includes/libs/rdbms/loadbalancer/ILoadBalancer.php

   1 <?php
   2 /**
   3  * Database load balancing interface
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 2 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License along
  16  * with this program; if not, write to the Free Software Foundation, Inc.,
  17  * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
  18  * http://www.gnu.org/copyleft/gpl.html
  19  *
  20  * @file
  21  * @ingroup Database
  22  * @author Aaron Schulz
  23  */
  24 namespace Wikimedia\Rdbms;
  25
  26 use Exception;
  27 use InvalidArgumentException;
  28
  29 /**
  30  * Database cluster connection, tracking, load balancing, and transaction manager interface
  31  *
  32  * A "cluster" is considered to be one master database and zero or more replica databases.
  33  * Typically, the replica DBs replicate from the master asynchronously. The first node in the
  34  * "servers" configuration array is always considered the "master". However, this class can still
  35  * be used when all or some of the "replica" DBs are multi-master peers of the master or even
  36  * when all the DBs are non-replicating clones of each other holding read-only data. Thus, the
  37  * role of "master" is in some cases merely nominal.
  38  *
  39  * By default, each DB server uses DBO_DEFAULT for its 'flags' setting, unless explicitly set
  40  * otherwise in configuration. DBO_DEFAULT behavior depends on whether 'cliMode' is set:
  41  *   - In CLI mode, the flag has no effect with regards to LoadBalancer.
  42  *   - In non-CLI mode, the flag causes implicit transactions to be used; the first query on
  43  *     a database starts a transaction on that database. The transactions are meant to remain
  44  *     pending until either commitMasterChanges() or rollbackMasterChanges() is called. The
  45  *     application must have some point where it calls commitMasterChanges() near the end of
  46  *     the PHP request.
  47  * Every iteration of beginMasterChanges()/commitMasterChanges() is called a "transaction round".
  48  * Rounds are useful on the master DB connections because they make single-DB (and by and large
  49  * multi-DB) updates in web requests all-or-nothing. Also, transactions on replica DBs are useful
  50  * when REPEATABLE-READ or SERIALIZABLE isolation is used because all foriegn keys and constraints
  51  * hold across separate queries in the DB transaction since the data appears within a consistent
  52  * point-in-time snapshot.
  53  *
  54  * The typical caller will use LoadBalancer::getConnection( DB_* ) to yield a live database
  55  * connection handle. The choice of which DB server to use is based on pre-defined loads for
  56  * weighted random selection, adjustments thereof by LoadMonitor, and the amount of replication
  57  * lag on each DB server. Lag checks might cause problems in certain setups, so they should be
  58  * tuned in the server configuration maps as follows:
  59  *   - Master + N Replica(s): set 'max lag' to an appropriate threshold for avoiding any database
  60  *      lagged by this much or more. If all DBs are this lagged, then the load balancer considers
  61  *      the cluster to be read-only.
  62  *   - Galera Cluster: Seconds_Behind_Master will be 0, so there probably is nothing to tune.
  63  *      Note that lag is still possible depending on how wsrep-sync-wait is set server-side.
  64  *   - Read-only archive clones: set 'is static' in the server configuration maps. This will
  65  *      treat all such DBs as having 0 lag.
  66  *   - SQL load balancing proxy: any proxy should handle lag checks on its own, so the 'max lag'
  67  *      parameter should probably be set to INF in the server configuration maps. This will make
  68  *      the load balancer ignore whatever it detects as the lag of the logical replica is (which
  69  *      would probably just randomly bounce around).
  70  *
  71  * If using a SQL proxy service, it would probably be best to have two proxy hosts for the
  72  * load balancer to talk to. One would be the 'host' of the master server entry and another for
  73  * the (logical) replica server entry. The proxy could map the load balancer's "replica" DB to
  74  * any number of physical replica DBs.
  75  *
  76  * @since 1.28
  77  * @ingroup Database
  78  */
  79 interface ILoadBalancer {
  80         /** @var integer Request a replica DB connection */
  81         const DB_REPLICA = -1;
  82         /** @var integer Request a master DB connection */
  83         const DB_MASTER = -2;
  84
  85         /** @var string Domain specifier when no specific database needs to be selected */
  86         const DOMAIN_ANY = '';
  87
  88         /**
  89          * Construct a manager of IDatabase connection objects
  90          *
  91          * @param array $params Parameter map with keys:
  92          *  - servers : Required. Array of server info structures.
  93          *  - localDomain: A DatabaseDomain or domain ID string.
  94          *  - loadMonitor : Name of a class used to fetch server lag and load.
  95          *  - readOnlyReason : Reason the master DB is read-only if so [optional]
  96          *  - waitTimeout : Maximum time to wait for replicas for consistency [optional]
  97          *  - srvCache : BagOStuff object for server cache [optional]
  98          *  - memCache : BagOStuff object for cluster memory cache [optional]
  99          *  - wanCache : WANObjectCache object [optional]
 100          *  - chronologyProtector: ChronologyProtector object [optional]
 101          *  - hostname : The name of the current server [optional]
 102          *  - cliMode: Whether the execution context is a CLI script. [optional]
 103          *  - profiler : Class name or instance with profileIn()/profileOut() methods. [optional]
 104          *  - trxProfiler: TransactionProfiler instance. [optional]
 105          *  - replLogger: PSR-3 logger instance. [optional]
 106          *  - connLogger: PSR-3 logger instance. [optional]
 107          *  - queryLogger: PSR-3 logger instance. [optional]
 108          *  - perfLogger: PSR-3 logger instance. [optional]
 109          *  - errorLogger : Callback that takes an Exception and logs it. [optional]
 110          * @throws InvalidArgumentException
 111          */
 112         public function __construct( array $params );
 113
 114         /**
 115          * Get the index of the reader connection, which may be a replica DB
 116          *
 117          * This takes into account load ratios and lag times. It should
 118          * always return a consistent index during a given invocation.
 119          *
 120          * Side effect: opens connections to databases
 121          * @param string|bool $group Query group, or false for the generic reader
 122          * @param string|bool $domain Domain ID, or false for the current domain
 123          * @throws DBError
 124          * @return bool|int|string
 125          */
 126         public function getReaderIndex( $group = false, $domain = false );
 127
 128         /**
 129          * Set the master wait position
 130          *
 131          * If a DB_REPLICA connection has been opened already, then wait immediately.
 132          * Otherwise sets a variable telling it to wait if such a connection is opened.
 133          *
 134          * This only applies to connections to the generic replica DB for this request.
 135          * If a timeout happens when waiting, then getLaggedReplicaMode()/laggedReplicaUsed()
 136          * will return true.
 137          *
 138          * @param DBMasterPos|bool $pos Master position or false
 139          */
 140         public function waitFor( $pos );
 141
 142         /**
 143          * Set the master wait position and wait for a "generic" replica DB to catch up to it
 144          *
 145          * This can be used a faster proxy for waitForAll()
 146          *
 147          * @param DBMasterPos|bool $pos Master position or false
 148          * @param int $timeout Max seconds to wait; default is mWaitTimeout
 149          * @return bool Success (able to connect and no timeouts reached)
 150          */
 151         public function waitForOne( $pos, $timeout = null );
 152
 153         /**
 154          * Set the master wait position and wait for ALL replica DBs to catch up to it
 155          *
 156          * @param DBMasterPos|bool $pos Master position or false
 157          * @param int $timeout Max seconds to wait; default is mWaitTimeout
 158          * @return bool Success (able to connect and no timeouts reached)
 159          */
 160         public function waitForAll( $pos, $timeout = null );
 161
 162         /**
 163          * Get any open connection to a given server index, local or foreign
 164          *
 165          * @param int $i Server index or DB_MASTER/DB_REPLICA
 166          * @return Database|bool False if no such connection is open
 167          */
 168         public function getAnyOpenConnection( $i );
 169
 170         /**
 171          * Get a connection by index
 172          *
 173          * @param int $i Server index or DB_MASTER/DB_REPLICA
 174          * @param array|string|bool $groups Query group(s), or false for the generic reader
 175          * @param string|bool $domain Domain ID, or false for the current domain
 176          *
 177          * @throws DBError
 178          * @return Database
 179          */
 180         public function getConnection( $i, $groups = [], $domain = false );
 181
 182         /**
 183          * Mark a foreign connection as being available for reuse under a different DB domain
 184          *
 185          * This mechanism is reference-counted, and must be called the same number of times
 186          * as getConnection() to work.
 187          *
 188          * @param IDatabase $conn
 189          * @throws InvalidArgumentException
 190          */
 191         public function reuseConnection( $conn );
 192
 193         /**
 194          * Get a database connection handle reference
 195          *
 196          * The handle's methods simply wrap those of a Database handle
 197          *
 198          * @see ILoadBalancer::getConnection() for parameter information
 199          *
 200          * @param int $i Server index or DB_MASTER/DB_REPLICA
 201          * @param array|string|bool $groups Query group(s), or false for the generic reader
 202          * @param string|bool $domain Domain ID, or false for the current domain
 203          * @return DBConnRef
 204          */
 205         public function getConnectionRef( $i, $groups = [], $domain = false );
 206
 207         /**
 208          * Get a database connection handle reference without connecting yet
 209          *
 210          * The handle's methods simply wrap those of a Database handle
 211          *
 212          * @see ILoadBalancer::getConnection() for parameter information
 213          *
 214          * @param int $i Server index or DB_MASTER/DB_REPLICA
 215          * @param array|string|bool $groups Query group(s), or false for the generic reader
 216          * @param string|bool $domain Domain ID, or false for the current domain
 217          * @return DBConnRef
 218          */
 219         public function getLazyConnectionRef( $i, $groups = [], $domain = false );
 220
 221         /**
 222          * Get a maintenance database connection handle reference for migrations and schema changes
 223          *
 224          * The handle's methods simply wrap those of a Database handle
 225          *
 226          * @see ILoadBalancer::getConnection() for parameter information
 227          *
 228          * @param int $db Server index or DB_MASTER/DB_REPLICA
 229          * @param array|string|bool $groups Query group(s), or false for the generic reader
 230          * @param string|bool $domain Domain ID, or false for the current domain
 231          * @return MaintainableDBConnRef
 232          */
 233         public function getMaintenanceConnectionRef( $db, $groups = [], $domain = false );
 234
 235         /**
 236          * Open a connection to the server given by the specified index
 237          * Index must be an actual index into the array.
 238          * If the server is already open, returns it.
 239          *
 240          * @note If disable() was called on this LoadBalancer, this method will throw a DBAccessError.
 241          *
 242          * @param int $i Server index or DB_MASTER/DB_REPLICA
 243          * @param string|bool $domain Domain ID, or false for the current domain
 244          * @return Database|bool Returns false on errors
 245          * @throws DBAccessError
 246          */
 247         public function openConnection( $i, $domain = false );
 248
 249         /**
 250          * @return int
 251          */
 252         public function getWriterIndex();
 253
 254         /**
 255          * Returns true if the specified index is a valid server index
 256          *
 257          * @param string $i
 258          * @return bool
 259          */
 260         public function haveIndex( $i );
 261
 262         /**
 263          * Returns true if the specified index is valid and has non-zero load
 264          *
 265          * @param string $i
 266          * @return bool
 267          */
 268         public function isNonZeroLoad( $i );
 269
 270         /**
 271          * Get the number of defined servers (not the number of open connections)
 272          *
 273          * @return int
 274          */
 275         public function getServerCount();
 276
 277         /**
 278          * Get the host name or IP address of the server with the specified index
 279          * Prefer a readable name if available.
 280          * @param string $i
 281          * @return string
 282          */
 283         public function getServerName( $i );
 284
 285         /**
 286          * Return the server info structure for a given index, or false if the index is invalid.
 287          * @param int $i
 288          * @return array|bool
 289          */
 290         public function getServerInfo( $i );
 291
 292         /**
 293          * Sets the server info structure for the given index. Entry at index $i
 294          * is created if it doesn't exist
 295          * @param int $i
 296          * @param array $serverInfo
 297          */
 298         public function setServerInfo( $i, array $serverInfo );
 299
 300         /**
 301          * Get the current master position for chronology control purposes
 302          * @return DBMasterPos|bool Returns false if not applicable
 303          */
 304         public function getMasterPos();
 305
 306         /**
 307          * Disable this load balancer. All connections are closed, and any attempt to
 308          * open a new connection will result in a DBAccessError.
 309          */
 310         public function disable();
 311
 312         /**
 313          * Close all open connections
 314          */
 315         public function closeAll();
 316
 317         /**
 318          * Close a connection
 319          *
 320          * Using this function makes sure the LoadBalancer knows the connection is closed.
 321          * If you use $conn->close() directly, the load balancer won't update its state.
 322          *
 323          * @param IDatabase $conn
 324          */
 325         public function closeConnection( IDatabase $conn );
 326
 327         /**
 328          * Commit transactions on all open connections
 329          * @param string $fname Caller name
 330          * @throws DBExpectedError
 331          */
 332         public function commitAll( $fname = __METHOD__ );
 333
 334         /**
 335          * Perform all pre-commit callbacks that remain part of the atomic transactions
 336          * and disable any post-commit callbacks until runMasterPostTrxCallbacks()
 337          *
 338          * Use this only for mutli-database commits
 339          */
 340         public function finalizeMasterChanges();
 341
 342         /**
 343          * Perform all pre-commit checks for things like replication safety
 344          *
 345          * Use this only for mutli-database commits
 346          *
 347          * @param array $options Includes:
 348          *   - maxWriteDuration : max write query duration time in seconds
 349          * @throws DBTransactionError
 350          */
 351         public function approveMasterChanges( array $options );
 352
 353         /**
 354          * Flush any master transaction snapshots and set DBO_TRX (if DBO_DEFAULT is set)
 355          *
 356          * The DBO_TRX setting will be reverted to the default in each of these methods:
 357          *   - commitMasterChanges()
 358          *   - rollbackMasterChanges()
 359          *   - commitAll()
 360          * This allows for custom transaction rounds from any outer transaction scope.
 361          *
 362          * @param string $fname
 363          * @throws DBExpectedError
 364          */
 365         public function beginMasterChanges( $fname = __METHOD__ );
 366
 367         /**
 368          * Issue COMMIT on all master connections where writes where done
 369          * @param string $fname Caller name
 370          * @throws DBExpectedError
 371          */
 372         public function commitMasterChanges( $fname = __METHOD__ );
 373
 374         /**
 375          * Issue all pending post-COMMIT/ROLLBACK callbacks
 376          *
 377          * Use this only for mutli-database commits
 378          *
 379          * @param int $type IDatabase::TRIGGER_* constant
 380          * @return Exception|null The first exception or null if there were none
 381          */
 382         public function runMasterPostTrxCallbacks( $type );
 383
 384         /**
 385          * Issue ROLLBACK only on master, only if queries were done on connection
 386          * @param string $fname Caller name
 387          * @throws DBExpectedError
 388          */
 389         public function rollbackMasterChanges( $fname = __METHOD__ );
 390
 391         /**
 392          * Suppress all pending post-COMMIT/ROLLBACK callbacks
 393          *
 394          * Use this only for mutli-database commits
 395          *
 396          * @return Exception|null The first exception or null if there were none
 397          */
 398         public function suppressTransactionEndCallbacks();
 399
 400         /**
 401          * Commit all replica DB transactions so as to flush any REPEATABLE-READ or SSI snapshot
 402          *
 403          * @param string $fname Caller name
 404          */
 405         public function flushReplicaSnapshots( $fname = __METHOD__ );
 406
 407         /**
 408          * @return bool Whether a master connection is already open
 409          */
 410         public function hasMasterConnection();
 411
 412         /**
 413          * Determine if there are pending changes in a transaction by this thread
 414          * @return bool
 415          */
 416         public function hasMasterChanges();
 417
 418         /**
 419          * Get the timestamp of the latest write query done by this thread
 420          * @return float|bool UNIX timestamp or false
 421          */
 422         public function lastMasterChangeTimestamp();
 423
 424         /**
 425          * Check if this load balancer object had any recent or still
 426          * pending writes issued against it by this PHP thread
 427          *
 428          * @param float $age How many seconds ago is "recent" [defaults to mWaitTimeout]
 429          * @return bool
 430          */
 431         public function hasOrMadeRecentMasterChanges( $age = null );
 432
 433         /**
 434          * Get the list of callers that have pending master changes
 435          *
 436          * @return string[] List of method names
 437          */
 438         public function pendingMasterChangeCallers();
 439
 440         /**
 441          * @note This method will trigger a DB connection if not yet done
 442          * @param string|bool $domain Domain ID, or false for the current domain
 443          * @return bool Whether the database for generic connections this request is highly "lagged"
 444          */
 445         public function getLaggedReplicaMode( $domain = false );
 446
 447         /**
 448          * Checks whether the database for generic connections this request was both:
 449          *   - a) Already choosen due to a prior connection attempt
 450          *   - b) Considered highly "lagged"
 451          *
 452          * @note This method will never cause a new DB connection
 453          * @return bool
 454          */
 455         public function laggedReplicaUsed();
 456
 457         /**
 458          * @note This method may trigger a DB connection if not yet done
 459          * @param string|bool $domain Domain ID, or false for the current domain
 460          * @param IDatabase|null $conn DB master connection; used to avoid loops [optional]
 461          * @return string|bool Reason the master is read-only or false if it is not
 462          */
 463         public function getReadOnlyReason( $domain = false, IDatabase $conn = null );
 464
 465         /**
 466          * Disables/enables lag checks
 467          * @param null|bool $mode
 468          * @return bool
 469          */
 470         public function allowLagged( $mode = null );
 471
 472         /**
 473          * @return bool
 474          */
 475         public function pingAll();
 476
 477         /**
 478          * Call a function with each open connection object
 479          * @param callable $callback
 480          * @param array $params
 481          */
 482         public function forEachOpenConnection( $callback, array $params = [] );
 483
 484         /**
 485          * Call a function with each open connection object to a master
 486          * @param callable $callback
 487          * @param array $params
 488          */
 489         public function forEachOpenMasterConnection( $callback, array $params = [] );
 490
 491         /**
 492          * Call a function with each open replica DB connection object
 493          * @param callable $callback
 494          * @param array $params
 495          */
 496         public function forEachOpenReplicaConnection( $callback, array $params = [] );
 497
 498         /**
 499          * Get the hostname and lag time of the most-lagged replica DB
 500          *
 501          * This is useful for maintenance scripts that need to throttle their updates.
 502          * May attempt to open connections to replica DBs on the default DB. If there is
 503          * no lag, the maximum lag will be reported as -1.
 504          *
 505          * @param bool|string $domain Domain ID, or false for the default database
 506          * @return array ( host, max lag, index of max lagged host )
 507          */
 508         public function getMaxLag( $domain = false );
 509
 510         /**
 511          * Get an estimate of replication lag (in seconds) for each server
 512          *
 513          * Results are cached for a short time in memcached/process cache
 514          *
 515          * Values may be "false" if replication is too broken to estimate
 516          *
 517          * @param string|bool $domain
 518          * @return int[] Map of (server index => float|int|bool)
 519          */
 520         public function getLagTimes( $domain = false );
 521
 522         /**
 523          * Get the lag in seconds for a given connection, or zero if this load
 524          * balancer does not have replication enabled.
 525          *
 526          * This should be used in preference to Database::getLag() in cases where
 527          * replication may not be in use, since there is no way to determine if
 528          * replication is in use at the connection level without running
 529          * potentially restricted queries such as SHOW SLAVE STATUS. Using this
 530          * function instead of Database::getLag() avoids a fatal error in this
 531          * case on many installations.
 532          *
 533          * @param IDatabase $conn
 534          * @return int|bool Returns false on error
 535          */
 536         public function safeGetLag( IDatabase $conn );
 537
 538         /**
 539          * Wait for a replica DB to reach a specified master position
 540          *
 541          * This will connect to the master to get an accurate position if $pos is not given
 542          *
 543          * @param IDatabase $conn Replica DB
 544          * @param DBMasterPos|bool $pos Master position; default: current position
 545          * @param int $timeout Timeout in seconds [optional]
 546          * @return bool Success
 547          */
 548         public function safeWaitForMasterPos( IDatabase $conn, $pos = false, $timeout = 10 );
 549
 550         /**
 551          * Set a callback via IDatabase::setTransactionListener() on
 552          * all current and future master connections of this load balancer
 553          *
 554          * @param string $name Callback name
 555          * @param callable|null $callback
 556          */
 557         public function setTransactionListener( $name, callable $callback = null );
 558
 559         /**
 560          * Set a new table prefix for the existing local domain ID for testing
 561          *
 562          * @param string $prefix
 563          */
 564         public function setDomainPrefix( $prefix );
 565
 566         /**
 567          * Make certain table names use their own database, schema, and table prefix
 568          * when passed into SQL queries pre-escaped and without a qualified database name
 569          *
 570          * For example, "user" can be converted to "myschema.mydbname.user" for convenience.
 571          * Appearances like `user`, somedb.user, somedb.someschema.user will used literally.
 572          *
 573          * Calling this twice will completely clear any old table aliases. Also, note that
 574          * callers are responsible for making sure the schemas and databases actually exist.
 575          *
 576          * @param array[] $aliases Map of (table => (dbname, schema, prefix) map)
 577          */
 578         public function setTableAliases( array $aliases );
 579 }