Loading...
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 | /*
* GPL HEADER START
*
* DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 only,
* as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License version 2 for more details (a copy is included
* in the LICENSE file that accompanied this code).
*
* You should have received a copy of the GNU General Public License
* version 2 along with this program; If not, see
* http://www.sun.com/software/products/lustre/docs/GPLv2.pdf
*
* Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara,
* CA 95054 USA or visit www.sun.com if you need additional information or
* have any questions.
*
* GPL HEADER END
*/
/*
* Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
* Use is subject to license terms.
*
* Copyright (c) 2011, 2013, Intel Corporation.
*/
/*
* This file is part of Lustre, http://www.lustre.org/
* Lustre is a trademark of Sun Microsystems, Inc.
*
* lustre/fid/fid_request.c
*
* Lustre Sequence Manager
*
* Author: Yury Umanets <umka@clusterfs.com>
*/
#define DEBUG_SUBSYSTEM S_FID
#include <linux/libcfs/libcfs.h>
#include <linux/module.h>
#include <obd.h>
#include <obd_class.h>
#include <obd_support.h>
#include <lustre_fid.h>
/* mdc RPC locks */
#include <lustre_mdc.h>
#include "fid_internal.h"
static int seq_client_rpc(struct lu_client_seq *seq,
struct lu_seq_range *output, __u32 opc,
const char *opcname)
{
struct obd_export *exp = seq->lcs_exp;
struct ptlrpc_request *req;
struct lu_seq_range *out, *in;
__u32 *op;
unsigned int debug_mask;
int rc;
req = ptlrpc_request_alloc_pack(class_exp2cliimp(exp), &RQF_SEQ_QUERY,
LUSTRE_MDS_VERSION, SEQ_QUERY);
if (req == NULL)
return -ENOMEM;
/* Init operation code */
op = req_capsule_client_get(&req->rq_pill, &RMF_SEQ_OPC);
*op = opc;
/* Zero out input range, this is not recovery yet. */
in = req_capsule_client_get(&req->rq_pill, &RMF_SEQ_RANGE);
range_init(in);
ptlrpc_request_set_replen(req);
in->lsr_index = seq->lcs_space.lsr_index;
if (seq->lcs_type == LUSTRE_SEQ_METADATA)
fld_range_set_mdt(in);
else
fld_range_set_ost(in);
if (opc == SEQ_ALLOC_SUPER) {
req->rq_request_portal = SEQ_CONTROLLER_PORTAL;
req->rq_reply_portal = MDC_REPLY_PORTAL;
/* During allocating super sequence for data object,
* the current thread might hold the export of MDT0(MDT0
* precreating objects on this OST), and it will send the
* request to MDT0 here, so we can not keep resending the
* request here, otherwise if MDT0 is failed(umounted),
* it can not release the export of MDT0 */
if (seq->lcs_type == LUSTRE_SEQ_DATA)
req->rq_no_delay = req->rq_no_resend = 1;
debug_mask = D_CONSOLE;
} else {
if (seq->lcs_type == LUSTRE_SEQ_METADATA)
req->rq_request_portal = SEQ_METADATA_PORTAL;
else
req->rq_request_portal = SEQ_DATA_PORTAL;
debug_mask = D_INFO;
}
ptlrpc_at_set_req_timeout(req);
if (seq->lcs_type == LUSTRE_SEQ_METADATA)
mdc_get_rpc_lock(exp->exp_obd->u.cli.cl_rpc_lock, NULL);
rc = ptlrpc_queue_wait(req);
if (seq->lcs_type == LUSTRE_SEQ_METADATA)
mdc_put_rpc_lock(exp->exp_obd->u.cli.cl_rpc_lock, NULL);
if (rc)
GOTO(out_req, rc);
out = req_capsule_server_get(&req->rq_pill, &RMF_SEQ_RANGE);
*output = *out;
if (!range_is_sane(output)) {
CERROR("%s: Invalid range received from server: "
DRANGE"\n", seq->lcs_name, PRANGE(output));
GOTO(out_req, rc = -EINVAL);
}
if (range_is_exhausted(output)) {
CERROR("%s: Range received from server is exhausted: "
DRANGE"]\n", seq->lcs_name, PRANGE(output));
GOTO(out_req, rc = -EINVAL);
}
CDEBUG_LIMIT(debug_mask, "%s: Allocated %s-sequence "DRANGE"]\n",
seq->lcs_name, opcname, PRANGE(output));
out_req:
ptlrpc_req_finished(req);
return rc;
}
/* Request sequence-controller node to allocate new super-sequence. */
int seq_client_alloc_super(struct lu_client_seq *seq,
const struct lu_env *env)
{
int rc;
mutex_lock(&seq->lcs_mutex);
if (seq->lcs_srv) {
rc = 0;
} else {
/* Check whether the connection to seq controller has been
* setup (lcs_exp != NULL) */
if (seq->lcs_exp == NULL) {
mutex_unlock(&seq->lcs_mutex);
return -EINPROGRESS;
}
rc = seq_client_rpc(seq, &seq->lcs_space,
SEQ_ALLOC_SUPER, "super");
}
mutex_unlock(&seq->lcs_mutex);
return rc;
}
/* Request sequence-controller node to allocate new meta-sequence. */
static int seq_client_alloc_meta(const struct lu_env *env,
struct lu_client_seq *seq)
{
int rc;
if (seq->lcs_srv) {
rc = 0;
} else {
do {
/* If meta server return -EINPROGRESS or EAGAIN,
* it means meta server might not be ready to
* allocate super sequence from sequence controller
* (MDT0)yet */
rc = seq_client_rpc(seq, &seq->lcs_space,
SEQ_ALLOC_META, "meta");
} while (rc == -EINPROGRESS || rc == -EAGAIN);
}
return rc;
}
/* Allocate new sequence for client. */
static int seq_client_alloc_seq(const struct lu_env *env,
struct lu_client_seq *seq, seqno_t *seqnr)
{
int rc;
LASSERT(range_is_sane(&seq->lcs_space));
if (range_is_exhausted(&seq->lcs_space)) {
rc = seq_client_alloc_meta(env, seq);
if (rc) {
CERROR("%s: Can't allocate new meta-sequence,"
"rc %d\n", seq->lcs_name, rc);
return rc;
} else {
CDEBUG(D_INFO, "%s: New range - "DRANGE"\n",
seq->lcs_name, PRANGE(&seq->lcs_space));
}
} else {
rc = 0;
}
LASSERT(!range_is_exhausted(&seq->lcs_space));
*seqnr = seq->lcs_space.lsr_start;
seq->lcs_space.lsr_start += 1;
CDEBUG(D_INFO, "%s: Allocated sequence ["LPX64"]\n", seq->lcs_name,
*seqnr);
return rc;
}
static int seq_fid_alloc_prep(struct lu_client_seq *seq,
wait_queue_t *link)
{
if (seq->lcs_update) {
add_wait_queue(&seq->lcs_waitq, link);
set_current_state(TASK_UNINTERRUPTIBLE);
mutex_unlock(&seq->lcs_mutex);
waitq_wait(link, TASK_UNINTERRUPTIBLE);
mutex_lock(&seq->lcs_mutex);
remove_wait_queue(&seq->lcs_waitq, link);
set_current_state(TASK_RUNNING);
return -EAGAIN;
}
++seq->lcs_update;
mutex_unlock(&seq->lcs_mutex);
return 0;
}
static void seq_fid_alloc_fini(struct lu_client_seq *seq)
{
LASSERT(seq->lcs_update == 1);
mutex_lock(&seq->lcs_mutex);
--seq->lcs_update;
wake_up(&seq->lcs_waitq);
}
/**
* Allocate the whole seq to the caller.
**/
int seq_client_get_seq(const struct lu_env *env,
struct lu_client_seq *seq, seqno_t *seqnr)
{
wait_queue_t link;
int rc;
LASSERT(seqnr != NULL);
mutex_lock(&seq->lcs_mutex);
init_waitqueue_entry_current(&link);
while (1) {
rc = seq_fid_alloc_prep(seq, &link);
if (rc == 0)
break;
}
rc = seq_client_alloc_seq(env, seq, seqnr);
if (rc) {
CERROR("%s: Can't allocate new sequence, "
"rc %d\n", seq->lcs_name, rc);
seq_fid_alloc_fini(seq);
mutex_unlock(&seq->lcs_mutex);
return rc;
}
CDEBUG(D_INFO, "%s: allocate sequence "
"[0x%16.16"LPF64"x]\n", seq->lcs_name, *seqnr);
/* Since the caller require the whole seq,
* so marked this seq to be used */
if (seq->lcs_type == LUSTRE_SEQ_METADATA)
seq->lcs_fid.f_oid = LUSTRE_METADATA_SEQ_MAX_WIDTH;
else
seq->lcs_fid.f_oid = LUSTRE_DATA_SEQ_MAX_WIDTH;
seq->lcs_fid.f_seq = *seqnr;
seq->lcs_fid.f_ver = 0;
/*
* Inform caller that sequence switch is performed to allow it
* to setup FLD for it.
*/
seq_fid_alloc_fini(seq);
mutex_unlock(&seq->lcs_mutex);
return rc;
}
EXPORT_SYMBOL(seq_client_get_seq);
/* Allocate new fid on passed client @seq and save it to @fid. */
int seq_client_alloc_fid(const struct lu_env *env,
struct lu_client_seq *seq, struct lu_fid *fid)
{
wait_queue_t link;
int rc;
LASSERT(seq != NULL);
LASSERT(fid != NULL);
init_waitqueue_entry_current(&link);
mutex_lock(&seq->lcs_mutex);
if (OBD_FAIL_CHECK(OBD_FAIL_SEQ_EXHAUST))
seq->lcs_fid.f_oid = seq->lcs_width;
while (1) {
seqno_t seqnr;
if (!fid_is_zero(&seq->lcs_fid) &&
fid_oid(&seq->lcs_fid) < seq->lcs_width) {
/* Just bump last allocated fid and return to caller. */
seq->lcs_fid.f_oid += 1;
rc = 0;
break;
}
rc = seq_fid_alloc_prep(seq, &link);
if (rc)
continue;
rc = seq_client_alloc_seq(env, seq, &seqnr);
if (rc) {
CERROR("%s: Can't allocate new sequence, "
"rc %d\n", seq->lcs_name, rc);
seq_fid_alloc_fini(seq);
mutex_unlock(&seq->lcs_mutex);
return rc;
}
CDEBUG(D_INFO, "%s: Switch to sequence "
"[0x%16.16"LPF64"x]\n", seq->lcs_name, seqnr);
seq->lcs_fid.f_oid = LUSTRE_FID_INIT_OID;
seq->lcs_fid.f_seq = seqnr;
seq->lcs_fid.f_ver = 0;
/*
* Inform caller that sequence switch is performed to allow it
* to setup FLD for it.
*/
rc = 1;
seq_fid_alloc_fini(seq);
break;
}
*fid = seq->lcs_fid;
mutex_unlock(&seq->lcs_mutex);
CDEBUG(D_INFO, "%s: Allocated FID "DFID"\n", seq->lcs_name, PFID(fid));
return rc;
}
EXPORT_SYMBOL(seq_client_alloc_fid);
/*
* Finish the current sequence due to disconnect.
* See mdc_import_event()
*/
void seq_client_flush(struct lu_client_seq *seq)
{
wait_queue_t link;
LASSERT(seq != NULL);
init_waitqueue_entry_current(&link);
mutex_lock(&seq->lcs_mutex);
while (seq->lcs_update) {
add_wait_queue(&seq->lcs_waitq, &link);
set_current_state(TASK_UNINTERRUPTIBLE);
mutex_unlock(&seq->lcs_mutex);
waitq_wait(&link, TASK_UNINTERRUPTIBLE);
mutex_lock(&seq->lcs_mutex);
remove_wait_queue(&seq->lcs_waitq, &link);
set_current_state(TASK_RUNNING);
}
fid_zero(&seq->lcs_fid);
/**
* this id shld not be used for seq range allocation.
* set to -1 for dgb check.
*/
seq->lcs_space.lsr_index = -1;
range_init(&seq->lcs_space);
mutex_unlock(&seq->lcs_mutex);
}
EXPORT_SYMBOL(seq_client_flush);
static void seq_client_proc_fini(struct lu_client_seq *seq)
{
#ifdef LPROCFS
if (seq->lcs_proc_dir) {
if (!IS_ERR(seq->lcs_proc_dir))
lprocfs_remove(&seq->lcs_proc_dir);
seq->lcs_proc_dir = NULL;
}
#endif /* LPROCFS */
}
static int seq_client_proc_init(struct lu_client_seq *seq)
{
#ifdef LPROCFS
int rc;
seq->lcs_proc_dir = lprocfs_register(seq->lcs_name,
seq_type_proc_dir,
NULL, NULL);
if (IS_ERR(seq->lcs_proc_dir)) {
CERROR("%s: LProcFS failed in seq-init\n",
seq->lcs_name);
rc = PTR_ERR(seq->lcs_proc_dir);
return rc;
}
rc = lprocfs_add_vars(seq->lcs_proc_dir,
seq_client_proc_list, seq);
if (rc) {
CERROR("%s: Can't init sequence manager "
"proc, rc %d\n", seq->lcs_name, rc);
GOTO(out_cleanup, rc);
}
return 0;
out_cleanup:
seq_client_proc_fini(seq);
return rc;
#else /* LPROCFS */
return 0;
#endif
}
int seq_client_init(struct lu_client_seq *seq,
struct obd_export *exp,
enum lu_cli_type type,
const char *prefix,
struct lu_server_seq *srv)
{
int rc;
LASSERT(seq != NULL);
LASSERT(prefix != NULL);
seq->lcs_srv = srv;
seq->lcs_type = type;
mutex_init(&seq->lcs_mutex);
if (type == LUSTRE_SEQ_METADATA)
seq->lcs_width = LUSTRE_METADATA_SEQ_MAX_WIDTH;
else
seq->lcs_width = LUSTRE_DATA_SEQ_MAX_WIDTH;
init_waitqueue_head(&seq->lcs_waitq);
/* Make sure that things are clear before work is started. */
seq_client_flush(seq);
if (exp != NULL)
seq->lcs_exp = class_export_get(exp);
else if (type == LUSTRE_SEQ_METADATA)
LASSERT(seq->lcs_srv != NULL);
snprintf(seq->lcs_name, sizeof(seq->lcs_name),
"cli-%s", prefix);
rc = seq_client_proc_init(seq);
if (rc)
seq_client_fini(seq);
return rc;
}
EXPORT_SYMBOL(seq_client_init);
void seq_client_fini(struct lu_client_seq *seq)
{
seq_client_proc_fini(seq);
if (seq->lcs_exp != NULL) {
class_export_put(seq->lcs_exp);
seq->lcs_exp = NULL;
}
seq->lcs_srv = NULL;
}
EXPORT_SYMBOL(seq_client_fini);
int client_fid_init(struct obd_device *obd,
struct obd_export *exp, enum lu_cli_type type)
{
struct client_obd *cli = &obd->u.cli;
char *prefix;
int rc;
OBD_ALLOC_PTR(cli->cl_seq);
if (cli->cl_seq == NULL)
return -ENOMEM;
OBD_ALLOC(prefix, MAX_OBD_NAME + 5);
if (prefix == NULL)
GOTO(out_free_seq, rc = -ENOMEM);
snprintf(prefix, MAX_OBD_NAME + 5, "cli-%s", obd->obd_name);
/* Init client side sequence-manager */
rc = seq_client_init(cli->cl_seq, exp, type, prefix, NULL);
OBD_FREE(prefix, MAX_OBD_NAME + 5);
if (rc)
GOTO(out_free_seq, rc);
return rc;
out_free_seq:
OBD_FREE_PTR(cli->cl_seq);
cli->cl_seq = NULL;
return rc;
}
EXPORT_SYMBOL(client_fid_init);
int client_fid_fini(struct obd_device *obd)
{
struct client_obd *cli = &obd->u.cli;
if (cli->cl_seq != NULL) {
seq_client_fini(cli->cl_seq);
OBD_FREE_PTR(cli->cl_seq);
cli->cl_seq = NULL;
}
return 0;
}
EXPORT_SYMBOL(client_fid_fini);
struct proc_dir_entry *seq_type_proc_dir;
static int __init fid_mod_init(void)
{
seq_type_proc_dir = lprocfs_register(LUSTRE_SEQ_NAME,
proc_lustre_root,
NULL, NULL);
if (IS_ERR(seq_type_proc_dir))
return PTR_ERR(seq_type_proc_dir);
return 0;
}
static void __exit fid_mod_exit(void)
{
if (seq_type_proc_dir != NULL && !IS_ERR(seq_type_proc_dir)) {
lprocfs_remove(&seq_type_proc_dir);
seq_type_proc_dir = NULL;
}
}
MODULE_AUTHOR("Sun Microsystems, Inc. <http://www.lustre.org/>");
MODULE_DESCRIPTION("Lustre FID Module");
MODULE_LICENSE("GPL");
MODULE_VERSION("0.1.0");
module_init(fid_mod_init);
module_exit(fid_mod_exit);
|