rpl_rli.cc 40.8 KB
Newer Older
1 2 3 4
/* Copyright (C) 2000-2003 MySQL AB

   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
5
   the Free Software Foundation; version 2 of the License.
6 7 8 9 10 11 12 13 14 15 16 17

   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 for more details.

   You should have received a copy of the GNU General Public License
   along with this program; if not, write to the Free Software
   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA */

#include "mysql_priv.h"

18
#include "rpl_mi.h"
19 20 21
#include "rpl_rli.h"
#include <my_dir.h>    // For MY_STAT
#include "sql_repl.h"  // For check_binlog_magic
22
#include "rpl_utility.h"
23

24
static int count_relay_log_space(Relay_log_info* rli);
25 26 27 28 29 30 31

// Defined in slave.cc
int init_intvar_from_file(int* var, IO_CACHE* f, int default_val);
int init_strvar_from_file(char *var, int max_size, IO_CACHE *f,
			  const char *default_val);


32
Relay_log_info::Relay_log_info()
33
  :Slave_reporting_capability("SQL"),
34
   no_storage(FALSE), replicate_same_server_id(::replicate_same_server_id),
35
   info_fd(-1), cur_log_fd(-1), save_temporary_tables(0),
36
   group_relay_log_pos(0),
37 38
   cur_log_old_open_count(0), group_master_log_pos(0), log_space_total(0),
   ignore_log_space_limit(0), last_master_timestamp(0), slave_skip_counter(0),
39
   abort_pos_wait(0), slave_run_id(0), sql_thd(0),
40 41 42
   inited(0), abort_slave(0), slave_running(0), until_condition(UNTIL_NONE),
   until_log_pos(0), retried_trans(0),
   tables_to_lock(0), tables_to_lock_count(0),
43
   last_event_start_time(0), m_flags(0)
44
{
45
  DBUG_ENTER("Relay_log_info::Relay_log_info");
46 47 48

  group_relay_log_name[0]= event_relay_log_name[0]=
    group_master_log_name[0]= 0;
49
  until_log_name[0]= ign_master_log_name_end[0]= 0;
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64
  bzero((char*) &info_file, sizeof(info_file));
  bzero((char*) &cache_buf, sizeof(cache_buf));
  cached_charset_invalidate();
  pthread_mutex_init(&run_lock, MY_MUTEX_INIT_FAST);
  pthread_mutex_init(&data_lock, MY_MUTEX_INIT_FAST);
  pthread_mutex_init(&log_space_lock, MY_MUTEX_INIT_FAST);
  pthread_cond_init(&data_cond, NULL);
  pthread_cond_init(&start_cond, NULL);
  pthread_cond_init(&stop_cond, NULL);
  pthread_cond_init(&log_space_cond, NULL);
  relay_log.init_pthread_objects();
  DBUG_VOID_RETURN;
}


65
Relay_log_info::~Relay_log_info()
66
{
67
  DBUG_ENTER("Relay_log_info::~Relay_log_info");
68 69 70 71 72 73 74 75 76 77 78 79 80

  pthread_mutex_destroy(&run_lock);
  pthread_mutex_destroy(&data_lock);
  pthread_mutex_destroy(&log_space_lock);
  pthread_cond_destroy(&data_cond);
  pthread_cond_destroy(&start_cond);
  pthread_cond_destroy(&stop_cond);
  pthread_cond_destroy(&log_space_cond);
  relay_log.cleanup();
  DBUG_VOID_RETURN;
}


81
int init_relay_log_info(Relay_log_info* rli,
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
			const char* info_fname)
{
  char fname[FN_REFLEN+128];
  int info_fd;
  const char* msg = 0;
  int error = 0;
  DBUG_ENTER("init_relay_log_info");
  DBUG_ASSERT(!rli->no_storage);         // Don't init if there is no storage

  if (rli->inited)                       // Set if this function called
    DBUG_RETURN(0);
  fn_format(fname, info_fname, mysql_data_home, "", 4+32);
  pthread_mutex_lock(&rli->data_lock);
  info_fd = rli->info_fd;
  rli->cur_log_fd = -1;
  rli->slave_skip_counter=0;
  rli->abort_pos_wait=0;
  rli->log_space_limit= relay_log_space_limit;
  rli->log_space_total= 0;
  rli->tables_to_lock= 0;
  rli->tables_to_lock_count= 0;

  /*
    The relay log will now be opened, as a SEQ_READ_APPEND IO_CACHE.
    Note that the I/O thread flushes it to disk after writing every
    event, in flush_master_info(mi, 1).
  */

  /*
    For the maximum log size, we choose max_relay_log_size if it is
    non-zero, max_binlog_size otherwise. If later the user does SET
    GLOBAL on one of these variables, fix_max_binlog_size and
    fix_max_relay_log_size will reconsider the choice (for example
    if the user changes max_relay_log_size to zero, we have to
    switch to using max_binlog_size for the relay log) and update
    rli->relay_log.max_size (and mysql_bin_log.max_size).
  */
  {
    char buf[FN_REFLEN];
    const char *ln;
    static bool name_warning_sent= 0;
    ln= rli->relay_log.generate_name(opt_relay_logname, "-relay-bin",
                                     1, buf);
    /* We send the warning only at startup, not after every RESET SLAVE */
    if (!opt_relay_logname && !opt_relaylog_index_name && !name_warning_sent)
    {
      /*
        User didn't give us info to name the relay log index file.
        Picking `hostname`-relay-bin.index like we do, causes replication to
        fail if this slave's hostname is changed later. So, we would like to
        instead require a name. But as we don't want to break many existing
        setups, we only give warning, not error.
      */
      sql_print_warning("Neither --relay-log nor --relay-log-index were used;"
                        " so replication "
                        "may break when this MySQL server acts as a "
                        "slave and has his hostname changed!! Please "
                        "use '--relay-log=%s' to avoid this problem.", ln);
      name_warning_sent= 1;
    }
    /*
      note, that if open() fails, we'll still have index file open
      but a destructor will take care of that
    */
    if (rli->relay_log.open_index_file(opt_relaylog_index_name, ln) ||
        rli->relay_log.open(ln, LOG_BIN, 0, SEQ_READ_APPEND, 0,
                            (max_relay_log_size ? max_relay_log_size :
                            max_binlog_size), 1))
    {
      pthread_mutex_unlock(&rli->data_lock);
      sql_print_error("Failed in open_log() called from init_relay_log_info()");
      DBUG_RETURN(1);
    }
  }

  /* if file does not exist */
  if (access(fname,F_OK))
  {
    /*
      If someone removed the file from underneath our feet, just close
      the old descriptor and re-create the old file
    */
    if (info_fd >= 0)
      my_close(info_fd, MYF(MY_WME));
    if ((info_fd = my_open(fname, O_CREAT|O_RDWR|O_BINARY, MYF(MY_WME))) < 0)
    {
      sql_print_error("Failed to create a new relay log info file (\
file '%s', errno %d)", fname, my_errno);
170
      msg= current_thd->main_da.message();
171 172 173 174 175 176 177
      goto err;
    }
    if (init_io_cache(&rli->info_file, info_fd, IO_SIZE*2, READ_CACHE, 0L,0,
                      MYF(MY_WME)))
    {
      sql_print_error("Failed to create a cache on relay log info file '%s'",
                      fname);
178
      msg= current_thd->main_da.message();
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
      goto err;
    }

    /* Init relay log with first entry in the relay index file */
    if (init_relay_log_pos(rli,NullS,BIN_LOG_HEADER_SIZE,0 /* no data lock */,
                           &msg, 0))
    {
      sql_print_error("Failed to open the relay log 'FIRST' (relay_log_pos 4)");
      goto err;
    }
    rli->group_master_log_name[0]= 0;
    rli->group_master_log_pos= 0;
    rli->info_fd= info_fd;
  }
  else // file exists
  {
    if (info_fd >= 0)
      reinit_io_cache(&rli->info_file, READ_CACHE, 0L,0,0);
    else
    {
      int error=0;
      if ((info_fd = my_open(fname, O_RDWR|O_BINARY, MYF(MY_WME))) < 0)
      {
        sql_print_error("\
Failed to open the existing relay log info file '%s' (errno %d)",
                        fname, my_errno);
        error= 1;
      }
      else if (init_io_cache(&rli->info_file, info_fd,
                             IO_SIZE*2, READ_CACHE, 0L, 0, MYF(MY_WME)))
      {
        sql_print_error("Failed to create a cache on relay log info file '%s'",
                        fname);
        error= 1;
      }
      if (error)
      {
        if (info_fd >= 0)
          my_close(info_fd, MYF(0));
        rli->info_fd= -1;
        rli->relay_log.close(LOG_CLOSE_INDEX | LOG_CLOSE_STOP_EVENT);
        pthread_mutex_unlock(&rli->data_lock);
        DBUG_RETURN(1);
      }
    }

    rli->info_fd = info_fd;
    int relay_log_pos, master_log_pos;
    if (init_strvar_from_file(rli->group_relay_log_name,
                              sizeof(rli->group_relay_log_name),
                              &rli->info_file, "") ||
       init_intvar_from_file(&relay_log_pos,
                             &rli->info_file, BIN_LOG_HEADER_SIZE) ||
       init_strvar_from_file(rli->group_master_log_name,
                             sizeof(rli->group_master_log_name),
                             &rli->info_file, "") ||
       init_intvar_from_file(&master_log_pos, &rli->info_file, 0))
    {
      msg="Error reading slave log configuration";
      goto err;
    }
    strmake(rli->event_relay_log_name,rli->group_relay_log_name,
            sizeof(rli->event_relay_log_name)-1);
    rli->group_relay_log_pos= rli->event_relay_log_pos= relay_log_pos;
    rli->group_master_log_pos= master_log_pos;

    if (init_relay_log_pos(rli,
                           rli->group_relay_log_name,
                           rli->group_relay_log_pos,
                           0 /* no data lock*/,
                           &msg, 0))
    {
      char llbuf[22];
      sql_print_error("Failed to open the relay log '%s' (relay_log_pos %s)",
                      rli->group_relay_log_name,
                      llstr(rli->group_relay_log_pos, llbuf));
      goto err;
    }
  }

#ifndef DBUG_OFF
  {
    char llbuf1[22], llbuf2[22];
    DBUG_PRINT("info", ("my_b_tell(rli->cur_log)=%s rli->event_relay_log_pos=%s",
                        llstr(my_b_tell(rli->cur_log),llbuf1),
                        llstr(rli->event_relay_log_pos,llbuf2)));
    DBUG_ASSERT(rli->event_relay_log_pos >= BIN_LOG_HEADER_SIZE);
    DBUG_ASSERT(my_b_tell(rli->cur_log) == rli->event_relay_log_pos);
  }
#endif

  /*
    Now change the cache from READ to WRITE - must do this
    before flush_relay_log_info
  */
  reinit_io_cache(&rli->info_file, WRITE_CACHE,0L,0,1);
  if ((error= flush_relay_log_info(rli)))
    sql_print_error("Failed to flush relay log info file");
  if (count_relay_log_space(rli))
  {
    msg="Error counting relay log space";
    goto err;
  }
  rli->inited= 1;
  pthread_mutex_unlock(&rli->data_lock);
  DBUG_RETURN(error);

err:
  sql_print_error(msg);
  end_io_cache(&rli->info_file);
  if (info_fd >= 0)
    my_close(info_fd, MYF(0));
  rli->info_fd= -1;
  rli->relay_log.close(LOG_CLOSE_INDEX | LOG_CLOSE_STOP_EVENT);
  pthread_mutex_unlock(&rli->data_lock);
  DBUG_RETURN(1);
}


298
static inline int add_relay_log(Relay_log_info* rli,LOG_INFO* linfo)
299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316
{
  MY_STAT s;
  DBUG_ENTER("add_relay_log");
  if (!my_stat(linfo->log_file_name,&s,MYF(0)))
  {
    sql_print_error("log %s listed in the index, but failed to stat",
                    linfo->log_file_name);
    DBUG_RETURN(1);
  }
  rli->log_space_total += s.st_size;
#ifndef DBUG_OFF
  char buf[22];
  DBUG_PRINT("info",("log_space_total: %s", llstr(rli->log_space_total,buf)));
#endif
  DBUG_RETURN(0);
}


317
static int count_relay_log_space(Relay_log_info* rli)
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
{
  LOG_INFO linfo;
  DBUG_ENTER("count_relay_log_space");
  rli->log_space_total= 0;
  if (rli->relay_log.find_log_pos(&linfo, NullS, 1))
  {
    sql_print_error("Could not find first log while counting relay log space");
    DBUG_RETURN(1);
  }
  do
  {
    if (add_relay_log(rli,&linfo))
      DBUG_RETURN(1);
  } while (!rli->relay_log.find_next_log(&linfo, 1));
  /*
     As we have counted everything, including what may have written in a
     preceding write, we must reset bytes_written, or we may count some space
     twice.
  */
  rli->relay_log.reset_bytes_written();
  DBUG_RETURN(0);
}


/*
343
   Reset UNTIL condition for Relay_log_info
344 345 346

   SYNOPSYS
    clear_until_condition()
347
      rli - Relay_log_info structure where UNTIL condition should be reset
348 349
 */

350
void Relay_log_info::clear_until_condition()
351 352 353
{
  DBUG_ENTER("clear_until_condition");

354
  until_condition= Relay_log_info::UNTIL_NONE;
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
  until_log_name[0]= 0;
  until_log_pos= 0;
  DBUG_VOID_RETURN;
}


/*
  Open the given relay log

  SYNOPSIS
    init_relay_log_pos()
    rli                 Relay information (will be initialized)
    log                 Name of relay log file to read from. NULL = First log
    pos                 Position in relay log file
    need_data_lock      Set to 1 if this functions should do mutex locks
    errmsg              Store pointer to error message here
    look_for_description_event
                        1 if we should look for such an event. We only need
                        this when the SQL thread starts and opens an existing
                        relay log and has to execute it (possibly from an
                        offset >4); then we need to read the first event of
                        the relay log to be able to parse the events we have
                        to execute.

  DESCRIPTION
  - Close old open relay log files.
  - If we are using the same relay log as the running IO-thread, then set
    rli->cur_log to point to the same IO_CACHE entry.
  - If not, open the 'log' binary file.

  TODO
    - check proper initialization of group_master_log_name/group_master_log_pos

  RETURN VALUES
    0   ok
    1   error.  errmsg is set to point to the error message
*/

393
int init_relay_log_pos(Relay_log_info* rli,const char* log,
394 395 396 397 398
                       ulonglong pos, bool need_data_lock,
                       const char** errmsg,
                       bool look_for_description_event)
{
  DBUG_ENTER("init_relay_log_pos");
399
  DBUG_PRINT("info", ("pos: %lu", (ulong) pos));
400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602

  *errmsg=0;
  pthread_mutex_t *log_lock=rli->relay_log.get_log_lock();

  if (need_data_lock)
    pthread_mutex_lock(&rli->data_lock);

  /*
    Slave threads are not the only users of init_relay_log_pos(). CHANGE MASTER
    is, too, and init_slave() too; these 2 functions allocate a description
    event in init_relay_log_pos, which is not freed by the terminating SQL slave
    thread as that thread is not started by these functions. So we have to free
    the description_event here, in case, so that there is no memory leak in
    running, say, CHANGE MASTER.
  */
  delete rli->relay_log.description_event_for_exec;
  /*
    By default the relay log is in binlog format 3 (4.0).
    Even if format is 4, this will work enough to read the first event
    (Format_desc) (remember that format 4 is just lenghtened compared to format
    3; format 3 is a prefix of format 4).
  */
  rli->relay_log.description_event_for_exec= new
    Format_description_log_event(3);

  pthread_mutex_lock(log_lock);

  /* Close log file and free buffers if it's already open */
  if (rli->cur_log_fd >= 0)
  {
    end_io_cache(&rli->cache_buf);
    my_close(rli->cur_log_fd, MYF(MY_WME));
    rli->cur_log_fd = -1;
  }

  rli->group_relay_log_pos = rli->event_relay_log_pos = pos;

  /*
    Test to see if the previous run was with the skip of purging
    If yes, we do not purge when we restart
  */
  if (rli->relay_log.find_log_pos(&rli->linfo, NullS, 1))
  {
    *errmsg="Could not find first log during relay log initialization";
    goto err;
  }

  if (log && rli->relay_log.find_log_pos(&rli->linfo, log, 1))
  {
    *errmsg="Could not find target log during relay log initialization";
    goto err;
  }
  strmake(rli->group_relay_log_name,rli->linfo.log_file_name,
          sizeof(rli->group_relay_log_name)-1);
  strmake(rli->event_relay_log_name,rli->linfo.log_file_name,
          sizeof(rli->event_relay_log_name)-1);
  if (rli->relay_log.is_active(rli->linfo.log_file_name))
  {
    /*
      The IO thread is using this log file.
      In this case, we will use the same IO_CACHE pointer to
      read data as the IO thread is using to write data.
    */
    my_b_seek((rli->cur_log=rli->relay_log.get_log_file()), (off_t)0);
    if (check_binlog_magic(rli->cur_log,errmsg))
      goto err;
    rli->cur_log_old_open_count=rli->relay_log.get_open_count();
  }
  else
  {
    /*
      Open the relay log and set rli->cur_log to point at this one
    */
    if ((rli->cur_log_fd=open_binlog(&rli->cache_buf,
                                     rli->linfo.log_file_name,errmsg)) < 0)
      goto err;
    rli->cur_log = &rli->cache_buf;
  }
  /*
    In all cases, check_binlog_magic() has been called so we're at offset 4 for
    sure.
  */
  if (pos > BIN_LOG_HEADER_SIZE) /* If pos<=4, we stay at 4 */
  {
    Log_event* ev;
    while (look_for_description_event)
    {
      /*
        Read the possible Format_description_log_event; if position
        was 4, no need, it will be read naturally.
      */
      DBUG_PRINT("info",("looking for a Format_description_log_event"));

      if (my_b_tell(rli->cur_log) >= pos)
        break;

      /*
        Because of we have rli->data_lock and log_lock, we can safely read an
        event
      */
      if (!(ev=Log_event::read_log_event(rli->cur_log,0,
                                         rli->relay_log.description_event_for_exec)))
      {
        DBUG_PRINT("info",("could not read event, rli->cur_log->error=%d",
                           rli->cur_log->error));
        if (rli->cur_log->error) /* not EOF */
        {
          *errmsg= "I/O error reading event at position 4";
          goto err;
        }
        break;
      }
      else if (ev->get_type_code() == FORMAT_DESCRIPTION_EVENT)
      {
        DBUG_PRINT("info",("found Format_description_log_event"));
        delete rli->relay_log.description_event_for_exec;
        rli->relay_log.description_event_for_exec= (Format_description_log_event*) ev;
        /*
          As ev was returned by read_log_event, it has passed is_valid(), so
          my_malloc() in ctor worked, no need to check again.
        */
        /*
          Ok, we found a Format_description event. But it is not sure that this
          describes the whole relay log; indeed, one can have this sequence
          (starting from position 4):
          Format_desc (of slave)
          Rotate (of master)
          Format_desc (of master)
          So the Format_desc which really describes the rest of the relay log
          is the 3rd event (it can't be further than that, because we rotate
          the relay log when we queue a Rotate event from the master).
          But what describes the Rotate is the first Format_desc.
          So what we do is:
          go on searching for Format_description events, until you exceed the
          position (argument 'pos') or until you find another event than Rotate
          or Format_desc.
        */
      }
      else
      {
        DBUG_PRINT("info",("found event of another type=%d",
                           ev->get_type_code()));
        look_for_description_event= (ev->get_type_code() == ROTATE_EVENT);
        delete ev;
      }
    }
    my_b_seek(rli->cur_log,(off_t)pos);
#ifndef DBUG_OFF
  {
    char llbuf1[22], llbuf2[22];
    DBUG_PRINT("info", ("my_b_tell(rli->cur_log)=%s rli->event_relay_log_pos=%s",
                        llstr(my_b_tell(rli->cur_log),llbuf1),
                        llstr(rli->event_relay_log_pos,llbuf2)));
  }
#endif

  }

err:
  /*
    If we don't purge, we can't honour relay_log_space_limit ;
    silently discard it
  */
  if (!relay_log_purge)
    rli->log_space_limit= 0;
  pthread_cond_broadcast(&rli->data_cond);

  pthread_mutex_unlock(log_lock);

  if (need_data_lock)
    pthread_mutex_unlock(&rli->data_lock);
  if (!rli->relay_log.description_event_for_exec->is_valid() && !*errmsg)
    *errmsg= "Invalid Format_description log event; could be out of memory";

  DBUG_RETURN ((*errmsg) ? 1 : 0);
}


/*
  Waits until the SQL thread reaches (has executed up to) the
  log/position or timed out.

  SYNOPSIS
    wait_for_pos()
    thd             client thread that sent SELECT MASTER_POS_WAIT
    log_name        log name to wait for
    log_pos         position to wait for
    timeout         timeout in seconds before giving up waiting

  NOTES
    timeout is longlong whereas it should be ulong ; but this is
    to catch if the user submitted a negative timeout.

  RETURN VALUES
    -2          improper arguments (log_pos<0)
                or slave not running, or master info changed
                during the function's execution,
                or client thread killed. -2 is translated to NULL by caller
    -1          timed out
    >=0         number of log events the function had to wait
                before reaching the desired log/position
 */

603
int Relay_log_info::wait_for_pos(THD* thd, String* log_name,
604 605 606 607 608 609 610 611
                                    longlong log_pos,
                                    longlong timeout)
{
  int event_count = 0;
  ulong init_abort_pos_wait;
  int error=0;
  struct timespec abstime; // for timeout checking
  const char *msg;
612
  DBUG_ENTER("Relay_log_info::wait_for_pos");
613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782

  if (!inited)
    DBUG_RETURN(-1);

  DBUG_PRINT("enter",("log_name: '%s'  log_pos: %lu  timeout: %lu",
                      log_name->c_ptr(), (ulong) log_pos, (ulong) timeout));

  set_timespec(abstime,timeout);
  pthread_mutex_lock(&data_lock);
  msg= thd->enter_cond(&data_cond, &data_lock,
                       "Waiting for the slave SQL thread to "
                       "advance position");
  /*
     This function will abort when it notices that some CHANGE MASTER or
     RESET MASTER has changed the master info.
     To catch this, these commands modify abort_pos_wait ; We just monitor
     abort_pos_wait and see if it has changed.
     Why do we have this mechanism instead of simply monitoring slave_running
     in the loop (we do this too), as CHANGE MASTER/RESET SLAVE require that
     the SQL thread be stopped?
     This is becasue if someones does:
     STOP SLAVE;CHANGE MASTER/RESET SLAVE; START SLAVE;
     the change may happen very quickly and we may not notice that
     slave_running briefly switches between 1/0/1.
  */
  init_abort_pos_wait= abort_pos_wait;

  /*
    We'll need to
    handle all possible log names comparisons (e.g. 999 vs 1000).
    We use ulong for string->number conversion ; this is no
    stronger limitation than in find_uniq_filename in sql/log.cc
  */
  ulong log_name_extension;
  char log_name_tmp[FN_REFLEN]; //make a char[] from String

  strmake(log_name_tmp, log_name->ptr(), min(log_name->length(), FN_REFLEN-1));

  char *p= fn_ext(log_name_tmp);
  char *p_end;
  if (!*p || log_pos<0)
  {
    error= -2; //means improper arguments
    goto err;
  }
  // Convert 0-3 to 4
  log_pos= max(log_pos, BIN_LOG_HEADER_SIZE);
  /* p points to '.' */
  log_name_extension= strtoul(++p, &p_end, 10);
  /*
    p_end points to the first invalid character.
    If it equals to p, no digits were found, error.
    If it contains '\0' it means conversion went ok.
  */
  if (p_end==p || *p_end)
  {
    error= -2;
    goto err;
  }

  /* The "compare and wait" main loop */
  while (!thd->killed &&
         init_abort_pos_wait == abort_pos_wait &&
         slave_running)
  {
    bool pos_reached;
    int cmp_result= 0;

    DBUG_PRINT("info",
               ("init_abort_pos_wait: %ld  abort_pos_wait: %ld",
                init_abort_pos_wait, abort_pos_wait));
    DBUG_PRINT("info",("group_master_log_name: '%s'  pos: %lu",
                       group_master_log_name, (ulong) group_master_log_pos));

    /*
      group_master_log_name can be "", if we are just after a fresh
      replication start or after a CHANGE MASTER TO MASTER_HOST/PORT
      (before we have executed one Rotate event from the master) or
      (rare) if the user is doing a weird slave setup (see next
      paragraph).  If group_master_log_name is "", we assume we don't
      have enough info to do the comparison yet, so we just wait until
      more data. In this case master_log_pos is always 0 except if
      somebody (wrongly) sets this slave to be a slave of itself
      without using --replicate-same-server-id (an unsupported
      configuration which does nothing), then group_master_log_pos
      will grow and group_master_log_name will stay "".
    */
    if (*group_master_log_name)
    {
      char *basename= (group_master_log_name +
                       dirname_length(group_master_log_name));
      /*
        First compare the parts before the extension.
        Find the dot in the master's log basename,
        and protect against user's input error :
        if the names do not match up to '.' included, return error
      */
      char *q= (char*)(fn_ext(basename)+1);
      if (strncmp(basename, log_name_tmp, (int)(q-basename)))
      {
        error= -2;
        break;
      }
      // Now compare extensions.
      char *q_end;
      ulong group_master_log_name_extension= strtoul(q, &q_end, 10);
      if (group_master_log_name_extension < log_name_extension)
        cmp_result= -1 ;
      else
        cmp_result= (group_master_log_name_extension > log_name_extension) ? 1 : 0 ;

      pos_reached= ((!cmp_result && group_master_log_pos >= (ulonglong)log_pos) ||
                    cmp_result > 0);
      if (pos_reached || thd->killed)
        break;
    }

    //wait for master update, with optional timeout.

    DBUG_PRINT("info",("Waiting for master update"));
    /*
      We are going to pthread_cond_(timed)wait(); if the SQL thread stops it
      will wake us up.
    */
    if (timeout > 0)
    {
      /*
        Note that pthread_cond_timedwait checks for the timeout
        before for the condition ; i.e. it returns ETIMEDOUT
        if the system time equals or exceeds the time specified by abstime
        before the condition variable is signaled or broadcast, _or_ if
        the absolute time specified by abstime has already passed at the time
        of the call.
        For that reason, pthread_cond_timedwait will do the "timeoutting" job
        even if its condition is always immediately signaled (case of a loaded
        master).
      */
      error=pthread_cond_timedwait(&data_cond, &data_lock, &abstime);
    }
    else
      pthread_cond_wait(&data_cond, &data_lock);
    DBUG_PRINT("info",("Got signal of master update or timed out"));
    if (error == ETIMEDOUT || error == ETIME)
    {
      error= -1;
      break;
    }
    error=0;
    event_count++;
    DBUG_PRINT("info",("Testing if killed or SQL thread not running"));
  }

err:
  thd->exit_cond(msg);
  DBUG_PRINT("exit",("killed: %d  abort: %d  slave_running: %d \
improper_arguments: %d  timed_out: %d",
                     thd->killed_errno(),
                     (int) (init_abort_pos_wait != abort_pos_wait),
                     (int) slave_running,
                     (int) (error == -2),
                     (int) (error == -1)));
  if (thd->killed || init_abort_pos_wait != abort_pos_wait ||
      !slave_running)
  {
    error= -2;
  }
  DBUG_RETURN( error ? error : event_count );
}


783
void Relay_log_info::inc_group_relay_log_pos(ulonglong log_pos,
784 785
                                                bool skip_lock)
{
786
  DBUG_ENTER("Relay_log_info::inc_group_relay_log_pos");
787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839

  if (!skip_lock)
    pthread_mutex_lock(&data_lock);
  inc_event_relay_log_pos();
  group_relay_log_pos= event_relay_log_pos;
  strmake(group_relay_log_name,event_relay_log_name,
          sizeof(group_relay_log_name)-1);

  notify_group_relay_log_name_update();

  /*
    If the slave does not support transactions and replicates a transaction,
    users should not trust group_master_log_pos (which they can display with
    SHOW SLAVE STATUS or read from relay-log.info), because to compute
    group_master_log_pos the slave relies on log_pos stored in the master's
    binlog, but if we are in a master's transaction these positions are always
    the BEGIN's one (excepted for the COMMIT), so group_master_log_pos does
    not advance as it should on the non-transactional slave (it advances by
    big leaps, whereas it should advance by small leaps).
  */
  /*
    In 4.x we used the event's len to compute the positions here. This is
    wrong if the event was 3.23/4.0 and has been converted to 5.0, because
    then the event's len is not what is was in the master's binlog, so this
    will make a wrong group_master_log_pos (yes it's a bug in 3.23->4.0
    replication: Exec_master_log_pos is wrong). Only way to solve this is to
    have the original offset of the end of the event the relay log. This is
    what we do in 5.0: log_pos has become "end_log_pos" (because the real use
    of log_pos in 4.0 was to compute the end_log_pos; so better to store
    end_log_pos instead of begin_log_pos.
    If we had not done this fix here, the problem would also have appeared
    when the slave and master are 5.0 but with different event length (for
    example the slave is more recent than the master and features the event
    UID). It would give false MASTER_POS_WAIT, false Exec_master_log_pos in
    SHOW SLAVE STATUS, and so the user would do some CHANGE MASTER using this
    value which would lead to badly broken replication.
    Even the relay_log_pos will be corrupted in this case, because the len is
    the relay log is not "val".
    With the end_log_pos solution, we avoid computations involving lengthes.
  */
  DBUG_PRINT("info", ("log_pos: %lu  group_master_log_pos: %lu",
                      (long) log_pos, (long) group_master_log_pos));
  if (log_pos) // 3.23 binlogs don't have log_posx
  {
    group_master_log_pos= log_pos;
  }
  pthread_cond_broadcast(&data_cond);
  if (!skip_lock)
    pthread_mutex_unlock(&data_lock);
  DBUG_VOID_RETURN;
}


840
void Relay_log_info::close_temporary_tables()
841 842
{
  TABLE *table,*next;
843
  DBUG_ENTER("Relay_log_info::close_temporary_tables");
844 845 846 847 848 849 850 851

  for (table=save_temporary_tables ; table ; table=next)
  {
    next=table->next;
    /*
      Don't ask for disk deletion. For now, anyway they will be deleted when
      slave restarts, but it is a better intention to not delete them.
    */
852
    DBUG_PRINT("info", ("table: 0x%lx", (long) table));
853 854 855 856 857 858 859 860 861 862 863 864 865 866
    close_temporary(table, 1, 0);
  }
  save_temporary_tables= 0;
  slave_open_temp_tables= 0;
  DBUG_VOID_RETURN;
}

/*
  purge_relay_logs()

  NOTES
    Assumes to have a run lock on rli and that no slave thread are running.
*/

867
int purge_relay_logs(Relay_log_info* rli, THD *thd, bool just_reset,
868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953
                     const char** errmsg)
{
  int error=0;
  DBUG_ENTER("purge_relay_logs");

  /*
    Even if rli->inited==0, we still try to empty rli->master_log_* variables.
    Indeed, rli->inited==0 does not imply that they already are empty.
    It could be that slave's info initialization partly succeeded :
    for example if relay-log.info existed but *relay-bin*.*
    have been manually removed, init_relay_log_info reads the old
    relay-log.info and fills rli->master_log_*, then init_relay_log_info
    checks for the existence of the relay log, this fails and
    init_relay_log_info leaves rli->inited to 0.
    In that pathological case, rli->master_log_pos* will be properly reinited
    at the next START SLAVE (as RESET SLAVE or CHANGE
    MASTER, the callers of purge_relay_logs, will delete bogus *.info files
    or replace them with correct files), however if the user does SHOW SLAVE
    STATUS before START SLAVE, he will see old, confusing rli->master_log_*.
    In other words, we reinit rli->master_log_* for SHOW SLAVE STATUS
    to display fine in any case.
  */

  rli->group_master_log_name[0]= 0;
  rli->group_master_log_pos= 0;

  if (!rli->inited)
  {
    DBUG_PRINT("info", ("rli->inited == 0"));
    DBUG_RETURN(0);
  }

  DBUG_ASSERT(rli->slave_running == 0);
  DBUG_ASSERT(rli->mi->slave_running == 0);

  rli->slave_skip_counter=0;
  pthread_mutex_lock(&rli->data_lock);

  /*
    we close the relay log fd possibly left open by the slave SQL thread,
    to be able to delete it; the relay log fd possibly left open by the slave
    I/O thread will be closed naturally in reset_logs() by the
    close(LOG_CLOSE_TO_BE_OPENED) call
  */
  if (rli->cur_log_fd >= 0)
  {
    end_io_cache(&rli->cache_buf);
    my_close(rli->cur_log_fd, MYF(MY_WME));
    rli->cur_log_fd= -1;
  }

  if (rli->relay_log.reset_logs(thd))
  {
    *errmsg = "Failed during log reset";
    error=1;
    goto err;
  }
  /* Save name of used relay log file */
  strmake(rli->group_relay_log_name, rli->relay_log.get_log_fname(),
          sizeof(rli->group_relay_log_name)-1);
  strmake(rli->event_relay_log_name, rli->relay_log.get_log_fname(),
          sizeof(rli->event_relay_log_name)-1);
  rli->group_relay_log_pos= rli->event_relay_log_pos= BIN_LOG_HEADER_SIZE;
  if (count_relay_log_space(rli))
  {
    *errmsg= "Error counting relay log space";
    goto err;
  }
  if (!just_reset)
    error= init_relay_log_pos(rli, rli->group_relay_log_name,
                              rli->group_relay_log_pos,
                              0 /* do not need data lock */, errmsg, 0);

err:
#ifndef DBUG_OFF
  char buf[22];
#endif
  DBUG_PRINT("info",("log_space_total: %s",llstr(rli->log_space_total,buf)));
  pthread_mutex_unlock(&rli->data_lock);
  DBUG_RETURN(error);
}


/*
     Check if condition stated in UNTIL clause of START SLAVE is reached.
   SYNOPSYS
954
     Relay_log_info::is_until_satisfied()
955 956 957 958
   DESCRIPTION
     Checks if UNTIL condition is reached. Uses caching result of last
     comparison of current log file name and target log file name. So cached
     value should be invalidated if current log file name changes
959
     (see Relay_log_info::notify_... functions).
960 961 962 963 964

     This caching is needed to avoid of expensive string comparisons and
     strtol() conversions needed for log names comparison. We don't need to
     compare them each time this function is called, we only need to do this
     when current log name changes. If we have UNTIL_MASTER_POS condition we
965
     need to do this only after Rotate_log_event::do_apply_event() (which is
966 967 968 969 970 971 972 973 974 975 976 977 978
     rare, so caching gives real benifit), and if we have UNTIL_RELAY_POS
     condition then we should invalidate cached comarison value after
     inc_group_relay_log_pos() which called for each group of events (so we
     have some benefit if we have something like queries that use
     autoincrement or if we have transactions).

     Should be called ONLY if until_condition != UNTIL_NONE !
   RETURN VALUE
     true - condition met or error happened (condition seems to have
            bad log file name)
     false - condition not met
*/

979
bool Relay_log_info::is_until_satisfied()
980 981 982
{
  const char *log_name;
  ulonglong log_pos;
983
  DBUG_ENTER("Relay_log_info::is_until_satisfied");
984 985 986 987 988 989 990 991 992 993 994 995 996 997

  DBUG_ASSERT(until_condition != UNTIL_NONE);

  if (until_condition == UNTIL_MASTER_POS)
  {
    log_name= group_master_log_name;
    log_pos= group_master_log_pos;
  }
  else
  { /* until_condition == UNTIL_RELAY_POS */
    log_name= group_relay_log_name;
    log_pos= group_relay_log_pos;
  }

998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
#ifndef DBUG_OFF
  {
    char buf[32];
    DBUG_PRINT("info", ("group_master_log_name='%s', group_master_log_pos=%s",
                        group_master_log_name, llstr(group_master_log_pos, buf)));
    DBUG_PRINT("info", ("group_relay_log_name='%s', group_relay_log_pos=%s",
                        group_relay_log_name, llstr(group_relay_log_pos, buf)));
    DBUG_PRINT("info", ("(%s) log_name='%s', log_pos=%s",
                        until_condition == UNTIL_MASTER_POS ? "master" : "relay",
                        log_name, llstr(log_pos, buf)));
    DBUG_PRINT("info", ("(%s) until_log_name='%s', until_log_pos=%s",
                        until_condition == UNTIL_MASTER_POS ? "master" : "relay",
                        until_log_name, llstr(until_log_pos, buf)));
  }
#endif

1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058
  if (until_log_names_cmp_result == UNTIL_LOG_NAMES_CMP_UNKNOWN)
  {
    /*
      We have no cached comparison results so we should compare log names
      and cache result.
      If we are after RESET SLAVE, and the SQL slave thread has not processed
      any event yet, it could be that group_master_log_name is "". In that case,
      just wait for more events (as there is no sensible comparison to do).
    */

    if (*log_name)
    {
      const char *basename= log_name + dirname_length(log_name);

      const char *q= (const char*)(fn_ext(basename)+1);
      if (strncmp(basename, until_log_name, (int)(q-basename)) == 0)
      {
        /* Now compare extensions. */
        char *q_end;
        ulong log_name_extension= strtoul(q, &q_end, 10);
        if (log_name_extension < until_log_name_extension)
          until_log_names_cmp_result= UNTIL_LOG_NAMES_CMP_LESS;
        else
          until_log_names_cmp_result=
            (log_name_extension > until_log_name_extension) ?
            UNTIL_LOG_NAMES_CMP_GREATER : UNTIL_LOG_NAMES_CMP_EQUAL ;
      }
      else
      {
        /* Probably error so we aborting */
        sql_print_error("Slave SQL thread is stopped because UNTIL "
                        "condition is bad.");
        DBUG_RETURN(TRUE);
      }
    }
    else
      DBUG_RETURN(until_log_pos == 0);
  }

  DBUG_RETURN(((until_log_names_cmp_result == UNTIL_LOG_NAMES_CMP_EQUAL &&
           log_pos >= until_log_pos) ||
          until_log_names_cmp_result == UNTIL_LOG_NAMES_CMP_GREATER));
}


1059
void Relay_log_info::cached_charset_invalidate()
1060
{
1061
  DBUG_ENTER("Relay_log_info::cached_charset_invalidate");
1062 1063 1064 1065 1066 1067 1068

  /* Full of zeroes means uninitialized. */
  bzero(cached_charset, sizeof(cached_charset));
  DBUG_VOID_RETURN;
}


1069
bool Relay_log_info::cached_charset_compare(char *charset) const
1070
{
1071
  DBUG_ENTER("Relay_log_info::cached_charset_compare");
1072

1073 1074
  if (bcmp((uchar*) cached_charset, (uchar*) charset,
           sizeof(cached_charset)))
1075
  {
1076
    memcpy(const_cast<char*>(cached_charset), charset, sizeof(cached_charset));
1077 1078 1079 1080 1081 1082
    DBUG_RETURN(1);
  }
  DBUG_RETURN(0);
}


1083
void Relay_log_info::stmt_done(my_off_t event_master_log_pos,
1084
                                  time_t event_creation_time)
1085
{
1086 1087 1088
#ifndef DBUG_OFF
  extern uint debug_not_change_ts_if_art_event;
#endif
1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127
  clear_flag(IN_STMT);

  /*
    If in a transaction, and if the slave supports transactions, just
    inc_event_relay_log_pos(). We only have to check for OPTION_BEGIN
    (not OPTION_NOT_AUTOCOMMIT) as transactions are logged with
    BEGIN/COMMIT, not with SET AUTOCOMMIT= .

    CAUTION: opt_using_transactions means innodb || bdb ; suppose the
    master supports InnoDB and BDB, but the slave supports only BDB,
    problems will arise: - suppose an InnoDB table is created on the
    master, - then it will be MyISAM on the slave - but as
    opt_using_transactions is true, the slave will believe he is
    transactional with the MyISAM table. And problems will come when
    one does START SLAVE; STOP SLAVE; START SLAVE; (the slave will
    resume at BEGIN whereas there has not been any rollback).  This is
    the problem of using opt_using_transactions instead of a finer
    "does the slave support _transactional handler used on the
    master_".

    More generally, we'll have problems when a query mixes a
    transactional handler and MyISAM and STOP SLAVE is issued in the
    middle of the "transaction". START SLAVE will resume at BEGIN
    while the MyISAM table has already been updated.
  */
  if ((sql_thd->options & OPTION_BEGIN) && opt_using_transactions)
    inc_event_relay_log_pos();
  else
  {
    inc_group_relay_log_pos(event_master_log_pos);
    flush_relay_log_info(this);
    /*
      Note that Rotate_log_event::do_apply_event() does not call this
      function, so there is no chance that a fake rotate event resets
      last_master_timestamp.  Note that we update without mutex
      (probably ok - except in some very rare cases, only consequence
      is that value may take some time to display in
      Seconds_Behind_Master - not critical).
    */
1128 1129 1130 1131 1132 1133
#ifndef DBUG_OFF
    if (!(event_creation_time == 0 && debug_not_change_ts_if_art_event > 0))
#else
      if (event_creation_time != 0)
#endif
        last_master_timestamp= event_creation_time;
1134 1135 1136
  }
}

1137
#if !defined(MYSQL_CLIENT) && defined(HAVE_REPLICATION)
1138
void Relay_log_info::cleanup_context(THD *thd, bool error)
1139
{
1140
  DBUG_ENTER("Relay_log_info::cleanup_context");
1141 1142 1143

  DBUG_ASSERT(sql_thd == thd);
  /*
1144
    1) Instances of Table_map_log_event, if ::do_apply_event() was called on them,
1145 1146 1147 1148
    may have opened tables, which we cannot be sure have been closed (because
    maybe the Rows_log_event have not been found or will not be, because slave
    SQL thread is stopping, or relay log has a missing tail etc). So we close
    all thread's tables. And so the table mappings have to be cancelled.
1149
    2) Rows_log_event::do_apply_event() may even have started statements or
1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162
    transactions on them, which we need to rollback in case of error.
    3) If finding a Format_description_log_event after a BEGIN, we also need
    to rollback before continuing with the next events.
    4) so we need this "context cleanup" function.
  */
  if (error)
  {
    ha_autocommit_or_rollback(thd, 1); // if a "statement transaction"
    end_trans(thd, ROLLBACK); // if a "real transaction"
  }
  m_table_map.clear_tables();
  close_thread_tables(thd);
  clear_tables_to_lock();
1163
  clear_flag(IN_STMT);
1164 1165 1166 1167 1168
  /*
    Cleanup for the flags that have been set at do_apply_event.
  */
  thd->options&= ~OPTION_NO_FOREIGN_KEY_CHECKS;
  thd->options&= ~OPTION_RELAXED_UNIQUE_CHECKS;
1169
  last_event_start_time= 0;
1170 1171
  DBUG_VOID_RETURN;
}
1172

1173
void Relay_log_info::clear_tables_to_lock()
1174 1175 1176
{
  while (tables_to_lock)
  {
1177
    uchar* to_free= reinterpret_cast<uchar*>(tables_to_lock);
1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190
    if (tables_to_lock->m_tabledef_valid)
    {
      tables_to_lock->m_tabledef.table_def::~table_def();
      tables_to_lock->m_tabledef_valid= FALSE;
    }
    tables_to_lock=
      static_cast<RPL_TABLE_LIST*>(tables_to_lock->next_global);
    tables_to_lock_count--;
    my_free(to_free, MYF(MY_WME));
  }
  DBUG_ASSERT(tables_to_lock == NULL && tables_to_lock_count == 0);
}

1191
#endif