspace); |
1b6a78b5b libceph: add osdm... |
1052 |
map->crush = crush; |
66a0e2d57 crush: remove mut... |
1053 |
map->crush_workspace = workspace; |
1b6a78b5b libceph: add osdm... |
1054 1055 |
return 0; } |
ec7af9725 libceph: introduc... |
1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 |
#define OSDMAP_WRAPPER_COMPAT_VER 7 #define OSDMAP_CLIENT_DATA_COMPAT_VER 1 /* * Return 0 or error. On success, *v is set to 0 for old (v6) osdmaps, * to struct_v of the client_data section for new (v7 and above) * osdmaps. */ static int get_osdmap_client_data_v(void **p, void *end, const char *prefix, u8 *v) { u8 struct_v; ceph_decode_8_safe(p, end, struct_v, e_inval); if (struct_v >= 7) { u8 struct_compat; ceph_decode_8_safe(p, end, struct_compat, e_inval); if (struct_compat > OSDMAP_WRAPPER_COMPAT_VER) { |
b9a678994 libceph: Convert ... |
1075 1076 1077 1078 |
pr_warn("got v %d cv %d > %d of %s ceph_osdmap ", struct_v, struct_compat, OSDMAP_WRAPPER_COMPAT_VER, prefix); |
ec7af9725 libceph: introduc... |
1079 1080 1081 1082 1083 1084 1085 |
return -EINVAL; } *p += 4; /* ignore wrapper struct_len */ ceph_decode_8_safe(p, end, struct_v, e_inval); ceph_decode_8_safe(p, end, struct_compat, e_inval); if (struct_compat > OSDMAP_CLIENT_DATA_COMPAT_VER) { |
b9a678994 libceph: Convert ... |
1086 1087 1088 1089 |
pr_warn("got v %d cv %d > %d of %s ceph_osdmap client data ", struct_v, struct_compat, OSDMAP_CLIENT_DATA_COMPAT_VER, prefix); |
ec7af9725 libceph: introduc... |
1090 1091 1092 1093 1094 1095 1096 1097 1098 |
return -EINVAL; } *p += 4; /* ignore client data struct_len */ } else { u16 version; *p -= 1; ceph_decode_16_safe(p, end, version, e_inval); if (version < 6) { |
b9a678994 libceph: Convert ... |
1099 1100 1101 |
pr_warn("got v %d < 6 of %s ceph_osdmap ", version, prefix); |
ec7af9725 libceph: introduc... |
1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 |
return -EINVAL; } /* old osdmap enconding */ struct_v = 0; } *v = struct_v; return 0; e_inval: return -EINVAL; } |
433fbdd31 libceph: introduc... |
1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 |
static int __decode_pools(void **p, void *end, struct ceph_osdmap *map, bool incremental) { u32 n; ceph_decode_32_safe(p, end, n, e_inval); while (n--) { struct ceph_pg_pool_info *pi; u64 pool; int ret; ceph_decode_64_safe(p, end, pool, e_inval); pi = __lookup_pg_pool(&map->pg_pools, pool); if (!incremental || !pi) { pi = kzalloc(sizeof(*pi), GFP_NOFS); if (!pi) return -ENOMEM; pi->id = pool; ret = __insert_pg_pool(&map->pg_pools, pi); if (ret) { kfree(pi); return ret; } } ret = decode_pool(p, end, pi); if (ret) return ret; } return 0; e_inval: return -EINVAL; } static int decode_pools(void **p, void *end, struct ceph_osdmap *map) { return __decode_pools(p, end, map, false); } static int decode_new_pools(void **p, void *end, struct ceph_osdmap *map) { return __decode_pools(p, end, map, true); } |
a303bb0e5 libceph: introduc... |
1163 1164 1165 1166 |
typedef struct ceph_pg_mapping *(*decode_mapping_fn_t)(void **, void *, bool); static int decode_pg_mapping(void **p, void *end, struct rb_root *mapping_root, decode_mapping_fn_t fn, bool incremental) |
10db634e2 libceph: introduc... |
1167 1168 |
{ u32 n; |
a303bb0e5 libceph: introduc... |
1169 |
WARN_ON(!incremental && !fn); |
10db634e2 libceph: introduc... |
1170 1171 |
ceph_decode_32_safe(p, end, n, e_inval); while (n--) { |
a303bb0e5 libceph: introduc... |
1172 |
struct ceph_pg_mapping *pg; |
10db634e2 libceph: introduc... |
1173 |
struct ceph_pg pgid; |
10db634e2 libceph: introduc... |
1174 1175 1176 1177 1178 |
int ret; ret = ceph_decode_pgid(p, end, &pgid); if (ret) return ret; |
ab75144be libceph: kill __{... |
1179 1180 1181 1182 1183 1184 |
pg = lookup_pg_mapping(mapping_root, &pgid); if (pg) { WARN_ON(!incremental); erase_pg_mapping(mapping_root, pg); free_pg_mapping(pg); } |
10db634e2 libceph: introduc... |
1185 |
|
a303bb0e5 libceph: introduc... |
1186 1187 1188 1189 |
if (fn) { pg = fn(p, end, incremental); if (IS_ERR(pg)) return PTR_ERR(pg); |
10db634e2 libceph: introduc... |
1190 |
|
a303bb0e5 libceph: introduc... |
1191 1192 |
if (pg) { pg->pgid = pgid; /* struct */ |
ab75144be libceph: kill __{... |
1193 |
insert_pg_mapping(mapping_root, pg); |
10db634e2 libceph: introduc... |
1194 1195 1196 1197 1198 1199 1200 1201 1202 |
} } } return 0; e_inval: return -EINVAL; } |
a303bb0e5 libceph: introduc... |
1203 1204 |
static struct ceph_pg_mapping *__decode_pg_temp(void **p, void *end, bool incremental) |
10db634e2 libceph: introduc... |
1205 |
{ |
a303bb0e5 libceph: introduc... |
1206 1207 |
struct ceph_pg_mapping *pg; u32 len, i; |
10db634e2 libceph: introduc... |
1208 |
|
a303bb0e5 libceph: introduc... |
1209 1210 1211 1212 1213 |
ceph_decode_32_safe(p, end, len, e_inval); if (len == 0 && incremental) return NULL; /* new_pg_temp: [] to remove */ if (len > (SIZE_MAX - sizeof(*pg)) / sizeof(u32)) return ERR_PTR(-EINVAL); |
10db634e2 libceph: introduc... |
1214 |
|
a303bb0e5 libceph: introduc... |
1215 1216 1217 1218 |
ceph_decode_need(p, end, len * sizeof(u32), e_inval); pg = alloc_pg_mapping(len * sizeof(u32)); if (!pg) return ERR_PTR(-ENOMEM); |
d286de796 libceph: primary_... |
1219 |
|
a303bb0e5 libceph: introduc... |
1220 1221 1222 |
pg->pg_temp.len = len; for (i = 0; i < len; i++) pg->pg_temp.osds[i] = ceph_decode_32(p); |
d286de796 libceph: primary_... |
1223 |
|
a303bb0e5 libceph: introduc... |
1224 |
return pg; |
d286de796 libceph: primary_... |
1225 |
|
a303bb0e5 libceph: introduc... |
1226 1227 1228 |
e_inval: return ERR_PTR(-EINVAL); } |
d286de796 libceph: primary_... |
1229 |
|
a303bb0e5 libceph: introduc... |
1230 1231 1232 1233 1234 |
static int decode_pg_temp(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_temp, __decode_pg_temp, false); } |
d286de796 libceph: primary_... |
1235 |
|
a303bb0e5 libceph: introduc... |
1236 1237 1238 1239 1240 |
static int decode_new_pg_temp(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_temp, __decode_pg_temp, true); } |
d286de796 libceph: primary_... |
1241 |
|
a303bb0e5 libceph: introduc... |
1242 1243 1244 1245 1246 |
static struct ceph_pg_mapping *__decode_primary_temp(void **p, void *end, bool incremental) { struct ceph_pg_mapping *pg; u32 osd; |
d286de796 libceph: primary_... |
1247 |
|
a303bb0e5 libceph: introduc... |
1248 1249 1250 |
ceph_decode_32_safe(p, end, osd, e_inval); if (osd == (u32)-1 && incremental) return NULL; /* new_primary_temp: -1 to remove */ |
d286de796 libceph: primary_... |
1251 |
|
a303bb0e5 libceph: introduc... |
1252 1253 1254 |
pg = alloc_pg_mapping(0); if (!pg) return ERR_PTR(-ENOMEM); |
d286de796 libceph: primary_... |
1255 |
|
a303bb0e5 libceph: introduc... |
1256 1257 |
pg->primary_temp.osd = osd; return pg; |
d286de796 libceph: primary_... |
1258 1259 |
e_inval: |
a303bb0e5 libceph: introduc... |
1260 |
return ERR_PTR(-EINVAL); |
d286de796 libceph: primary_... |
1261 1262 1263 1264 |
} static int decode_primary_temp(void **p, void *end, struct ceph_osdmap *map) { |
a303bb0e5 libceph: introduc... |
1265 1266 |
return decode_pg_mapping(p, end, &map->primary_temp, __decode_primary_temp, false); |
d286de796 libceph: primary_... |
1267 1268 1269 1270 1271 |
} static int decode_new_primary_temp(void **p, void *end, struct ceph_osdmap *map) { |
a303bb0e5 libceph: introduc... |
1272 1273 |
return decode_pg_mapping(p, end, &map->primary_temp, __decode_primary_temp, true); |
d286de796 libceph: primary_... |
1274 |
} |
2cfa34f2d libceph: primary_... |
1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 |
u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd) { BUG_ON(osd >= map->max_osd); if (!map->osd_primary_affinity) return CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; return map->osd_primary_affinity[osd]; } static int set_primary_affinity(struct ceph_osdmap *map, int osd, u32 aff) { BUG_ON(osd >= map->max_osd); if (!map->osd_primary_affinity) { int i; map->osd_primary_affinity = kmalloc(map->max_osd*sizeof(u32), GFP_NOFS); if (!map->osd_primary_affinity) return -ENOMEM; for (i = 0; i < map->max_osd; i++) map->osd_primary_affinity[i] = CEPH_OSD_DEFAULT_PRIMARY_AFFINITY; } map->osd_primary_affinity[osd] = aff; return 0; } |
63a6993f5 libceph: primary_... |
1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 |
static int decode_primary_affinity(void **p, void *end, struct ceph_osdmap *map) { u32 len, i; ceph_decode_32_safe(p, end, len, e_inval); if (len == 0) { kfree(map->osd_primary_affinity); map->osd_primary_affinity = NULL; return 0; } if (len != map->max_osd) goto e_inval; ceph_decode_need(p, end, map->max_osd*sizeof(u32), e_inval); for (i = 0; i < map->max_osd; i++) { int ret; ret = set_primary_affinity(map, i, ceph_decode_32(p)); if (ret) return ret; } return 0; e_inval: return -EINVAL; } static int decode_new_primary_affinity(void **p, void *end, struct ceph_osdmap *map) { u32 n; ceph_decode_32_safe(p, end, n, e_inval); while (n--) { u32 osd, aff; int ret; ceph_decode_32_safe(p, end, osd, e_inval); ceph_decode_32_safe(p, end, aff, e_inval); ret = set_primary_affinity(map, osd, aff); if (ret) return ret; |
f31da0f3e libceph: output p... |
1352 1353 1354 |
pr_info("osd%d primary-affinity 0x%x ", osd, aff); |
63a6993f5 libceph: primary_... |
1355 1356 1357 1358 1359 1360 1361 |
} return 0; e_inval: return -EINVAL; } |
6f428df47 libceph: pg_upmap... |
1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 |
static struct ceph_pg_mapping *__decode_pg_upmap(void **p, void *end, bool __unused) { return __decode_pg_temp(p, end, false); } static int decode_pg_upmap(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap, false); } static int decode_new_pg_upmap(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_upmap, __decode_pg_upmap, true); } static int decode_old_pg_upmap(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_upmap, NULL, true); } static struct ceph_pg_mapping *__decode_pg_upmap_items(void **p, void *end, bool __unused) { struct ceph_pg_mapping *pg; u32 len, i; ceph_decode_32_safe(p, end, len, e_inval); if (len > (SIZE_MAX - sizeof(*pg)) / (2 * sizeof(u32))) return ERR_PTR(-EINVAL); ceph_decode_need(p, end, 2 * len * sizeof(u32), e_inval); |
f5cc68986 libceph: use allo... |
1396 |
pg = alloc_pg_mapping(2 * len * sizeof(u32)); |
6f428df47 libceph: pg_upmap... |
1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 |
if (!pg) return ERR_PTR(-ENOMEM); pg->pg_upmap_items.len = len; for (i = 0; i < len; i++) { pg->pg_upmap_items.from_to[i][0] = ceph_decode_32(p); pg->pg_upmap_items.from_to[i][1] = ceph_decode_32(p); } return pg; e_inval: return ERR_PTR(-EINVAL); } static int decode_pg_upmap_items(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_upmap_items, __decode_pg_upmap_items, false); } static int decode_new_pg_upmap_items(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_upmap_items, __decode_pg_upmap_items, true); } static int decode_old_pg_upmap_items(void **p, void *end, struct ceph_osdmap *map) { return decode_pg_mapping(p, end, &map->pg_upmap_items, NULL, true); } |
4fc51be8f ceph: use rbtree ... |
1430 |
/* |
f24e9980e ceph: OSD client |
1431 1432 |
* decode a full map. */ |
a2505d63e libceph: split os... |
1433 |
static int osdmap_decode(void **p, void *end, struct ceph_osdmap *map) |
f24e9980e ceph: OSD client |
1434 |
{ |
ec7af9725 libceph: introduc... |
1435 |
u8 struct_v; |
38a8d5602 libceph: dump osd... |
1436 |
u32 epoch = 0; |
f24e9980e ceph: OSD client |
1437 |
void *start = *p; |
3977058c4 libceph: safely d... |
1438 1439 |
u32 max; u32 len, i; |
597b52f6c libceph: fixup er... |
1440 |
int err; |
f24e9980e ceph: OSD client |
1441 |
|
a2505d63e libceph: split os... |
1442 1443 |
dout("%s %p to %p len %d ", __func__, *p, end, (int)(end - *p)); |
f24e9980e ceph: OSD client |
1444 |
|
ec7af9725 libceph: introduc... |
1445 1446 1447 |
err = get_osdmap_client_data_v(p, end, "full", &struct_v); if (err) goto bad; |
f24e9980e ceph: OSD client |
1448 |
|
53bbaba9d libceph: fix and ... |
1449 1450 1451 |
/* fsid, epoch, created, modified */ ceph_decode_need(p, end, sizeof(map->fsid) + sizeof(u32) + sizeof(map->created) + sizeof(map->modified), e_inval); |
f24e9980e ceph: OSD client |
1452 |
ceph_decode_copy(p, &map->fsid, sizeof(map->fsid)); |
38a8d5602 libceph: dump osd... |
1453 |
epoch = map->epoch = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
1454 1455 |
ceph_decode_copy(p, &map->created, sizeof(map->created)); ceph_decode_copy(p, &map->modified, sizeof(map->modified)); |
433fbdd31 libceph: introduc... |
1456 1457 1458 1459 |
/* pools */ err = decode_pools(p, end, map); if (err) goto bad; |
2844a76a2 ceph: decode v5 o... |
1460 |
|
0f70c7eed libceph: rename _... |
1461 1462 |
/* pool_name */ err = decode_pool_names(p, end, map); |
597b52f6c libceph: fixup er... |
1463 |
if (err) |
4f6a7e5ee ceph: update supp... |
1464 |
goto bad; |
2844a76a2 ceph: decode v5 o... |
1465 |
|
597b52f6c libceph: fixup er... |
1466 |
ceph_decode_32_safe(p, end, map->pool_max, e_inval); |
f24e9980e ceph: OSD client |
1467 |
|
597b52f6c libceph: fixup er... |
1468 |
ceph_decode_32_safe(p, end, map->flags, e_inval); |
f24e9980e ceph: OSD client |
1469 |
|
3977058c4 libceph: safely d... |
1470 1471 |
/* max_osd */ ceph_decode_32_safe(p, end, max, e_inval); |
f24e9980e ceph: OSD client |
1472 1473 1474 |
/* (re)alloc osd arrays */ err = osdmap_set_max_osd(map, max); |
597b52f6c libceph: fixup er... |
1475 |
if (err) |
f24e9980e ceph: OSD client |
1476 |
goto bad; |
f24e9980e ceph: OSD client |
1477 |
|
2d88b2e08 libceph: check le... |
1478 |
/* osd_state, osd_weight, osd_addrs->client_addr */ |
f24e9980e ceph: OSD client |
1479 |
ceph_decode_need(p, end, 3*sizeof(u32) + |
0bb05da2e libceph: osd_stat... |
1480 1481 1482 |
map->max_osd*((struct_v >= 5 ? sizeof(u32) : sizeof(u8)) + sizeof(*map->osd_weight) + |
597b52f6c libceph: fixup er... |
1483 |
sizeof(*map->osd_addr)), e_inval); |
2d88b2e08 libceph: check le... |
1484 1485 |
if (ceph_decode_32(p) != map->max_osd) goto e_inval; |
0bb05da2e libceph: osd_stat... |
1486 1487 1488 1489 1490 1491 1492 |
if (struct_v >= 5) { for (i = 0; i < map->max_osd; i++) map->osd_state[i] = ceph_decode_32(p); } else { for (i = 0; i < map->max_osd; i++) map->osd_state[i] = ceph_decode_8(p); } |
f24e9980e ceph: OSD client |
1493 |
|
2d88b2e08 libceph: check le... |
1494 1495 |
if (ceph_decode_32(p) != map->max_osd) goto e_inval; |
f24e9980e ceph: OSD client |
1496 |
for (i = 0; i < map->max_osd; i++) |
c89136ea4 ceph: convert enc... |
1497 |
map->osd_weight[i] = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
1498 |
|
2d88b2e08 libceph: check le... |
1499 1500 |
if (ceph_decode_32(p) != map->max_osd) goto e_inval; |
f24e9980e ceph: OSD client |
1501 |
ceph_decode_copy(p, map->osd_addr, map->max_osd*sizeof(*map->osd_addr)); |
63f2d2119 ceph: use fixed e... |
1502 1503 |
for (i = 0; i < map->max_osd; i++) ceph_decode_addr(&map->osd_addr[i]); |
f24e9980e ceph: OSD client |
1504 1505 |
/* pg_temp */ |
10db634e2 libceph: introduc... |
1506 1507 1508 |
err = decode_pg_temp(p, end, map); if (err) goto bad; |
f24e9980e ceph: OSD client |
1509 |
|
d286de796 libceph: primary_... |
1510 1511 1512 1513 1514 1515 |
/* primary_temp */ if (struct_v >= 1) { err = decode_primary_temp(p, end, map); if (err) goto bad; } |
63a6993f5 libceph: primary_... |
1516 1517 1518 1519 1520 1521 |
/* primary_affinity */ if (struct_v >= 2) { err = decode_primary_affinity(p, end, map); if (err) goto bad; } else { |
6f428df47 libceph: pg_upmap... |
1522 |
WARN_ON(map->osd_primary_affinity); |
63a6993f5 libceph: primary_... |
1523 |
} |
f24e9980e ceph: OSD client |
1524 |
/* crush */ |
597b52f6c libceph: fixup er... |
1525 |
ceph_decode_32_safe(p, end, len, e_inval); |
1b6a78b5b libceph: add osdm... |
1526 1527 |
err = osdmap_set_crush(map, crush_decode(*p, min(*p + len, end))); if (err) |
f24e9980e ceph: OSD client |
1528 |
goto bad; |
f24e9980e ceph: OSD client |
1529 |
|
6f428df47 libceph: pg_upmap... |
1530 1531 1532 1533 |
*p += len; if (struct_v >= 3) { /* erasure_code_profiles */ ceph_decode_skip_map_of_map(p, end, string, string, string, |
00c8ebb36 libceph: NULL der... |
1534 |
e_inval); |
6f428df47 libceph: pg_upmap... |
1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 |
} if (struct_v >= 4) { err = decode_pg_upmap(p, end, map); if (err) goto bad; err = decode_pg_upmap_items(p, end, map); if (err) goto bad; } else { WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap)); WARN_ON(!RB_EMPTY_ROOT(&map->pg_upmap_items)); } |
38a8d5602 libceph: dump osd... |
1549 |
/* ignore the rest */ |
f24e9980e ceph: OSD client |
1550 |
*p = end; |
38a8d5602 libceph: dump osd... |
1551 1552 |
dout("full osdmap epoch %d max_osd %d ", map->epoch, map->max_osd); |
a2505d63e libceph: split os... |
1553 |
return 0; |
f24e9980e ceph: OSD client |
1554 |
|
597b52f6c libceph: fixup er... |
1555 1556 |
e_inval: err = -EINVAL; |
f24e9980e ceph: OSD client |
1557 |
bad: |
38a8d5602 libceph: dump osd... |
1558 1559 1560 1561 1562 1563 |
pr_err("corrupt full osdmap (%d) epoch %d off %d (%p of %p-%p) ", err, epoch, (int)(*p - start), *p, start, end); print_hex_dump(KERN_DEBUG, "osdmap: ", DUMP_PREFIX_OFFSET, 16, 1, start, end - start, true); |
a2505d63e libceph: split os... |
1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 |
return err; } /* * Allocate and decode a full map. */ struct ceph_osdmap *ceph_osdmap_decode(void **p, void *end) { struct ceph_osdmap *map; int ret; |
e5253a7bd libceph: allocate... |
1574 |
map = ceph_osdmap_alloc(); |
a2505d63e libceph: split os... |
1575 1576 |
if (!map) return ERR_PTR(-ENOMEM); |
a2505d63e libceph: split os... |
1577 1578 1579 1580 1581 1582 1583 |
ret = osdmap_decode(p, end, map); if (ret) { ceph_osdmap_destroy(map); return ERR_PTR(ret); } return map; |
f24e9980e ceph: OSD client |
1584 1585 1586 |
} /* |
930c53286 libceph: apply ne... |
1587 1588 1589 1590 1591 1592 1593 |
* Encoding order is (new_up_client, new_state, new_weight). Need to * apply in the (new_weight, new_state, new_up_client) order, because * an incremental map may look like e.g. * * new_up_client: { osd=6, addr=... } # set osd_state and addr * new_state: { osd=6, xorstate=EXISTS } # clear osd_state */ |
0bb05da2e libceph: osd_stat... |
1594 |
static int decode_new_up_state_weight(void **p, void *end, u8 struct_v, |
930c53286 libceph: apply ne... |
1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 |
struct ceph_osdmap *map) { void *new_up_client; void *new_state; void *new_weight_end; u32 len; new_up_client = *p; ceph_decode_32_safe(p, end, len, e_inval); len *= sizeof(u32) + sizeof(struct ceph_entity_addr); ceph_decode_need(p, end, len, e_inval); *p += len; new_state = *p; ceph_decode_32_safe(p, end, len, e_inval); |
0bb05da2e libceph: osd_stat... |
1610 |
len *= sizeof(u32) + (struct_v >= 5 ? sizeof(u32) : sizeof(u8)); |
930c53286 libceph: apply ne... |
1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 |
ceph_decode_need(p, end, len, e_inval); *p += len; /* new_weight */ ceph_decode_32_safe(p, end, len, e_inval); while (len--) { s32 osd; u32 w; ceph_decode_need(p, end, 2*sizeof(u32), e_inval); osd = ceph_decode_32(p); w = ceph_decode_32(p); BUG_ON(osd >= map->max_osd); pr_info("osd%d weight 0x%x %s ", osd, w, w == CEPH_OSD_IN ? "(in)" : (w == CEPH_OSD_OUT ? "(out)" : "")); map->osd_weight[osd] = w; /* * If we are marking in, set the EXISTS, and clear the * AUTOOUT and NEW bits. */ if (w) { map->osd_state[osd] |= CEPH_OSD_EXISTS; map->osd_state[osd] &= ~(CEPH_OSD_AUTOOUT | CEPH_OSD_NEW); } } new_weight_end = *p; /* new_state (up/down) */ *p = new_state; len = ceph_decode_32(p); while (len--) { s32 osd; |
0bb05da2e libceph: osd_stat... |
1647 |
u32 xorstate; |
930c53286 libceph: apply ne... |
1648 1649 1650 |
int ret; osd = ceph_decode_32(p); |
0bb05da2e libceph: osd_stat... |
1651 1652 1653 1654 |
if (struct_v >= 5) xorstate = ceph_decode_32(p); else xorstate = ceph_decode_8(p); |
930c53286 libceph: apply ne... |
1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 |
if (xorstate == 0) xorstate = CEPH_OSD_UP; BUG_ON(osd >= map->max_osd); if ((map->osd_state[osd] & CEPH_OSD_UP) && (xorstate & CEPH_OSD_UP)) pr_info("osd%d down ", osd); if ((map->osd_state[osd] & CEPH_OSD_EXISTS) && (xorstate & CEPH_OSD_EXISTS)) { pr_info("osd%d does not exist ", osd); |
930c53286 libceph: apply ne... |
1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 |
ret = set_primary_affinity(map, osd, CEPH_OSD_DEFAULT_PRIMARY_AFFINITY); if (ret) return ret; memset(map->osd_addr + osd, 0, sizeof(*map->osd_addr)); map->osd_state[osd] = 0; } else { map->osd_state[osd] ^= xorstate; } } /* new_up_client */ *p = new_up_client; len = ceph_decode_32(p); while (len--) { s32 osd; struct ceph_entity_addr addr; osd = ceph_decode_32(p); ceph_decode_copy(p, &addr, sizeof(addr)); ceph_decode_addr(&addr); BUG_ON(osd >= map->max_osd); pr_info("osd%d up ", osd); map->osd_state[osd] |= CEPH_OSD_EXISTS | CEPH_OSD_UP; map->osd_addr[osd] = addr; } *p = new_weight_end; return 0; e_inval: return -EINVAL; } /* |
f24e9980e ceph: OSD client |
1702 1703 1704 |
* decode and apply an incremental map update. */ struct ceph_osdmap *osdmap_apply_incremental(void **p, void *end, |
0c0a8de13 libceph: nuke unu... |
1705 |
struct ceph_osdmap *map) |
f24e9980e ceph: OSD client |
1706 |
{ |
f24e9980e ceph: OSD client |
1707 1708 1709 |
struct ceph_fsid fsid; u32 epoch = 0; struct ceph_timespec modified; |
4f6a7e5ee ceph: update supp... |
1710 1711 1712 1713 |
s32 len; u64 pool; __s64 new_pool_max; __s32 new_flags, max; |
f24e9980e ceph: OSD client |
1714 |
void *start = *p; |
86f1742b9 libceph: fixup er... |
1715 |
int err; |
ec7af9725 libceph: introduc... |
1716 |
u8 struct_v; |
f24e9980e ceph: OSD client |
1717 |
|
38a8d5602 libceph: dump osd... |
1718 1719 |
dout("%s %p to %p len %d ", __func__, *p, end, (int)(end - *p)); |
ec7af9725 libceph: introduc... |
1720 1721 1722 |
err = get_osdmap_client_data_v(p, end, "inc", &struct_v); if (err) goto bad; |
f24e9980e ceph: OSD client |
1723 |
|
53bbaba9d libceph: fix and ... |
1724 1725 1726 |
/* fsid, epoch, modified, new_pool_max, new_flags */ ceph_decode_need(p, end, sizeof(fsid) + sizeof(u32) + sizeof(modified) + sizeof(u64) + sizeof(u32), e_inval); |
f24e9980e ceph: OSD client |
1727 |
ceph_decode_copy(p, &fsid, sizeof(fsid)); |
c89136ea4 ceph: convert enc... |
1728 |
epoch = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
1729 1730 |
BUG_ON(epoch != map->epoch+1); ceph_decode_copy(p, &modified, sizeof(modified)); |
4f6a7e5ee ceph: update supp... |
1731 |
new_pool_max = ceph_decode_64(p); |
c89136ea4 ceph: convert enc... |
1732 |
new_flags = ceph_decode_32(p); |
f24e9980e ceph: OSD client |
1733 1734 |
/* full map? */ |
86f1742b9 libceph: fixup er... |
1735 |
ceph_decode_32_safe(p, end, len, e_inval); |
f24e9980e ceph: OSD client |
1736 1737 1738 1739 |
if (len > 0) { dout("apply_incremental full map len %d, %p to %p ", len, *p, end); |
a2505d63e libceph: split os... |
1740 |
return ceph_osdmap_decode(p, min(*p+len, end)); |
f24e9980e ceph: OSD client |
1741 1742 1743 |
} /* new crush? */ |
86f1742b9 libceph: fixup er... |
1744 |
ceph_decode_32_safe(p, end, len, e_inval); |
f24e9980e ceph: OSD client |
1745 |
if (len > 0) { |
1b6a78b5b libceph: add osdm... |
1746 1747 1748 |
err = osdmap_set_crush(map, crush_decode(*p, min(*p + len, end))); if (err) |
86f1742b9 libceph: fixup er... |
1749 |
goto bad; |
cebc5be6b ceph: fix crush m... |
1750 |
*p += len; |
f24e9980e ceph: OSD client |
1751 1752 1753 1754 1755 |
} /* new flags? */ if (new_flags >= 0) map->flags = new_flags; |
4fc51be8f ceph: use rbtree ... |
1756 1757 |
if (new_pool_max >= 0) map->pool_max = new_pool_max; |
f24e9980e ceph: OSD client |
1758 |
|
f24e9980e ceph: OSD client |
1759 |
/* new max? */ |
53bbaba9d libceph: fix and ... |
1760 |
ceph_decode_32_safe(p, end, max, e_inval); |
f24e9980e ceph: OSD client |
1761 1762 |
if (max >= 0) { err = osdmap_set_max_osd(map, max); |
86f1742b9 libceph: fixup er... |
1763 |
if (err) |
f24e9980e ceph: OSD client |
1764 1765 1766 1767 |
goto bad; } map->epoch++; |
31456665a libceph: fix osdm... |
1768 |
map->modified = modified; |
f24e9980e ceph: OSD client |
1769 |
|
433fbdd31 libceph: introduc... |
1770 1771 1772 1773 |
/* new_pools */ err = decode_new_pools(p, end, map); if (err) goto bad; |
9464d0086 libceph: nuke bog... |
1774 |
|
0f70c7eed libceph: rename _... |
1775 1776 |
/* new_pool_names */ err = decode_pool_names(p, end, map); |
9464d0086 libceph: nuke bog... |
1777 1778 |
if (err) goto bad; |
f24e9980e ceph: OSD client |
1779 |
|
4fc51be8f ceph: use rbtree ... |
1780 |
/* old_pool */ |
86f1742b9 libceph: fixup er... |
1781 |
ceph_decode_32_safe(p, end, len, e_inval); |
4fc51be8f ceph: use rbtree ... |
1782 1783 |
while (len--) { struct ceph_pg_pool_info *pi; |
86f1742b9 libceph: fixup er... |
1784 |
ceph_decode_64_safe(p, end, pool, e_inval); |
4fc51be8f ceph: use rbtree ... |
1785 |
pi = __lookup_pg_pool(&map->pg_pools, pool); |
2844a76a2 ceph: decode v5 o... |
1786 1787 |
if (pi) __remove_pg_pool(&map->pg_pools, pi); |
4fc51be8f ceph: use rbtree ... |
1788 |
} |
f24e9980e ceph: OSD client |
1789 |
|
930c53286 libceph: apply ne... |
1790 |
/* new_up_client, new_state, new_weight */ |
0bb05da2e libceph: osd_stat... |
1791 |
err = decode_new_up_state_weight(p, end, struct_v, map); |
930c53286 libceph: apply ne... |
1792 1793 |
if (err) goto bad; |
f24e9980e ceph: OSD client |
1794 1795 |
/* new_pg_temp */ |
10db634e2 libceph: introduc... |
1796 1797 1798 |
err = decode_new_pg_temp(p, end, map); if (err) goto bad; |
f24e9980e ceph: OSD client |
1799 |
|
d286de796 libceph: primary_... |
1800 1801 1802 1803 1804 1805 |
/* new_primary_temp */ if (struct_v >= 1) { err = decode_new_primary_temp(p, end, map); if (err) goto bad; } |
63a6993f5 libceph: primary_... |
1806 1807 1808 1809 1810 1811 |
/* new_primary_affinity */ if (struct_v >= 2) { err = decode_new_primary_affinity(p, end, map); if (err) goto bad; } |
6f428df47 libceph: pg_upmap... |
1812 1813 1814 |
if (struct_v >= 3) { /* new_erasure_code_profiles */ ceph_decode_skip_map_of_map(p, end, string, string, string, |
00c8ebb36 libceph: NULL der... |
1815 |
e_inval); |
6f428df47 libceph: pg_upmap... |
1816 |
/* old_erasure_code_profiles */ |
00c8ebb36 libceph: NULL der... |
1817 |
ceph_decode_skip_set(p, end, string, e_inval); |
6f428df47 libceph: pg_upmap... |
1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 |
} if (struct_v >= 4) { err = decode_new_pg_upmap(p, end, map); if (err) goto bad; err = decode_old_pg_upmap(p, end, map); if (err) goto bad; err = decode_new_pg_upmap_items(p, end, map); if (err) goto bad; err = decode_old_pg_upmap_items(p, end, map); if (err) goto bad; } |
f24e9980e ceph: OSD client |
1837 1838 |
/* ignore the rest */ *p = end; |
38a8d5602 libceph: dump osd... |
1839 1840 1841 |
dout("inc osdmap epoch %d max_osd %d ", map->epoch, map->max_osd); |
f24e9980e ceph: OSD client |
1842 |
return map; |
86f1742b9 libceph: fixup er... |
1843 1844 |
e_inval: err = -EINVAL; |
f24e9980e ceph: OSD client |
1845 |
bad: |
38a8d5602 libceph: dump osd... |
1846 1847 1848 |
pr_err("corrupt inc osdmap (%d) epoch %d off %d (%p of %p-%p) ", err, epoch, (int)(*p - start), *p, start, end); |
9ec7cab14 ceph: hex dump co... |
1849 1850 1851 |
print_hex_dump(KERN_DEBUG, "osdmap: ", DUMP_PREFIX_OFFSET, 16, 1, start, end - start, true); |
f24e9980e ceph: OSD client |
1852 1853 |
return ERR_PTR(err); } |
30c156d99 libceph: rados po... |
1854 1855 1856 |
void ceph_oloc_copy(struct ceph_object_locator *dest, const struct ceph_object_locator *src) { |
ca35ffea8 libceph: handle n... |
1857 |
ceph_oloc_destroy(dest); |
30c156d99 libceph: rados po... |
1858 1859 1860 1861 |
dest->pool = src->pool; if (src->pool_ns) dest->pool_ns = ceph_get_string(src->pool_ns); |
ca35ffea8 libceph: handle n... |
1862 1863 |
else dest->pool_ns = NULL; |
30c156d99 libceph: rados po... |
1864 1865 1866 1867 1868 1869 1870 1871 |
} EXPORT_SYMBOL(ceph_oloc_copy); void ceph_oloc_destroy(struct ceph_object_locator *oloc) { ceph_put_string(oloc->pool_ns); } EXPORT_SYMBOL(ceph_oloc_destroy); |
d30291b98 libceph: variable... |
1872 1873 1874 |
void ceph_oid_copy(struct ceph_object_id *dest, const struct ceph_object_id *src) { |
ca35ffea8 libceph: handle n... |
1875 |
ceph_oid_destroy(dest); |
d30291b98 libceph: variable... |
1876 1877 1878 1879 1880 |
if (src->name != src->inline_name) { /* very rare, see ceph_object_id definition */ dest->name = kmalloc(src->name_len + 1, GFP_NOIO | __GFP_NOFAIL); |
ca35ffea8 libceph: handle n... |
1881 1882 |
} else { dest->name = dest->inline_name; |
d30291b98 libceph: variable... |
1883 |
} |
d30291b98 libceph: variable... |
1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 |
memcpy(dest->name, src->name, src->name_len + 1); dest->name_len = src->name_len; } EXPORT_SYMBOL(ceph_oid_copy); static __printf(2, 0) int oid_printf_vargs(struct ceph_object_id *oid, const char *fmt, va_list ap) { int len; WARN_ON(!ceph_oid_empty(oid)); len = vsnprintf(oid->inline_name, sizeof(oid->inline_name), fmt, ap); if (len >= sizeof(oid->inline_name)) return len; oid->name_len = len; return 0; } /* * If oid doesn't fit into inline buffer, BUG. */ void ceph_oid_printf(struct ceph_object_id *oid, const char *fmt, ...) { va_list ap; va_start(ap, fmt); BUG_ON(oid_printf_vargs(oid, fmt, ap)); va_end(ap); } EXPORT_SYMBOL(ceph_oid_printf); static __printf(3, 0) int oid_aprintf_vargs(struct ceph_object_id *oid, gfp_t gfp, const char *fmt, va_list ap) { va_list aq; int len; va_copy(aq, ap); len = oid_printf_vargs(oid, fmt, aq); va_end(aq); if (len) { char *external_name; external_name = kmalloc(len + 1, gfp); if (!external_name) return -ENOMEM; |
f24e9980e ceph: OSD client |
1934 |
|
d30291b98 libceph: variable... |
1935 1936 1937 1938 |
oid->name = external_name; WARN_ON(vsnprintf(oid->name, len + 1, fmt, ap) != len); oid->name_len = len; } |
f24e9980e ceph: OSD client |
1939 |
|
d30291b98 libceph: variable... |
1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 |
return 0; } /* * If oid doesn't fit into inline buffer, allocate. */ int ceph_oid_aprintf(struct ceph_object_id *oid, gfp_t gfp, const char *fmt, ...) { va_list ap; int ret; va_start(ap, fmt); ret = oid_aprintf_vargs(oid, gfp, fmt, ap); va_end(ap); return ret; } EXPORT_SYMBOL(ceph_oid_aprintf); void ceph_oid_destroy(struct ceph_object_id *oid) { if (oid->name != oid->inline_name) kfree(oid->name); } EXPORT_SYMBOL(ceph_oid_destroy); |
f24e9980e ceph: OSD client |
1966 |
|
63244fa12 libceph: introduc... |
1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 |
/* * osds only */ static bool __osds_equal(const struct ceph_osds *lhs, const struct ceph_osds *rhs) { if (lhs->size == rhs->size && !memcmp(lhs->osds, rhs->osds, rhs->size * sizeof(rhs->osds[0]))) return true; return false; } /* * osds + primary */ static bool osds_equal(const struct ceph_osds *lhs, const struct ceph_osds *rhs) { if (__osds_equal(lhs, rhs) && lhs->primary == rhs->primary) return true; return false; } |
6f3bfd45c libceph: ceph_osd... |
1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 |
static bool osds_valid(const struct ceph_osds *set) { /* non-empty set */ if (set->size > 0 && set->primary >= 0) return true; /* empty can_shift_osds set */ if (!set->size && set->primary == -1) return true; /* empty !can_shift_osds set - all NONE */ if (set->size > 0 && set->primary == -1) { int i; for (i = 0; i < set->size; i++) { if (set->osds[i] != CRUSH_ITEM_NONE) break; } if (i == set->size) return true; } return false; } void ceph_osds_copy(struct ceph_osds *dest, const struct ceph_osds *src) { memcpy(dest->osds, src->osds, src->size * sizeof(src->osds[0])); dest->size = src->size; dest->primary = src->primary; } |
7de030d6b libceph: resend o... |
2023 2024 |
bool ceph_pg_is_split(const struct ceph_pg *pgid, u32 old_pg_num, u32 new_pg_num) |
63244fa12 libceph: introduc... |
2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 |
{ int old_bits = calc_bits_of(old_pg_num); int old_mask = (1 << old_bits) - 1; int n; WARN_ON(pgid->seed >= old_pg_num); if (new_pg_num <= old_pg_num) return false; for (n = 1; ; n++) { int next_bit = n << (old_bits - 1); u32 s = next_bit | pgid->seed; if (s < old_pg_num || s == pgid->seed) continue; if (s >= new_pg_num) break; s = ceph_stable_mod(s, old_pg_num, old_mask); if (s == pgid->seed) return true; } return false; } 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, |
ae78dd813 libceph: make REC... |
2063 2064 |
bool old_recovery_deletes, bool new_recovery_deletes, |
63244fa12 libceph: introduc... |
2065 2066 2067 2068 2069 2070 |
const struct ceph_pg *pgid) { return !osds_equal(old_acting, new_acting) || !osds_equal(old_up, new_up) || old_size != new_size || old_min_size != new_min_size || |
7de030d6b libceph: resend o... |
2071 |
ceph_pg_is_split(pgid, old_pg_num, new_pg_num) || |
ae78dd813 libceph: make REC... |
2072 2073 |
old_sort_bitwise != new_sort_bitwise || old_recovery_deletes != new_recovery_deletes; |
63244fa12 libceph: introduc... |
2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 |
} static int calc_pg_rank(int osd, const struct ceph_osds *acting) { int i; for (i = 0; i < acting->size; i++) { if (acting->osds[i] == osd) return i; } return -1; } static bool primary_changed(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting) { if (!old_acting->size && !new_acting->size) return false; /* both still empty */ if (!old_acting->size ^ !new_acting->size) return true; /* was empty, now not, or vice versa */ if (old_acting->primary != new_acting->primary) return true; /* primary changed */ if (calc_pg_rank(old_acting->primary, old_acting) != calc_pg_rank(new_acting->primary, new_acting)) return true; return false; /* same primary (tho replicas may have changed) */ } bool ceph_osds_changed(const struct ceph_osds *old_acting, const struct ceph_osds *new_acting, bool any_change) { if (primary_changed(old_acting, new_acting)) return true; if (any_change && !__osds_equal(old_acting, new_acting)) return true; return false; } |
f24e9980e ceph: OSD client |
2119 2120 2121 2122 2123 2124 2125 2126 |
/* * calculate file layout from given offset, length. * fill in correct oid, logical length, and object extent * offset, length. * * for now, we write only a single su, until we can * pass a stride back to the caller. */ |
d63b77f4c libceph: check fo... |
2127 |
int ceph_calc_file_object_mapping(struct ceph_file_layout *layout, |
e8afad656 libceph: pass len... |
2128 |
u64 off, u64 len, |
645a10258 ceph: fix object ... |
2129 |
u64 *ono, |
f24e9980e ceph: OSD client |
2130 2131 |
u64 *oxoff, u64 *oxlen) { |
7627151ea libceph: define n... |
2132 2133 2134 |
u32 osize = layout->object_size; u32 su = layout->stripe_unit; u32 sc = layout->stripe_count; |
f24e9980e ceph: OSD client |
2135 2136 |
u32 bl, stripeno, stripepos, objsetno; u32 su_per_object; |
ff1d1f717 ceph: fix intra s... |
2137 |
u64 t, su_offset; |
f24e9980e ceph: OSD client |
2138 |
|
e8afad656 libceph: pass len... |
2139 2140 |
dout("mapping %llu~%llu osize %u fl_su %u ", off, len, |
f24e9980e ceph: OSD client |
2141 |
osize, su); |
d63b77f4c libceph: check fo... |
2142 2143 |
if (su == 0 || sc == 0) goto invalid; |
35e054a66 ceph: remove redu... |
2144 |
su_per_object = osize / su; |
d63b77f4c libceph: check fo... |
2145 2146 |
if (su_per_object == 0) goto invalid; |
f24e9980e ceph: OSD client |
2147 2148 2149 |
dout("osize %u / su %u = su_per_object %u ", osize, su, su_per_object); |
d63b77f4c libceph: check fo... |
2150 2151 |
if ((su & ~PAGE_MASK) != 0) goto invalid; |
f24e9980e ceph: OSD client |
2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 |
/* bl = *off / su; */ t = off; do_div(t, su); bl = t; dout("off %llu / su %u = bl %u ", off, su, bl); stripeno = bl / sc; stripepos = bl % sc; objsetno = stripeno / su_per_object; |
645a10258 ceph: fix object ... |
2162 |
*ono = objsetno * sc + stripepos; |
95c961747 net: cleanup unsi... |
2163 2164 |
dout("objset %u * sc %u = ono %u ", objsetno, sc, (unsigned int)*ono); |
645a10258 ceph: fix object ... |
2165 2166 |
/* *oxoff = *off % layout->fl_stripe_unit; # offset in su */ |
f24e9980e ceph: OSD client |
2167 |
t = off; |
ff1d1f717 ceph: fix intra s... |
2168 2169 2170 2171 2172 |
su_offset = do_div(t, su); *oxoff = su_offset + (stripeno % su_per_object) * su; /* * Calculate the length of the extent being written to the selected |
e8afad656 libceph: pass len... |
2173 |
* object. This is the minimum of the full length requested (len) or |
ff1d1f717 ceph: fix intra s... |
2174 2175 |
* the remainder of the current stripe being written to. */ |
e8afad656 libceph: pass len... |
2176 |
*oxlen = min_t(u64, len, su - su_offset); |
f24e9980e ceph: OSD client |
2177 2178 2179 |
dout(" obj extent %llu~%llu ", *oxoff, *oxlen); |
d63b77f4c libceph: check fo... |
2180 2181 2182 2183 2184 2185 2186 2187 2188 |
return 0; invalid: dout(" invalid layout "); *ono = 0; *oxoff = 0; *oxlen = 0; return -EINVAL; |
f24e9980e ceph: OSD client |
2189 |
} |
3d14c5d2b ceph: factor out ... |
2190 |
EXPORT_SYMBOL(ceph_calc_file_object_mapping); |
f24e9980e ceph: OSD client |
2191 2192 |
/* |
d9591f5e2 libceph: rename c... |
2193 2194 2195 2196 |
* Map an object into a PG. * * Should only be called with target_oid and target_oloc (as opposed to * base_oid and base_oloc), since tiering isn't taken into account. |
f24e9980e ceph: OSD client |
2197 |
*/ |
df28152d5 libceph: avoid un... |
2198 2199 2200 2201 |
int __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) |
f24e9980e ceph: OSD client |
2202 |
{ |
df28152d5 libceph: avoid un... |
2203 |
WARN_ON(pi->id != oloc->pool); |
f24e9980e ceph: OSD client |
2204 |
|
30c156d99 libceph: rados po... |
2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 |
if (!oloc->pool_ns) { raw_pgid->pool = oloc->pool; raw_pgid->seed = ceph_str_hash(pi->object_hash, oid->name, oid->name_len); dout("%s %s -> raw_pgid %llu.%x ", __func__, oid->name, raw_pgid->pool, raw_pgid->seed); } else { char stack_buf[256]; char *buf = stack_buf; int nsl = oloc->pool_ns->len; size_t total = nsl + 1 + oid->name_len; if (total > sizeof(stack_buf)) { buf = kmalloc(total, GFP_NOIO); if (!buf) return -ENOMEM; } memcpy(buf, oloc->pool_ns->str, nsl); buf[nsl] = '\037'; memcpy(buf + nsl + 1, oid->name, oid->name_len); raw_pgid->pool = oloc->pool; raw_pgid->seed = ceph_str_hash(pi->object_hash, buf, total); if (buf != stack_buf) kfree(buf); dout("%s %s ns %.*s -> raw_pgid %llu.%x ", __func__, oid->name, nsl, oloc->pool_ns->str, raw_pgid->pool, raw_pgid->seed); } |
f24e9980e ceph: OSD client |
2235 2236 |
return 0; } |
df28152d5 libceph: avoid un... |
2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 |
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) { struct ceph_pg_pool_info *pi; pi = ceph_pg_pool_by_id(osdmap, oloc->pool); if (!pi) return -ENOENT; return __ceph_object_locator_to_pg(pi, oid, oloc, raw_pgid); } |
d9591f5e2 libceph: rename c... |
2251 |
EXPORT_SYMBOL(ceph_object_locator_to_pg); |
f24e9980e ceph: OSD client |
2252 |
|
6f3bfd45c libceph: ceph_osd... |
2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 |
/* * Map a raw PG (full precision ps) into an actual PG. */ static void raw_pg_to_pg(struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid, struct ceph_pg *pgid) { pgid->pool = raw_pgid->pool; pgid->seed = ceph_stable_mod(raw_pgid->seed, pi->pg_num, pi->pg_num_mask); } /* * Map a raw PG (full precision ps) into a placement ps (placement * seed). Include pool id in that value so that different pools don't * use the same seeds. */ static u32 raw_pg_to_pps(struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid) { if (pi->flags & CEPH_POOL_FLAG_HASHPSPOOL) { /* hash pool id and seed so that pool PGs do not overlap */ return crush_hash32_2(CRUSH_HASH_RJENKINS1, ceph_stable_mod(raw_pgid->seed, pi->pgp_num, pi->pgp_num_mask), raw_pgid->pool); } else { /* * legacy behavior: add ps and pool together. this is * not a great approach because the PGs from each pool * will overlap on top of each other: 0.5 == 1.4 == * 2.3 == ... */ return ceph_stable_mod(raw_pgid->seed, pi->pgp_num, pi->pgp_num_mask) + (unsigned)raw_pgid->pool; } } |
e17e8969f libceph: fallback... |
2292 2293 2294 2295 2296 2297 |
/* * Magic value used for a "default" fallback choose_args, used if the * crush_choose_arg_map passed to do_crush() does not exist. If this * also doesn't exist, fall back to canonical weights. */ #define CEPH_DEFAULT_CHOOSE_ARGS -1 |
9d521470a libceph: a per-os... |
2298 2299 |
static int do_crush(struct ceph_osdmap *map, int ruleno, int x, int *result, int result_max, |
5cf9c4a99 libceph, crush: p... |
2300 |
const __u32 *weight, int weight_max, |
e17e8969f libceph: fallback... |
2301 |
s64 choose_args_index) |
e8ef19c4a crush: eliminate ... |
2302 |
{ |
5cf9c4a99 libceph, crush: p... |
2303 |
struct crush_choose_arg_map *arg_map; |
9d521470a libceph: a per-os... |
2304 2305 2306 |
int r; BUG_ON(result_max > CEPH_PG_MAX_SIZE); |
5cf9c4a99 libceph, crush: p... |
2307 2308 |
arg_map = lookup_choose_arg_map(&map->crush->choose_args, choose_args_index); |
e17e8969f libceph: fallback... |
2309 2310 2311 |
if (!arg_map) arg_map = lookup_choose_arg_map(&map->crush->choose_args, CEPH_DEFAULT_CHOOSE_ARGS); |
5cf9c4a99 libceph, crush: p... |
2312 |
|
743efcfff crush: merge work... |
2313 |
mutex_lock(&map->crush_workspace_mutex); |
9d521470a libceph: a per-os... |
2314 |
r = crush_do_rule(map->crush, ruleno, x, result, result_max, |
5cf9c4a99 libceph, crush: p... |
2315 2316 |
weight, weight_max, map->crush_workspace, arg_map ? arg_map->args : NULL); |
743efcfff crush: merge work... |
2317 |
mutex_unlock(&map->crush_workspace_mutex); |
e8ef19c4a crush: eliminate ... |
2318 |
|
9d521470a libceph: a per-os... |
2319 |
return r; |
e8ef19c4a crush: eliminate ... |
2320 |
} |
1c2e7b451 libceph: apply_up... |
2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 |
static void remove_nonexistent_osds(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, struct ceph_osds *set) { int i; if (ceph_can_shift_osds(pi)) { int removed = 0; /* shift left */ for (i = 0; i < set->size; i++) { if (!ceph_osd_exists(osdmap, set->osds[i])) { removed++; continue; } if (removed) set->osds[i - removed] = set->osds[i]; } set->size -= removed; } else { /* set dne devices to NONE */ for (i = 0; i < set->size; i++) { if (!ceph_osd_exists(osdmap, set->osds[i])) set->osds[i] = CRUSH_ITEM_NONE; } } } |
f24e9980e ceph: OSD client |
2348 |
/* |
1c2e7b451 libceph: apply_up... |
2349 2350 |
* Calculate raw set (CRUSH output) for given PG and filter out * nonexistent OSDs. ->primary is undefined for a raw set. |
2bd93d4d7 libceph: introduc... |
2351 |
* |
6f3bfd45c libceph: ceph_osd... |
2352 |
* Placement seed (CRUSH input) is returned through @ppps. |
2bd93d4d7 libceph: introduc... |
2353 |
*/ |
6f3bfd45c libceph: ceph_osd... |
2354 2355 2356 2357 2358 |
static void pg_to_raw_osds(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, const struct ceph_pg *raw_pgid, struct ceph_osds *raw, u32 *ppps) |
2bd93d4d7 libceph: introduc... |
2359 |
{ |
6f3bfd45c libceph: ceph_osd... |
2360 |
u32 pps = raw_pg_to_pps(pi, raw_pgid); |
2bd93d4d7 libceph: introduc... |
2361 2362 |
int ruleno; int len; |
6f3bfd45c libceph: ceph_osd... |
2363 2364 2365 2366 2367 2368 |
ceph_osds_init(raw); if (ppps) *ppps = pps; ruleno = crush_find_rule(osdmap->crush, pi->crush_ruleset, pi->type, pi->size); |
2bd93d4d7 libceph: introduc... |
2369 2370 2371 |
if (ruleno < 0) { pr_err("no crush rule: pool %lld ruleset %d type %d size %d ", |
6f3bfd45c libceph: ceph_osd... |
2372 2373 |
pi->id, pi->crush_ruleset, pi->type, pi->size); return; |
2bd93d4d7 libceph: introduc... |
2374 |
} |
ef9324bb1 libceph: don't go... |
2375 2376 2377 2378 2379 2380 2381 2382 2383 |
if (pi->size > ARRAY_SIZE(raw->osds)) { pr_err_ratelimited("pool %lld ruleset %d type %d too wide: size %d > %zu ", pi->id, pi->crush_ruleset, pi->type, pi->size, ARRAY_SIZE(raw->osds)); return; } len = do_crush(osdmap, ruleno, pps, raw->osds, pi->size, |
5cf9c4a99 libceph, crush: p... |
2384 |
osdmap->osd_weight, osdmap->max_osd, pi->id); |
2bd93d4d7 libceph: introduc... |
2385 2386 2387 |
if (len < 0) { pr_err("error %d from crush rule %d: pool %lld ruleset %d type %d size %d ", |
6f3bfd45c libceph: ceph_osd... |
2388 2389 2390 |
len, ruleno, pi->id, pi->crush_ruleset, pi->type, pi->size); return; |
2bd93d4d7 libceph: introduc... |
2391 |
} |
6f3bfd45c libceph: ceph_osd... |
2392 |
raw->size = len; |
1c2e7b451 libceph: apply_up... |
2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 |
remove_nonexistent_osds(osdmap, pi, raw); } /* apply pg_upmap[_items] mappings */ static void apply_upmap(struct ceph_osdmap *osdmap, const struct ceph_pg *pgid, struct ceph_osds *raw) { struct ceph_pg_mapping *pg; int i, j; pg = lookup_pg_mapping(&osdmap->pg_upmap, pgid); if (pg) { /* make sure targets aren't marked out */ for (i = 0; i < pg->pg_upmap.len; i++) { int osd = pg->pg_upmap.osds[i]; if (osd != CRUSH_ITEM_NONE && osd < osdmap->max_osd && osdmap->osd_weight[osd] == 0) { /* reject/ignore explicit mapping */ return; } } for (i = 0; i < pg->pg_upmap.len; i++) raw->osds[i] = pg->pg_upmap.osds[i]; raw->size = pg->pg_upmap.len; |
f53b7665c libceph: upmap se... |
2420 |
/* check and apply pg_upmap_items, if any */ |
1c2e7b451 libceph: apply_up... |
2421 2422 2423 2424 |
} pg = lookup_pg_mapping(&osdmap->pg_upmap_items, pgid); if (pg) { |
29a0cfbf9 libceph: don't al... |
2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 |
/* * Note: this approach does not allow a bidirectional swap, * e.g., [[1,2],[2,1]] applied to [0,1,2] -> [0,2,1]. */ for (i = 0; i < pg->pg_upmap_items.len; i++) { int from = pg->pg_upmap_items.from_to[i][0]; int to = pg->pg_upmap_items.from_to[i][1]; int pos = -1; bool exists = false; /* make sure replacement doesn't already appear */ for (j = 0; j < raw->size; j++) { int osd = raw->osds[j]; if (osd == to) { exists = true; |
1c2e7b451 libceph: apply_up... |
2441 2442 |
break; } |
29a0cfbf9 libceph: don't al... |
2443 2444 2445 2446 2447 2448 2449 |
/* ignore mapping if target is marked out */ if (osd == from && pos < 0 && !(to != CRUSH_ITEM_NONE && to < osdmap->max_osd && osdmap->osd_weight[to] == 0)) { pos = j; } |
1c2e7b451 libceph: apply_up... |
2450 |
} |
29a0cfbf9 libceph: don't al... |
2451 2452 |
if (!exists && pos >= 0) raw->osds[pos] = to; |
1c2e7b451 libceph: apply_up... |
2453 2454 |
} } |
2bd93d4d7 libceph: introduc... |
2455 2456 2457 |
} /* |
6f3bfd45c libceph: ceph_osd... |
2458 2459 |
* Given raw set, calculate up set and up primary. By definition of an * up set, the result won't contain nonexistent or down OSDs. |
2bd93d4d7 libceph: introduc... |
2460 |
* |
6f3bfd45c libceph: ceph_osd... |
2461 2462 |
* This is done in-place - on return @set is the up set. If it's * empty, ->primary will remain undefined. |
2bd93d4d7 libceph: introduc... |
2463 |
*/ |
6f3bfd45c libceph: ceph_osd... |
2464 2465 2466 |
static void raw_to_up_osds(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, struct ceph_osds *set) |
2bd93d4d7 libceph: introduc... |
2467 |
{ |
2bd93d4d7 libceph: introduc... |
2468 |
int i; |
6f3bfd45c libceph: ceph_osd... |
2469 2470 2471 2472 |
/* ->primary is undefined for a raw set */ BUG_ON(set->primary != -1); if (ceph_can_shift_osds(pi)) { |
2bd93d4d7 libceph: introduc... |
2473 |
int removed = 0; |
6f3bfd45c libceph: ceph_osd... |
2474 2475 2476 |
/* shift left */ for (i = 0; i < set->size; i++) { if (ceph_osd_is_down(osdmap, set->osds[i])) { |
2bd93d4d7 libceph: introduc... |
2477 2478 2479 2480 |
removed++; continue; } if (removed) |
6f3bfd45c libceph: ceph_osd... |
2481 |
set->osds[i - removed] = set->osds[i]; |
2bd93d4d7 libceph: introduc... |
2482 |
} |
6f3bfd45c libceph: ceph_osd... |
2483 2484 2485 |
set->size -= removed; if (set->size > 0) set->primary = set->osds[0]; |
2bd93d4d7 libceph: introduc... |
2486 |
} else { |
6f3bfd45c libceph: ceph_osd... |
2487 2488 2489 2490 |
/* set down/dne devices to NONE */ for (i = set->size - 1; i >= 0; i--) { if (ceph_osd_is_down(osdmap, set->osds[i])) set->osds[i] = CRUSH_ITEM_NONE; |
2bd93d4d7 libceph: introduc... |
2491 |
else |
6f3bfd45c libceph: ceph_osd... |
2492 |
set->primary = set->osds[i]; |
2bd93d4d7 libceph: introduc... |
2493 2494 |
} } |
2bd93d4d7 libceph: introduc... |
2495 |
} |
6f3bfd45c libceph: ceph_osd... |
2496 2497 2498 2499 |
static void apply_primary_affinity(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, u32 pps, struct ceph_osds *up) |
47ec1f3cc libceph: add supp... |
2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 |
{ int i; int pos = -1; /* * Do we have any non-default primary_affinity values for these * osds? */ if (!osdmap->osd_primary_affinity) return; |
6f3bfd45c libceph: ceph_osd... |
2510 2511 |
for (i = 0; i < up->size; i++) { int osd = up->osds[i]; |
92b2e7515 libceph: fix non-... |
2512 2513 2514 |
if (osd != CRUSH_ITEM_NONE && osdmap->osd_primary_affinity[osd] != |
47ec1f3cc libceph: add supp... |
2515 2516 2517 2518 |
CEPH_OSD_DEFAULT_PRIMARY_AFFINITY) { break; } } |
6f3bfd45c libceph: ceph_osd... |
2519 |
if (i == up->size) |
47ec1f3cc libceph: add supp... |
2520 2521 2522 2523 2524 2525 2526 |
return; /* * Pick the primary. Feed both the seed (for the pg) and the * osd into the hash/rng so that a proportional fraction of an * osd's pgs get rejected as primary. */ |
6f3bfd45c libceph: ceph_osd... |
2527 2528 |
for (i = 0; i < up->size; i++) { int osd = up->osds[i]; |
47ec1f3cc libceph: add supp... |
2529 |
u32 aff; |
47ec1f3cc libceph: add supp... |
2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 |
if (osd == CRUSH_ITEM_NONE) continue; aff = osdmap->osd_primary_affinity[osd]; if (aff < CEPH_OSD_MAX_PRIMARY_AFFINITY && (crush_hash32_2(CRUSH_HASH_RJENKINS1, pps, osd) >> 16) >= aff) { /* * We chose not to use this primary. Note it * anyway as a fallback in case we don't pick * anyone else, but keep looking. */ if (pos < 0) pos = i; } else { pos = i; break; } } if (pos < 0) return; |
6f3bfd45c libceph: ceph_osd... |
2551 |
up->primary = up->osds[pos]; |
47ec1f3cc libceph: add supp... |
2552 |
|
6f3bfd45c libceph: ceph_osd... |
2553 |
if (ceph_can_shift_osds(pi) && pos > 0) { |
47ec1f3cc libceph: add supp... |
2554 2555 |
/* move the new primary to the front */ for (i = pos; i > 0; i--) |
6f3bfd45c libceph: ceph_osd... |
2556 2557 |
up->osds[i] = up->osds[i - 1]; up->osds[0] = up->primary; |
47ec1f3cc libceph: add supp... |
2558 2559 |
} } |
2bd93d4d7 libceph: introduc... |
2560 |
/* |
6f3bfd45c libceph: ceph_osd... |
2561 |
* Get pg_temp and primary_temp mappings for given PG. |
45966c346 libceph: introduc... |
2562 |
* |
6f3bfd45c libceph: ceph_osd... |
2563 2564 2565 2566 |
* Note that a PG may have none, only pg_temp, only primary_temp or * both pg_temp and primary_temp mappings. This means @temp isn't * always a valid OSD set on return: in the "only primary_temp" case, * @temp will have its ->primary >= 0 but ->size == 0. |
45966c346 libceph: introduc... |
2567 |
*/ |
6f3bfd45c libceph: ceph_osd... |
2568 2569 |
static void get_temp_osds(struct ceph_osdmap *osdmap, struct ceph_pg_pool_info *pi, |
463bb8da5 libceph: compute ... |
2570 |
const struct ceph_pg *pgid, |
6f3bfd45c libceph: ceph_osd... |
2571 |
struct ceph_osds *temp) |
45966c346 libceph: introduc... |
2572 2573 |
{ struct ceph_pg_mapping *pg; |
45966c346 libceph: introduc... |
2574 |
int i; |
6f3bfd45c libceph: ceph_osd... |
2575 |
ceph_osds_init(temp); |
45966c346 libceph: introduc... |
2576 2577 |
/* pg_temp? */ |
463bb8da5 libceph: compute ... |
2578 |
pg = lookup_pg_mapping(&osdmap->pg_temp, pgid); |
45966c346 libceph: introduc... |
2579 |
if (pg) { |
45966c346 libceph: introduc... |
2580 2581 |
for (i = 0; i < pg->pg_temp.len; i++) { if (ceph_osd_is_down(osdmap, pg->pg_temp.osds[i])) { |
6f3bfd45c libceph: ceph_osd... |
2582 |
if (ceph_can_shift_osds(pi)) |
45966c346 libceph: introduc... |
2583 |
continue; |
6f3bfd45c libceph: ceph_osd... |
2584 2585 |
temp->osds[temp->size++] = CRUSH_ITEM_NONE; |
45966c346 libceph: introduc... |
2586 |
} else { |
6f3bfd45c libceph: ceph_osd... |
2587 |
temp->osds[temp->size++] = pg->pg_temp.osds[i]; |
45966c346 libceph: introduc... |
2588 2589 2590 2591 |
} } /* apply pg_temp's primary */ |
6f3bfd45c libceph: ceph_osd... |
2592 2593 2594 |
for (i = 0; i < temp->size; i++) { if (temp->osds[i] != CRUSH_ITEM_NONE) { temp->primary = temp->osds[i]; |
45966c346 libceph: introduc... |
2595 2596 2597 |
break; } } |
45966c346 libceph: introduc... |
2598 |
} |
5e8d4d36b libceph: add supp... |
2599 |
/* primary_temp? */ |
463bb8da5 libceph: compute ... |
2600 |
pg = lookup_pg_mapping(&osdmap->primary_temp, pgid); |
5e8d4d36b libceph: add supp... |
2601 |
if (pg) |
6f3bfd45c libceph: ceph_osd... |
2602 |
temp->primary = pg->primary_temp.osd; |
45966c346 libceph: introduc... |
2603 2604 2605 |
} /* |
6f3bfd45c libceph: ceph_osd... |
2606 |
* Map a PG to its acting set as well as its up set. |
ac972230e libceph: switch c... |
2607 |
* |
6f3bfd45c libceph: ceph_osd... |
2608 2609 2610 |
* Acting set is used for data mapping purposes, while up set can be * recorded for detecting interval changes and deciding whether to * resend a request. |
d85b70566 ceph: resubmit re... |
2611 |
*/ |
6f3bfd45c libceph: ceph_osd... |
2612 |
void ceph_pg_to_up_acting_osds(struct ceph_osdmap *osdmap, |
df28152d5 libceph: avoid un... |
2613 |
struct ceph_pg_pool_info *pi, |
6f3bfd45c libceph: ceph_osd... |
2614 2615 2616 |
const struct ceph_pg *raw_pgid, struct ceph_osds *up, struct ceph_osds *acting) |
d85b70566 ceph: resubmit re... |
2617 |
{ |
463bb8da5 libceph: compute ... |
2618 |
struct ceph_pg pgid; |
ac972230e libceph: switch c... |
2619 |
u32 pps; |
d85b70566 ceph: resubmit re... |
2620 |
|
df28152d5 libceph: avoid un... |
2621 |
WARN_ON(pi->id != raw_pgid->pool); |
463bb8da5 libceph: compute ... |
2622 |
raw_pg_to_pg(pi, raw_pgid, &pgid); |
d85b70566 ceph: resubmit re... |
2623 |
|
6f3bfd45c libceph: ceph_osd... |
2624 |
pg_to_raw_osds(osdmap, pi, raw_pgid, up, &pps); |
1c2e7b451 libceph: apply_up... |
2625 |
apply_upmap(osdmap, &pgid, up); |
6f3bfd45c libceph: ceph_osd... |
2626 2627 |
raw_to_up_osds(osdmap, pi, up); apply_primary_affinity(osdmap, pi, pps, up); |
463bb8da5 libceph: compute ... |
2628 |
get_temp_osds(osdmap, pi, &pgid, acting); |
6f3bfd45c libceph: ceph_osd... |
2629 2630 2631 2632 2633 |
if (!acting->size) { memcpy(acting->osds, up->osds, up->size * sizeof(up->osds[0])); acting->size = up->size; if (acting->primary == -1) acting->primary = up->primary; |
8008ab108 libceph: return p... |
2634 |
} |
6f3bfd45c libceph: ceph_osd... |
2635 |
WARN_ON(!osds_valid(up) || !osds_valid(acting)); |
d85b70566 ceph: resubmit re... |
2636 |
} |
dc98ff723 libceph: introduc... |
2637 |
bool ceph_pg_to_primary_shard(struct ceph_osdmap *osdmap, |
df28152d5 libceph: avoid un... |
2638 |
struct ceph_pg_pool_info *pi, |
dc98ff723 libceph: introduc... |
2639 2640 2641 |
const struct ceph_pg *raw_pgid, struct ceph_spg *spgid) { |
dc98ff723 libceph: introduc... |
2642 2643 2644 |
struct ceph_pg pgid; struct ceph_osds up, acting; int i; |
df28152d5 libceph: avoid un... |
2645 |
WARN_ON(pi->id != raw_pgid->pool); |
dc98ff723 libceph: introduc... |
2646 2647 2648 2649 2650 2651 2652 |
raw_pg_to_pg(pi, raw_pgid, &pgid); if (ceph_can_shift_osds(pi)) { spgid->pgid = pgid; /* struct */ spgid->shard = CEPH_SPG_NOSHARD; return true; } |
df28152d5 libceph: avoid un... |
2653 |
ceph_pg_to_up_acting_osds(osdmap, pi, &pgid, &up, &acting); |
dc98ff723 libceph: introduc... |
2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 |
for (i = 0; i < acting.size; i++) { if (acting.osds[i] == acting.primary) { spgid->pgid = pgid; /* struct */ spgid->shard = i; return true; } } return false; } |
d85b70566 ceph: resubmit re... |
2664 |
/* |
f81f16339 libceph: rename c... |
2665 |
* Return acting primary for given PG, or -1 if none. |
f24e9980e ceph: OSD client |
2666 |
*/ |
f81f16339 libceph: rename c... |
2667 2668 |
int ceph_pg_to_acting_primary(struct ceph_osdmap *osdmap, const struct ceph_pg *raw_pgid) |
f24e9980e ceph: OSD client |
2669 |
{ |
df28152d5 libceph: avoid un... |
2670 |
struct ceph_pg_pool_info *pi; |
6f3bfd45c libceph: ceph_osd... |
2671 |
struct ceph_osds up, acting; |
f24e9980e ceph: OSD client |
2672 |
|
df28152d5 libceph: avoid un... |
2673 2674 2675 2676 2677 |
pi = ceph_pg_pool_by_id(osdmap, raw_pgid->pool); if (!pi) return -1; ceph_pg_to_up_acting_osds(osdmap, pi, raw_pgid, &up, &acting); |
6f3bfd45c libceph: ceph_osd... |
2678 |
return acting.primary; |
f24e9980e ceph: OSD client |
2679 |
} |
f81f16339 libceph: rename c... |
2680 |
EXPORT_SYMBOL(ceph_pg_to_acting_primary); |