大数据工具篇之Hive与HBase整合完整教程

 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.exec.scratchdir</name>  75 <value>/tmp/hive-${user.name}</value>  76 <description>Scratch space for Hive jobs</description>  77 </property>  78  79 <property>  80 <name>hive.exec.local.scratchdir</name>  81 <value>/tmp/${user.name}</value>  82 <description>Local scratch space for Hive jobs</description>  83 </property>  84  85 <property>  86 <name>hive.test.mode</name>  87 <value>false</value>  88 <description>whether hive is running in test mode. If yes, it turns on sampling and prefixes the output tablename</description>  89 </property>  90  91 <property>  92 <name>hive.test.mode.prefix</name>  93 <value>test_</value>  94 <description>if hive is running in test mode, prefixes the output table by this string</description>  95 </property>  96  97 <!-- If the input table is not bucketed, the denominator of the tablesample is determinied by the parameter below -->  98 <!-- For example, the following query: -->  99 <!-- INSERT OVERWRITE TABLE dest -->  100 <!-- SELECT col1 from src -->  101 <!-- would be converted to -->  102 <!-- INSERT OVERWRITE TABLE test_dest -->  103 <!-- SELECT col1 from src TABLESAMPLE (BUCKET 1 out of 32 on rand(1)) -->  104 <property>  105 <name>hive.test.mode.samplefreq</name>  106 <value>32</value>  107 <description>if hive is running in test mode and table is not bucketed, sampling frequency</description>  108 </property>  109  110 <property>  111 <name>hive.test.mode.nosamplelist</name>  112 <value></value>  113 <description>if hive is running in test mode, dont sample the above comma seperated list of tables</description>  114 </property>  115  116 <property>  117 <name>hive.metastore.uris</name>  118 <value></value>  119 <description>Thrift uri for the remote metastore. Used by metastore client to connect to remote metastore.</description>  120 </property>  121  122 <property>  123 <name>javax.jdo.option.ConnectionURL</name>  124 <value>jdbc:derby:;databaseName=metastore_db;create=true</value>  125 <description>JDBC connect string for a JDBC metastore</description>  126 </property>  127  128 <property>  129 <name>javax.jdo.option.ConnectionDriverName</name>  130 <value>org.apache.derby.jdbc.EmbeddedDriver</value>  131 <description>Driver class name for a JDBC metastore</description>  132 </property>  133  134 <property>  135 <name>javax.jdo.PersistenceManagerFactoryClass</name>  136 <value>org.datanucleus.jdo.JDOPersistenceManagerFactory</value>  137 <description>class implementing the jdo persistence</description>  138 </property>  139  140 <property>  141 <name>javax.jdo.option.DetachAllOnCommit</name>  142 <value>true</value>  143 <description>detaches all objects from session so that they can be used after transaction is committed</description>  144 </property>  145  146 <property>  147 <name>javax.jdo.option.NonTransactionalRead</name>  148 <value>true</value>  149 <description>reads outside of transactions</description>  150 </property>  151  152 <property>  153 <name>javax.jdo.option.ConnectionUserName</name>  154 <value>APP</value>  155 <description>username to use against metastore database</description>  156 </property>  157  158 <property>  159 <name>javax.jdo.option.ConnectionPassword</name>  160 <value>mine</value>  161 <description>password to use against metastore database</description>  162 </property>  163  164 <property>  165 <name>javax.jdo.option.Multithreaded</name>  166 <value>true</value>  167 <description>Set this to true if multiple threads access metastore through JDO concurrently.</description>  168 </property>  169  170 <property>  171 <name>datanucleus.connectionPoolingType</name>  172 <value>DBCP</value>  173 <description>Uses a DBCP connection pool for JDBC metastore</description>  174 </property>  175  176 <property>  177 <name>datanucleus.validateTables</name>  178 <value>false</value>  179 <description>validates existing schema against code. turn this on if you want to verify existing schema </description>  180 </property>  181  182 <property>  183 <name>datanucleus.validateColumns</name>  184 <value>false</value>  185 <description>validates existing schema against code. turn this on if you want to verify existing schema </description>  186 </property>  187  188 <property>  189 <name>datanucleus.validateConstraints</name>  190 <value>false</value>  191 <description>validates existing schema against code. turn this on if you want to verify existing schema </description>  192 </property>  193  194 <property>  195 <name>datanucleus.storeManagerType</name>  196 <value>rdbms</value>  197 <description>metadata store type</description>  198 </property>  199  200 <property>  201 <name>datanucleus.autoCreateSchema</name>  202 <value>true</value>  203 <description>creates necessary schema on a startup if one doesn't exist. set this to false, after creating it once</description>  204 </property>  205  206 <property>  207 <name>datanucleus.autoStartMechanismMode</name>  208 <value>checked</value>  209 <description>throw exception if metadata tables are incorrect</description>  210 </property>  211  212 <property>  213 <name>datanucleus.transactionIsolation</name>  214 <value>read-committed</value>  215 <description>Default transaction isolation level for identity generation. </description>  216 </property>  217  218 <property>  219 <name>datanucleus.cache.level2</name>  220 <value>false</value>  221 <description>Use a level 2 cache. Turn this off if metadata is changed independently of hive metastore server</description>  222 </property>  223  224 <property>  225 <name>datanucleus.cache.level2.type</name>  226 <value>SOFT</value>  227 <description>SOFT=soft reference based cache, WEAK=weak reference based cache.</description>  228 </property>  229  230 <property>  231 <name>datanucleus.identifierFactory</name>  232 <value>datanucleus</value>  233 <description>Name of the identifier factory to use when generating table/column names etc. 'datanucleus' is used for backward compatibility</description>  234 </property>  235  236 <property>  237 <name>datanucleus.plugin.pluginRegistryBundleCheck</name>  238 <value>LOG</value>  239 <description>Defines what happens when plugin bundles are found and are duplicated [EXCEPTION|LOG|NONE]</description>  240 </property>  241  242 <property>  243 <name>hive.metastore.warehouse.dir</name>  244 <value>/user/hive/warehouse</value>  245 <description>location of default database for the warehouse</description>  246 </property>  247  248 <property>  249 <name>hive.metastore.execute.setugi</name>  250 <value>false</value>  251 <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>  252 </property>  253  254 <property>  255 <name>hive.metastore.event.listeners</name>  256 <value></value>  257 <description>list of comma seperated listeners for metastore events.</description>  258 </property>  259  260 <property>  261 <name>hive.metastore.partition.inherit.table.properties</name>  262 <value></value>  263 <description>list of comma seperated keys occurring in table properties which will get inherited to newly created partitions. * implies all the keys will get inherited.</description>  264 </property>  265  266 <property>  267 <name>hive.metadata.export.location</name>  268 <value></value>  269 <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>  270 </property>  271  272 <property>  273 <name>hive.metadata.move.exported.metadata.to.trash</name>  274 <value></value>  275 <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>  276 </property>  277  278 <property>  279 <name>hive.metastore.partition.name.whitelist.pattern</name>  280 <value></value>  281 <description>Partition names will be checked against this regex pattern and rejected if not matched. To use, enable hive.metastore.pre.event.listeners=org.apache.hadoop.hive.metastore.PartitionNameWhitelistPreEventListener Listener will not register if this property value is empty.</description>  282 </property>  283  284 <property>  285 <name>hive.metastore.end.function.listeners</name>  286 <value></value>  287 <description>list of comma separated listeners for the end of metastore functions.</description>  288 </property>  289  290 <property>  291 <name>hive.metastore.event.expiry.duration</name>  292 <value>0</value>  293 <description>Duration after which events expire from events table (in seconds)</description>  294 </property>  295  296 <property>  297 <name>hive.metastore.event.clean.freq</name>  298 <value>0</value>  299 <description>Frequency at which timer task runs to purge expired events in metastore(in seconds).</description>  300 </property>  301  302 <property>  303 <name>hive.metastore.connect.retries</name>  304 <value>5</value>  305 <description>Number of retries while opening a connection to metastore</description>  306 </property>  307  308 <property>  309 <name>hive.metastore.failure.retries</name>  310 <value>3</value>  311 <description>Number of retries upon failure of Thrift metastore calls</description>  312 </property>  313  314 <property>  315 <name>hive.metastore.client.connect.retry.delay</name>  316 <value>1</value>  317 <description>Number of seconds for the client to wait between consecutive connection attempts</description>  318 </property>  319  320 <property>  321 <name>hive.metastore.client.socket.timeout</name>  322 <value>20</value>  323 <description>MetaStore Client socket timeout in seconds</description>  324 </property>  325  326 <property>  327 <name>hive.metastore.rawstore.impl</name>  328 <value>org.apache.hadoop.hive.metastore.ObjectStore</value>  329 <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>  330 </property>  331  332 <property>  333 <name>hive.metastore.batch.retrieve.max</name>  334 <value>300</value>  335 <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>  336 </property>  337  338 <property>  339 <name>hive.metastore.batch.retrieve.table.partition.max</name>  340 <value>1000</value>  341 <description>Maximum number of table partitions that metastore internally retrieves in one batch.</description>  342 </property>  343  344 <property>  345 <name>hive.default.fileformat</name>  346 <value>TextFile</value>  347 <description>Default file format for CREATE TABLE statement. Options are TextFile and SequenceFile. Users can explicitly say CREATE TABLE ... STORED AS &lt;TEXTFILE|SEQUENCEFILE&gt; to override</description>  348 </property>  349  350 <property>  351 <name>hive.fileformat.check</name>  352 <value>true</value>  353 <description>Whether to check file format or not when loading data files</description>  354 </property>  355  356 <property>  357 <name>hive.map.aggr</name>  358 <value>true</value>  359 <description>Whether to use map-side aggregation in Hive Group By queries</description>  360 </property>  361  362 <property>  363 <name>hive.groupby.skewindata</name>  364 <value>false</value>  365 <description>Whether there is skew in data to optimize group by queries</description>  366 </property>  367  368 <property>  369 <name>hive.groupby.mapaggr.checkinterval</name>  370 <value>100000</value>  371 <description>Number of rows after which size of the grouping keys/aggregation classes is performed</description>  372 </property>  373  374 <property>  375 <name>hive.mapred.local.mem</name>  376 <value>0</value>  377 <description>For local mode, memory of the mappers/reducers</description>  378 </property>  379  380 <property>  381 <name>hive.mapjoin.followby.map.aggr.hash.percentmemory</name>  382 <value>0.3</value>  383 <description>Portion of total memory to be used by map-side grup aggregation hash table, when this group by is followed by map join</description>  384 </property>  385  386 <property>  387 <name>hive.map.aggr.hash.force.flush.memory.threshold</name>  388 <value>0.9</value>  389 <description>The max memory to be used by map-side grup aggregation hash table, if the memory usage is higher than this number, force to flush data</description>  390 </property>  391  392 <property>  393 <name>hive.map.aggr.hash.percentmemory</name>  394 <value>0.5</value>  395 <description>Portion of total memory to be used by map-side grup aggregation hash table</description>  396 </property>  397  398 <property>  399 <name>hive.map.aggr.hash.min.reduction</name>  400 <value>0.5</value>  401 <description>Hash aggregation will be turned off if the ratio between hash  402  table size and input rows is bigger than this number. Set to 1 to make sure  403 hash aggregation is never turned off.</description>  404 </property>  405  406 <property>  407 <name>hive.optimize.cp</name>  408 <value>true</value>  409 <description>Whether to enable column pruner</description>  410 </property>  411  412 <property>  413 <name>hive.optimize.index.filter</name>  414 <value>false</value>  415 <description>Whether to enable automatic use of indexes</description>  416 </property>  417  418 <property>  419 <name>hive.optimize.index.groupby</name>  420 <value>false</value>  421 <description>Whether to enable optimization of group-by queries using Aggregate indexes.</description>  422 </property>  423  424 <property>  425 <name>hive.optimize.ppd</name>  426 <value>true</value>  427 <description>Whether to enable predicate pushdown</description>  428 </property>  429  430 <property>  431 <name>hive.optimize.ppd.storage</name>  432 <value>true</value>  433 <description>Whether to push predicates down into storage handlers. Ignored when hive.optimize.ppd is false.</description>  434 </property>  435  436 <property>  437 <name>hive.ppd.recognizetransivity</name>  438 <value>true</value>  439 <description>Whether to transitively replicate predicate filters over equijoin conditions.</description>  440 </property>  441  442 <property>  443 <name>hive.optimize.groupby</name>  444 <value>true</value>  445 <description>Whether to enable the bucketed group by from bucketed partitions/tables.</description>  446 </property>  447  448 <property>  449 <name>hive.optimize.skewjoin.compiletime</name>  450 <value>false</value>  451 <description>Whether to create a separate plan for skewed keys for the tables in the join.  452  This is based on the skewed keys stored in the metadata. At compile time, the plan is broken  453  into different joins: one for the skewed keys, and the other for the remaining keys. And then,  454  a union is performed for the 2 joins generated above. So unless the same skewed key is present  455  in both the joined tables, the join for the skewed key will be performed as a map-side join.  456  457  The main difference between this paramater and hive.optimize.skewjoin is that this parameter  458  uses the skew information stored in the metastore to optimize the plan at compile time itself.  459  If there is no skew information in the metadata, this parameter will not have any affect.  460  Both hive.optimize.skewjoin.compiletime and hive.optimize.skewjoin should be set to true.  461  Ideally, hive.optimize.skewjoin should be renamed as hive.optimize.skewjoin.runtime, but not doing  462  so for backward compatibility.  463  464  If the skew information is correctly stored in the metadata, hive.optimize.skewjoin.compiletime  465  would change the query plan to take care of it, and hive.optimize.skewjoin will be a no-op.  466 </description>  467 </property>  468  469 <property>  470 <name>hive.optimize.union.remove</name>  471 <value>false</value>  472 <description>  473  Whether to remove the union and push the operators between union and the filesink above  474  union. This avoids an extra scan of the output by union. This is independently useful for union  475  queries, and specially useful when hive.optimize.skewjoin.compiletime is set to true, since an  476  extra union is inserted.  477  478  The merge is triggered if either of hive.merge.mapfiles or hive.merge.mapredfiles is set to true.  479  If the user has set hive.merge.mapfiles to true and hive.merge.mapredfiles to false, the idea was the  480  number of reducers are few, so the number of files anyway are small. However, with this optimization,  481  we are increasing the number of files possibly by a big margin. So, we merge aggresively.  482 </description>  483 </property>  484  485 <property>  486 <name>hive.mapred.supports.subdirectories</name>  487 <value>false</value>  488 <description>Whether the version of hadoop which is running supports sub-directories for tables/partitions.  489  Many hive optimizations can be applied if the hadoop version supports sub-directories for  490  tables/partitions. It was added by MAPREDUCE-1501  491 </description>  492 </property>  493  494 <property>  495 <name>hive.multigroupby.singlemr</name>  496 <value>false</value>  497 <description>Whether to optimize multi group by query to generate single M/R  498  job plan. If the multi group by query has common group by keys, it will be  499 optimized to generate single M/R job.</description>  500 </property>  501  502 <property>  503 <name>hive.map.groupby.sorted</name>  504 <value>false</value>  505 <description>If the bucketing/sorting properties of the table exactly match the grouping key, whether to  506  perform the group by in the mapper by using BucketizedHiveInputFormat. The only downside to this  507  is that it limits the number of mappers to the number of files.  508 </description>  509 </property>  510  511 <property>  512 <name>hive.join.emit.interval</name>  513 <value>1000</value>  514 <description>How many rows in the right-most join operand Hive should buffer before emitting the join result. </description>  515 </property>  516  517 <property>  518 <name>hive.join.cache.size</name>  519 <value>25000</value>  520 <description>How many rows in the joining tables (except the streaming table) should be cached in memory. </description>  521 </property>  522  523 <property>  524 <name>hive.mapjoin.bucket.cache.size</name>  525 <value>100</value>  526 <description>How many values in each keys in the map-joined table should be cached in memory. </description>  527 </property>  528  529 <property>  530 <name>hive.mapjoin.cache.numrows</name>  531 <value>25000</value>  532 <description>How many rows should be cached by jdbm for map join. </description>  533 </property>  534  535 <property>  536 <name>hive.optimize.skewjoin</name>  537 <value>false</value>  538 <description>Whether to enable skew join optimization.  539  The algorithm is as follows: At runtime, detect the keys with a large skew. Instead of  540  processing those keys, store them temporarily in a hdfs directory. In a follow-up map-reduce  541  job, process those skewed keys. The same key need not be skewed for all the tables, and so,  542  the follow-up map-reduce job (for the skewed keys) would be much faster, since it would be a  543  map-join.  544 </description>  545 </property>  546  547 <property>  548 <name>hive.exec.list.bucketing.default.dir</name>  549 <value>HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME</value>  550 <description>Default directory name used in list bucketing.  551  List bucketing feature will create sub-directory for each skewed-value and a default directory  552  for non-skewed value. This config specifies the default name for the default directory.  553  Sub-directory is created by list bucketing DML and under partition directory. User doesn't need  554  to know how to construct the canonical path. It just gives user choice if they want to change  555  the default directory name.  556  For example, there are 2 skewed column c1 and c2. 2 skewed value: (1,a) and (2,b). subdirectory:  557 <partition-dir>/c1=1/c2=a/</partition-dir>  558 <partition-dir>/c1=2/c2=b/</partition-dir>  559 <partition-dir>/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME/</partition-dir>  560  Note: This config won't impact users if they don't list bucketing.  561 </description>  562 </property>  563  564 <property>  565 <name>hive.skewjoin.key</name>  566 <value>100000</value>  567 <description>Determine if we get a skew key in join. If we see more  568  than the specified number of rows with the same key in join operator,  569 we think the key as a skew join key. </description>  570 </property>  571  572 <property>  573 <name>hive.skewjoin.mapjoin.map.tasks</name>  574 <value>10000</value>  575 <description> Determine the number of map task used in the follow up map join job  576  for a skew join. It should be used together with hive.skewjoin.mapjoin.min.split  577 to perform a fine grained control.</description>  578 </property>  579  580 <property>  581 <name>hive.skewjoin.mapjoin.min.split</name>  582 <value>33554432</value>  583 <description> Determine the number of map task at most used in the follow up map join job  584  for a skew join by specifying the minimum split size. It should be used together with  585 hive.skewjoin.mapjoin.map.tasks to perform a fine grained control.</description>  586 </property>  587  588 <property>  589 <name>hive.mapred.mode</name>  590 <value>nonstrict</value>  591 <description>The mode in which the hive operations are being performed.  592  In strict mode, some risky queries are not allowed to run. They include:  593  Cartesian Product.  594  No partition being picked up for a query.  595  Comparing bigints and strings.  596  Comparing bigints and doubles.  597  Orderby without limit.  598 </description>  599 </property>  600  601 <property>  602 <name>hive.enforce.bucketmapjoin</name>  603 <value>false</value>  604 <description>If the user asked for bucketed map-side join, and it cannot be performed,  605  should the query fail or not ? For eg, if the buckets in the tables being joined are  606  not a multiple of each other, bucketed map-side join cannot be performed, and the  607  query will fail if hive.enforce.bucketmapjoin is set to true.  608 </description>  609 </property>  610  611 <property>  612 <name>hive.exec.script.maxerrsize</name>  613 <value>100000</value>  614 <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>  615 </property>  616  617 <property>  618 <name>hive.exec.script.allow.partial.consumption</name>  619 <value>false</value>  620 <description> When enabled, this option allows a user script to exit successfully without consuming all the data from the standard input.  621 </description>  622 </property>  623  624 <property>  625 <name>hive.script.operator.id.env.var</name>  626 <value>HIVE_SCRIPT_OPERATOR_ID</value>  627 <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)  628 </description>  629 </property>  630  631 <property>  632 <name>hive.script.operator.truncate.env</name>  633 <value>false</value>  634 <description>Truncate each environment variable for external script in scripts operator to 20KB (to fit system limits)</description>  635 </property>  636  637 <property>  638 <name>hive.exec.compress.output</name>  639 <value>false</value>  640 <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>  641 </property>  642  643 <property>  644 <name>hive.exec.compress.intermediate</name>  645 <value>false</value>  646 <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>  647 </property>  648  649 <property>  650 <name>hive.exec.parallel</name>  651 <value>false</value>  652 <description>Whether to execute jobs in parallel</description>  653 </property>  654  655 <property>  656 <name>hive.exec.parallel.thread.number</name>  657 <value>8</value>  658 <description>How many jobs at most can be executed in parallel</description>  659 </property>  660  661 <property>  662 <name>hive.exec.rowoffset</name>  663 <value>false</value>  664 <description>Whether to provide the row offset virtual column</description>  665 </property>  666  667 <property>  668 <name>hive.task.progress</name>  669 <value>false</value>  670 <description>Whether Hive should periodically update task progress counters during execution. Enabling this allows task progress to be monitored more closely in the job tracker, but may impose a performance penalty. This flag is automatically set to true for jobs with hive.exec.dynamic.partition set to true.</description>  671 </property>  672  673 <property>  674 <name>hive.hwi.war.file</name>  675 <value>lib/hive-hwi-0.10.0.war</value>  676 <description>This sets the path to the HWI war file, relative to ${HIVE_HOME}. </description>  677 </property>  678  679 <property>  680 <name>hive.hwi.listen.host</name>  681 <value>0.0.0.0</value>  682 <description>This is the host address the Hive Web Interface will listen on</description>  683 </property>  684  685 <property>  686 <name>hive.hwi.listen.port</name>  687 <value>9999</value>  688 <description>This is the port the Hive Web Interface will listen on</description>  689 </property>  690  691 <property>  692 <name>hive.exec.pre.hooks</name>  693 <value></value>  694 <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>  695 </property>  696  697 <property>  698 <name>hive.exec.post.hooks</name>  699 <value></value>  700 <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>  701 </property>  702  703 <property>  704 <name>hive.exec.failure.hooks</name>  705 <value></value>  706 <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>  707 </property>  708  709 <property>  710 <name>hive.client.stats.publishers</name>  711 <value></value>  712 <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>  713 </property>  714  715 <property>  716 <name>hive.client.stats.counters</name>  717 <value></value>  718 <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>  719 </property>  720  721 <property>  722 <name>hive.merge.mapfiles</name>  723 <value>true</value>  724 <description>Merge small files at the end of a map-only job</description>  725 </property>  726  727 <property>  728 <name>hive.merge.mapredfiles</name>  729 <value>false</value>  730 <description>Merge small files at the end of a map-reduce job</description>  731 </property>  732  733 <property>  734 <name>hive.mergejob.maponly</name>  735 <value>true</value>  736 <description>Try to generate a map-only job for merging files if CombineHiveInputFormat is supported.</description>  737 </property>  738  739 <property>  740 <name>hive.heartbeat.interval</name>  741 <value>1000</value>  742 <description>Send a heartbeat after this interval - used by mapjoin and filter operators</description>  743 </property>  744  745 <property>  746 <name>hive.merge.size.per.task</name>  747 <value>256000000</value>  748 <description>Size of merged files at the end of the job</description>  749 </property>  750  751 <property>  752 <name>hive.merge.smallfiles.avgsize</name>  753 <value>16000000</value>  754 <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>  755 </property>  756  757 <property>  758 <name>hive.mapjoin.smalltable.filesize</name>  759 <value>25000000</value>  760 <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>  761 </property>  762  763 <property>  764 <name>hive.mapjoin.localtask.max.memory.usage</name>  765 <value>0.90</value>  766 <description>This number means how much memory the local task can take to hold the key/value into in-memory hash table; If the local task's memory usage is more than this number, the local task will be abort by themself. It means the data of small table is too large to be hold in the memory.</description>  767 </property>  768  769 <property>  770 <name>hive.mapjoin.followby.gby.localtask.max.memory.usage</name>  771 <value>0.55</value>  772 <description>This number means how much memory the local task can take to hold the key/value into in-memory hash table when this map join followed by a group by; If the local task's memory usage is more than this number, the local task will be abort by themself. It means the data of small table is too large to be hold in the memory.</description>  773 </property>  774  775 <property>  776 <name>hive.mapjoin.check.memory.rows</name>  777 <value>100000</value>  778 <description>The number means after how many rows processed it needs to check the memory usage</description>  779 </property>  780  781 <property>  782 <name>hive.auto.convert.join</name>  783 <value>false</value>  784 <description>Whether Hive enable the optimization about converting common join into mapjoin based on the input file size</description>  785 </property>  786  787  788 <property>  789 <name>hive.script.auto.progress</name>  790 <value>false</value>  791 <description>Whether Hive Tranform/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>  792 </property>  793  794 <property>  795 <name>hive.script.serde</name>  796 <value>org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe</value>  797 <description>The default serde for trasmitting input data to and reading output data from the user scripts. </description>  798 </property>  799  800 <property>  801 <name>hive.binary.record.max.length</name>  802 <value>1000</value>  803 <description>Read from a binary stream and treat each hive.binary.record.max.length bytes as a record.  804 The last record before the end of stream can have less than hive.binary.record.max.length bytes</description>  805 </property>  806  807  808 <property>  809 <name>hive.script.recordreader</name>  810 <value>org.apache.hadoop.hive.ql.exec.TextRecordReader</value>  811 <description>The default record reader for reading data from the user scripts. </description>  812 </property>  813  814 <property>  815 <name>hive.script.recordwriter</name>  816 <value>org.apache.hadoop.hive.ql.exec.TextRecordWriter</value>  817 <description>The default record writer for writing data to the user scripts. </description>  818 </property>  819  820 <property>  821 <name>hive.input.format</name>  822 <value>org.apache.hadoop.hive.ql.io.CombineHiveInputFormat</value>  823 <description>The default input format. Set this to HiveInputFormat if you encounter problems with CombineHiveInputFormat.</description>  824 </property>  825  826 <property>  827 <name>hive.udtf.auto.progress</name>  828 <value>false</value>  829 <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 infinte loops. </description>  830 </property>  831  832 <property>  833 <name>hive.mapred.reduce.tasks.speculative.execution</name>  834 <value>true</value>  835 <description>Whether speculative execution for reducers should be turned on. </description>  836 </property>  837  838 <property>  839 <name>hive.exec.counters.pull.interval</name>  840 <value>1000</value>  841 <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>  842 </property>  843  844 <property>  845 <name>hive.querylog.location</name>  846 <value>/tmp/${user.name}</value>  847 <description>  848  Location of Hive run time structured log file  849 </description>  850 </property>  851  852 <property>  853 <name>hive.querylog.enable.plan.progress</name>  854 <value>true</value>  855 <description>  856  Whether to log the plan's progress every time a job's progress is checked.  857  These logs are written to the location specified by hive.querylog.location  858 </description>  859 </property>  860  861 <property>  862 <name>hive.querylog.plan.progress.interval</name>  863 <value>60000</value>  864 <description>  865  The interval to wait between logging the plan's progress in milliseconds.  866  If there is a whole number percentage change in the progress of the mappers or the reducers,  867  the progress is logged regardless of this value.  868  The actual interval will be the ceiling of (this value divided by the value of  869  hive.exec.counters.pull.interval) multiplied by the value of hive.exec.counters.pull.interval  870  I.e. if it is not divide evenly by the value of hive.exec.counters.pull.interval it will be  871  logged less frequently than specified.  872  This only has an effect if hive.querylog.enable.plan.progress is set to true.  873 </description>  874 </property>  875  876 <property>  877 <name>hive.enforce.bucketing</name>  878 <value>false</value>  879 <description>Whether bucketing is enforced. If true, while inserting into the table, bucketing is enforced. </description>  880 </property>  881  882 <property>  883 <name>hive.enforce.sorting</name>  884 <value>false</value>  885 <description>Whether sorting is enforced. If true, while inserting into the table, sorting is enforced. </description>  886 </property>  887  888 <property>  889 <name>hive.enforce.sortmergebucketmapjoin</name>  890 <value>false</value>  891 <description>If the user asked for sort-merge bucketed map-side join, and it cannot be performed,  892  should the query fail or not ?  893 </description>  894 </property>  895  896 <property>  897 <name>hive.metastore.ds.connection.url.hook</name>  898 <value></value>  899 <description>Name of the hook to use for retriving the JDO connection URL. If empty, the value in javax.jdo.option.ConnectionURL is used </description>  900 </property>  901  902 <property>  903 <name>hive.metastore.ds.retry.attempts</name>  904 <value>1</value>  905 <description>The number of times to retry a metastore call if there were a connection error</description>  906 </property>  907  908 <property>  909 <name>hive.metastore.ds.retry.interval</name>  910 <value>1000</value>  911 <description>The number of miliseconds between metastore retry attempts</description>  912 </property>  913  914 <property>  915 <name>hive.metastore.server.min.threads</name>  916 <value>200</value>  917 <description>Minimum number of worker threads in the Thrift server's pool.</description>  918 </property>  919  920 <property>  921 <name>hive.metastore.server.max.threads</name>  922 <value>100000</value>  923 <description>Maximum number of worker threads in the Thrift server's pool.</description>  924 </property>  925  926 <property>  927 <name>hive.metastore.server.tcp.keepalive</name>  928 <value>true</value>  929 <description>Whether to enable TCP keepalive for the metastore server. Keepalive will prevent accumulation of half-open connections.</description>  930 </property>  931  932 <property>  933 <name>hive.metastore.sasl.enabled</name>  934 <value>false</value>  935 <description>If true, the metastore thrift interface will be secured with SASL. Clients must authenticate with Kerberos.</description>  936 </property>  937  938 <property>  939 <name>hive.metastore.thrift.framed.transport.enabled</name>  940 <value>false</value>  941 <description>If true, the metastore thrift interface will use TFramedTransport. When false (default) a standard TTransport is used.</description>  942 </property>  943  944 <property>  945 <name>hive.metastore.kerberos.keytab.file</name>  946 <value></value>  947 <description>The path to the Kerberos Keytab file containing the metastore thrift server's service principal.</description>  948 </property>  949  950 <property>  951 <name>hive.metastore.kerberos.principal</name>  952 <value>hive-metastore/_HOST@EXAMPLE.COM</value>  953 <description>The service principal for the metastore thrift server. The special string _HOST will be replaced automatically with the correct host name.</description>  954 </property>  955  956 <property>  957 <name>hive.cluster.delegation.token.store.class</name>  958 <value>org.apache.hadoop.hive.thrift.MemoryTokenStore</value>  959 <description>The delegation token store implementation. Set to org.apache.hadoop.hive.thrift.ZooKeeperTokenStore for load-balanced cluster.</description>  960 </property>  961  962 <property>  963 <name>hive.cluster.delegation.token.store.zookeeper.connectString</name>  964 <value>localhost:2181</value>  965 <description>The ZooKeeper token store connect string.</description>  966 </property>  967  968 <property>  969 <name>hive.cluster.delegation.token.store.zookeeper.znode</name>  970 <value>/hive/cluster/delegation</value>  971 <description>The root path for token store data.</description>  972 </property>  973  974 <property>  975 <name>hive.cluster.delegation.token.store.zookeeper.acl</name>  976 <value>sasl:hive/host1@EXAMPLE.COM:cdrwa,sasl:hive/host2@EXAMPLE.COM:cdrwa</value>  977 <description>ACL for token store entries. List comma separated all server principals for the cluster.</description>  978 </property>  979  980 <property>  981 <name>hive.metastore.cache.pinobjtypes</name>  982 <value>Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order</value>  983 <description>List of comma separated metastore object types that should be pinned in the cache</description>  984 </property>  985  986 <property>  987 <name>hive.optimize.reducededuplication</name>  988 <value>true</value>  989 <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>  990 </property>  991  992 <property>  993 <name>hive.exec.dynamic.partition</name>  994 <value>true</value>  995 <description>Whether or not to allow dynamic partitions in DML/DDL.</description>  996 </property>  997  998 <property>  999 <name>hive.exec.dynamic.partition.mode</name> 1000 <value>strict</value> 1001 <description>In strict mode, the user must specify at least one static partition in case the user accidentally overwrites all partitions.</description> 1002 </property> 1003 1004 <property> 1005 <name>hive.exec.max.dynamic.partitions</name> 1006 <value>1000</value> 1007 <description>Maximum number of dynamic partitions allowed to be created in total.</description> 1008 </property> 1009 1010 <property> 1011 <name>hive.exec.max.dynamic.partitions.pernode</name> 1012 <value>100</value> 1013 <description>Maximum number of dynamic partitions allowed to be created in each mapper/reducer node.</description> 1014 </property> 1015 1016 <property> 1017 <name>hive.exec.max.created.files</name> 1018 <value>100000</value> 1019 <description>Maximum number of HDFS files created by all mappers/reducers in a MapReduce job.</description> 1020 </property> 1021 1022 <property> 1023 <name>hive.exec.default.partition.name</name> 1024 <value>__HIVE_DEFAULT_PARTITION__</value> 1025 <description>The default partition name in case the dynamic partition column value is null/empty string or anyother 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> 1026 </property> 1027 1028 <property> 1029 <name>hive.stats.dbclass</name> 1030 <value>jdbc:derby</value> 1031 <description>The default database that stores temporary hive statistics.</description> 1032 </property> 1033 1034 <property> 1035 <name>hive.stats.autogather</name> 1036 <value>true</value> 1037 <description>A flag to gather statistics automatically during the INSERT OVERWRITE command.</description> 1038 </property> 1039 1040 <property> 1041 <name>hive.stats.jdbcdriver</name> 1042 <value>org.apache.derby.jdbc.EmbeddedDriver</value> 1043 <description>The JDBC driver for the database that stores temporary hive statistics.</description> 1044 </property> 1045 1046 <property> 1047 <name>hive.stats.dbconnectionstring</name> 1048 <value>jdbc:derby:;databaseName=TempStatsStore;create=true</value> 1049 <description>The default connection string for the database that stores temporary hive statistics.</description> 1050 </property> 1051 1052 <property> 1053 <name>hive.stats.default.publisher</name> 1054 <value></value> 1055 <description>The Java class (implementing the StatsPublisher interface) that is used by default if hive.stats.dbclass is not JDBC or HBase.</description> 1056 </property> 1057 1058 <property> 1059 <name>hive.stats.default.aggregator</name> 1060 <value></value> 1061 <description>The Java class (implementing the StatsAggregator interface) that is used by default if hive.stats.dbclass is not JDBC or HBase.</description> 1062 </property> 1063 1064 <property> 1065 <name>hive.stats.jdbc.timeout</name> 1066 <value>30</value> 1067 <description>Timeout value (number of seconds) used by JDBC connection and statements.</description> 1068 </property> 1069 1070 <property> 1071 <name>hive.stats.retries.max</name> 1072 <value>0</value> 1073 <description>Maximum number of retries when stats publisher/aggregator got an exception updating intermediate database. Default is no tries on failures.</description> 1074 </property> 1075 1076 <property> 1077 <name>hive.stats.retries.wait</name> 1078 <value>3000</value> 1079 <description>The base waiting window (in milliseconds) before the next retry. The actual wait time is calculated by baseWindow * failues + baseWindow * (failure + 1) * (random number between [0.0,1.0]).</description> 1080 </property> 1081 1082 <property> 1083 <name>hive.stats.reliable</name> 1084 <value>false</value> 1085 <description>Whether queries will fail because stats cannot be collected completely accurately. 1086  If this is set to true, reading/writing from/into a partition may fail becuase the stats 1087  could not be computed accurately. 1088 </description> 1089 </property> 1090 1091 <property> 1092 <name>hive.stats.collect.tablekeys</name> 1093 <value>false</value> 1094 <description>Whether join and group by keys on tables are derived and maintained in the QueryPlan. 1095  This is useful to identify how tables are accessed and to determine if they should be bucketed. 1096 </description> 1097 </property> 1098 1099 <property> 1100 <name>hive.stats.ndv.error</name> 1101 <value>20.0</value> 1102 <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. 1103 </description> 1104 </property> 1105 1106 <property> 1107 <name>hive.support.concurrency</name> 1108 <value>false</value> 1109 <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> 1110 </property> 1111 1112 <property> 1113 <name>hive.lock.numretries</name> 1114 <value>100</value> 1115 <description>The number of times you want to try to get all the locks</description> 1116 </property> 1117 1118 <property> 1119 <name>hive.unlock.numretries</name> 1120 <value>10</value> 1121 <description>The number of times you want to retry to do one unlock</description> 1122 </property> 1123 1124 <property> 1125 <name>hive.lock.sleep.between.retries</name> 1126 <value>60</value> 1127 <description>The sleep time (in seconds) between various retries</description> 1128 </property> 1129 1130 <property> 1131 <name>hive.zookeeper.quorum</name> 1132 <value></value> 1133 <description>The list of zookeeper servers to talk to. This is only needed for read/write locks.</description> 1134 </property> 1135 1136 <property> 1137 <name>hive.zookeeper.client.port</name> 1138 <value>2181</value> 1139 <description>The port of zookeeper servers to talk to. This is only needed for read/write locks.</description> 1140 </property> 1141 1142 <property> 1143 <name>hive.zookeeper.session.timeout</name> 1144 <value>600000</value> 1145 <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> 1146 </property> 1147 1148 <property> 1149 <name>hive.zookeeper.namespace</name> 1150 <value>hive_zookeeper_namespace</value> 1151 <description>The parent node under which all zookeeper nodes are created.</description> 1152 </property> 1153 1154 <property> 1155 <name>hive.zookeeper.clean.extra.nodes</name> 1156 <value>false</value> 1157 <description>Clean extra nodes at the end of the session.</description> 1158 </property> 1159 1160 <property> 1161 <name>fs.har.impl</name> 1162 <value>org.apache.hadoop.hive.shims.HiveHarFileSystem</value> 1163 <description>The implementation for accessing Hadoop Archives. Note that this won't be applicable to Hadoop vers less than 0.20</description> 1164 </property> 1165 1166 <property> 1167 <name>hive.archive.enabled</name> 1168 <value>false</value> 1169 <description>Whether archiving operations are permitted</description> 1170 </property> 1171 1172 <property> 1173 <name>hive.fetch.output.serde</name> 1174 <value>org.apache.hadoop.hive.serde2.DelimitedJSONSerDe</value> 1175 <description>The serde used by FetchTask to serialize the fetch output.</description> 1176 </property> 1177 1178 <property> 1179 <name>hive.exec.mode.local.auto</name> 1180 <value>false</value> 1181 <description> Let hive determine whether to run in local mode automatically </description> 1182 </property> 1183 1184 <property> 1185 <name>hive.exec.drop.ignorenonexistent</name> 1186 <value>true</value> 1187 <description> 1188  Do not report an error if DROP TABLE/VIEW specifies a non-existent table/view 1189 </description> 1190 </property> 1191 1192 <property> 1193 <name>hive.exec.show.job.failure.debug.info</name> 1194 <value>true</value> 1195 <description> 1196  If a job fails, whether to provide a link in the CLI to the task with the 1197  most failures, along with debugging hints if applicable. 1198 </description> 1199 </property> 1200 1201 <property> 1202 <name>hive.auto.progress.timeout</name> 1203 <value>0</value> 1204 <description> 1205  How long to run autoprogressor for the script/UDTF operators (in seconds). 1206  Set to 0 for forever. 1207 </description> 1208 </property> 1209 1210 <!-- HBase Storage Handler Parameters --> 1211 1212 <property> 1213 <name>hive.hbase.wal.enabled</name> 1214 <value>true</value> 1215 <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> 1216 </property> 1217 1218 <property> 1219 <name>hive.table.parameters.default</name> 1220 <value></value> 1221 <description>Default property values for newly created tables</description> 1222 </property> 1223 1224 <property> 1225 <name>hive.entity.separator</name> 1226 <value>@</value> 1227 <description>Separator used to construct names of tables and partitions. For example, dbname@tablename@partitionname</description> 1228 </property> 1229 1230 <property> 1231 <name>hive.ddl.createtablelike.properties.whitelist</name> 1232 <value></value> 1233 <description>Table Properties to copy over when executing a Create Table Like.</description> 1234 </property> 1235 1236 <property> 1237 <name>hive.variable.substitute</name> 1238 <value>true</value> 1239 <description>This enables substitution using syntax like ${var} ${system:var} and ${env:var}.</description> 1240 </property> 1241 1242 <property> 1243 <name>hive.variable.substitute.depth</name> 1244 <value>40</value> 1245 <description>The maximum replacements the substitution engine will do.</description> 1246 </property> 1247 1248 <property> 1249 <name>hive.conf.validation</name> 1250 <value>true</value> 1251 <description>Eables type checking for registered hive configurations</description> 1252 </property> 1253 1254 <property> 1255 <name>hive.security.authorization.enabled</name> 1256 <value>false</value> 1257 <description>enable or disable the hive client authorization</description> 1258 </property> 1259 1260 <property> 1261 <name>hive.security.authorization.manager</name> 1262 <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveAuthorizationProvider</value> 1263 <description>the hive client authorization manager class name. 1264  The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveAuthorizationProvider. 1265 </description> 1266 </property> 1267 1268 <property> 1269 <name>hive.security.metastore.authorization.manager</name> 1270 <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider</value> 1271 <description>authorization manager class name to be used in the metastore for authorization. 1272  The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider. 1273 </description> 1274 </property> 1275 1276 <property> 1277 <name>hive.security.metastore.authorization.manager</name> 1278 <value>org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider</value> 1279 <description>authorization manager class name to be used in the metastore for authorization. 1280  The user defined authorization class should implement interface org.apache.hadoop.hive.ql.security.authorization.HiveMetastoreAuthorizationProvider. 1281 </description> 1282 </property> 1283 1284 <property> 1285 <name>hive.security.authenticator.manager</name> 1286 <value>org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator</value> 1287 <description>hive client authenticator manager class name. 1288 The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.</description> 1289 </property> 1290 1291 <property> 1292 <name>hive.security.metastore.authenticator.manager</name> 1293 <value>org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator</value> 1294 <description>authenticator manager class name to be used in the metastore for authentication. 1295 The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.</description> 1296 </property> 1297 1298 <property> 1299 <name>hive.security.metastore.authenticator.manager</name> 1300 <value>org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator</value> 1301 <description>authenticator manager class name to be used in the metastore for authentication. 1302 The user defined authenticator should implement interface org.apache.hadoop.hive.ql.security.HiveAuthenticationProvider.</description> 1303 </property> 1304 1305 <property> 1306 <name>hive.security.authorization.createtable.user.grants</name> 1307 <value></value> 1308 <description>the privileges automatically granted to some users whenever a table gets created. 1309  An example like "userX,userY:select;userZ:create" will grant select privilege to userX and userY, 1310 and grant create privilege to userZ whenever a new table created.</description> 1311 </property> 1312 1313 <property> 1314 <name>hive.security.authorization.createtable.group.grants</name> 1315 <value></value> 1316 <description>the privileges automatically granted to some groups whenever a table gets created. 1317  An example like "groupX,groupY:select;groupZ:create" will grant select privilege to groupX and groupY, 1318 and grant create privilege to groupZ whenever a new table created.</description> 1319 </property> 1320 1321 <property> 1322 <name>hive.security.authorization.createtable.role.grants</name> 1323 <value></value> 1324 <description>the privileges automatically granted to some roles whenever a table gets created. 1325  An example like "roleX,roleY:select;roleZ:create" will grant select privilege to roleX and roleY, 1326 and grant create privilege to roleZ whenever a new table created.</description> 1327 </property> 1328 1329 <property> 1330 <name>hive.security.authorization.createtable.owner.grants</name> 1331 <value></value> 1332 <description>the privileges automatically granted to the owner whenever a table gets created. 1333 An example like "select,drop" will grant select and drop privilege to the owner of the table</description> 1334 </property> 1335 1336 <property> 1337 <name>hive.metastore.authorization.storage.checks</name> 1338 <value>false</value> 1339 <description>Should the metastore do authorization checks against the underlying storage 1340  for operations like drop-partition (disallow the drop-partition if the user in 1341  question doesn't have permissions to delete the corresponding directory 1342 on the storage).</description> 1343 </property> 1344 1345 <property> 1346 <name>hive.error.on.empty.partition</name> 1347 <value>false</value> 1348 <description>Whether to throw an excpetion if dynamic partition insert generates empty results.</description> 1349 </property> 1350 1351 <property> 1352 <name>hive.index.compact.file.ignore.hdfs</name> 1353 <value>false</value> 1354 <description>True the hdfs location stored in the index file will be igbored at runtime. 1355 If the data got moved or the name of the cluster got changed, the index data should still be usable.</description> 1356 </property> 1357 1358 <property> 1359 <name>hive.optimize.index.filter.compact.minsize</name> 1360 <value>5368709120</value> 1361 <description>Minimum size (in bytes) of the inputs on which a compact index is automatically used.</description> 1362 </property> 1363 1364 <property> 1365 <name>hive.optimize.index.filter.compact.maxsize</name> 1366 <value>-1</value> 1367 <description>Maximum size (in bytes) of the inputs on which a compact index is automatically used. 1368 A negative number is equivalent to infinity.</description> 1369 </property> 1370 1371 <property> 1372 <name>hive.index.compact.query.max.size</name> 1373 <value>10737418240</value> 1374 <description>The maximum number of bytes that a query using the compact index can read. Negative value is equivalent to infinity.</description> 1375 </property> 1376 1377 <property> 1378 <name>hive.index.compact.query.max.entries</name> 1379 <value>10000000</value> 1380 <description>The maximum number of index entries to read during a query that uses the compact index. Negative value is equivalent to infinity.</description> 1381 </property> 1382 1383 <property> 1384 <name>hive.index.compact.binary.search</name> 1385 <value>true</value> 1386 <description>Whether or not to use a binary search to find the entries in an index table that match the filter, where possible</description> 1387 </property> 1388 1389 <property> 1390 <name>hive.exim.uri.scheme.whitelist</name> 1391 <value>hdfs,pfile</value> 1392 <description>A comma separated list of acceptable URI schemes for import and export.</description> 1393 </property> 1394 1395 <property> 1396 <name>hive.lock.mapred.only.operation</name> 1397 <value>false</value> 1398 <description>This param is to control whether or not only do lock on queries 1399 that need to execute at least one mapred job.</description> 1400 </property> 1401 1402 <property> 1403 <name>hive.limit.row.max.size</name> 1404 <value>100000</value> 1405 <description>When trying a smaller subset of data for simple LIMIT, how much size we need to guarantee 1406 each row to have at least.</description> 1407 </property> 1408 1409 <property> 1410 <name>hive.limit.optimize.limit.file</name> 1411 <value>10</value> 1412 <description>When trying a smaller subset of data for simple LIMIT, maximum number of files we can 1413 sample.</description> 1414 </property> 1415 1416 <property> 1417 <name>hive.limit.optimize.enable</name> 1418 <value>false</value> 1419 <description>Whether to enable to optimization to trying a smaller subset of data for simple LIMIT first.</description> 1420 </property> 1421 1422 <property> 1423 <name>hive.limit.optimize.fetch.max</name> 1424 <value>50000</value> 1425 <description>Maximum number of rows allowed for a smaller subset of data for simple LIMIT, if it is a fetch query. 1426 Insert queries are not restricted by this limit.</description> 1427 </property> 1428 1429 <property> 1430 <name>hive.rework.mapredwork</name> 1431 <value>false</value> 1432 <description>should rework the mapred work or not. 1433 This is first introduced by SymlinkTextInputFormat to replace symlink files with real paths at compile time.</description> 1434 </property> 1435 1436 <property> 1437 <name>hive.exec.concatenate.check.index</name> 1438 <value>true</value> 1439 <description>If this sets to true, hive will throw error when doing 1440  'alter table tbl_name [partSpec] concatenate' on a table/partition 1441  that has indexes on it. The reason the user want to set this to true 1442  is because it can help user to avoid handling all index drop, recreation, 1443 rebuild work. This is very helpful for tables with thousands of partitions.</description> 1444 </property> 1445 1446 <property> 1447 <name>hive.sample.seednumber</name> 1448 <value>0</value> 1449 <description>A number used to percentage sampling. By changing this number, user will change the subsets 1450 of data sampled.</description> 1451 </property> 1452 1453 <property> 1454 <name>hive.io.exception.handlers</name> 1455 <value></value> 1456 <description>A list of io exception handler class names. This is used 1457  to construct a list exception handlers to handle exceptions thrown 1458 by record readers</description> 1459 </property> 1460 1461 <property> 1462 <name>hive.autogen.columnalias.prefix.label</name> 1463 <value>_c</value> 1464 <description>String used as a prefix when auto generating column alias. 1465 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> 1466 </property> 1467 1468 <property> 1469 <name>hive.autogen.columnalias.prefix.includefuncname</name> 1470 <value>false</value> 1471 <description>Whether to include function name in the column alias auto generated by hive.</description> 1472 </property> 1473 1474 <property> 1475 <name>hive.exec.perf.logger</name> 1476 <value>org.apache.hadoop.hive.ql.log.PerfLogger</value> 1477 <description>The class responsible logging client side performance metrics. Must be a subclass of org.apache.hadoop.hive.ql.log.PerfLogger</description> 1478 </property> 1479 1480 <property> 1481 <name>hive.start.cleanup.scratchdir</name> 1482 <value>false</value> 1483 <description>To cleanup the hive scratchdir while starting the hive server</description> 1484 </property> 1485 1486 <property> 1487 <name>hive.output.file.extension</name> 1488 <value></value> 1489 <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> 1490 </property> 1491 1492 <property> 1493 <name>hive.insert.into.multilevel.dirs</name> 1494 <value>false</value> 1495 <description>Where to insert into multilevel directories like 1496 "insert directory '/HIVEFT25686/chinna/' from table"</description> 1497 </property> 1498 1499 <property> 1500 <name>hive.warehouse.subdir.inherit.perms</name> 1501 <value>false</value> 1502 <description>Set this to true if the the table directories should inherit the 1503  permission of the warehouse or database directory instead of being created 1504 with the permissions derived from dfs umask</description> 1505 </property> 1506 1507 <property> 1508 <name>hive.exec.job.debug.capture.stacktraces</name> 1509 <value>true</value> 1510 <description>Whether or not stack traces parsed from the task logs of a sampled failed task for 1511  each failed job should be stored in the SessionState 1512 </description> 1513 </property> 1514 1515 <property> 1516 <name>hive.exec.driver.run.hooks</name> 1517 <value></value> 1518 <description>A comma separated list of hooks which implement HiveDriverRunHook and will be run at the 1519  beginning and end of Driver.run, these will be run in the order specified 1520 </description> 1521 </property> 1522 1523 <property> 1524 <name>hive.ddl.output.format</name> 1525 <value>text</value> 1526 <description> 1527  The data format to use for DDL output. One of "text" (for human 1528  readable text) or "json" (for a json object). 1529 </description> 1530 </property> 1531 1532 <property> 1533 <name>hive.transform.escape.input</name> 1534 <value>false</value> 1535 <description> 1536  This adds an option to escape special chars (newlines, carriage returns and 1537  tabs) when they are passed to the user script. This is useful if the hive tables 1538  can contain data that contains special characters. 1539 </description> 1540 </property> 1541 1542 <property> 1543 <name>hive.exec.rcfile.use.explicit.header</name> 1544 <value>true</value> 1545 <description> 1546  If this is set the header for RC Files will simply be RCF. If this is not 1547  set the header will be that borrowed from sequence files, e.g. SEQ- followed 1548  by the input and output RC File formats. 1549 </description> 1550 </property> 1551 1552 <property> 1553 <name>hive.multi.insert.move.tasks.share.dependencies</name> 1554 <value>false</value> 1555 <description> 1556  If this is set all move tasks for tables/partitions (not directories) at the end of a 1557  multi-insert query will only begin once the dependencies for all these move tasks have been 1558  met. 1559  Advantages: If concurrency is enabled, the locks will only be released once the query has 1560  finished, so with this config enabled, the time when the table/partition is 1561  generated will be much closer to when the lock on it is released. 1562  Disadvantages: If concurrency is not enabled, with this disabled, the tables/partitions which 1563  are produced by this query and finish earlier will be available for querying 1564  much earlier. Since the locks are only released once the query finishes, this 1565  does not apply if concurrency is enabled. 1566 </description> 1567 </property> 1568 1569 <property> 1570 <name>hive.fetch.task.conversion</name> 1571 <value>minimal</value> 1572 <description> 1573  Some select queries can be converted to single FETCH task minimizing latency. 1574  Currently the query should be single sourced not having any subquery and should not have 1575  any aggregations or distincts (which incurrs RS), lateral views and joins. 1576  1. minimal : SELECT STAR, FILTER on partition columns, LIMIT only 1577  2. more : SELECT, FILTER, LIMIT only (+TABLESAMPLE, virtual columns) 1578 </description> 1579 </property> 1580 1581 <property> 1582 <name>hive.hmshandler.retry.attempts</name> 1583 <value>1</value> 1584 <description>The number of times to retry a HMSHandler call if there were a connection error</description> 1585 </property> 1586 1587 <property> 1588 <name>hive.hmshandler.retry.interval</name> 1589 <value>1000</value> 1590 <description>The number of miliseconds between HMSHandler retry attempts</description> 1591 </property> 1592 1593 1594 <property> 1595 <name>hive.server.read.socket.timeout</name> 1596 <value>10</value> 1597 <description>Timeout for the HiveServer to close the connection if no response from the client in N seconds, defaults to 10 seconds.</description> 1598 </property> 1599 1600 <property> 1601 <name>hive.server.tcp.keepalive</name> 1602 <value>true</value> 1603 <description>Whether to enable TCP keepalive for the Hive server. Keepalive will prevent accumulation of half-open connections.</description> 1604 </property> 1605 <!--zhangziliang--> 1606 <property> 1607 <name>hive.aux.jars.path</name> 1608 <value>file:///home/hadoop/source/hive/lib/hive-hbase-handler-0.10.0.jar,file:///home/hadoop/source/hive/lib/hbase-0.94.0.jar,file:///home/hadoop/source/hive/lib/zookeeper-3.4.3.jar</value> 1609 </property> 1610 </configuration>