标签：
1 <?xml version="1.0"?> 2 <?xml-stylesheet type="text/xsl" href="configuration.xsl"?> 3 <!-- 4 Licensed to the Apache Software Foundation (ASF) under one or more 5 contributor license agreements. See the NOTICE file distributed with 6 this work for additional information regarding copyright ownership. 7 The ASF licenses this file to You under the Apache License, Version 2.0 8 (the "License"); you may not use this file except in compliance with 9 the License. You may obtain a copy of the License at 10 11 http://www.apache.org/licenses/LICENSE-2.0 12 13 Unless required by applicable law or agreed to in writing, software 14 distributed under the License is distributed on an "AS IS" BASIS, 15 WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 16 See the License for the specific language governing permissions and 17 limitations under the License. 18 --> 19 20 <configuration> 21 22 <!-- WARNING!!! This file is provided for documentation purposes ONLY! --> 23 <!-- WARNING!!! Any changes you make to this file will be ignored by Hive. --> 24 <!-- WARNING!!! You must make your changes in hive-site.xml instead. --> 25 26 27 <!-- Hive Execution Parameters --> 28 <property> 29 <name>mapred.reduce.tasks</name> 30 <value>-1</value> 31 <description>The default number of reduce tasks per job. Typically set 32 to a prime close to the number of available hosts. Ignored when 33 mapred.job.tracker is "local". Hadoop set this to 1 by default, whereas Hive uses -1 as its default value. 34 By setting this property to -1, Hive will automatically figure out what should be the number of reducers. 35 </description> 36 </property> 37 38 <property> 39 <name>hive.exec.reducers.bytes.per.reducer</name> 40 <value>1000000000</value> 41 <description>size per reducer.The default is 1G, i.e if the input size is 10G, it will use 10 reducers.</description> 42 </property> 43 44 <property> 45 <name>hive.exec.reducers.max</name> 46 <value>999</value> 47 <description>max number of reducers will be used. If the one 48 specified in the configuration parameter mapred.reduce.tasks is 49 negative, Hive will use this one as the max number of reducers when 50 automatically determine number of reducers.</description> 51 </property> 52 53 <property> 54 <name>hive.cli.print.header</name> 55 <value>false</value> 56 <description>Whether to print the names of the columns in query output.</description> 57 </property> 58 59 <property> 60 <name>hive.cli.print.current.db</name> 61 <value>false</value> 62 <description>Whether to include the current database in the Hive prompt.</description> 63 </property> 64 65 <property> 66 <name>hive.cli.prompt</name> 67 <value>hive</value> 68 <description>Command line prompt configuration value. Other hiveconf can be used in 69 this configuration value. Variable substitution will only be invoked at the Hive 70 CLI startup.</description> 71 </property> 72 73 <property> 74 <name>hive.cli.pretty.output.num.cols</name> 75 <value>-1</value> 76 <description>The number of columns to use when formatting output generated 77 by the DESCRIBE PRETTY table_name command. If the value of this property 78 is -1, then Hive will use the auto-detected terminal width.</description> 79 </property> 80 81 <property> 82 <name>hive.exec.scratchdir</name> 83 <value>/tmp/hive-${user.name}</value> 84 <description>Scratch space for Hive jobs</description> 85 </property> 86 87 <property> 88 <name>hive.exec.local.scratchdir</name> 89 <value>/tmp/${user.name}</value> 90 <description>Local scratch space for Hive jobs</description> 91 </property> 92 93 <property> 94 <name>hive.test.mode</name> 95 <value>false</value> 96 <description>Whether Hive is running in test mode. If yes, it turns on sampling and prefixes the output tablename.</description> 97 </property> 98 99 <property> 100 <name>hive.test.mode.prefix</name> 101 <value>test_</value> 102 <description>if Hive is running in test mode, prefixes the output table by this string</description> 103 </property> 104 105 <!-- If the input table is not bucketed, the denominator of the tablesample is determined by the parameter below --> 106 <!-- For example, the following query: --> 107 <!-- INSERT OVERWRITE TABLE dest --> 108 <!-- SELECT col1 from src --> 109 <!-- would be converted to --> 110 <!-- INSERT OVERWRITE TABLE test_dest --> 111 <!-- SELECT col1 from src TABLESAMPLE (BUCKET 1 out of 32 on rand(1)) --> 112 <property> 113 <name>hive.test.mode.samplefreq</name> 114 <value>32</value> 115 <description>if Hive is running in test mode and table is not bucketed, sampling frequency</description> 116 </property> 117 118 <property> 119 <name>hive.test.mode.nosamplelist</name> 120 <value></value> 121 <description>if Hive is running in test mode, don‘t sample the above comma separated list of tables</description> 122 </property> 123 124 <property> 125 <name>hive.metastore.uris</name> 126 <value></value> 127 <description>Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore.</description> 128 </property> 129 130 <property> 131 <name>javax.jdo.option.ConnectionURL</name> 132 <value>jdbc:mysql://10.14.46.90:3306/metastore_db</value> 133 <description>JDBC connect string for a JDBC metastore</description> 134 </property> 135 136 <property> 137 <name>javax.jdo.option.ConnectionDriverName</name> 138 <value>com.mysql.jdbc.Driver</value> 139 <description>Driver class name for a JDBC metastore</description> 140 </property> 141 142 <property> 143 <name>javax.jdo.PersistenceManagerFactoryClass</name> 144 <value>org.datanucleus.api.jdo.JDOPersistenceManagerFactory</value> 145 <description>class implementing the jdo persistence</description> 146 </property> 147 148 <property> 149 <name>javax.jdo.option.DetachAllOnCommit</name> 150 <value>true</value> 151 <description>detaches all objects from session so that they can be used after transaction is committed</description> 152 </property> 153 154 <property> 155 <name>javax.jdo.option.NonTransactionalRead</name> 156 <value>true</value> 157 <description>reads outside of transactions</description> 158 </property> 159 160 <property> 161 <name>javax.jdo.option.ConnectionUserName</name> 162 <value>web.app</value> 163 <description>username to use against metastore database</description> 164 </property> 165 166 <property> 167 <name>javax.jdo.option.ConnectionPassword</name> 168 <value>easou_app</value> 169 <description>password to use against metastore database</description> 170 </property> 171 172 <property> 173 <name>javax.jdo.option.Multithreaded</name> 174 <value>true</value> 175 <description>Set this to true if multiple threads access metastore through JDO concurrently.</description> 176 </property> 177 178 <property> 179 <name>datanucleus.connectionPoolingType</name> 180 <value>BoneCP</value> 181 <description>Uses a BoneCP connection pool for JDBC metastore</description> 182 </property> 183 184 <property> 185 <name>datanucleus.validateTables</name> 186 <value>false</value> 187 <description>validates existing schema against code. turn this on if you want to verify existing schema </description> 188 </property> 189 190 <property> 191 <name>datanucleus.validateColumns</name> 192 <value>false</value> 193 <description>validates existing schema against code. turn this on if you want to verify existing schema </description> 194 </property> 195 196 <property> 197 <name>datanucleus.validateConstraints</name> 198 <value>false</value> 199 <description>validates existing schema against code. turn this on if you want to verify existing schema </description> 200 </property> 201 202 <property> 203 <name>datanucleus.storeManagerType</name> 204 <value>rdbms</value> 205 <description>metadata store type</description> 206 </property> 207 208 <property> 209 <name>datanucleus.autoCreateSchema</name> 210 <value>true</value> 211 <description>creates necessary schema on a startup if one doesn‘t exist. set this to false, after creating it once</description> 212 </property> 213 214 <property> 215 <name>datanucleus.autoStartMechanismMode</name> 216 <value>checked</value> 217 <description>throw exception if metadata tables are incorrect</description> 218 </property> 219 220 <property> 221 <name>datanucleus.transactionIsolation</name> 222 <value>read-committed</value> 223 <description>Default transaction isolation level for identity generation. </description> 224 </property> 225 226 <property> 227 <name>datanucleus.cache.level2</name> 228 <value>false</value> 229 <description>Use a level 2 cache. Turn this off if metadata is changed independently of Hive metastore server</description> 230 </property> 231 232 <property> 233 <name>datanucleus.cache.level2.type</name> 234 <value>SOFT</value> 235 <description>SOFT=soft reference based cache, WEAK=weak reference based cache.</description> 236 </property> 237 238 <property> 239 <name>datanucleus.identifierFactory</name> 240 <value>datanucleus1</value> 241 <description>Name of the identifier factory to use when generating table/column names etc. ‘datanucleus1‘ is used for backward compatibility with DataNucleus v1</description> 242 </property> 243 244 <property> 245 <name>datanucleus.plugin.pluginRegistryBundleCheck</name> 246 <value>LOG</value> 247 <description>Defines what happens when plugin bundles are found and are duplicated [EXCEPTION|LOG|NONE]</description> 248 </property> 249 250 <property> 251 <name>hive.metastore.warehouse.dir</name> 252 <value>/data/wapage/hive/warehouse</value> 253 <description>location of default database for the warehouse</description> 254 </property> 255 256 <property> 257 <name>hive.metastore.execute.setugi</name> 258 <value>false</value> 259 <description>In unsecure mode, setting this property to true will cause the metastore to execute DFS operations using the client‘s reported user and group permissions. Note that this property must be set on both the client and server sides. Further note that its best effort. If client sets its to true and server sets it to false, client setting will be ignored.</description> 260 </property> 261 262 <property> 263 <name>hive.metastore.event.listeners</name> 264 <value></value> 265 <description>list of comma separated listeners for metastore events.</description> 266 </property> 267 268 <property> 269 <name>hive.metastore.partition.inherit.table.properties</name> 270 <value></value> 271 <description>list of comma separated keys occurring in table properties which will get inherited to newly created partitions. * implies all the keys will get inherited.</description> 272 </property> 273 274 <property> 275 <name>hive.metadata.export.location</name> 276 <value></value> 277 <description>When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, it is the location to which the metadata will be exported. The default is an empty string, which results in the metadata being exported to the current user‘s home directory on HDFS.</description> 278 </property> 279 280 <property> 281 <name>hive.metadata.move.exported.metadata.to.trash</name> 282 <value></value> 283 <description>When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, this setting determines if the metadata that is exported will subsequently be moved to the user‘s trash directory alongside the dropped table data. This ensures that the metadata will be cleaned up along with the dropped table data.</description> 284 </property> 285 286 <property> 287 <name>hive.metastore.partition.name.whitelist.pattern</name> 288 <value></value> 289 <description>Partition names will be checked against this regex pattern and rejected if not matched.</description> 290 </property> 291 292 <property> 293 <name>hive.metastore.disallow.incompatible.col.type.change</name> 294 <value></value> 295 <description>If true (default is false), ALTER TABLE operations which change the type of 296 a column (say STRING) to an incompatible type (say MAP<STRING, STRING>) are disallowed. 297 RCFile default SerDe (ColumnarSerDe) serializes the values in such a way that the 298 datatypes can be converted from string to any type. The map is also serialized as 299 a string, which can be read as a string as well. However, with any binary 300 serialization, this is not true. Blocking the ALTER TABLE prevents ClassCastExceptions 301 when subsequently trying to access old partitions. 302 303 Primitive types like INT, STRING, BIGINT, etc are compatible with each other and are 304 not blocked. 305 306 See HIVE-4409 for more details. 307 </description> 308 </property> 309 310 <property> 311 <name>hive.metastore.end.function.listeners</name> 312 <value></value> 313 <description>list of comma separated listeners for the end of metastore functions.</description> 314 </property> 315 316 <property> 317 <name>hive.metastore.event.expiry.duration</name> 318 <value>0</value> 319 <description>Duration after which events expire from events table (in seconds)</description> 320 </property> 321 322 <property> 323 <name>hive.metastore.event.clean.freq</name> 324 <value>0</value> 325 <description>Frequency at which timer task runs to purge expired events in metastore(in seconds).</description> 326 </property> 327 328 <property> 329 <name>hive.metastore.connect.retries</name> 330 <value>5</value> 331 <description>Number of retries while opening a connection to metastore</description> 332 </property> 333 334 <property> 335 <name>hive.metastore.failure.retries</name> 336 <value>3</value> 337 <description>Number of retries upon failure of Thrift metastore calls</description> 338 </property> 339 340 <property> 341 <name>hive.metastore.client.connect.retry.delay</name> 342 <value>1</value> 343 <description>Number of seconds for the client to wait between consecutive connection attempts</description> 344 </property> 345 346 <property> 347 <name>hive.metastore.client.socket.timeout</name> 348 <value>20</value> 349 <description>MetaStore Client socket timeout in seconds</description> 350 </property> 351 352 <property> 353 <name>hive.metastore.rawstore.impl</name> 354 <value>org.apache.hadoop.hive.metastore.ObjectStore</value> 355 <description>Name of the class that implements org.apache.hadoop.hive.metastore.rawstore interface. This class is used to store and retrieval of raw metadata objects such as table, database</description> 356 </property> 357 358 <property> 359 <name>hive.metastore.batch.retrieve.max</name> 360 <value>300</value> 361 <description>Maximum number of objects (tables/partitions) can be retrieved from metastore in one batch. The higher the number, the less the number of round trips is needed to the Hive metastore server, but it may also cause higher memory requirement at the client side.</description> 362 </property> 363 364 <property> 365 <name>hive.metastore.batch.retrieve.table.partition.max</name> 366 <value>1000</value> 367 <description>Maximum number of table partitions that metastore internally retrieves in one batch.</description> 368 </property> 369 370 <property> 371 <name>hive.default.fileformat</name> 372 <value>TextFile</value> 373 <description>Default file format for CREATE TABLE statement. Options are TextFile and SequenceFile. Users can explicitly say CREATE TABLE ... STORED AS <TEXTFILE|SEQUENCEFILE> to override</description> 374 </property> 375 376 <property> 377 <name>hive.default.rcfile.serde</name> 378 <value>org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe</value> 379 <description>The default SerDe Hive will use for the RCFile format</description> 380 </property> 381 382 <property> 383 <name>hive.fileformat.check</name> 384 <value>true</value> 385 <description>Whether to check file format or not when loading data files</description> 386 </property> 387 388 <property> 389 <name>hive.file.max.footer</name> 390 <value>100</value> 391 <description>maximum number of lines for footer user can define for a table file</description> 392 </property> 393 394 <property> 395 <name>hive.map.aggr</name> 396 <value>true</value> 397 <description>Whether to use map-side aggregation in Hive Group By queries</description> 398 </property> 399 400 <property> 401 <name>hive.groupby.skewindata</name> 402 <value>false</value> 403 <description>Whether there is skew in data to optimize group by queries</description> 404 </property> 405 406 <property> 407 <name>hive.optimize.multigroupby.common.distincts</name> 408 <value>true</value> 409 <description>Whether to optimize a multi-groupby query with the same distinct. 410 Consider a query like: 411 412 from src 413 insert overwrite table dest1 select col1, count(distinct colx) group by col1 414 insert overwrite table dest2 select col2, count(distinct colx) group by col2; 415 416 With this parameter set to true, first we spray by the distinct value (colx), and then 417 perform the 2 groups bys. This makes sense if map-side aggregation is turned off. However, 418 with maps-side aggregation, it might be useful in some cases to treat the 2 inserts independently, 419 thereby performing the query above in 2MR jobs instead of 3 (due to spraying by distinct key first). 420 If this parameter is turned off, we don‘t consider the fact that the distinct key is the same across 421 different MR jobs. 422 </description> 423 </property> 424 425 <property> 426 <name>hive.groupby.mapaggr.checkinterval</name> 427 <value>100000</value> 428 <description>Number of rows after which size of the grouping keys/aggregation classes is performed</description> 429 </property> 430 431 <property> 432 <name>hive.mapred.local.mem</name> 433 <value>0</value> 434 <description>For local mode, memory of the mappers/reducers</description> 435 </property> 436 437 <property> 438 <name>hive.mapjoin.followby.map.aggr.hash.percentmemory</name> 439 <value>0.3</value> 440 <description>Portion of total memory to be used by map-side group aggregation hash table, when this group by is followed by map join</description> 441 </property> 442 443 <property> 444 <name>hive.map.aggr.hash.force.flush.memory.threshold</name> 445 <value>0.9</value> 446 <description>The max memory to be used by map-side group aggregation hash table, if the memory usage is higher than this number, force to flush data</description> 447 </property> 448 449 <property> 450 <name>hive.map.aggr.hash.percentmemory</name> 451 <value>0.5</value> 452 <description>Portion of total memory to be used by map-side group aggregation hash table</description> 453 </property> 454 455 <property> 456 <name>hive.session.history.enabled</name> 457 <value>false</value> 458 <description>Whether to log Hive query, query plan, runtime statistics etc.</description> 459 </property> 460 461 <property> 462 <name>hive.map.aggr.hash.min.reduction</name> 463 <value>0.5</value> 464 <description>Hash aggregation will be turned off if the ratio between hash 465 table size and input rows is bigger than this number. Set to 1 to make sure 466 hash aggregation is never turned off.</description> 467 </property> 468 469 <property> 470 <name>hive.optimize.index.filter</name> 471 <value>false</value> 472 <description>Whether to enable automatic use of indexes</description> 473 </property> 474 475 <property> 476 <name>hive.optimize.index.groupby</name> 477 <value>false</value> 478 <description>Whether to enable optimization of group-by queries using Aggregate indexes.</description> 479 </property> 480 481 <property> 482 <name>hive.optimize.ppd</name> 483 <value>true</value> 484 <description>Whether to enable predicate pushdown</description> 485 </property> 486 487 <property> 488 <name>hive.optimize.ppd.storage</name> 489 <value>true</value> 490 <description>Whether to push predicates down into storage handlers. Ignored when hive.optimize.ppd is false.</description> 491 </property> 492 493 <property> 494 <name>hive.ppd.recognizetransivity</name> 495 <value>true</value> 496 <description>Whether to transitively replicate predicate filters over equijoin conditions.</description> 497 </property> 498 499 <property> 500 <name>hive.optimize.groupby</name> 501 <value>true</value> 502 <description>Whether to enable the bucketed group by from bucketed partitions/tables.</description> 503 </property> 504 505 <property> 506 <name>hive.optimize.sort.dynamic.partition</name> 507 <value>true</value> 508 <description>When enabled dynamic partitioning column will be globally sorted. 509 This way we can keep only one record writer open for each partition value 510 in the reducer thereby reducing the memory pressure on reducers.</description> 511 </property> 512 513 <property> 514 <name>hive.optimize.skewjoin.compiletime</name> 515 <value>false</value> 516 <description>Whether to create a separate plan for skewed keys for the tables in the join. 517 This is based on the skewed keys stored in the metadata. At compile time, the plan is broken 518 into different joins: one for the skewed keys, and the other for the remaining keys. And then, 519 a union is performed for the 2 joins generated above. So unless the same skewed key is present 520 in both the joined tables, the join for the skewed key will be performed as a map-side join. 521 522 The main difference between this parameter and hive.optimize.skewjoin is that this parameter 523 uses the skew information stored in the metastore to optimize the plan at compile time itself. 524 If there is no skew information in the metadata, this parameter will not have any affect. 525 Both hive.optimize.skewjoin.compiletime and hive.optimize.skewjoin should be set to true. 526 Ideally, hive.optimize.skewjoin should be renamed as hive.optimize.skewjoin.runtime, but not doing 527 so for backward compatibility. 528 529 If the skew information is correctly stored in the metadata, hive.optimize.skewjoin.compiletime 530 would change the query plan to take care of it, and hive.optimize.skewjoin will be a no-op. 531 </description> 532 </property> 533 534 <property> 535 <name>hive.optimize.union.remove</name> 536 <value>false</value> 537 <description> 538 Whether to remove the union and push the operators between union and the filesink above 539 union. This avoids an extra scan of the output by union. This is independently useful for union 540 queries, and specially useful when hive.optimize.skewjoin.compiletime is set to true, since an 541 extra union is inserted. 542 543 The merge is triggered if either of hive.merge.mapfiles or hive.merge.mapredfiles is set to true. 544 If the user has set hive.merge.mapfiles to true and hive.merge.mapredfiles to false, the idea was the 545 number of reducers are few, so the number of files anyway are small. However, with this optimization, 546 we are increasing the number of files possibly by a big margin. So, we merge aggressively.</description> 547 </property> 548 549 <property> 550 <name>hive.mapred.supports.subdirectories</name> 551 <value>false</value> 552 <description>Whether the version of Hadoop which is running supports sub-directories for tables/partitions. 553 Many Hive optimizations can be applied if the Hadoop version supports sub-directories for 554 tables/partitions. It was added by MAPREDUCE-1501</description> 555 </property> 556 557 <property> 558 <name>hive.multigroupby.singlereducer</name> 559 <value>false</value> 560 <description>Whether to optimize multi group by query to generate single M/R 561 job plan. If the multi group by query has common group by keys, it will be 562 optimized to generate single M/R job.</description> 563 </property> 564 565 <property> 566 <name>hive.map.groupby.sorted</name> 567 <value>false</value> 568 <description>If the bucketing/sorting properties of the table exactly match the grouping key, whether to 569 perform the group by in the mapper by using BucketizedHiveInputFormat. The only downside to this 570 is that it limits the number of mappers to the number of files. 571 </description> 572 </property> 573 574 <property> 575 <name>hive.map.groupby.sorted.testmode</name> 576 <value>false</value> 577 <description>If the bucketing/sorting properties of the table exactly match the grouping key, whether to 578 perform the group by in the mapper by using BucketizedHiveInputFormat. If the test mode is set, the plan 579 is not converted, but a query property is set to denote the same. 580 </description> 581 </property> 582 583 <property> 584 <name>hive.new.job.grouping.set.cardinality</name> 585 <value>30</value> 586 <description> 587 Whether a new map-reduce job should be launched for grouping sets/rollups/cubes. 588 For a query like: select a, b, c, count(1) from T group by a, b, c with rollup; 589 4 rows are created per row: (a, b, c), (a, b, null), (a, null, null), (null, null, null). 590 This can lead to explosion across map-reduce boundary if the cardinality of T is very high, 591 and map-side aggregation does not do a very good job. 592 593 This parameter decides if Hive should add an additional map-reduce job. If the grouping set 594 cardinality (4 in the example above), is more than this value, a new MR job is added under the 595 assumption that the original group by will reduce the data size. 596 </description> 597 </property> 598 599 <property> 600 <name>hive.join.emit.interval</name> 601 <value>1000</value> 602 <description>How many rows in the right-most join operand Hive should buffer before emitting the join result.</description> 603 </property> 604 605 <property> 606 <name>hive.join.cache.size</name> 607 <value>25000</value> 608 <description>How many rows in the joining tables (except the streaming table) should be cached in memory. </description> 609 </property> 610 611 <property> 612 <name>hive.smbjoin.cache.rows</name> 613 <value>10000</value> 614 <description>How many rows with the same key value should be cached in memory per SMB joined table.</description> 615 </property> 616 617 <property> 618 <name>hive.optimize.skewjoin</name> 619 <value>false</value> 620 <description>Whether to enable skew join optimization. 621 The algorithm is as follows: At runtime, detect the keys with a large skew. Instead of 622 processing those keys, store them temporarily in an HDFS directory. In a follow-up map-reduce 623 job, process those skewed keys. The same key need not be skewed for all the tables, and so, 624 the follow-up map-reduce job (for the skewed keys) would be much faster, since it would be a 625 map-join. 626 </description> 627 </property> 628 629 <property> 630 <name>hive.skewjoin.key</name> 631 <value>100000</value> 632 <description>Determine if we get a skew key in join. If we see more 633 than the specified number of rows with the same key in join operator, 634 we think the key as a skew join key. </description> 635 </property> 636 637 <property> 638 <name>hive.skewjoin.mapjoin.map.tasks</name> 639 <value>10000</value> 640 <description> Determine the number of map task used in the follow up map join job 641 for a skew join. It should be used together with hive.skewjoin.mapjoin.min.split 642 to perform a fine grained control.</description> 643 </property> 644 645 <property> 646 <name>hive.skewjoin.mapjoin.min.split</name> 647 <value>33554432</value> 648 <description> Determine the number of map task at most used in the follow up map join job 649 for a skew join by specifying the minimum split size. It should be used together with 650 hive.skewjoin.mapjoin.map.tasks to perform a fine grained control.</description> 651 </property> 652 653 <property> 654 <name>hive.mapred.mode</name> 655 <value>nonstrict</value> 656 <description>The mode in which the Hive operations are being performed. 657 In strict mode, some risky queries are not allowed to run. They include: 658 Cartesian Product. 659 No partition being picked up for a query. 660 Comparing bigints and strings. 661 Comparing bigints and doubles. 662 Orderby without limit. 663 </description> 664 </property> 665 666 <property> 667 <name>hive.enforce.bucketmapjoin</name> 668 <value>false</value> 669 <description>If the user asked for bucketed map-side join, and it cannot be performed, 670 should the query fail or not ? For example, if the buckets in the tables being joined are 671 not a multiple of each other, bucketed map-side join cannot be performed, and the 672 query will fail if hive.enforce.bucketmapjoin is set to true. 673 </description> 674 </property> 675 676 <property> 677 <name>hive.exec.script.maxerrsize</name> 678 <value>100000</value> 679 <description>Maximum number of bytes a script is allowed to emit to standard error (per map-reduce task). This prevents runaway scripts from filling logs partitions to capacity </description> 680 </property> 681 682 <property> 683 <name>hive.exec.script.allow.partial.consumption</name> 684 <value>false</value> 685 <description> When enabled, this option allows a user script to exit successfully without consuming all the data from the standard input. 686 </description> 687 </property> 688 689 <property> 690 <name>hive.script.operator.id.env.var</name> 691 <value>HIVE_SCRIPT_OPERATOR_ID</value> 692 <description> Name of the environment variable that holds the unique script operator ID in the user‘s transform function (the custom mapper/reducer that the user has specified in the query) 693 </description> 694 </property> 695 696 <property> 697 <name>hive.script.operator.truncate.env</name> 698 <value>false</value> 699 <description>Truncate each environment variable for external script in scripts operator to 20KB (to fit system limits)</description> 700 </property> 701 702 <property> 703 <name>hive.exec.compress.output</name> 704 <value>false</value> 705 <description> This controls whether the final outputs of a query (to a local/HDFS file or a Hive table) is compressed. The compression codec and other options are determined from Hadoop config variables mapred.output.compress* </description> 706 </property> 707 708 <property> 709 <name>hive.exec.compress.intermediate</name> 710 <value>false</value> 711 <description> This controls whether intermediate files produced by Hive between multiple map-reduce jobs are compressed. The compression codec and other options are determined from Hadoop config variables mapred.output.compress* </description> 712 </property> 713 714 <property> 715 <name>hive.exec.parallel</name> 716 <value>false</value> 717 <description>Whether to execute jobs in parallel</description> 718 </property> 719 720 <property> 721 <name>hive.exec.parallel.thread.number</name> 722 <value>8</value> 723 <description>How many jobs at most can be executed in parallel</description> 724 </property> 725 726 <property> 727 <name>hive.exec.rowoffset</name> 728 <value>false</value> 729 <description>Whether to provide the row offset virtual column</description> 730 </property> 731 732 <property> 733 <name>hive.counters.group.name</name> 734 <value>HIVE</value> 735 <description>The name of counter group for internal Hive variables (CREATED_FILE, FATAL_ERROR, etc.)</description> 736 </property> 737 738 <property> 739 <name>hive.hwi.war.file</name> 740 <value>lib/hive-hwi-@VERSION@.war</value> 741 <description>This sets the path to the HWI war file, relative to ${HIVE_HOME}. </description> 742 </property> 743 744 <property> 745 <name>hive.hwi.listen.host</name> 746 <value>0.0.0.0</value> 747 <description>This is the host address the Hive Web Interface will listen on</description> 748 </property> 749 750 <property> 751 <name>hive.hwi.listen.port</name> 752 <value>9999</value> 753 <description>This is the port the Hive Web Interface will listen on</description> 754 </property> 755 756 <property> 757 <name>hive.exec.pre.hooks</name> 758 <value></value> 759 <description>Comma-separated list of pre-execution hooks to be invoked for each statement. A pre-execution hook is specified as the name of a Java class which implements the org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.</description> 760 </property> 761 762 <property> 763 <name>hive.exec.post.hooks</name> 764 <value></value> 765 <description>Comma-separated list of post-execution hooks to be invoked for each statement. A post-execution hook is specified as the name of a Java class which implements the org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.</description> 766 </property> 767 768 <property> 769 <name>hive.exec.failure.hooks</name> 770 <value></value> 771 <description>Comma-separated list of on-failure hooks to be invoked for each statement. An on-failure hook is specified as the name of Java class which implements the org.apache.hadoop.hive.ql.hooks.ExecuteWithHookContext interface.</description> 772 </property> 773 774 <property> 775 <name>hive.metastore.init.hooks</name> 776 <value></value> 777 <description>A comma separated list of hooks to be invoked at the beginning of HMSHandler initialization. An init hook is specified as the name of Java class which extends org.apache.hadoop.hive.metastore.MetaStoreInitListener.</description> 778 </property> 779 780 <property> 781 <name>hive.client.stats.publishers</name> 782 <value></value> 783 <description>Comma-separated list of statistics publishers to be invoked on counters on each job. A client stats publisher is specified as the name of a Java class which implements the org.apache.hadoop.hive.ql.stats.ClientStatsPublisher interface.</description> 784 </property> 785 786 <property> 787 <name>hive.client.stats.counters</name> 788 <value></value> 789 <description>Subset of counters that should be of interest for hive.client.stats.publishers (when one wants to limit their publishing). Non-display names should be used</description> 790 </property> 791 792 <property> 793 <name>hive.merge.mapfiles</name> 794 <value>true</value> 795 <description>Merge small files at the end of a map-only job</description> 796 </property> 797 798 <property> 799 <name>hive.merge.mapredfiles</name> 800 <value>false</value> 801 <description>Merge small files at the end of a map-reduce job</description> 802 </property> 803 804 <property> 805 <name>hive.merge.tezfiles</name> 806 <value>false</value> 807 <description>Merge small files at the end of a Tez DAG</description> 808 </property> 809 810 <property> 811 <name>hive.heartbeat.interval</name> 812 <value>1000</value> 813 <description>Send a heartbeat after this interval - used by mapjoin and filter operators</description> 814 </property> 815 816 <property> 817 <name>hive.merge.size.per.task</name> 818 <value>256000000</value> 819 <description>Size of merged files at the end of the job</description> 820 </property> 821 822 <property> 823 <name>hive.merge.smallfiles.avgsize</name> 824 <value>16000000</value> 825 <description>When the average output file size of a job is less than this number, Hive will start an additional map-reduce job to merge the output files into bigger files. This is only done for map-only jobs if hive.merge.mapfiles is true, and for map-reduce jobs if hive.merge.mapredfiles is true.</description> 826 </property> 827 828 <property> 829 <name>hive.mapjoin.smalltable.filesize</name> 830 <value>25000000</value> 831 <description>The threshold for the input file size of the small tables; if the file size is smaller than this threshold, it will try to convert the common join into map join</description> 832 </property> 833 834 <property> 835 <name>hive.ignore.mapjoin.hint</name> 836 <value>true</value> 837 <description>Ignore the mapjoin hint</description> 838 </property> 839 840 <property> 841 <name>hive.mapjoin.localtask.max.memory.usage</name> 842 <value>0.90</value> 843 <description>This number means how much memory the local task can take to hold the key/value into an in-memory hash table. If the local task‘s memory usage is more than this number, the local task will abort by itself. It means the data of the small table is too large to be held in memory.</description> 844 </property> 845 846 <property> 847 <name>hive.mapjoin.followby.gby.localtask.max.memory.usage</name> 848 <value>0.55</value> 849 <description>This number means how much memory the local task can take to hold the key/value into an in-memory hash table when this map join is followed by a group by. If the local task‘s memory usage is more than this number, the local task will abort by itself. It means the data of the small table is too large to be held in memory.</description> 850 </property> 851 852 <property> 853 <name>hive.mapjoin.check.memory.rows</name> 854 <value>100000</value> 855 <description>The number means after how many rows processed it needs to check the memory usage</description> 856 </property> 857 858 <property> 859 <name>hive.auto.convert.join</name> 860 <value>true</value> 861 <description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file size</description> 862 </property> 863 864 <property> 865 <name>hive.auto.convert.join.noconditionaltask</name> 866 <value>true</value> 867 <description>Whether Hive enables the optimization about converting common join into mapjoin based on the input file 868 size. If this parameter is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than the 869 specified size, the join is directly converted to a mapjoin (there is no conditional task). 870 </description> 871 </property> 872 873 <property> 874 <name>hive.auto.convert.join.noconditionaltask.size</name> 875 <value>10000000</value> 876 <description>If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. However, if it 877 is on, and the sum of size for n-1 of the tables/partitions for a n-way join is smaller than this size, the join is directly 878 converted to a mapjoin(there is no conditional task). The default is 10MB 879 </description> 880 </property> 881 882 <property> 883 <name>hive.auto.convert.join.use.nonstaged</name> 884 <value>false</value> 885 <description>For conditional joins, if input stream from a small alias can be directly applied to join operator without 886 filtering or projection, the alias need not to be pre-staged in distributed cache via mapred local task. 887 Currently, this is not working with vectorization or tez execution engine. 888 </description> 889 </property> 890 891 <property> 892 <name>hive.script.auto.progress</name> 893 <value>false</value> 894 <description>Whether Hive Transform/Map/Reduce Clause should automatically send progress information to TaskTracker to avoid the task getting killed because of inactivity. Hive sends progress information when the script is outputting to stderr. This option removes the need of periodically producing stderr messages, but users should be cautious because this may prevent infinite loops in the scripts to be killed by TaskTracker. </description> 895 </property> 896 897 <property> 898 <name>hive.script.serde</name> 899 <value>org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe</value> 900 <description>The default SerDe for transmitting input data to and reading output data from the user scripts. </description> 901 </property> 902 903 <property> 904 <name>hive.binary.record.max.length</name> 905 <value>1000</value> 906 <description>Read from a binary stream and treat each hive.binary.record.max.length bytes as a record. 907 The last record before the end of stream can have less than hive.binary.record.max.length bytes</description> 908 </property> 909 910 <property> 911 <name>hive.server2.max.start.attempts</name> 912 <value>30</value> 913 <description>This number of times HiveServer2 will attempt to start before exiting, sleeping 60 seconds between retries. The default of 30 will keep trying for 30 minutes.</description> 914 </property> 915 916 <property> 917 <name>hive.server2.transport.mode</name> 918 <value>binary</value> 919 <description>Server transport mode. "binary" or "http".</description> 920 </property> 921 922 <property> 923 <name>hive.server2.thrift.http.port</name> 924 <value>10001</value> 925 <description>Port number when in HTTP mode.</description> 926 </property> 927 928 <property> 929 <name>hive.server2.thrift.http.path</name> 930 <value>cliservice</value> 931 <description>Path component of URL endpoint when in HTTP mode.</description> 932 </property> 933 934 <property> 935 <name>hive.server2.thrift.http.min.worker.threads</name> 936 <value>5</value> 937 <description>Minimum number of worker threads when in HTTP mode.</description> 938 </property> 939 940 <property> 941 <name>hive.server2.thrift.http.max.worker.threads</name> 942 <value>500</value> 943 <description>Maximum number of worker threads when in HTTP mode.</description> 944 </property> 945 946 <property> 947 <name>hive.script.recordreader</name> 948 <value>org.apache.hadoop.hive.ql.exec.TextRecordReader</value> 949 <description>The default record reader for reading data from the user scripts. </description> 950 </property> 951 952 <property> 953 <name>stream.stderr.reporter.prefix</name> 954 <value>reporter:</value> 955 <description>Streaming jobs that log to standard error with this prefix can log counter or status information.</description> 956 </property> 957 958 <property> 959 <name>stream.stderr.reporter.enabled</name> 960 <value>true</value> 961 <description>Enable consumption of status and counter messages for streaming jobs.</description> 962 </property> 963 964 <property> 965 <name>hive.script.recordwriter</name> 966 <value>org.apache.hadoop.hive.ql.exec.TextRecordWriter</value> 967 <description>The default record writer for writing data to the user scripts. </description> 968 </property> 969 970 <property> 971 <name>hive.input.format</name> 972 <value>org.apache.hadoop.hive.ql.io.CombineHiveInputFormat</value> 973 <description>The default input format. Set this to HiveInputFormat if you encounter problems with CombineHiveInputFormat.</description> 974 </property> 975 976 <property> 977 <name>hive.tez.input.format</name> 978 <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value> 979 <description>The default input format for tez. Tez groups splits in the AM.</description> 980 </property> 981 982 <property> 983 <name>hive.udtf.auto.progress</name> 984 <value>false</value> 985 <description>Whether Hive should automatically send progress information to TaskTracker when using UDTF‘s to prevent the task getting killed because of inactivity. Users should be cautious because this may prevent TaskTracker from killing tasks with infinite loops. </description> 986 </property> 987 988 <property> 989 <name>hive.mapred.reduce.tasks.speculative.execution</name> 990 <value>true</value> 991 <description>Whether speculative execution for reducers should be turned on. </description> 992 </property> 993 994 <property> 995 <name>hive.exec.counters.pull.interval</name> 996 <value>1000</value> 997 <description>The interval with which to poll the JobTracker for the counters the running job. The smaller it is the more load there will be on the jobtracker, the higher it is the less granular the caught will be.</description> 998 </property> 999 1000 <property> 1001 <name>hive.querylog.location</name> 1002 <value>/tmp/${user.name}</value> 1003 <description> 1004 Location of Hive run time structured log file 1005 </description> 1006 </property> 1007 1008 <property> 1009 <name>hive.querylog.enable.plan.progress</name> 1010 <value>true</value> 1011 <description> 1012 Whether to log the plan‘s progress every time a job‘s progress is checked. 1013 These logs are written to the location specified by hive.querylog.location 1014 </description> 1015 </property> 1016 1017 <property> 1018 <name>hive.querylog.plan.progress.interval</name> 1019 <value>60000</value> 1020 <description> 1021 The interval to wait between logging the plan‘s progress in milliseconds. 1022 If there is a whole number percentage change in the progress of the mappers or the reducers, 1023 the progress is logged regardless of this value. 1024 The actual interval will be the ceiling of (this value divided by the value of 1025 hive.exec.counters.pull.interval) multiplied by the value of hive.exec.counters.pull.interval 1026 I.e. if it is not divide evenly by the value of hive.exec.counters.pull.interval it will be 1027 logged less frequently than specified. 1028 This only has an effect if hive.querylog.enable.plan.progress is set to true. 1029 </description> 1030 </property> 1031 1032 <property> 1033 <name>hive.enforce.bucketing</name> 1034 <value>false</value> 1035 <description>Whether bucketing is enforced. If true, while inserting into the table, bucketing is enforced. </description> 1036 </property> 1037 1038 <property> 1039 <name>hive.enforce.sorting</name> 1040 <value>false</value> 1041 <description>Whether sorting is enforced. If true, while inserting into the table, sorting is enforced. </description> 1042 </property> 1043 1044 <property> 1045 <name>hive.optimize.bucketingsorting</name> 1046 <value>true</value> 1047 <description>If hive.enforce.bucketing or hive.enforce.sorting is true, don‘t create a reducer for enforcing 1048 bucketing/sorting for queries of the form: 1049 insert overwrite table T2 select * from T1; 1050 where T1 and T2 are bucketed/sorted by the same keys into the same number of buckets. 1051 </description> 1052 </property> 1053 1054 <property> 1055 <name>hive.enforce.sortmergebucketmapjoin</name> 1056 <value>false</value> 1057 <description>If the user asked for sort-merge bucketed map-side join, and it cannot be performed, 1058 should the query fail or not ? 1059 </description> 1060 </property> 1061 1062 <property> 1063 <name>hive.auto.convert.sortmerge.join</name> 1064 <value>false</value> 1065 <description>Will the join be automatically converted to a sort-merge join, if the joined tables pass 1066 the criteria for sort-merge join. 1067 </description> 1068 </property> 1069 1070 <property> 1071 <name>hive.auto.convert.sortmerge.join.bigtable.selection.policy</name> 1072 <value>org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ</value> 1073 <description>The policy to choose the big table for automatic conversion to sort-merge join. 1074 By default, the table with the largest partitions is assigned the big table. All policies are: 1075 . based on position of the table - the leftmost table is selected 1076 org.apache.hadoop.hive.ql.optimizer.LeftmostBigTableSMJ. 1077 . based on total size (all the partitions selected in the query) of the table 1078 org.apache.hadoop.hive.ql.optimizer.TableSizeBasedBigTableSelectorForAutoSMJ. 1079 . based on average size (all the partitions selected in the query) of the table 1080 org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ. 1081 New policies can be added in future. 1082 </description> 1083 </property> 1084 1085 <property> 1086 <name>hive.auto.convert.sortmerge.join.to.mapjoin</name> 1087 <value>false</value> 1088 <description>If hive.auto.convert.sortmerge.join is set to true, and a join was converted to a sort-merge join, 1089 this parameter decides whether each table should be tried as a big table, and effectively a map-join should be 1090 tried. That would create a conditional task with n+1 children for a n-way join (1 child for each table as the 1091 big table), and the backup task will be the sort-merge join. In some cases, a map-join would be faster than a 1092 sort-merge join, if there is no advantage of having the output bucketed and sorted. For example, if a very big sorted 1093 and bucketed table with few files (say 10 files) are being joined with a very small sorter and bucketed table 1094 with few files (10 files), the sort-merge join will only use 10 mappers, and a simple map-only join might be faster 1095 if the complete small table can fit in memory, and a map-join can be performed. 1096 </description> 1097 </property> 1098 1099 <property> 1100 <name>hive.metastore.ds.connection.url.hook</name> 1101 <value></value> 1102 <description>Name of the hook to use for retrieving the JDO connection URL. If empty, the value in javax.jdo.option.ConnectionURL is used </description> 1103 </property> 1104 1105 <property> 1106 <name>hive.metastore.ds.retry.attempts</name> 1107 <value>1</value> 1108 <description>The number of times to retry a metastore call if there were a connection error</description> 1109 </property> 1110 1111 <property> 1112 <name>hive.metastore.ds.retry.interval</name> 1113 <value>1000</value> 1114 <description>The number of milliseconds between metastore retry attempts</description> 1115 </property> 1116 1117 <property> 1118 <name>hive.metastore.server.min.threads</name> 1119 <value>200</value> 1120 <description>Minimum number of worker threads in the Thrift server‘s pool.</description> 1121 </property> 1122 1123 <property> 1124 <name>hive.metastore.server.max.threads</name> 1125 <value>100000</value> 1126 <description>Maximum number of worker threads in the Thrift server‘s pool.</description> 1127 </property> 1128 1129 <property> 1130 <name>hive.metastore.server.tcp.keepalive</name> 1131 <value>true</value> 1132 <description>Whether to enable TCP keepalive for the metastore server. Keepalive will prevent accumulation of half-open connections.</description> 1133 </property> 1134 1135 <property> 1136 <name>hive.metastore.sasl.enabled</name> 1137 <value>false</value> 1138 <description>If true, the metastore Thrift interface will be secured with SASL. Clients must authenticate with Kerberos.</description> 1139 </property> 1140 1141 <property> 1142 <name>hive.metastore.thrift.framed.transport.enabled</name> 1143 <value>false</value> 1144 <description>If true, the metastore Thrift interface will use TFramedTransport. When false (default) a standard TTransport is used.</description> 1145 </property> 1146 1147 <property> 1148 <name>hive.metastore.kerberos.keytab.file</name> 1149 <value></value> 1150 <description>The path to the Kerberos Keytab file containing the metastore Thrift server‘s service principal.</description> 1151 </property> 1152 1153 <property> 1154 <name>hive.metastore.kerberos.principal</name> 1155 <value>hive-metastore/_HOST@EXAMPLE.COM</value> 1156 <description>The service principal for the metastore Thrift server. The special string _HOST will be replaced automatically with the correct host name.</description> 1157 </property> 1158 1159 <property> 1160 <name>hive.cluster.delegation.token.store.class</name> 1161 <value>org.apache.hadoop.hive.thrift.MemoryTokenStore</value> 1162 <description>The delegation token store implementation. Set to org.apache.hadoop.hive.thrift.ZooKeeperTokenStore for load-balanced cluster.</description> 1163 </property> 1164 1165 <property> 1166 <name>hive.cluster.delegation.token.store.zookeeper.connectString</name> 1167 <value>localhost:2181</value> 1168 <description>The ZooKeeper token store connect string.</description> 1169 </property> 1170 1171 <property> 1172 <name>hive.cluster.delegation.token.store.zookeeper.znode</name> 1173 <value>/hive/cluster/delegation</value> 1174 <description>The root path for token store data.</description> 1175 </property> 1176 1177 <property> 1178 <name>hive.cluster.delegation.token.store.zookeeper.acl</name> 1179 <value>sasl:hive/host1@EXAMPLE.COM:cdrwa,sasl:hive/host2@EXAMPLE.COM:cdrwa</value> 1180 <description>ACL for token store entries. List comma separated all server principals for the cluster.</description> 1181 </property> 1182 1183 <property> 1184 <name>hive.metastore.cache.pinobjtypes</name> 1185 <value>Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order</value> 1186 <description>List of comma separated metastore object types that should be pinned in the cache</description> 1187 </property> 1188 1189 <property> 1190 <name>hive.optimize.reducededuplication</name> 1191 <value>true</value> 1192 <description>Remove extra map-reduce jobs if the data is already clustered by the same key which needs to be used again. This should always be set to true. Since it is a new feature, it has been made configurable.</description> 1193 </property> 1194 1195 <property> 1196 <name>hive.optimize.correlation</name> 1197 <value>false</value> 1198 <description>exploit intra-query correlations.</description> 1199 </property> 1200 1201 <property> 1202 <name>hive.optimize.reducededuplication.min.reducer</name> 1203 <value>4</value> 1204 <description>Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS. 1205 That means if reducer-num of the child RS is fixed (order by or forced bucketing) and small, it can make very slow, single MR. 1206 The optimization will be disabled if number of reducers is less than specified value.</description> 1207 </property> 1208 1209 <property> 1210 <name>hive.exec.dynamic.partition</name> 1211 <value>true</value> 1212 <description>Whether or not to allow dynamic partitions in DML/DDL.</description> 1213 </property> 1214 1215 <property> 1216 <name>hive.exec.dynamic.partition.mode</name> 1217 <value>strict</value> 1218 <description>In strict mode, the user must specify at least one static partition in case the user accidentally overwrites all partitions.</description> 1219 </property> 1220 1221 <property> 1222 <name>hive.exec.max.dynamic.partitions</name> 1223 <value>1000</value> 1224 <description>Maximum number of dynamic partitions allowed to be created in total.</description> 1225 </property> 1226 1227 <property> 1228 <name>hive.exec.max.dynamic.partitions.pernode</name> 1229 <value>100</value> 1230 <description>Maximum number of dynamic partitions allowed to be created in each mapper/reducer node.</description> 1231 </property> 1232 1233 <property> 1234 <name>hive.exec.max.created.files</name> 1235 <value>100000</value> 1236 <description>Maximum number of HDFS files created by all mappers/reducers in a MapReduce job.</description> 1237 </property> 1238 1239 <property> 1240 <name>hive.exec.default.partition.name</name> 1241 <value>__HIVE_DEFAULT_PARTITION__</value> 1242 <description>The default partition name in case the dynamic partition column value is null/empty string or any other values that cannot be escaped. This value must not contain any special character used in HDFS URI (e.g., ‘:‘, ‘%‘, ‘/‘ etc). The user has to be aware that the dynamic partition value should not contain this value to avoid confusions.</description> 1243 </property> 1244 1245 <property> 1246 <name>hive.stats.dbclass</name> 1247 <value>fs</value> 1248 <description>The storage that stores temporary Hive statistics. Supported values are 1249 fs (filesystem), jdbc(:.*), hbase, counter, and custom. In FS based statistics collection, 1250 each task writes statistics it has collected in a file on the filesystem, which will be 1251 aggregated after the job has finished.</description> 1252 </property> 1253 1254 <property> 1255 <name>hive.stats.autogather</name> 1256 <value>true</value> 1257 <description>A flag to gather statistics automatically during the INSERT OVERWRITE command.</description> 1258 </property> 1259 1260 <property> 1261 <name>hive.stats.jdbcdriver</name> 1262 <value>org.apache.derby.jdbc.EmbeddedDriver</value> 1263 <description>The JDBC driver for the database that stores temporary Hive statistics.</description> 1264 </property> 1265 1266 <property> 1267 <name>hive.stats.dbconnectionstring</name> 1268 <value>jdbc:derby:;databaseName=TempStatsStore;create=true</value> 1269 <description>The default connection string for the database that stores temporary Hive statistics.</description> 1270 </property> 1271 1272 <property> 1273 <name>hive.stats.default.publisher</name> 1274 <value></value> 1275 <description>The Java class (implementing the StatsPublisher interface) that is used by default if hive.stats.dbclass is custom type.</description> 1276 </property> 1277 1278 <property> 1279 <name>hive.stats.default.aggregator</name> 1280 <value></value> 1281 <description>The Java class (implementing the StatsAggregator interface) that is used by default if hive.stats.dbclass is custom type.</description> 1282 </property> 1283 1284 <property> 1285 <name>hive.stats.jdbc.timeout</name> 1286 <value>30</value> 1287 <description>Timeout value (number of seconds) used by JDBC connection and statements.</description> 1288 </property> 1289 1290 <property> 1291 <name>hive.stats.retries.max</name> 1292 <value>0</value> 1293 <description>Maximum number of retries when stats publisher/aggregator got an exception updating intermediate database. Default is no tries on failures.</description> 1294 </property> 1295 1296 <property> 1297 <name>hive.stats.retries.wait</name> 1298 <value>3000</value> 1299 <description>The base waiting window (in milliseconds) before the next retry. The actual wait time is calculated by baseWindow * failures baseWindow * (failure 1) * (random number between [0.0,1.0]).</description> 1300 </property> 1301 1302 <property> 1303 <name>hive.stats.reliable</name> 1304 <value>false</value> 1305 <description>Whether queries will fail because stats cannot be collected completely accurately. 1306 If this is set to true, reading/writing from/into a partition may fail because the stats 1307 could not be computed accurately. 1308 </description> 1309 </property> 1310 1311 <property> 1312 <name>hive.stats.collect.tablekeys</name> 1313 <value>false</value> 1314 <description>Whether join and group by keys on tables are derived and maintained in the QueryPlan. 1315 This is useful to identify how tables are accessed and to determine if they should be bucketed. 1316 </description> 1317 </property> 1318 1319 <property> 1320 <name>hive.stats.collect.scancols</name> 1321 <value>false</value> 1322 <description>Whether column accesses are tracked in the QueryPlan. 1323 This is useful to identify how tables are accessed and to determine if there are wasted columns that can be trimmed. 1324 </description> 1325 </property> 1326 1327 <property> 1328 <name>hive.stats.ndv.error</name> 1329 <value>20.0</value> 1330 <description>Standard error expressed in percentage. Provides a tradeoff between accuracy and compute cost.A lower value for error indicates higher accuracy and a higher compute cost. 1331 </description> 1332 </property> 1333 1334 <property> 1335 <name>hive.stats.key.prefix.max.length</name> 1336 <value>200</value> 1337 <description> 1338 Determines if when the prefix of the key used for intermediate stats collection 1339 exceeds a certain length, a hash of the key is used instead. If the value < 0 then hashing 1340 is never used, if the value >= 0 then hashing is used only when the key prefixes length 1341 exceeds that value. The key prefix is defined as everything preceding the task ID in the key. 1342 For counter type stats, it‘s maxed by mapreduce.job.counters.group.name.max, which is by default 128. 1343 </description> 1344 </property> 1345 1346 <property> 1347 <name>hive.stats.key.prefix.reserve.length</name> 1348 <value>24</value> 1349 <description> 1350 Reserved length for postfix of stats key. Currently only meaningful for counter type which should 1351 keep length of full stats key smaller than max length configured by hive.stats.key.prefix.max.length. 1352 For counter type, it should be bigger than the length of LB spec if exists. 1353 </description> 1354 </property> 1355 1356 <property> 1357 <name>hive.stats.max.variable.length</name> 1358 <value>100</value> 1359 <description> 1360 To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), 1361 average row size is multiplied with the total number of rows coming out of each operator. 1362 Average row size is computed from average column size of all columns in the row. In the absence 1363 of column statistics, for variable length columns (like string, bytes etc.), this value will be 1364 used. For fixed length columns their corresponding Java equivalent sizes are used 1365 (float - 4 bytes, double - 8 bytes etc.). 1366 </description> 1367 </property> 1368 1369 <property> 1370 <name>hive.stats.list.num.entries</name> 1371 <value>10</value> 1372 <description> 1373 To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), 1374 average row size is multiplied with the total number of rows coming out of each operator. 1375 Average row size is computed from average column size of all columns in the row. In the absence 1376 of column statistics and for variable length complex columns like list, the average number of 1377 entries/values can be specified using this config. 1378 </description> 1379 </property> 1380 1381 <property> 1382 <name>hive.stats.map.num.entries</name> 1383 <value>10</value> 1384 <description> 1385 To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), 1386 average row size is multiplied with the total number of rows coming out of each operator. 1387 Average row size is computed from average column size of all columns in the row. In the absence 1388 of column statistics and for variable length complex columns like map, the average number of 1389 entries/values can be specified using this config. 1390 </description> 1391 </property> 1392 1393 <property> 1394 <name>hive.stats.map.parallelism</name> 1395 <value>1</value> 1396 <description> 1397 Hive/Tez optimizer estimates the data size flowing through each of the operators. 1398 For GROUPBY operator, to accurately compute the data size map-side parallelism needs to 1399 be known. By default, this value is set to 1 since optimizer is not aware of the number of 1400 mappers during compile-time. This Hive config can be used to specify the number of mappers 1401 to be used for data size computation of GROUPBY operator. 1402 </description> 1403 </property> 1404 1405 <property> 1406 <name>hive.stats.fetch.column.stats</name> 1407 <value>false</value> 1408 <description> 1409 Annotation of operator tree with statistics information requires column statisitcs. 1410 Column statistics are fetched from metastore. Fetching column statistics for each needed column 1411 can be expensive when the number of columns is high. This flag can be used to disable fetching 1412 of column statistics from metastore. 1413 </description> 1414 </property> 1415 1416 <property> 1417 <name>hive.stats.fetch.partition.stats</name> 1418 <value>true</value> 1419 <description> 1420 Annotation of operator tree with statistics information requires partition level basic 1421 statisitcs like number of rows, data size and file size. Partition statistics are fetched from 1422 metastore. Fetching partition statistics for each needed partition can be expensive when the 1423 number of partitions is high. This flag can be used to disable fetching of partition statistics 1424 from metastore. When this flag is disabled, Hive will make calls to filesystem to get file sizes 1425 and will estimate the number of rows from row schema. 1426 </description> 1427 </property> 1428 1429 <property> 1430 <name>hive.stats.join.factor</name> 1431 <value>1.1</value> 1432 <description> 1433 Hive/Tez optimizer estimates the data size flowing through each of the operators. JOIN operator 1434 uses column statistics to estimate the number of rows flowing out of it and hence the data size. 1435 In the absence of column statistics, this factor determines the amount of rows that flows out 1436 of JOIN operator. 1437 </description> 1438 </property> 1439 1440 <property> 1441 <name>hive.stats.deserialization.factor</name> 1442 <value>1.0</value> 1443 <description> 1444 Hive/Tez optimizer estimates the data size flowing through each of the operators. In the absence 1445 of basic statistics like number of rows and data size, file size is used to estimate the number 1446 of rows and data size. Since files in tables/partitions are serialized (and optionally 1447 compressed) the estimates of number of rows and data size cannot be reliably determined. 1448 This factor is multiplied with the file size to account for serialization and compression. 1449 </description> 1450 </property> 1451 1452 <property> 1453 <name>hive.support.concurrency</name> 1454 <value>false</value> 1455 <description>Whether Hive supports concurrency or not. A ZooKeeper instance must be up and running for the default Hive lock manager to support read-write locks.</description> 1456 </property> 1457 1458 <property> 1459 <name>hive.lock.numretries</name> 1460 <value>100</value> 1461 <description>The number of times you want to try to get all the locks</description> 1462 </property> 1463 1464 <property> 1465 <name>hive.unlock.numretries</name> 1466 <value>10</value> 1467 <description>The number of times you want to retry to do one unlock</description> 1468 </property> 1469 1470 <property> 1471 <name>hive.lock.sleep.between.retries</name> 1472 <value>60</value> 1473 <description>The sleep time (in seconds) between various retries</description> 1474 </property> 1475 1476 <property> 1477 <name>hive.zookeeper.quorum</name> 1478 <value>namenode</value> 1479 <description>The list of ZooKeeper servers to talk to. This is only needed for read/write locks.</description> 1480 </property> 1481 1482 <property> 1483 <name>hive.zookeeper.client.port</name> 1484 <value>2181</value> 1485 <description>The port of ZooKeeper servers to talk to. This is only needed for read/write locks.</description> 1486 </property> 1487 1488 <property> 1489 <name>hive.zookeeper.session.timeout</name> 1490 <value>600000</value> 1491 <description>ZooKeeper client‘s session timeout. The client is disconnected, and as a result, all locks released, if a heartbeat is not sent in the timeout.</description> 1492 </property> 1493 1494 <property> 1495 <name>hive.zookeeper.namespace</name> 1496 <value>hive_zookeeper_namespace</value> 1497 <description>The parent node under which all ZooKeeper nodes are created.</description> 1498 </property> 1499 1500 <property> 1501 <name>hive.zookeeper.clean.extra.nodes</name> 1502 <value>false</value> 1503 <description>Clean extra nodes at the end of the session.</description> 1504 </property> 1505 1506 <property> 1507 <name>fs.har.impl</name> 1508 <value>org.apache.hadoop.hive.shims.HiveHarFileSystem</value> 1509 <description>The implementation for accessing Hadoop Archives. Note that this won‘t be applicable to Hadoop versions less than 0.20</description> 1510 </property> 1511 1512 <property> 1513 <name>hive.archive.enabled</name> 1514 <value>false</value> 1515 <description>Whether archiving operations are permitted</description> 1516 </property> 1517 1518 <property> 1519 <name>hive.fetch.output.serde</name> 1520 <value>org.apache.hadoop.hive.serde2.DelimitedJSONSerDe</value> 1521 <description>The SerDe used by FetchTask to serialize the fetch output.</description> 1522 </property> 1523 1524 <property> 1525 <name>hive.exec.mode.local.auto</name> 1526 <value>false</value> 1527 <description> Let Hive determine whether to run in local mode automatically </description> 1528 </property> 1529 1530 <property> 1531 <name>hive.exec.drop.ignorenonexistent</name> 1532 <value>true</value> 1533 <description> 1534 Do not report an error if DROP TABLE/VIEW specifies a non-existent table/view 1535 </description> 1536 </property> 1537 1538 <property> 1539 <name>hive.exec.show.job.failure.debug.info</name> 1540 <value>true</value> 1541 <description> 1542 If a job fails, whether to provide a link in the CLI to the task with the 1543 most failures, along with debugging hints if applicable. 1544 </description> 1545 </property> 1546 1547 <property> 1548 <name>hive.auto.progress.timeout</name> 1549 <value>0</value> 1550 <description> 1551 How long to run autoprogressor for the script/UDTF operators (in seconds). 1552 Set to 0 for forever. 1553 </description> 1554 </property> 1555 1556 <!-- HBase Storage Handler Parameters --> 1557 1558 <property> 1559 <name>hive.hbase.wal.enabled</name> 1560 <value>true</value> 1561 <description>Whether writes to HBase should be forced to the write-ahead log. Disabling this improves HBase write performance at the risk of lost writes in case of a crash.</description> 1562 </property> 1563 1564 <property> 1565 <name>hive.table.parameters.default</name> 1566 <value></value> 1567 <description>Default property values for newly created tables</description> 1568 </property> 1569 1570 <property> 1571 <name>hive.entity.separator</name> 1572 <value>@</value> 1573 <description>Separator used to construct names of tables and partitions. For example, dbname@tablename@partitionname</description> 1574 </property> 1575 1576 <property> 1577 <name>hive.ddl.createtablelike.properties.whitelist</name> 1578 <value></value> 1579 <description>Table Properties to copy over when executing a Create Table Like.</description> 1580 </property> 1581 1582 <property> 1583 <name>hive.variable.substitute</name> 1584 <value>true</value> 1585 <description>This enables substitution using syntax like ${var} ${system:var} and ${env:var}.</description> 1586 </property> 1587 1588 <property> 1589 <name>hive.variable.substitute.depth</name> 1590 <value>40</value> 1591 <description>The maximum replacements the substitution engine will do.</description> 1592 </property> 1593 1594 <property> 1595 <name>hive.conf.validation</name> 1596 <value>true</value> 1597 <description>Enables type checking for registered Hive configurations</description> 1598 </property> 1599 1600 <property> 1601 <name>hive.security.authorization.enabled</name> 1602 <value>false</value> 1603 <description>enable or disable the Hive client authorization</description> 1604 </property> 1605 1606 <property> 1607 <name>hive.security.authorization.manager</name> 1608 <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveAuthorizationProvider</value> 1609 <description>The Hive client authorization manager class name. 1610 The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider. 1611 </description> 1612 </property> 1613 1614 <property> 1615 <name>hive.security.metastore.authorization.manager</name> 1616 <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider</value> 1617 <description>authorization manager class name to be used in the metastore for authorization. 1618 The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider. 1619 </description> 1620 </property> 1621 1622 <property> 1623 <name>hive.security.authenticator.manager</name> 1624 <value>org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator</value> 1625 <description>hive client authenticator manager class name. 1626 The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.</description> 1627 </property> 1628 1629 <property> 1630 <name>hive.security.metastore.authenticator.manager</name> 1631 <value>org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator</value> 1632 <description>authenticator manager class name to be used in the metastore for authentication. 1633 The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.</description> 1634 </property> 1635 1636 <property> 1637 <name>hive.security.authorization.createtable.user.grants</name> 1638 <value></value> 1639 <description>the privileges automatically granted to some users whenever a table gets created. 1640 An example like "userX,userY:select;userZ:create" will grant select privilege to userX and userY, 1641 and grant create privilege to userZ whenever a new table created.</description> 1642 </property> 1643 1644 <property> 1645 <name>hive.security.authorization.createtable.group.grants</name> 1646 <value></value> 1647 <description>the privileges automatically granted to some groups whenever a table gets created. 1648 An example like "groupX,groupY:select;groupZ:create" will grant select privilege to groupX and groupY, 1649 and grant create privilege to groupZ whenever a new table created.</description> 1650 </property> 1651 1652 <property> 1653 <name>hive.security.authorization.createtable.role.grants</name> 1654 <value></value> 1655 <description>the privileges automatically granted to some roles whenever a table gets created. 1656 An example like "roleX,roleY:select;roleZ:create" will grant select privilege to roleX and roleY, 1657 and grant create privilege to roleZ whenever a new table created.</description> 1658 </property> 1659 1660 <property> 1661 <name>hive.security.authorization.createtable.owner.grants</name> 1662 <value></value> 1663 <description>the privileges automatically granted to the owner whenever a table gets created. 1664 An example like "select,drop" will grant select and drop privilege to the owner of the table</description> 1665 </property> 1666 1667 <property> 1668 <name>hive.users.in.admin.role</name> 1669 <value></value> 1670 <description>Comma separated list of users who are in admin role for bootstrapping. 1671 More users can be added in ADMIN role later.</description> 1672 </property> 1673 1674 <property> 1675 <name>hive.security.command.whitelist</name> 1676 <value>set,reset,dfs,add,delete</value> 1677 <description>Comma separated list of non-SQL Hive commands users are authorized to execute</description> 1678 </property> 1679 1680 <property> 1681 <name>hive.conf.restricted.list</name> 1682 <value>hive.security.authenticator.manager,hive.security.authorization.manager</value> 1683 <description>Comma separated list of configuration options which are immutable at runtime</description> 1684 </property> 1685 1686 <property> 1687 <name>hive.metastore.authorization.storage.checks</name> 1688 <value>false</value> 1689 <description>Should the metastore do authorization checks against the underlying storage 1690 for operations like drop-partition (disallow the drop-partition if the user in 1691 question doesn‘t have permissions to delete the corresponding directory 1692 on the storage).</description> 1693 </property> 1694 1695 <property> 1696 <name>hive.error.on.empty.partition</name> 1697 <value>false</value> 1698 <description>Whether to throw an exception if dynamic partition insert generates empty results.</description> 1699 </property> 1700 1701 <property> 1702 <name>hive.index.compact.file.ignore.hdfs</name> 1703 <value>false</value> 1704 <description>When true the HDFS location stored in the index file will be ignored at runtime. 1705 If the data got moved or the name of the cluster got changed, the index data should still be usable.</description> 1706 </property> 1707 1708 <property> 1709 <name>hive.optimize.index.filter.compact.minsize</name> 1710 <value>5368709120</value> 1711 <description>Minimum size (in bytes) of the inputs on which a compact index is automatically used.</description> 1712 </property> 1713 1714 <property> 1715 <name>hive.optimize.index.filter.compact.maxsize</name> 1716 <value>-1</value> 1717 <description>Maximum size (in bytes) of the inputs on which a compact index is automatically used. 1718 A negative number is equivalent to infinity.</description> 1719 </property> 1720 1721 <property> 1722 <name>hive.index.compact.query.max.size</name> 1723 <value>10737418240</value> 1724 <description>The maximum number of bytes that a query using the compact index can read. Negative value is equivalent to infinity.</description> 1725 </property> 1726 1727 <property> 1728 <name>hive.index.compact.query.max.entries</name> 1729 <value>10000000</value> 1730 <description>The maximum number of index entries to read during a query that uses the compact index. Negative value is equivalent to infinity.</description> 1731 </property> 1732 1733 <property> 1734 <name>hive.index.compact.binary.search</name> 1735 <value>true</value> 1736 <description>Whether or not to use a binary search to find the entries in an index table that match the filter, where possible</description> 1737 </property> 1738 1739 <property> 1740 <name>hive.exim.uri.scheme.whitelist</name> 1741 <value>hdfs,pfile</value> 1742 <description>A comma separated list of acceptable URI schemes for import and export.</description> 1743 </property> 1744 1745 <property> 1746 <name>hive.lock.mapred.only.operation</name> 1747 <value>false</value> 1748 <description>This param is to control whether or not only do lock on queries 1749 that need to execute at least one mapred job.</description> 1750 </property> 1751 1752 <property> 1753 <name>hive.limit.row.max.size</name> 1754 <value>100000</value> 1755 <description>When trying a smaller subset of data for simple LIMIT, how much size we need to guarantee 1756 each row to have at least.</description> 1757 </property> 1758 1759 <property> 1760 <name>hive.limit.optimize.limit.file</name> 1761 <value>10</value> 1762 <description>When trying a smaller subset of data for simple LIMIT, maximum number of files we can 1763 sample.</description> 1764 </property> 1765 1766 <property> 1767 <name>hive.limit.optimize.enable</name> 1768 <value>false</value> 1769 <description>Whether to enable to optimization to trying a smaller subset of data for simple LIMIT first.</description> 1770 </property> 1771 1772 <property> 1773 <name>hive.limit.optimize.fetch.max</name> 1774 <value>50000</value> 1775 <description>Maximum number of rows allowed for a smaller subset of data for simple LIMIT, if it is a fetch query. 1776 Insert queries are not restricted by this limit.</description> 1777 </property> 1778 1779 <property> 1780 <name>hive.limit.pushdown.memory.usage</name> 1781 <value>0.3f</value> 1782 <description>The max memory to be used for hash in RS operator for top K selection.</description> 1783 </property> 1784 1785 <property> 1786 <name>hive.rework.mapredwork</name> 1787 <value>false</value> 1788 <description>should rework the mapred work or not. 1789 This is first introduced by SymlinkTextInputFormat to replace symlink files with real paths at compile time.</description> 1790 </property> 1791 1792 <property> 1793 <name>hive.exec.concatenate.check.index</name> 1794 <value>true</value> 1795 <description>If this is set to true, Hive will throw error when doing 1796 ‘alter table tbl_name [partSpec] concatenate‘ on a table/partition 1797 that has indexes on it. The reason the user want to set this to true 1798 is because it can help user to avoid handling all index drop, recreation, 1799 rebuild work. This is very helpful for tables with thousands of partitions.</description> 1800 </property> 1801 1802 <property> 1803 <name>hive.sample.seednumber</name> 1804 <value>0</value> 1805 <description>A number used to percentage sampling. By changing this number, user will change the subsets 1806 of data sampled.</description> 1807 </property> 1808 1809 <property> 1810 <name>hive.io.exception.handlers</name> 1811 <value></value> 1812 <description>A list of io exception handler class names. This is used 1813 to construct a list exception handlers to handle exceptions thrown 1814 by record readers</description> 1815 </property> 1816 1817 <property> 1818 <name>hive.autogen.columnalias.prefix.label</name> 1819 <value>_c</value> 1820 <description>String used as a prefix when auto generating column alias. 1821 By default the prefix label will be appended with a column position number to form the column alias. Auto generation would happen if an aggregate function is used in a select clause without an explicit alias.</description> 1822 </property> 1823 1824 <property> 1825 <name>hive.autogen.columnalias.prefix.includefuncname</name> 1826 <value>false</value> 1827 <description>Whether to include function name in the column alias auto generated by Hive.</description> 1828 </property> 1829 1830 <property> 1831 <name>hive.exec.perf.logger</name> 1832 <value>org.apache.hadoop.hive.ql.log.PerfLogger</value> 1833 <description>The class responsible logging client side performance metrics. Must be a subclass of org.apache.hadoop.hive.ql.log.PerfLogger</description> 1834 </property> 1835 1836 <property> 1837 <name>hive.start.cleanup.scratchdir</name> 1838 <value>false</value> 1839 <description>To cleanup the Hive scratchdir while starting the Hive Server</description> 1840 </property> 1841 1842 <property> 1843 <name>hive.output.file.extension</name> 1844 <value></value> 1845 <description>String used as a file extension for output files. If not set, defaults to the codec extension for text files (e.g. ".gz"), or no extension otherwise.</description> 1846 </property> 1847 1848 <property> 1849 <name>hive.insert.into.multilevel.dirs</name> 1850 <value>false</value> 1851 <description>Where to insert into multilevel directories like 1852 "insert directory ‘/HIVEFT25686/chinna/‘ from table"</description> 1853 </property> 1854 1855 <property> 1856 <name>hive.warehouse.subdir.inherit.perms</name> 1857 <value>false</value> 1858 <description>Set this to true if the the table directories should inherit the 1859 permission of the warehouse or database directory instead of being created 1860 with the permissions derived from dfs umask</description> 1861 </property> 1862 1863 <property> 1864 <name>hive.exec.job.debug.capture.stacktraces</name> 1865 <value>true</value> 1866 <description>Whether or not stack traces parsed from the task logs of a sampled failed task for 1867 each failed job should be stored in the SessionState 1868 </description> 1869 </property> 1870 1871 <property> 1872 <name>hive.exec.driver.run.hooks</name> 1873 <value></value> 1874 <description>A comma separated list of hooks which implement HiveDriverRunHook 1875 and will be run at the beginning and end of Driver.run, these will be run in 1876 the order specified. 1877 </description> 1878 </property> 1879 1880 <property> 1881 <name>hive.ddl.output.format</name> 1882 <value>text</value> 1883 <description> 1884 The data format to use for DDL output. One of "text" (for human 1885 readable text) or "json" (for a json object). 1886 </description> 1887 </property> 1888 1889 <property> 1890 <name>hive.display.partition.cols.separately</name> 1891 <value>true</value> 1892 <description> 1893 In older Hive version (0.10 and earlier) no distinction was made between 1894 partition columns or non-partition columns while displaying columns in describe 1895 table. From 0.12 onwards, they are displayed separately. This flag will let you 1896 get old behavior, if desired. See, test-case in patch for HIVE-6689. 1897 </description> 1898 </property> 1899 1900 <property> 1901 <name>hive.transform.escape.input</name> 1902 <value>false</value> 1903 <description> 1904 This adds an option to escape special chars (newlines, carriage returns and 1905 tabs) when they are passed to the user script. This is useful if the Hive tables 1906 can contain data that contains special characters. 1907 </description> 1908 </property> 1909 1910 <property> 1911 <name>hive.exec.rcfile.use.explicit.header</name> 1912 <value>true</value> 1913 <description> 1914 If this is set the header for RCFiles will simply be RCF. If this is not 1915 set the header will be that borrowed from sequence files, e.g. SEQ- followed 1916 by the input and output RCFile formats. 1917 </description> 1918 </property> 1919 1920 <property> 1921 <name>hive.exec.orc.default.stripe.size</name> 1922 <value>268435456</value> 1923 <description> 1924 Define the default ORC stripe size. 1925 </description> 1926 </property> 1927 1928 <property> 1929 <name>hive.exec.orc.default.row.index.stride</name> 1930 <value>10000</value> 1931 <description> 1932 Define the default ORC index stride in number of rows. 1933 </description> 1934 </property> 1935 1936 <property> 1937 <name>hive.exec.orc.default.buffer.size</name> 1938 <value>262144</value> 1939 <description> 1940 Define the default ORC buffer size in bytes. 1941 </description> 1942 </property> 1943 1944 <property> 1945 <name>hive.exec.orc.default.block.padding</name> 1946 <value>true</value> 1947 <description> 1948 Define the default block padding. 1949 </description> 1950 </property> 1951 1952 <property> 1953 <name>hive.exec.orc.default.compress</name> 1954 <value>ZLIB</value> 1955 <description> 1956 Define the default compression codec for ORC file. 1957 </description> 1958 </property> 1959 1960 <property> 1961 <name>hive.exec.orc.dictionary.key.size.threshold</name> 1962 <value>0.8</value> 1963 <description> 1964 If the number of keys in a dictionary is greater than this fraction of the total number of 1965 non-null rows, turn off dictionary encoding. Use 1 to always use dictionary encoding. 1966 </description> 1967 </property> 1968 1969 <property> 1970 <name>hive.exec.orc.skip.corrupt.data</name> 1971 <value>false</value> 1972 <description>If ORC reader encounters corrupt data, this value will be used to determine 1973 whether to skip the corrupt data or throw exception. The default behavior is to throw exception. 1974 </description> 1975 </property> 1976 1977 <property> 1978 <name>hive.multi.insert.move.tasks.share.dependencies</name> 1979 <value>false</value> 1980 <description> 1981 If this is set all move tasks for tables/partitions (not directories) at the end of a 1982 multi-insert query will only begin once the dependencies for all these move tasks have been 1983 met. 1984 Advantages: If concurrency is enabled, the locks will only be released once the query has 1985 finished, so with this config enabled, the time when the table/partition is 1986 generated will be much closer to when the lock on it is released. 1987 Disadvantages: If concurrency is not enabled, with this disabled, the tables/partitions which 1988 are produced by this query and finish earlier will be available for querying 1989 much earlier. Since the locks are only released once the query finishes, this 1990 does not apply if concurrency is enabled. 1991 </description> 1992 </property> 1993 1994 <property> 1995 <name>hive.fetch.task.conversion</name> 1996 <value>minimal</value> 1997 <description> 1998 Some select queries can be converted to single FETCH task minimizing latency. 1999 Currently the query should be single sourced not having any subquery and should not have 2000 any aggregations or distincts (which incurs RS), lateral views and joins. 2001 1. minimal : SELECT STAR, FILTER on partition columns, LIMIT only 2002 2. more : SELECT, FILTER, LIMIT only (TABLESAMPLE, virtual columns) 2003 </description> 2004 </property> 2005 2006 <property> 2007 <name>hive.fetch.task.conversion.threshold</name> 2008 <value>-1</value> 2009 <description> 2010 Input threshold for applying hive.fetch.task.conversion. If target table is native, input length 2011 is calculated by summation of file lengths. If it‘s not native, storage handler for the table 2012 can optionally implement org.apache.hadoop.hive.ql.metadata.InputEstimator interface. 2013 </description> 2014 </property> 2015 2016 <property> 2017 <name>hive.fetch.task.aggr</name> 2018 <value>false</value> 2019 <description> 2020 Aggregation queries with no group-by clause (for example, select count(*) from src) execute 2021 final aggregations in single reduce task. If this is set true, Hive delegates final aggregation 2022 stage to fetch task, possibly decreasing the query time. 2023 </description> 2024 </property> 2025 2026 <property> 2027 <name>hive.cache.expr.evaluation</name> 2028 <value>true</value> 2029 <description> 2030 If true, evaluation result of deterministic expression referenced twice or more will be cached. 2031 For example, in filter condition like ".. where key + 10 > 10 or key + 10 = 0" 2032 "key + 10" will be evaluated/cached once and reused for following expression ("key + 10 = 0"). 2033 Currently, this is applied only to expressions in select or filter operator. 2034 </description> 2035 </property> 2036 2037 2038 <property> 2039 <name>hive.hmshandler.retry.attempts</name> 2040 <value>1</value> 2041 <description>The number of times to retry a HMSHandler call if there were a connection error</description> 2042 </property> 2043 2044 <property> 2045 <name>hive.hmshandler.retry.interval</name> 2046 <value>1000</value> 2047 <description>The number of milliseconds between HMSHandler retry attempts</description> 2048 </property> 2049 2050 <property> 2051 <name>hive.server.read.socket.timeout</name> 2052 <value>10</value> 2053 <description>Timeout for the HiveServer to close the connection if no response from the client in N seconds, defaults to 10 seconds.</description> 2054 </property> 2055 2056 <property> 2057 <name>hive.server.tcp.keepalive</name> 2058 <value>true</value> 2059 <description>Whether to enable TCP keepalive for the Hive Server. Keepalive will prevent accumulation of half-open connections.</description> 2060 </property> 2061 2062 <property> 2063 <name>hive.decode.partition.name</name> 2064 <value>false</value> 2065 <description>Whether to show the unquoted partition names in query results.</description> 2066 </property> 2067 2068 <property> 2069 <name>hive.log4j.file</name> 2070 <value></value> 2071 <description>Hive log4j configuration file. 2072 If the property is not set, then logging will be initialized using hive-log4j.properties found on the classpath. 2073 If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.properties"), which you can then extract a URL from and pass to PropertyConfigurator.configure(URL).</description> 2074 </property> 2075 2076 <property> 2077 <name>hive.exec.log4j.file</name> 2078 <value></value> 2079 <description>Hive log4j configuration file for execution mode(sub command). 2080 If the property is not set, then logging will be initialized using hive-exec-log4j.properties found on the classpath. 2081 If the property is set, the value must be a valid URI (java.net.URI, e.g. "file:///tmp/my-logging.properties"), which you can then extract a URL from and pass to PropertyConfigurator.configure(URL).</description> 2082 </property> 2083 2084 <property> 2085 <name>hive.exec.infer.bucket.sort</name> 2086 <value>false</value> 2087 <description> 2088 If this is set, when writing partitions, the metadata will include the bucketing/sorting 2089 properties with which the data was written if any (this will not overwrite the metadata 2090 inherited from the table if the table is bucketed/sorted) 2091 </description> 2092 </property> 2093 2094 <property> 2095 <name>hive.exec.infer.bucket.sort.num.buckets.power.two</name> 2096 <value>false</value> 2097 <description> 2098 If this is set, when setting the number of reducers for the map reduce task which writes the 2099 final output files, it will choose a number which is a power of two, unless the user specifies 2100 the number of reducers to use using mapred.reduce.tasks. The number of reducers 2101 may be set to a power of two, only to be followed by a merge task meaning preventing 2102 anything from being inferred. 2103 With hive.exec.infer.bucket.sort set to true: 2104 Advantages: If this is not set, the number of buckets for partitions will seem arbitrary, 2105 which means that the number of mappers used for optimized joins, for example, will 2106 be very low. With this set, since the number of buckets used for any partition is 2107 a power of two, the number of mappers used for optimized joins will be the least 2108 number of buckets used by any partition being joined. 2109 Disadvantages: This may mean a much larger or much smaller number of reducers being used in the 2110 final map reduce job, e.g. if a job was originally going to take 257 reducers, 2111 it will now take 512 reducers, similarly if the max number of reducers is 511, 2112 and a job was going to use this many, it will now use 256 reducers. 2113 2114 </description> 2115 </property> 2116 2117 <property> 2118 <name>hive.groupby.orderby.position.alias</name> 2119 <value>false</value> 2120 <description>Whether to enable using Column Position Alias in Group By or Order By</description> 2121 </property> 2122 2123 <property> 2124 <name>hive.server2.thrift.min.worker.threads</name> 2125 <value>5</value> 2126 <description>Minimum number of Thrift worker threads</description> 2127 </property> 2128 2129 <property> 2130 <name>hive.server2.thrift.max.worker.threads</name> 2131 <value>500</value> 2132 <description>Maximum number of Thrift worker threads</description> 2133 </property> 2134 2135 <property> 2136 <name>hive.server2.async.exec.threads</name> 2137 <value>100</value> 2138 <description>Number of threads in the async thread pool for HiveServer2</description> 2139 </property> 2140 2141 <property> 2142 <name>hive.server2.async.exec.shutdown.timeout</name> 2143 <value>10</value> 2144 <description>Time (in seconds) for which HiveServer2 shutdown will wait for async 2145 threads to terminate</description> 2146 </property> 2147 2148 <property> 2149 <name>hive.server2.async.exec.keepalive.time</name> 2150 <value>10</value> 2151 <description>Time (in seconds) that an idle HiveServer2 async thread (from the thread pool) will wait 2152 for a new task to arrive before terminating</description> 2153 </property> 2154 2155 <property> 2156 <name>hive.server2.long.polling.timeout</name> 2157 <value>5000L</value> 2158 <description>Time in milliseconds that HiveServer2 will wait, before responding to asynchronous calls that use long polling</description> 2159 </property> 2160 2161 <property> 2162 <name>hive.server2.async.exec.wait.queue.size</name> 2163 <value>100</value> 2164 <description>Size of the wait queue for async thread pool in HiveServer2. 2165 After hitting this limit, the async thread pool will reject new requests.</description> 2166 </property> 2167 2168 <property> 2169 <name>hive.server2.thrift.port</name> 2170 <value>10000</value> 2171 <description>Port number of HiveServer2 Thrift interface. 2172 Can be overridden by setting $HIVE_SERVER2_THRIFT_PORT</description> 2173 </property> 2174 2175 <property> 2176 <name>hive.server2.thrift.bind.host</name> 2177 <value>localhost</value> 2178 <description>Bind host on which to run the HiveServer2 Thrift interface. 2179 Can be overridden by setting $HIVE_SERVER2_THRIFT_BIND_HOST</description> 2180 </property> 2181 2182 <property> 2183 <name>hive.server2.authentication</name> 2184 <value>NONE</value> 2185 <description> 2186 Client authentication types. 2187 NONE: no authentication check 2188 LDAP: LDAP/AD based authentication 2189 KERBEROS: Kerberos/GSSAPI authentication 2190 CUSTOM: Custom authentication provider 2191 (Use with property hive.server2.custom.authentication.class) 2192 PAM: Pluggable authentication module. 2193 </description> 2194 </property> 2195 2196 <property> 2197 <name>hive.server2.custom.authentication.class</name> 2198 <value></value> 2199 <description> 2200 Custom authentication class. Used when property 2201 ‘hive.server2.authentication‘ is set to ‘CUSTOM‘. Provided class 2202 must be a proper implementation of the interface 2203 org.apache.hive.service.auth.PasswdAuthenticationProvider. HiveServer2 2204 will call its Authenticate(user, passed) method to authenticate requests. 2205 The implementation may optionally extend Hadoop‘s 2206 org.apache.hadoop.conf.Configured class to grab Hive‘s Configuration object. 2207 </description> 2208 </property> 2209 2210 <property> 2211 <name>hive.server2.authentication.kerberos.principal</name> 2212 <value></value> 2213 <description> 2214 Kerberos server principal 2215 </description> 2216 </property> 2217 2218 <property> 2219 <name>hive.server2.authentication.kerberos.keytab</name> 2220 <value></value> 2221 <description> 2222 Kerberos keytab file for server principal 2223 </description> 2224 </property> 2225 2226 <property> 2227 <name>hive.server2.authentication.spnego.principal</name> 2228 <value></value> 2229 <description> 2230 SPNego service principal, optional, 2231 typical value would look like HTTP/_HOST@EXAMPLE.COM 2232 SPNego service principal would be used by hiveserver2 when kerberos security is enabled 2233 and HTTP transport mode is used. 2234 This needs to be set only if SPNEGO is to be used in authentication. 2235 </description> 2236 </property> 2237 2238 <property> 2239 <name>hive.server2.authentication.spnego.keytab</name> 2240 <value></value> 2241 <description> 2242 keytab file for SPNego principal, optional, 2243 typical value would look like /etc/security/keytabs/spnego.service.keytab, 2244 This keytab would be used by hiveserver2 when kerberos security is enabled 2245 and HTTP transport mode is used. 2246 This needs to be set only if SPNEGO is to be used in authentication. 2247 SPNego authentication would be honored only if valid 2248 hive.server2.authentication.spnego.principal 2249 and 2250 hive.server2.authentication.spnego.keytab 2251 are specified. 2252 </description> 2253 </property> 2254 2255 <property> 2256 <name>hive.server2.authentication.ldap.url</name> 2257 <value></value> 2258 <description> 2259 LDAP connection URL. 2260 </description> 2261 </property> 2262 2263 <property> 2264 <name>hive.server2.authentication.ldap.baseDN</name> 2265 <value></value> 2266 <description> 2267 LDAP base DN (distinguished name). 2268 </description> 2269 </property> 2270 2271 <property> 2272 <name>hive.server2.authentication.ldap.Domain</name> 2273 <value></value> 2274 <description> 2275 LDAP domain. 2276 </description> 2277 </property> 2278 2279 <property> 2280 <name>hive.server2.enable.doAs</name> 2281 <value>true</value> 2282 <description> 2283 Setting this property to true will have HiveServer2 execute 2284 Hive operations as the user making the calls to it. 2285 </description> 2286 </property> 2287 2288 <property> 2289 <name>hive.execution.engine</name> 2290 <value>mr</value> 2291 <description> 2292 Chooses execution engine. Options are mr (MapReduce, default) or Tez (Hadoop 2 only). 2293 </description> 2294 </property> 2295 2296 <property> 2297 <name>hive.prewarm.enabled</name> 2298 <value>false</value> 2299 <description> 2300 Enables container prewarm for Tez (Hadoop 2 only). 2301 </description> 2302 </property> 2303 2304 <property> 2305 <name>hive.prewarm.numcontainers</name> 2306 <value>10</value> 2307 <description> 2308 Controls the number of containers to prewarm for Tez (Hadoop 2 only). 2309 </description> 2310 </property> 2311 2312 <property> 2313 <name>hive.server2.table.type.mapping</name> 2314 <value>CLASSIC</value> 2315 <description> 2316 This setting reflects how HiveServer2 will report the table types for JDBC and other 2317 client implementations that retrieve the available tables and supported table types 2318 HIVE : Exposes Hive‘s native table types like MANAGED_TABLE, EXTERNAL_TABLE, VIRTUAL_VIEW 2319 CLASSIC : More generic types like TABLE and VIEW 2320 </description> 2321 </property> 2322 2323 <property> 2324 <name>hive.server2.session.hook</name> 2325 <value></value> 2326 <description> 2327 Session-level hook for HiveServer2. 2328 </description> 2329 </property> 2330 2331 <property> 2332 <name>hive.server2.thrift.sasl.qop</name> 2333 <value>auth</value> 2334 <description>Sasl QOP value; set it to one of the following values to enable higher levels of 2335 protection for HiveServer2 communication with clients. 2336 "auth" - authentication only (default) 2337 "auth-int" - authentication plus integrity protection 2338 "auth-conf" - authentication plus integrity and confidentiality protection 2339 Note that hadoop.rpc.protection being set to a higher level than HiveServer2 does not 2340 make sense in most situations. HiveServer2 ignores hadoop.rpc.protection in favor of 2341 hive.server2.thrift.sasl.qop. 2342 This is applicable only if HiveServer2 is configured to use Kerberos authentication. 2343 </description> 2344 </property> 2345 2346 <property> 2347 <name>hive.plan.serialization.format</name> 2348 <value>kryo</value> 2349 <description> 2350 Query plan format serialization between client and task nodes. 2351 Two supported values are : kryo and javaXML. Kryo is default. 2352 </description> 2353 </property> 2354 2355 <property> 2356 <name>hive.vectorized.execution.enabled</name> 2357 <value>false</value> 2358 <description> 2359 This flag should be set to true to enable vectorized mode of query execution. 2360 The default value is false. 2361 </description> 2362 </property> 2363 2364 <property> 2365 <name>hive.vectorized.groupby.maxentries</name> 2366 <value>1000000</value> 2367 <description>Max number of entries in the vector group by aggregation hashtables. Exceeding this will trigger a flush irrelevant of memory pressure condition.</description> 2368 </property> 2369 2370 <property> 2371 <name>hive.vectorized.groupby.checkinterval</name> 2372 <value>100000</value> 2373 <description>Number of entries added to the group by aggregation hash before a reocmputation of average entry size is performed.</description> 2374 </property> 2375 2376 <property> 2377 <name>hive.vectorized.groupby.flush.percent</name> 2378 <value>0.1</value> 2379 <description>Percent of entries in the group by aggregation hash flushed when the memory treshold is exceeded.</description> 2380 </property> 2381 2382 <property> 2383 <name>hive.compute.query.using.stats</name> 2384 <value>false</value> 2385 <description> 2386 When set to true Hive will answer a few queries like count(1) purely using stats 2387 stored in metastore. For basic stats collection turn on the config hive.stats.autogather to true. 2388 For more advanced stats collection need to run analyze table queries. 2389 </description> 2390 </property> 2391 2392 <property> 2393 <name>hive.metastore.schema.verification</name> 2394 <value>false</value> 2395 <description> 2396 Enforce metastore schema version consistency. 2397 True: Verify that version information stored in metastore matches with one from Hive jars. Also disable automatic 2398 schema migration attempt. Users are required to manually migrate schema after Hive upgrade which ensures 2399 proper metastore schema migration. (Default) 2400 False: Warn if the version information stored in metastore doesn‘t match with one from in Hive jars. 2401 </description> 2402 </property> 2403 2404 <property> 2405 <name>hive.metastore.integral.jdo.pushdown</name> 2406 <value>false</value> 2407 <description> 2408 Allow JDO query pushdown for integral partition columns in the metastore. Off by default. 2409 This improves metastore performance for integral columns, especially with a large number of 2410 partitions. However, it doesn‘t work correctly for integral values that are not normalized 2411 (for example, if they have leading zeroes like 0012). If metastore direct SQL is enabled and 2412 works (hive.metastore.try.direct.sql), this optimization is also irrelevant. 2413 </description> 2414 </property> 2415 2416 <property> 2417 <name>hive.orc.splits.include.file.footer</name> 2418 <value>false</value> 2419 <description> 2420 If turned on splits generated by orc will include metadata about the stripes in the file. This 2421 data is read remotely (from the client or HS2 machine) and sent to all the tasks. 2422 </description> 2423 </property> 2424 2425 <property> 2426 <name>hive.orc.cache.stripe.details.size</name> 2427 <value>10000</value> 2428 <description> 2429 Cache size for keeping meta info about orc splits cached in the client. 2430 </description> 2431 </property> 2432 2433 <property> 2434 <name>hive.orc.compute.splits.num.threads</name> 2435 <value>10</value> 2436 <description> 2437 How many threads orc should use to create splits in parallel. 2438 </description> 2439 </property> 2440 2441 <property> 2442 <name>hive.stats.gather.num.threads</name> 2443 <value>10</value> 2444 <description> 2445 Number of threads used by partialscan/noscan analyze command for partitioned tables. 2446 This is applicable only for file formats that implement StatsProvidingRecordReader (like ORC). 2447 </description> 2448 </property> 2449 2450 <property> 2451 <name>hive.exec.orc.zerocopy</name>. 2452 <value>false</value> 2453 <description> 2454 Use zerocopy reads with ORC. 2455 </description> 2456 </property> 2457 2458 <property> 2459 <name>hive.jar.directory</name> 2460 <value></value> 2461 <description> 2462 This is the location Hive in Tez mode will look for to find a site wide 2463 installed Hive instance. If not set, the directory under hive.user.install.directory 2464 corresponding to current user name will be used. 2465 </description> 2466 </property> 2467 2468 <property> 2469 <name>hive.user.install.directory</name> 2470 <value>hdfs:///user/</value> 2471 <description> 2472 If Hive (in Tez mode only) cannot find a usable Hive jar in "hive.jar.directory", 2473 it will upload the Hive jar to <hive.user.install.directory>/<user name> 2474 and use it to run queries. 2475 </description> 2476 </property> 2477 2478 <property> 2479 <name>hive.tez.container.size</name> 2480 <value>-1</value> 2481 <description>By default Tez will spawn containers of the size of a mapper. This can be used to overwrite.</description> 2482 </property> 2483 2484 <property> 2485 <name>hive.tez.java.opts</name> 2486 <value></value> 2487 <description>By default Tez will use the Java options from map tasks. This can be used to overwrite.</description> 2488 </property> 2489 2490 <property> 2491 <name>hive.tez.log.level</name> 2492 <value>INFO</value> 2493 <description> 2494 The log level to use for tasks executing as part of the DAG. 2495 Used only if hive.tez.java.opts is used to configure Java options. 2496 </description> 2497 </property> 2498 2499 <property> 2500 <name>hive.server2.tez.default.queues</name> 2501 <value></value> 2502 <description> 2503 A list of comma separated values corresponding to YARN queues of the same name. 2504 When HiveServer2 is launched in Tez mode, this configuration needs to be set 2505 for multiple Tez sessions to run in parallel on the cluster. 2506 </description> 2507 </property> 2508 2509 <property> 2510 <name>hive.server2.tez.sessions.per.default.queue</name> 2511 <value>1</value> 2512 <description> 2513 A positive integer that determines the number of Tez sessions that should be 2514 launched on each of the queues specified by "hive.server2.tez.default.queues". 2515 Determines the parallelism on each queue. 2516 </description> 2517 </property> 2518 2519 <property> 2520 <name>hive.server2.tez.initialize.default.sessions</name> 2521 <value>false</value> 2522 <description> 2523 This flag is used in HiveServer2 to enable a user to use HiveServer2 without 2524 turning on Tez for HiveServer2. The user could potentially want to run queries 2525 over Tez without the pool of sessions. 2526 </description> 2527 </property> 2528 2529 <property> 2530 <name>hive.server2.allow.user.substitution</name> 2531 <value>true</value> 2532 <description> 2533 Allow alternate user to be specified as part of HiveServer2 open connection request 2534 </description> 2535 </property> 2536 2537 <property> 2538 <name>hive.resultset.use.unique.column.names</name> 2539 <value>true</value> 2540 <description> 2541 Make column names unique in the result set by qualifying column names with table alias if needed. 2542 Table alias will be added to column names for queries of type "select *" or 2543 if query explicitly uses table alias "select r1.x..". 2544 </description> 2545 </property> 2546 2547 <property> 2548 <name>hive.compat</name> 2549 <value>0.12</value> 2550 <description> 2551 Enable (configurable) deprecated behaviors by setting desired level of backward compatbility 2552 </description> 2553 </property> 2554 2555 <property> 2556 <name>hive.metastore.try.direct.sql</name> 2557 <value>true</value> 2558 <description> 2559 Whether Hive metastore should try to use direct SQL queries instead of DataNucleus for certain 2560 read paths. Can improve metastore performance when fetching many partitions or column stats by 2561 orders of magnitude; however, is not guaranteed to work on all RDBMS-es and all versions. In case 2562 of SQL failures, metastore will fall back to DataNucleus, so it‘s safe even if SQL doesn‘t work 2563 for all queries on your datastore. If all SQL queries fail (e.g. your metastore is backed by 2564 MongoDB), you might want to disable this to save the try-and-fall-back cost. 2565 </description> 2566 </property> 2567 2568 <property> 2569 <name>hive.metastore.try.direct.sql.ddl</name> 2570 <value>true</value> 2571 <description> 2572 Same as hive.metastore.try.direct.sql, for read statements within a transaction that modifies 2573 metastore data. Due to non-standard behavior in Postgres, if direct SQL select query has 2574 incorrect syntax or something inside a transaction, entire transaction will fail and fall-back to 2575 DataNucleus will not be possible. You should disable the usage of direct SQL inside transactions 2576 if that happens in your case. 2577 </description> 2578 </property> 2579 2580 <property> 2581 <name>hive.mapjoin.optimized.keys</name> 2582 <value>true</value> 2583 <description> 2584 Whether MapJoin hashtable should use optimized (size-wise), keys, allowing the table to take less 2585 memory. Depending on key, the memory savings for entire table can be 5-15% or so. 2586 </description> 2587 </property> 2588 2589 <property> 2590 <name>hive.mapjoin.lazy.hashtable</name> 2591 <value>true</value> 2592 <description> 2593 Whether MapJoin hashtable should deserialize values on demand. Depending on how many values in 2594 the table the join will actually touch, it can save a lot of memory by not creating objects for 2595 rows that are not needed. If all rows are needed obviously there‘s no gain. 2596 </description> 2597 </property> 2598 2599 <property> 2600 <name>hive.exec.check.crossproducts</name> 2601 <value>true</value> 2602 <description> 2603 Check if a plan contains a Cross Product. If there is one, output a warning to the Session‘s console. 2604 </description> 2605 </property> 2606 2607 <property> 2608 <name>hive.localize.resource.wait.interval</name> 2609 <value>5000</value> 2610 <description> 2611 Time in milliseconds to wait for another thread to localize the same resource for hive-tez. 2612 </description> 2613 </property> 2614 2615 <property> 2616 <name>hive.localize.resource.num.wait.attempts</name> 2617 <value>5</value> 2618 <description> 2619 The number of attempts waiting for localizing a resource in hive-tez. 2620 </description> 2621 </property> 2622 2623 <property> 2624 <name>hive.server2.use.SSL</name> 2625 <value>false</value> 2626 <description>Set this to true for using SSL encryption in HiveServer2</description> 2627 </property> 2628 2629 <property> 2630 <name>hive.server2.keystore.path</name> 2631 <value></value> 2632 <description>SSL certificate keystore location</description> 2633 </property> 2634 2635 <property> 2636 <name>hive.server2.keystore.password</name> 2637 <value></value> 2638 <description>SSL certificate keystore password.</description> 2639 </property> 2640 2641 <property> 2642 <name>hive.server2.authentication.pam.services</name> 2643 <value></value> 2644 <description>List of the underlying PAM services that should be used when authentication 2645 type is PAM (hive.server2.authentication). A file with the same name must exist in 2646 /etc/pam.d</description> 2647 </property> 2648 2649 <property> 2650 <name>hive.convert.join.bucket.mapjoin.tez</name> 2651 <value>false</value> 2652 <description>Whether joins can be automatically converted to bucket map 2653 joins in hive when tez is used as the execution engine. 2654 </description> 2655 </property> 2656 2657 <property> 2658 <name>hive.serdes.using.metastore.for.schema</name> 2659 <value>org.apache.hadoop.hive.ql.io.orc.OrcSerde,org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe,org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe,org.apache.hadoop.hive.serde2.dynamic_type.DynamicSerDe,org.apache.hadoop.hive.serde2.MetadataTypedColumnsetSerDe,org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe,org.apache.hadoop.hive.ql.io.parquet.serde.ParquetHiveSerDe,org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe</value> 2660 <description>This an internal parameter. Check with the hive dev. team</description> 2661 </property> 2662 2663 <property> 2664 <name>hive.limit.query.max.table.partition</name> 2665 <value>-1</value> 2666 <description>This controls how many partitions can be scanned for each partitioned table. The default value "-1" means no limit.</description> 2667 </property> 2668 2669 <property> 2670 <name>hive.txn.manager</name> 2671 <value>org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager</value> 2672 <description></description> 2673 </property> 2674 2675 <property> 2676 <name>hive.txn.timeout</name> 2677 <value>300</value> 2678 <description>time after which transactions are declared aborted if the client has 2679 not sent a heartbeat, in seconds.</description> 2680 </property> 2681 2682 <property> 2683 <name>hive.txn.max.open.batch</name> 2684 <value>1000</value> 2685 <description>Maximum number of transactions that can be fetched in one call to open_txns(). 2686 Increasing this will decrease the number of delta files created when 2687 streaming data into Hive. But it will also increase the number of 2688 open transactions at any given time, possibly impacting read 2689 performance. 2690 </description> 2691 </property> 2692 2693 <property> 2694 <name>hive.compactor.initiator.on</name> 2695 <value>false</value> 2696 <description>Whether to run the compactor‘s initiator thread in this metastore instance or not.</description> 2697 </property> 2698 2699 <property> 2700 <name>hive.compactor.worker.threads</name> 2701 <value>0</value> 2702 <description>Number of compactor worker threads to run on this metastore instance.</description> 2703 </property> 2704 2705 <property> 2706 <name>hive.compactor.worker.timeout</name> 2707 <value>86400</value> 2708 <description>Time, in seconds, before a given compaction in working state is declared a failure and returned to the initiated state.</description> 2709 </property> 2710 2711 <property> 2712 <name>hive.compactor.check.interval</name> 2713 <value>300</value> 2714 <description>Time in seconds between checks to see if any partitions need compacted. 2715 This should be kept high because each check for compaction requires many calls against the NameNode.</description> 2716 </property> 2717 2718 <property> 2719 <name>hive.compactor.delta.num.threshold</name> 2720 <value>10</value> 2721 <description>Number of delta files that must exist in a directory before the compactor will attempt a minor compaction.</description> 2722 </property> 2723 2724 <property> 2725 <name>hive.compactor.delta.pct.threshold</name> 2726 <value>0.1</value> 2727 <description>Percentage (by size) of base that deltas can be before major compaction is initiated.</description> 2728 </property> 2729 2730 <property> 2731 <name>hive.compactor.abortedtxn.threshold</name> 2732 <value>1000</value> 2733 <description>Number of aborted transactions involving a particular table or partition before major compaction is initiated.</description> 2734 </property> 2735 2736 </configuration>
标签：
原文地址：http://www.cnblogs.com/wq920/p/4287823.html
