diff --git a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java index 1939c9f..3b39328 100644 --- a/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java +++ b/common/src/java/org/apache/hadoop/hive/conf/HiveConf.java @@ -633,7 +633,7 @@ "How many rows in the joining tables (except the streaming table) should be cached in memory."), // CBO related - HIVE_CBO_ENABLED("hive.cbo.enable", false, "Flag to control enabling Cost Based Optimizations using Optiq framework."), + HIVE_CBO_ENABLED("hive.cbo.enable", true, "Flag to control enabling Cost Based Optimizations using Optiq framework."), // hive.mapjoin.bucket.cache.size has been replaced by hive.smbjoin.cache.row, // need to remove by hive .13. Also, do not change default (see SMB operator) diff --git a/conf/hive-default.xml.template b/conf/hive-default.xml.template index 79dead4..a3adeb3 100644 --- a/conf/hive-default.xml.template +++ b/conf/hive-default.xml.template @@ -23,17 +23,17 @@ - hive.exec.script.wrapper + hive.exec.script.wrapper - hive.exec.plan + hive.exec.plan - hive.plan.serialization.format + hive.plan.serialization.format kryo Query plan format serialization between client and task nodes. @@ -41,27 +41,27 @@ - hive.exec.scratchdir + hive.exec.scratchdir /tmp/hive-${system:user.name} Scratch space for Hive jobs - hive.exec.local.scratchdir + hive.exec.local.scratchdir ${system:java.io.tmpdir}/${system:user.name} Local scratch space for Hive jobs - hive.scratch.dir.permission + hive.scratch.dir.permission 700 - hive.exec.submitviachild + hive.exec.submitviachild false - hive.exec.submit.local.task.via.child + hive.exec.submit.local.task.via.child true Determines whether local tasks (typically mapjoin hashtable generation phase) runs in @@ -70,7 +70,7 @@ - hive.exec.script.maxerrsize + hive.exec.script.maxerrsize 100000 Maximum number of bytes a script is allowed to emit to standard error (per map-reduce task). @@ -78,7 +78,7 @@ - hive.exec.script.allow.partial.consumption + hive.exec.script.allow.partial.consumption false When enabled, this option allows a user script to exit successfully without consuming @@ -86,17 +86,17 @@ - stream.stderr.reporter.prefix + stream.stderr.reporter.prefix reporter: Streaming jobs that log to standard error with this prefix can log counter or status information. - stream.stderr.reporter.enabled + stream.stderr.reporter.enabled true Enable consumption of status and counter messages for streaming jobs. - hive.exec.compress.output + hive.exec.compress.output false This controls whether the final outputs of a query (to a local/HDFS file or a Hive table) is compressed. @@ -104,7 +104,7 @@ - hive.exec.compress.intermediate + hive.exec.compress.intermediate false This controls whether intermediate files produced by Hive between multiple map-reduce jobs are compressed. @@ -112,22 +112,22 @@ - hive.intermediate.compression.codec + hive.intermediate.compression.codec - hive.intermediate.compression.type + hive.intermediate.compression.type - hive.exec.reducers.bytes.per.reducer + hive.exec.reducers.bytes.per.reducer 1000000000 size per reducer.The default is 1G, i.e if the input size is 10G, it will use 10 reducers. - hive.exec.reducers.max + hive.exec.reducers.max 999 max number of reducers will be used. If the one specified in the configuration parameter mapred.reduce.tasks is @@ -135,7 +135,7 @@ - hive.exec.pre.hooks + hive.exec.pre.hooks Comma-separated list of pre-execution hooks to be invoked for each statement. @@ -144,7 +144,7 @@ - hive.exec.post.hooks + hive.exec.post.hooks Comma-separated list of post-execution hooks to be invoked for each statement. @@ -153,7 +153,7 @@ - hive.exec.failure.hooks + hive.exec.failure.hooks Comma-separated list of on-failure hooks to be invoked for each statement. @@ -162,7 +162,7 @@ - hive.client.stats.publishers + hive.client.stats.publishers Comma-separated list of statistics publishers to be invoked on counters on each job. @@ -171,22 +171,22 @@ - hive.exec.parallel + hive.exec.parallel false Whether to execute jobs in parallel - hive.exec.parallel.thread.number + hive.exec.parallel.thread.number 8 How many jobs at most can be executed in parallel - hive.mapred.reduce.tasks.speculative.execution + hive.mapred.reduce.tasks.speculative.execution true Whether speculative execution for reducers should be turned on. - hive.exec.counters.pull.interval + hive.exec.counters.pull.interval 1000 The interval with which to poll the JobTracker for the counters the running job. @@ -194,12 +194,12 @@ - hive.exec.dynamic.partition + hive.exec.dynamic.partition true Whether or not to allow dynamic partitions in DML/DDL. - hive.exec.dynamic.partition.mode + hive.exec.dynamic.partition.mode strict In strict mode, the user must specify at least one static partition @@ -207,27 +207,27 @@ - hive.exec.max.dynamic.partitions + hive.exec.max.dynamic.partitions 1000 Maximum number of dynamic partitions allowed to be created in total. - hive.exec.max.dynamic.partitions.pernode + hive.exec.max.dynamic.partitions.pernode 100 Maximum number of dynamic partitions allowed to be created in each mapper/reducer node. - hive.exec.max.created.files + hive.exec.max.created.files 100000 Maximum number of HDFS files created by all mappers/reducers in a MapReduce job. - hive.downloaded.resources.dir + hive.downloaded.resources.dir ${system:java.io.tmpdir}/${hive.session.id}_resources Temporary local directory for added resources in the remote file system. - hive.exec.default.partition.name + hive.exec.default.partition.name __HIVE_DEFAULT_PARTITION__ The default partition name in case the dynamic partition column value is null/empty string or any other values that cannot be escaped. @@ -236,12 +236,12 @@ - hive.lockmgr.zookeeper.default.partition.name + hive.lockmgr.zookeeper.default.partition.name __HIVE_DEFAULT_ZOOKEEPER_PARTITION__ - hive.exec.show.job.failure.debug.info + hive.exec.show.job.failure.debug.info true If a job fails, whether to provide a link in the CLI to the task with the @@ -249,7 +249,7 @@ - hive.exec.job.debug.capture.stacktraces + hive.exec.job.debug.capture.stacktraces true Whether or not stack traces parsed from the task logs of a sampled failed task @@ -257,17 +257,17 @@ - hive.exec.job.debug.timeout + hive.exec.job.debug.timeout 30000 - hive.exec.tasklog.debug.timeout + hive.exec.tasklog.debug.timeout 20000 - hive.output.file.extension + hive.output.file.extension String used as a file extension for output files. @@ -275,37 +275,37 @@ - hive.exec.mode.local.auto + hive.exec.mode.local.auto false Let Hive determine whether to run in local mode automatically - hive.exec.mode.local.auto.inputbytes.max + hive.exec.mode.local.auto.inputbytes.max 134217728 When hive.exec.mode.local.auto is true, input bytes should less than this for local mode. - hive.exec.mode.local.auto.input.files.max + hive.exec.mode.local.auto.input.files.max 4 When hive.exec.mode.local.auto is true, the number of tasks should less than this for local mode. - hive.exec.drop.ignorenonexistent + hive.exec.drop.ignorenonexistent true Do not report an error if DROP TABLE/VIEW specifies a non-existent table/view - hive.ignore.mapjoin.hint + hive.ignore.mapjoin.hint true Ignore the mapjoin hint - hive.file.max.footer + hive.file.max.footer 100 maximum number of lines for footer user can define for a table file - hive.resultset.use.unique.column.names + hive.resultset.use.unique.column.names true Make column names unique in the result set by qualifying column names with table alias if needed. @@ -314,77 +314,86 @@ - fs.har.impl + fs.har.impl org.apache.hadoop.hive.shims.HiveHarFileSystem The implementation for accessing Hadoop Archives. Note that this won't be applicable to Hadoop versions less than 0.20 - hive.metastore.metadb.dir + hive.metastore.metadb.dir - hive.metastore.warehouse.dir + hive.metastore.warehouse.dir /user/hive/warehouse location of default database for the warehouse - hive.metastore.uris + hive.metastore.uris Thrift URI for the remote metastore. Used by metastore client to connect to remote metastore. - hive.metastore.connect.retries + hive.metastore.connect.retries 3 Number of retries while opening a connection to metastore - hive.metastore.failure.retries + hive.metastore.failure.retries 1 Number of retries upon failure of Thrift metastore calls - hive.metastore.client.connect.retry.delay - 1 - Number of seconds for the client to wait between consecutive connection attempts + hive.metastore.client.connect.retry.delay + 1s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Number of seconds for the client to wait between consecutive connection attempts + - hive.metastore.client.socket.timeout - 600 - MetaStore Client socket timeout in seconds + hive.metastore.client.socket.timeout + 600s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + MetaStore Client socket timeout in seconds + - javax.jdo.option.ConnectionPassword + javax.jdo.option.ConnectionPassword mine password to use against metastore database - hive.metastore.ds.connection.url.hook + hive.metastore.ds.connection.url.hook Name of the hook to use for retrieving the JDO connection URL. If empty, the value in javax.jdo.option.ConnectionURL is used - javax.jdo.option.Multithreaded + javax.jdo.option.Multithreaded true Set this to true if multiple threads access metastore through JDO concurrently. - javax.jdo.option.ConnectionURL + javax.jdo.option.ConnectionURL jdbc:derby:;databaseName=metastore_db;create=true JDBC connect string for a JDBC metastore - hive.hmshandler.retry.attempts + hive.hmshandler.retry.attempts 1 - The number of times to retry a HMSHandler call if there were a connection error + The number of times to retry a HMSHandler call if there were a connection error. - hive.hmshandler.retry.interval - 1000 - The number of milliseconds between HMSHandler retry attempts + hive.hmshandler.retry.interval + 1000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The time between HMSHandler retry attempts on failure. + - hive.hmshandler.force.reload.conf + hive.hmshandler.force.reload.conf false Whether to force reloading of the HMSHandler configuration (including @@ -394,22 +403,22 @@ - hive.metastore.server.min.threads + hive.metastore.server.min.threads 200 Minimum number of worker threads in the Thrift server's pool. - hive.metastore.server.max.threads + hive.metastore.server.max.threads 100000 Maximum number of worker threads in the Thrift server's pool. - hive.metastore.server.tcp.keepalive + hive.metastore.server.tcp.keepalive true Whether to enable TCP keepalive for the metastore server. Keepalive will prevent accumulation of half-open connections. - hive.metastore.archive.intermediate.original + hive.metastore.archive.intermediate.original _INTERMEDIATE_ORIGINAL Intermediate dir suffixes used for archiving. Not important what they @@ -417,22 +426,22 @@ - hive.metastore.archive.intermediate.archived + hive.metastore.archive.intermediate.archived _INTERMEDIATE_ARCHIVED - hive.metastore.archive.intermediate.extracted + hive.metastore.archive.intermediate.extracted _INTERMEDIATE_EXTRACTED - hive.metastore.kerberos.keytab.file + hive.metastore.kerberos.keytab.file The path to the Kerberos Keytab file containing the metastore Thrift server's service principal. - hive.metastore.kerberos.principal + hive.metastore.kerberos.principal hive-metastore/_HOST@EXAMPLE.COM The service principal for the metastore Thrift server. @@ -440,77 +449,77 @@ - hive.metastore.sasl.enabled + hive.metastore.sasl.enabled false If true, the metastore Thrift interface will be secured with SASL. Clients must authenticate with Kerberos. - hive.metastore.thrift.framed.transport.enabled + hive.metastore.thrift.framed.transport.enabled false If true, the metastore Thrift interface will use TFramedTransport. When false (default) a standard TTransport is used. - hive.cluster.delegation.token.store.class + hive.cluster.delegation.token.store.class org.apache.hadoop.hive.thrift.MemoryTokenStore The delegation token store implementation. Set to org.apache.hadoop.hive.thrift.ZooKeeperTokenStore for load-balanced cluster. - hive.cluster.delegation.token.store.zookeeper.connectString + hive.cluster.delegation.token.store.zookeeper.connectString The ZooKeeper token store connect string. - hive.cluster.delegation.token.store.zookeeper.znode + hive.cluster.delegation.token.store.zookeeper.znode /hive/cluster/delegation The root path for token store data. - hive.cluster.delegation.token.store.zookeeper.acl + hive.cluster.delegation.token.store.zookeeper.acl ACL for token store entries. List comma separated all server principals for the cluster. - hive.metastore.cache.pinobjtypes + hive.metastore.cache.pinobjtypes Table,StorageDescriptor,SerDeInfo,Partition,Database,Type,FieldSchema,Order List of comma separated metastore object types that should be pinned in the cache - datanucleus.connectionPoolingType + datanucleus.connectionPoolingType BONECP Specify connection pool library for datanucleus - datanucleus.validateTables + datanucleus.validateTables false validates existing schema against code. turn this on if you want to verify existing schema - datanucleus.validateColumns + datanucleus.validateColumns false validates existing schema against code. turn this on if you want to verify existing schema - datanucleus.validateConstraints + datanucleus.validateConstraints false validates existing schema against code. turn this on if you want to verify existing schema - datanucleus.storeManagerType + datanucleus.storeManagerType rdbms metadata store type - datanucleus.autoCreateSchema + datanucleus.autoCreateSchema true creates necessary schema on a startup if one doesn't exist. set this to false, after creating it once - datanucleus.fixedDatastore + datanucleus.fixedDatastore false - hive.metastore.schema.verification + hive.metastore.schema.verification false Enforce metastore schema version consistency. @@ -521,27 +530,27 @@ - datanucleus.autoStartMechanismMode + datanucleus.autoStartMechanismMode checked throw exception if metadata tables are incorrect - datanucleus.transactionIsolation + datanucleus.transactionIsolation read-committed Default transaction isolation level for identity generation. - datanucleus.cache.level2 + datanucleus.cache.level2 false Use a level 2 cache. Turn this off if metadata is changed independently of Hive metastore server - datanucleus.cache.level2.type + datanucleus.cache.level2.type none - datanucleus.identifierFactory + datanucleus.identifierFactory datanucleus1 Name of the identifier factory to use when generating table/column names etc. @@ -549,17 +558,17 @@ - datanucleus.rdbms.useLegacyNativeValueStrategy + datanucleus.rdbms.useLegacyNativeValueStrategy true - datanucleus.plugin.pluginRegistryBundleCheck + datanucleus.plugin.pluginRegistryBundleCheck LOG Defines what happens when plugin bundles are found and are duplicated [EXCEPTION|LOG|NONE] - hive.metastore.batch.retrieve.max + hive.metastore.batch.retrieve.max 300 Maximum number of objects (tables/partitions) can be retrieved from metastore in one batch. @@ -568,12 +577,12 @@ - hive.metastore.batch.retrieve.table.partition.max + hive.metastore.batch.retrieve.table.partition.max 1000 Maximum number of table partitions that metastore internally retrieves in one batch. - hive.metastore.init.hooks + hive.metastore.init.hooks A comma separated list of hooks to be invoked at the beginning of HMSHandler initialization. @@ -581,17 +590,17 @@ - hive.metastore.pre.event.listeners + hive.metastore.pre.event.listeners List of comma separated listeners for metastore events. - hive.metastore.event.listeners + hive.metastore.event.listeners - hive.metastore.authorization.storage.checks + hive.metastore.authorization.storage.checks false Should the metastore do authorization checks against the underlying storage (usually hdfs) @@ -601,17 +610,23 @@ - hive.metastore.event.clean.freq - 0 - Frequency at which timer task runs to purge expired events in metastore(in seconds). + hive.metastore.event.clean.freq + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Frequency at which timer task runs to purge expired events in metastore. + - hive.metastore.event.expiry.duration - 0 - Duration after which events expire from events table (in seconds) + hive.metastore.event.expiry.duration + 0s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Duration after which events expire from events table + - hive.metastore.execute.setugi + hive.metastore.execute.setugi true In unsecure mode, setting this property to true will cause the metastore to execute DFS operations using @@ -621,12 +636,12 @@ - hive.metastore.partition.name.whitelist.pattern + hive.metastore.partition.name.whitelist.pattern Partition names will be checked against this regex pattern and rejected if not matched. - hive.metastore.integral.jdo.pushdown + hive.metastore.integral.jdo.pushdown false Allow JDO query pushdown for integral partition columns in metastore. Off by default. This @@ -637,17 +652,17 @@ - hive.metastore.try.direct.sql + hive.metastore.try.direct.sql true - hive.metastore.try.direct.sql.ddl + hive.metastore.try.direct.sql.ddl true - hive.metastore.disallow.incompatible.col.type.changes + hive.metastore.disallow.incompatible.col.type.changes false If true (default is false), ALTER TABLE operations which change the type of @@ -665,17 +680,17 @@ - hive.table.parameters.default + hive.table.parameters.default Default property values for newly created tables - hive.ddl.createtablelike.properties.whitelist + hive.ddl.createtablelike.properties.whitelist Table Properties to copy over when executing a Create Table Like. - hive.metastore.rawstore.impl + hive.metastore.rawstore.impl org.apache.hadoop.hive.metastore.ObjectStore Name of the class that implements org.apache.hadoop.hive.metastore.rawstore interface. @@ -683,42 +698,42 @@ - javax.jdo.option.ConnectionDriverName + javax.jdo.option.ConnectionDriverName org.apache.derby.jdbc.EmbeddedDriver Driver class name for a JDBC metastore - javax.jdo.PersistenceManagerFactoryClass + javax.jdo.PersistenceManagerFactoryClass org.datanucleus.api.jdo.JDOPersistenceManagerFactory class implementing the jdo persistence - hive.metastore.expression.proxy + hive.metastore.expression.proxy org.apache.hadoop.hive.ql.optimizer.ppr.PartitionExpressionForMetastore - javax.jdo.option.DetachAllOnCommit + javax.jdo.option.DetachAllOnCommit true Detaches all objects from session so that they can be used after transaction is committed - javax.jdo.option.NonTransactionalRead + javax.jdo.option.NonTransactionalRead true Reads outside of transactions - javax.jdo.option.ConnectionUserName + javax.jdo.option.ConnectionUserName APP Username to use against metastore database - hive.metastore.end.function.listeners + hive.metastore.end.function.listeners List of comma separated listeners for the end of metastore functions. - hive.metastore.partition.inherit.table.properties + hive.metastore.partition.inherit.table.properties List of comma separated keys occurring in table properties which will get inherited to newly created partitions. @@ -726,7 +741,7 @@ - hive.metadata.export.location + hive.metadata.export.location When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, @@ -735,7 +750,7 @@ - hive.metadata.move.exported.metadata.to.trash + hive.metadata.move.exported.metadata.to.trash true When used in conjunction with the org.apache.hadoop.hive.ql.parse.MetaDataExportListener pre event listener, @@ -744,17 +759,17 @@ - hive.cli.errors.ignore + hive.cli.errors.ignore false - hive.cli.print.current.db + hive.cli.print.current.db false Whether to include the current database in the Hive prompt. - hive.cli.prompt + hive.cli.prompt hive Command line prompt configuration value. Other hiveconf can be used in this configuration value. @@ -762,7 +777,7 @@ - hive.cli.pretty.output.num.cols + hive.cli.pretty.output.num.cols -1 The number of columns to use when formatting output generated by the DESCRIBE PRETTY table_name command. @@ -770,85 +785,86 @@ - hive.metastore.fs.handler.class + hive.metastore.fs.handler.class org.apache.hadoop.hive.metastore.HiveMetaStoreFsImpl - hive.session.id + hive.session.id - hive.session.silent + hive.session.silent false - hive.session.history.enabled + hive.session.history.enabled false Whether to log Hive query, query plan, runtime statistics etc. - hive.query.string + hive.query.string Query being executed (might be multiple per a session) - hive.query.id + hive.query.id ID for query being executed (might be multiple per a session) - hive.jobname.length + hive.jobname.length 50 max jobname length - hive.jar.path + hive.jar.path - hive.aux.jars.path + hive.aux.jars.path - hive.added.files.path + hive.added.files.path - hive.added.jars.path + hive.added.jars.path - hive.added.archives.path + hive.added.archives.path - hive.auto.progress.timeout - 0 + hive.auto.progress.timeout + 0s - How long to run autoprogressor for the script/UDTF operators (in seconds). + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + How long to run autoprogressor for the script/UDTF operators. Set to 0 for forever. - hive.table.name + hive.table.name - hive.partition.name + hive.partition.name - hive.script.auto.progress + hive.script.auto.progress false Whether Hive Transform/Map/Reduce Clause should automatically send progress information to TaskTracker @@ -858,7 +874,7 @@ - hive.script.operator.id.env.var + hive.script.operator.id.env.var HIVE_SCRIPT_OPERATOR_ID Name of the environment variable that holds the unique script operator ID in the user's @@ -866,12 +882,12 @@ - hive.script.operator.truncate.env + hive.script.operator.truncate.env false Truncate each environment variable for external script in scripts operator to 20KB (to fit system limits) - hive.mapred.mode + hive.mapred.mode nonstrict The mode in which the Hive operations are being performed. @@ -884,22 +900,22 @@ - hive.alias + hive.alias - hive.map.aggr + hive.map.aggr true Whether to use map-side aggregation in Hive Group By queries - hive.groupby.skewindata + hive.groupby.skewindata false Whether there is skew in data to optimize group by queries - hive.optimize.multigroupby.common.distincts + hive.optimize.multigroupby.common.distincts true Whether to optimize a multi-groupby query with the same distinct. @@ -918,27 +934,27 @@ - hive.join.emit.interval + hive.join.emit.interval 1000 How many rows in the right-most join operand Hive should buffer before emitting the join result. - hive.join.cache.size + hive.join.cache.size 25000 How many rows in the joining tables (except the streaming table) should be cached in memory. - hive.cbo.enable - false + hive.cbo.enable + true Flag to control enabling Cost Based Optimizations using Optiq framework. - hive.mapjoin.bucket.cache.size + hive.mapjoin.bucket.cache.size 100 - hive.mapjoin.optimized.hashtable + hive.mapjoin.optimized.hashtable true Whether Hive should use memory-optimized hash table for MapJoin. Only works on Tez, @@ -946,7 +962,7 @@ - hive.mapjoin.optimized.keys + hive.mapjoin.optimized.keys true Whether MapJoin hashtable should use optimized (size-wise), keys, allowing the table to take less @@ -954,7 +970,7 @@ - hive.mapjoin.lazy.hashtable + hive.mapjoin.lazy.hashtable true Whether MapJoin hashtable should deserialize values on demand. Depending on how many values in @@ -963,7 +979,7 @@ - hive.mapjoin.optimized.hashtable.wbsize + hive.mapjoin.optimized.hashtable.wbsize 10485760 Optimized hashtable (see hive.mapjoin.optimized.hashtable) uses a chain of buffers to @@ -972,27 +988,27 @@ - hive.smbjoin.cache.rows + hive.smbjoin.cache.rows 10000 How many rows with the same key value should be cached in memory per smb joined table. - hive.groupby.mapaggr.checkinterval + hive.groupby.mapaggr.checkinterval 100000 Number of rows after which size of the grouping keys/aggregation classes is performed - hive.map.aggr.hash.percentmemory + hive.map.aggr.hash.percentmemory 0.5 Portion of total memory to be used by map-side group aggregation hash table - hive.mapjoin.followby.map.aggr.hash.percentmemory + hive.mapjoin.followby.map.aggr.hash.percentmemory 0.3 Portion of total memory to be used by map-side group aggregation hash table, when this group by is followed by map join - hive.map.aggr.hash.force.flush.memory.threshold + hive.map.aggr.hash.force.flush.memory.threshold 0.9 The max memory to be used by map-side group aggregation hash table. @@ -1000,7 +1016,7 @@ - hive.map.aggr.hash.min.reduction + hive.map.aggr.hash.min.reduction 0.5 Hash aggregation will be turned off if the ratio between hash table size and input rows is bigger than this number. @@ -1008,7 +1024,7 @@ - hive.multigroupby.singlereducer + hive.multigroupby.singlereducer true Whether to optimize multi group by query to generate single M/R job plan. If the multi group by query has @@ -1016,7 +1032,7 @@ - hive.map.groupby.sorted + hive.map.groupby.sorted false If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform @@ -1025,7 +1041,7 @@ - hive.map.groupby.sorted.testmode + hive.map.groupby.sorted.testmode false If the bucketing/sorting properties of the table exactly match the grouping key, whether to perform @@ -1034,12 +1050,12 @@ - hive.groupby.orderby.position.alias + hive.groupby.orderby.position.alias false Whether to enable using Column Position Alias in Group By or Order By - hive.new.job.grouping.set.cardinality + hive.new.job.grouping.set.cardinality 30 Whether a new map-reduce job should be launched for grouping sets/rollups/cubes. @@ -1054,7 +1070,7 @@ - hive.udtf.auto.progress + hive.udtf.auto.progress false Whether Hive should automatically send progress information to TaskTracker @@ -1063,45 +1079,48 @@ - hive.default.fileformat + hive.default.fileformat TextFile - Default file format for CREATE TABLE statement. - Options are TextFile, SequenceFile, RCfile and ORC. Users can explicitly override it by CREATE TABLE ... STORED AS [FORMAT] + Expects one of [textfile, sequencefile, rcfile, orc]. + Default file format for CREATE TABLE statement. Users can explicitly override it by CREATE TABLE ... STORED AS [FORMAT] - hive.query.result.fileformat + hive.query.result.fileformat TextFile - Default file format for storing result of the query. Allows TextFile, SequenceFile and RCfile + + Expects one of [textfile, sequencefile, rcfile]. + Default file format for storing result of the query. + - hive.fileformat.check + hive.fileformat.check true Whether to check file format or not when loading data files - hive.default.rcfile.serde + hive.default.rcfile.serde org.apache.hadoop.hive.serde2.columnar.LazyBinaryColumnarSerDe The default SerDe Hive will use for the RCFile format - hive.default.serde + hive.default.serde org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe The default SerDe Hive will use for storage formats that do not specify a SerDe. - hive.serdes.using.metastore.for.schema + hive.serdes.using.metastore.for.schema 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 SerDes retriving schema from metastore. This an internal parameter. Check with the hive dev. team - hive.querylog.location + hive.querylog.location ${system:java.io.tmpdir}/${system:user.name} Location of Hive run time structured log file - hive.querylog.enable.plan.progress + hive.querylog.enable.plan.progress true Whether to log the plan's progress every time a job's progress is checked. @@ -1109,10 +1128,11 @@ - hive.querylog.plan.progress.interval - 60000 + hive.querylog.plan.progress.interval + 60000ms - The interval to wait between logging the plan's progress in milliseconds. + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The interval to wait between logging the plan's progress. If there is a whole number percentage change in the progress of the mappers or the reducers, the progress is logged regardless of this value. The actual interval will be the ceiling of (this value divided by the value of @@ -1123,22 +1143,22 @@ - hive.script.serde + hive.script.serde org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe The default SerDe for transmitting input data to and reading output data from the user scripts. - hive.script.recordreader + hive.script.recordreader org.apache.hadoop.hive.ql.exec.TextRecordReader The default record reader for reading data from the user scripts. - hive.script.recordwriter + hive.script.recordwriter org.apache.hadoop.hive.ql.exec.TextRecordWriter The default record writer for writing data to the user scripts. - hive.transform.escape.input + hive.transform.escape.input false This adds an option to escape special chars (newlines, carriage returns and @@ -1147,7 +1167,7 @@ - hive.binary.record.max.length + hive.binary.record.max.length 1000 Read from a binary stream and treat each hive.binary.record.max.length bytes as a record. @@ -1155,27 +1175,27 @@ - hive.hwi.listen.host + hive.hwi.listen.host 0.0.0.0 This is the host address the Hive Web Interface will listen on - hive.hwi.listen.port + hive.hwi.listen.port 9999 This is the port the Hive Web Interface will listen on - hive.hwi.war.file + hive.hwi.war.file ${env:HWI_WAR_FILE} This sets the path to the HWI war file, relative to ${HIVE_HOME}. - hive.mapred.local.mem + hive.mapred.local.mem 0 mapper/reducer memory in local mode - hive.mapjoin.smalltable.filesize + hive.mapjoin.smalltable.filesize 25000000 The threshold for the input file size of the small tables; if the file size is smaller @@ -1183,22 +1203,22 @@ - hive.sample.seednumber + hive.sample.seednumber 0 A number used to percentage sampling. By changing this number, user will change the subsets of data sampled. - hive.test.mode + hive.test.mode false Whether Hive is running in test mode. If yes, it turns on sampling and prefixes the output tablename. - hive.test.mode.prefix + hive.test.mode.prefix test_ In test mode, specfies prefixes for the output table - hive.test.mode.samplefreq + hive.test.mode.samplefreq 32 In test mode, specfies sampling frequency for table, which is not bucketed, @@ -1210,42 +1230,42 @@ - hive.test.mode.nosamplelist + hive.test.mode.nosamplelist In test mode, specifies comma separated table names which would not apply sampling - hive.test.dummystats.aggregator + hive.test.dummystats.aggregator internal variable for test - hive.test.dummystats.publisher + hive.test.dummystats.publisher internal variable for test - hive.merge.mapfiles + hive.merge.mapfiles true Merge small files at the end of a map-only job - hive.merge.mapredfiles + hive.merge.mapredfiles false Merge small files at the end of a map-reduce job - hive.merge.tezfiles + hive.merge.tezfiles false Merge small files at the end of a Tez DAG - hive.merge.size.per.task + hive.merge.size.per.task 256000000 Size of merged files at the end of the job - hive.merge.smallfiles.avgsize + hive.merge.smallfiles.avgsize 16000000 When the average output file size of a job is less than this number, Hive will start an additional @@ -1254,17 +1274,17 @@ - hive.merge.rcfile.block.level + hive.merge.rcfile.block.level true - hive.merge.input.format.block.level + hive.merge.input.format.block.level org.apache.hadoop.hive.ql.io.rcfile.merge.RCFileBlockMergeInputFormat - hive.merge.orcfile.stripe.level + hive.merge.orcfile.stripe.level true When hive.merge.mapfiles or hive.merge.mapredfiles is enabled while writing a @@ -1274,17 +1294,17 @@ - hive.merge.input.format.stripe.level + hive.merge.input.format.stripe.level org.apache.hadoop.hive.ql.io.orc.OrcFileStripeMergeInputFormat Input file format to use for ORC stripe level merging (for internal use only) - hive.merge.current.job.has.dynamic.partitions + hive.merge.current.job.has.dynamic.partitions false - hive.exec.rcfile.use.explicit.header + hive.exec.rcfile.use.explicit.header true If this is set the header for RCFiles will simply be RCF. If this is not @@ -1293,52 +1313,52 @@ - hive.exec.rcfile.use.sync.cache + hive.exec.rcfile.use.sync.cache true - hive.io.rcfile.record.interval + hive.io.rcfile.record.interval 2147483647 - hive.io.rcfile.column.number.conf + hive.io.rcfile.column.number.conf 0 - hive.io.rcfile.tolerate.corruptions + hive.io.rcfile.tolerate.corruptions false - hive.io.rcfile.record.buffer.size + hive.io.rcfile.record.buffer.size 4194304 - hive.exec.orc.memory.pool + hive.exec.orc.memory.pool 0.5 Maximum fraction of heap that can be used by ORC file writers - hive.exec.orc.write.format + hive.exec.orc.write.format Define the version of the file to write - hive.exec.orc.default.stripe.size + hive.exec.orc.default.stripe.size 67108864 Define the default ORC stripe size - hive.exec.orc.default.block.size + hive.exec.orc.default.block.size 268435456 Define the default file system block size for ORC files. - hive.exec.orc.dictionary.key.size.threshold + hive.exec.orc.dictionary.key.size.threshold 0.8 If the number of keys in a dictionary is greater than this fraction of the total number of @@ -1346,22 +1366,31 @@ - hive.exec.orc.default.row.index.stride + hive.exec.orc.default.row.index.stride 10000 Define the default ORC index stride - hive.exec.orc.default.buffer.size + hive.orc.row.index.stride.dictionary.check + true + + If enabled dictionary check will happen after first row index stride (default 10000 rows) + else dictionary check will happen before writing first stripe. In both cases, the decision + to use dictionary or not will be retained thereafter. + + + + hive.exec.orc.default.buffer.size 262144 Define the default ORC buffer size - hive.exec.orc.default.block.padding + hive.exec.orc.default.block.padding true Define the default block padding - hive.exec.orc.block.padding.tolerance + hive.exec.orc.block.padding.tolerance 0.05 Define the tolerance for block padding as a percentage of stripe size. @@ -1371,22 +1400,22 @@ - hive.exec.orc.default.compress + hive.exec.orc.default.compress ZLIB Define the default compression codec for ORC file - hive.exec.orc.encoding.strategy + hive.exec.orc.encoding.strategy SPEED + Expects one of [speed, compression]. Define the encoding strategy to use while writing data. Changing this will only affect the light weight encoding for integers. This flag will not change the compression level of higher level compression codec (like ZLIB). - Possible options are SPEED and COMPRESSION. - hive.orc.splits.include.file.footer + hive.orc.splits.include.file.footer false If turned on splits generated by orc will include metadata about the stripes in the file. This @@ -1394,17 +1423,17 @@ - hive.orc.cache.stripe.details.size + hive.orc.cache.stripe.details.size 10000 Cache size for keeping meta info about orc splits cached in the client. - hive.orc.compute.splits.num.threads + hive.orc.compute.splits.num.threads 10 How many threads orc should use to create splits in parallel. - hive.exec.orc.skip.corrupt.data + hive.exec.orc.skip.corrupt.data false If ORC reader encounters corrupt data, this value will be used to determine @@ -1412,12 +1441,12 @@ - hive.exec.orc.zerocopy + hive.exec.orc.zerocopy false Use zerocopy reads with ORC. - hive.lazysimple.extended_boolean_literal + hive.lazysimple.extended_boolean_literal false LazySimpleSerde uses this property to determine if it treats 'T', 't', 'F', 'f', @@ -1427,7 +1456,7 @@ - hive.optimize.skewjoin + hive.optimize.skewjoin false Whether to enable skew join optimization. @@ -1439,12 +1468,12 @@ - hive.auto.convert.join + hive.auto.convert.join true Whether Hive enables the optimization about converting common join into mapjoin based on the input file size - hive.auto.convert.join.noconditionaltask + hive.auto.convert.join.noconditionaltask true Whether Hive enables the optimization about converting common join into mapjoin based on the input file size. @@ -1453,7 +1482,7 @@ - hive.auto.convert.join.noconditionaltask.size + hive.auto.convert.join.noconditionaltask.size 10000000 If hive.auto.convert.join.noconditionaltask is off, this parameter does not take affect. @@ -1462,7 +1491,7 @@ - hive.auto.convert.join.use.nonstaged + hive.auto.convert.join.use.nonstaged false For conditional joins, if input stream from a small alias can be directly applied to join operator without @@ -1471,7 +1500,7 @@ - hive.skewjoin.key + hive.skewjoin.key 100000 Determine if we get a skew key in join. If we see more than the specified number of rows with the same key in join operator, @@ -1479,7 +1508,7 @@ - hive.skewjoin.mapjoin.map.tasks + hive.skewjoin.mapjoin.map.tasks 10000 Determine the number of map task used in the follow up map join job for a skew join. @@ -1487,7 +1516,7 @@ - hive.skewjoin.mapjoin.min.split + hive.skewjoin.mapjoin.min.split 33554432 Determine the number of map task at most used in the follow up map join job for a skew join by specifying @@ -1495,27 +1524,27 @@ - hive.heartbeat.interval + hive.heartbeat.interval 1000 Send a heartbeat after this interval - used by mapjoin and filter operators - hive.limit.row.max.size + hive.limit.row.max.size 100000 When trying a smaller subset of data for simple LIMIT, how much size we need to guarantee each row to have at least. - hive.limit.optimize.limit.file + hive.limit.optimize.limit.file 10 When trying a smaller subset of data for simple LIMIT, maximum number of files we can sample. - hive.limit.optimize.enable + hive.limit.optimize.enable false Whether to enable to optimization to trying a smaller subset of data for simple LIMIT first. - hive.limit.optimize.fetch.max + hive.limit.optimize.fetch.max 50000 Maximum number of rows allowed for a smaller subset of data for simple LIMIT, if it is a fetch query. @@ -1523,12 +1552,12 @@ - hive.limit.pushdown.memory.usage + hive.limit.pushdown.memory.usage -1.0 The max memory to be used for hash in RS operator for top K selection. - hive.limit.query.max.table.partition + hive.limit.query.max.table.partition -1 This controls how many partitions can be scanned for each partitioned table. @@ -1536,22 +1565,22 @@ - hive.hashtable.key.count.adjustment + hive.hashtable.key.count.adjustment 1.0 Adjustment to mapjoin hashtable size derived from table and column statistics; the estimate of the number of keys is divided by this value. If the value is 0, statistics are not usedand hive.hashtable.initialCapacity is used instead. - hive.hashtable.initialCapacity + hive.hashtable.initialCapacity 100000 Initial capacity of mapjoin hashtable if statistics are absent, or if hive.hashtable.stats.key.estimate.adjustment is set to 0 - hive.hashtable.loadfactor + hive.hashtable.loadfactor 0.75 - hive.mapjoin.followby.gby.localtask.max.memory.usage + hive.mapjoin.followby.gby.localtask.max.memory.usage 0.55 This number means how much memory the local task can take to hold the key/value into an in-memory hash table @@ -1560,7 +1589,7 @@ - hive.mapjoin.localtask.max.memory.usage + hive.mapjoin.localtask.max.memory.usage 0.9 This number means how much memory the local task can take to hold the key/value into an in-memory hash table. @@ -1569,37 +1598,37 @@ - hive.mapjoin.check.memory.rows + hive.mapjoin.check.memory.rows 100000 The number means after how many rows processed it needs to check the memory usage - hive.debug.localtask + hive.debug.localtask false - hive.input.format + hive.input.format org.apache.hadoop.hive.ql.io.CombineHiveInputFormat The default input format. Set this to HiveInputFormat if you encounter problems with CombineHiveInputFormat. - hive.tez.input.format + hive.tez.input.format org.apache.hadoop.hive.ql.io.HiveInputFormat The default input format for tez. Tez groups splits in the AM. - hive.tez.container.size + hive.tez.container.size -1 By default Tez will spawn containers of the size of a mapper. This can be used to overwrite. - hive.tez.java.opts + hive.tez.java.opts By default Tez will use the Java options from map tasks. This can be used to overwrite. - hive.tez.log.level + hive.tez.log.level INFO The log level to use for tasks executing as part of the DAG. @@ -1607,17 +1636,17 @@ - hive.enforce.bucketing + hive.enforce.bucketing false Whether bucketing is enforced. If true, while inserting into the table, bucketing is enforced. - hive.enforce.sorting + hive.enforce.sorting false Whether sorting is enforced. If true, while inserting into the table, sorting is enforced. - hive.optimize.bucketingsorting + hive.optimize.bucketingsorting true If hive.enforce.bucketing or hive.enforce.sorting is true, don't create a reducer for enforcing @@ -1627,17 +1656,17 @@ - hive.mapred.partitioner + hive.mapred.partitioner org.apache.hadoop.hive.ql.io.DefaultHivePartitioner - hive.enforce.sortmergebucketmapjoin + hive.enforce.sortmergebucketmapjoin false If the user asked for sort-merge bucketed map-side join, and it cannot be performed, should the query fail or not ? - hive.enforce.bucketmapjoin + hive.enforce.bucketmapjoin false If the user asked for bucketed map-side join, and it cannot be performed, @@ -1647,12 +1676,12 @@ - hive.auto.convert.sortmerge.join + hive.auto.convert.sortmerge.join false Will the join be automatically converted to a sort-merge join, if the joined tables pass the criteria for sort-merge join. - hive.auto.convert.sortmerge.join.bigtable.selection.policy + hive.auto.convert.sortmerge.join.bigtable.selection.policy org.apache.hadoop.hive.ql.optimizer.AvgPartitionSizeBasedBigTableSelectorForAutoSMJ The policy to choose the big table for automatic conversion to sort-merge join. @@ -1667,7 +1696,7 @@ - hive.auto.convert.sortmerge.join.to.mapjoin + hive.auto.convert.sortmerge.join.to.mapjoin false If hive.auto.convert.sortmerge.join is set to true, and a join was converted to a sort-merge join, @@ -1681,82 +1710,82 @@ - hive.exec.script.trust + hive.exec.script.trust false - hive.exec.rowoffset + hive.exec.rowoffset false Whether to provide the row offset virtual column - hive.hadoop.supports.splittable.combineinputformat + hive.hadoop.supports.splittable.combineinputformat false - hive.optimize.index.filter + hive.optimize.index.filter false Whether to enable automatic use of indexes - hive.optimize.index.autoupdate + hive.optimize.index.autoupdate false Whether to update stale indexes automatically - hive.optimize.ppd + hive.optimize.ppd true Whether to enable predicate pushdown - hive.ppd.recognizetransivity + hive.ppd.recognizetransivity true Whether to transitively replicate predicate filters over equijoin conditions. - hive.ppd.remove.duplicatefilters + hive.ppd.remove.duplicatefilters true Whether to push predicates down into storage handlers. Ignored when hive.optimize.ppd is false. - hive.optimize.constant.propagation + hive.optimize.constant.propagation true Whether to enable constant propagation optimizer - hive.optimize.metadataonly + hive.optimize.metadataonly true - hive.optimize.null.scan + hive.optimize.null.scan true Dont scan relations which are guaranteed to not generate any rows - hive.optimize.ppd.storage + hive.optimize.ppd.storage true Whether to push predicates down to storage handlers - hive.optimize.groupby + hive.optimize.groupby true Whether to enable the bucketed group by from bucketed partitions/tables. - hive.optimize.bucketmapjoin + hive.optimize.bucketmapjoin false Whether to try bucket mapjoin - hive.optimize.bucketmapjoin.sortedmerge + hive.optimize.bucketmapjoin.sortedmerge false Whether to try sorted bucket merge map join - hive.optimize.reducededuplication + hive.optimize.reducededuplication true Remove extra map-reduce jobs if the data is already clustered by the same key which needs to be used again. @@ -1764,7 +1793,7 @@ - hive.optimize.reducededuplication.min.reducer + hive.optimize.reducededuplication.min.reducer 4 Reduce deduplication merges two RSs by moving key/parts/reducer-num of the child RS to parent RS. @@ -1773,7 +1802,7 @@ - hive.optimize.sort.dynamic.partition + hive.optimize.sort.dynamic.partition true When enabled dynamic partitioning column will be globally sorted. @@ -1782,22 +1811,25 @@ - hive.optimize.sampling.orderby + hive.optimize.sampling.orderby false - + Uses sampling on order-by clause for parallel execution. - hive.optimize.sampling.orderby.number + hive.optimize.sampling.orderby.number 1000 - + Total number of samples to be obtained. - hive.optimize.sampling.orderby.percent + hive.optimize.sampling.orderby.percent 0.1 - + + Expects value between 0.0f and 1.0f. + Probability with which a row will be chosen. + - hive.optimize.union.remove + hive.optimize.union.remove false Whether to remove the union and push the operators between union and the filesink above union. @@ -1812,12 +1844,12 @@ - hive.optimize.correlation + hive.optimize.correlation false exploit intra-query correlations. - hive.mapred.supports.subdirectories + hive.mapred.supports.subdirectories false Whether the version of Hadoop which is running supports sub-directories for tables/partitions. @@ -1826,7 +1858,7 @@ - hive.optimize.skewjoin.compiletime + hive.optimize.skewjoin.compiletime false Whether to create a separate plan for skewed keys for the tables in the join. @@ -1847,72 +1879,78 @@ - hive.optimize.index.filter.compact.minsize + hive.optimize.index.filter.compact.minsize 5368709120 Minimum size (in bytes) of the inputs on which a compact index is automatically used. - hive.optimize.index.filter.compact.maxsize + hive.optimize.index.filter.compact.maxsize -1 Maximum size (in bytes) of the inputs on which a compact index is automatically used. A negative number is equivalent to infinity. - hive.index.compact.query.max.entries + hive.index.compact.query.max.entries 10000000 The maximum number of index entries to read during a query that uses the compact index. Negative value is equivalent to infinity. - hive.index.compact.query.max.size + hive.index.compact.query.max.size 10737418240 The maximum number of bytes that a query using the compact index can read. Negative value is equivalent to infinity. - hive.index.compact.binary.search + hive.index.compact.binary.search true Whether or not to use a binary search to find the entries in an index table that match the filter, where possible - hive.stats.autogather + hive.stats.autogather true A flag to gather statistics automatically during the INSERT OVERWRITE command. - hive.stats.dbclass + hive.stats.dbclass fs - The storage that stores temporary Hive statistics. Currently, jdbc, hbase, counter and custom type are supported. + + Expects one of the pattern in [jdbc(:.*), hbase, counter, custom, fs]. + The storage that stores temporary Hive statistics. Currently, jdbc, hbase, counter and custom type are supported. + - hive.stats.jdbcdriver + hive.stats.jdbcdriver org.apache.derby.jdbc.EmbeddedDriver The JDBC driver for the database that stores temporary Hive statistics. - hive.stats.dbconnectionstring + hive.stats.dbconnectionstring jdbc:derby:;databaseName=TempStatsStore;create=true The default connection string for the database that stores temporary Hive statistics. - hive.stats.default.publisher + hive.stats.default.publisher The Java class (implementing the StatsPublisher interface) that is used by default if hive.stats.dbclass is custom type. - hive.stats.default.aggregator + hive.stats.default.aggregator The Java class (implementing the StatsAggregator interface) that is used by default if hive.stats.dbclass is custom type. - hive.stats.jdbc.timeout - 30 - Timeout value (number of seconds) used by JDBC connection and statements. + hive.stats.jdbc.timeout + 30s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout value used by JDBC connection and statements. + - hive.stats.atomic + hive.stats.atomic false whether to update metastore stats only if all stats are available - hive.stats.retries.max + hive.stats.retries.max 0 Maximum number of retries when stats publisher/aggregator got an exception updating intermediate database. @@ -1920,17 +1958,20 @@ - hive.stats.retries.wait - 3000 - 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]). + hive.stats.retries.wait + 3000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The base waiting window before the next retry. The actual wait time is calculated by baseWindow * failures baseWindow * (failure + 1) * (random number between [0.0,1.0]). + - hive.stats.collect.rawdatasize + hive.stats.collect.rawdatasize true should the raw data size be collected when analyzing tables - hive.client.stats.counters + hive.client.stats.counters Subset of counters that should be of interest for hive.client.stats.publishers (when one wants to limit their publishing). @@ -1938,7 +1979,7 @@ - hive.stats.reliable + hive.stats.reliable false Whether queries will fail because stats cannot be collected completely accurately. @@ -1947,12 +1988,12 @@ - hive.analyze.stmt.collect.partlevel.stats + hive.analyze.stmt.collect.partlevel.stats true analyze table T compute statistics for columns. Queries like these should compute partitionlevel stats for partitioned table even when no part spec is specified. - hive.stats.gather.num.threads + hive.stats.gather.num.threads 10 Number of threads used by partialscan/noscan analyze command for partitioned tables. @@ -1960,7 +2001,7 @@ - hive.stats.collect.tablekeys + hive.stats.collect.tablekeys false Whether join and group by keys on tables are derived and maintained in the QueryPlan. @@ -1968,7 +2009,7 @@ - hive.stats.collect.scancols + hive.stats.collect.scancols false Whether column accesses are tracked in the QueryPlan. @@ -1976,7 +2017,7 @@ - hive.stats.ndv.error + hive.stats.ndv.error 20.0 Standard error expressed in percentage. Provides a tradeoff between accuracy and compute cost. @@ -1984,7 +2025,7 @@ - hive.stats.key.prefix.max.length + hive.stats.key.prefix.max.length 150 Determines if when the prefix of the key used for intermediate stats collection @@ -1992,7 +2033,7 @@ - hive.stats.key.prefix.reserve.length + hive.stats.key.prefix.reserve.length 24 Reserved length for postfix of stats key. Currently only meaningful for counter type which should @@ -2001,7 +2042,7 @@ - hive.stats.max.variable.length + hive.stats.max.variable.length 100 To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), @@ -2013,7 +2054,7 @@ - hive.stats.list.num.entries + hive.stats.list.num.entries 10 To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), @@ -2024,7 +2065,7 @@ - hive.stats.map.num.entries + hive.stats.map.num.entries 10 To estimate the size of data flowing through operators in Hive/Tez(for reducer estimation etc.), @@ -2035,7 +2076,7 @@ - hive.stats.map.parallelism + hive.stats.map.parallelism 1 Hive/Tez optimizer estimates the data size flowing through each of the operators. @@ -2046,7 +2087,7 @@ - hive.stats.fetch.partition.stats + hive.stats.fetch.partition.stats true Annotation of operator tree with statistics information requires partition level basic @@ -2058,7 +2099,7 @@ - hive.stats.fetch.column.stats + hive.stats.fetch.column.stats false Annotation of operator tree with statistics information requires column statistics. @@ -2068,7 +2109,7 @@ - hive.stats.join.factor + hive.stats.join.factor 1.1 Hive/Tez optimizer estimates the data size flowing through each of the operators. JOIN operator @@ -2078,7 +2119,7 @@ - hive.stats.deserialization.factor + hive.stats.deserialization.factor 1.0 Hive/Tez optimizer estimates the data size flowing through each of the operators. In the absence @@ -2089,7 +2130,7 @@ - hive.support.concurrency + hive.support.concurrency false Whether Hive supports concurrency control or not. @@ -2097,27 +2138,30 @@ - hive.lock.manager + hive.lock.manager org.apache.hadoop.hive.ql.lockmgr.zookeeper.ZooKeeperHiveLockManager - hive.lock.numretries + hive.lock.numretries 100 The number of times you want to try to get all the locks - hive.unlock.numretries + hive.unlock.numretries 10 The number of times you want to retry to do one unlock - hive.lock.sleep.between.retries - 60 - The sleep time (in seconds) between various retries + hive.lock.sleep.between.retries + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + The sleep time between various retries + - hive.lock.mapred.only.operation + hive.lock.mapred.only.operation false This param is to control whether or not only do lock on queries @@ -2125,17 +2169,17 @@ - hive.zookeeper.quorum + hive.zookeeper.quorum The list of ZooKeeper servers to talk to. This is only needed for read/write locks. - hive.zookeeper.client.port + hive.zookeeper.client.port 2181 The port of ZooKeeper servers to talk to. This is only needed for read/write locks. - hive.zookeeper.session.timeout + hive.zookeeper.session.timeout 600000 ZooKeeper client's session timeout. The client is disconnected, and as a result, all locks released, @@ -2143,27 +2187,30 @@ - hive.zookeeper.namespace + hive.zookeeper.namespace hive_zookeeper_namespace The parent node under which all ZooKeeper nodes are created. - hive.zookeeper.clean.extra.nodes + hive.zookeeper.clean.extra.nodes false Clean extra nodes at the end of the session. - hive.txn.manager + hive.txn.manager org.apache.hadoop.hive.ql.lockmgr.DummyTxnManager - hive.txn.timeout - 300 - time after which transactions are declared aborted if the client has not sent a heartbeat, in seconds. + hive.txn.timeout + 300s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + time after which transactions are declared aborted if the client has not sent a heartbeat. + - hive.txn.max.open.batch + hive.txn.max.open.batch 1000 Maximum number of transactions that can be fetched in one call to open_txns(). @@ -2173,33 +2220,35 @@ - hive.compactor.initiator.on + hive.compactor.initiator.on false Whether to run the compactor's initiator thread in this metastore instance or not. - hive.compactor.worker.threads + hive.compactor.worker.threads 0 Number of compactor worker threads to run on this metastore instance. - hive.compactor.worker.timeout - 86400 + hive.compactor.worker.timeout + 86400s - Time in seconds, before a given compaction in working state is declared a failure + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time before a given compaction in working state is declared a failure and returned to the initiated state. - hive.compactor.check.interval - 300 + hive.compactor.check.interval + 300s - Time in seconds between checks to see if any partitions need compacted. + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time between checks to see if any partitions need compacted. This should be kept high because each check for compaction requires many calls against the NameNode. - hive.compactor.delta.num.threshold + hive.compactor.delta.num.threshold 10 Number of delta files that must exist in a directory before the compactor will attempt @@ -2207,12 +2256,12 @@ - hive.compactor.delta.pct.threshold + hive.compactor.delta.pct.threshold 0.1 Percentage (by size) of base that deltas can be before major compaction is initiated. - hive.compactor.abortedtxn.threshold + hive.compactor.abortedtxn.threshold 1000 Number of aborted transactions involving a particular table or partition before major @@ -2220,7 +2269,7 @@ - hive.hbase.wal.enabled + hive.hbase.wal.enabled true Whether writes to HBase should be forced to the write-ahead log. @@ -2228,39 +2277,40 @@ - hive.hbase.generatehfiles + hive.hbase.generatehfiles false True when HBaseStorageHandler should generate hfiles instead of operate against the online table. - hive.hbase.snapshot.name + hive.hbase.snapshot.name The HBase table snapshot name to use. - hive.hbase.snapshot.restoredir + hive.hbase.snapshot.restoredir /tmp The directory in which to restore the HBase table snapshot. - hive.archive.enabled + hive.archive.enabled false Whether archiving operations are permitted - hive.optimize.index.groupby + hive.optimize.index.groupby false Whether to enable optimization of group-by queries using Aggregate indexes. - hive.outerjoin.supports.filters + hive.outerjoin.supports.filters true - hive.fetch.task.conversion + hive.fetch.task.conversion more + Expects one of [minimal, more]. Some select queries can be converted to single FETCH task minimizing latency. Currently the query should be single sourced not having any subquery and should not have any aggregations or distincts (which incurs RS), lateral views and joins. @@ -2269,7 +2319,7 @@ - hive.fetch.task.conversion.threshold + hive.fetch.task.conversion.threshold 1073741824 Input threshold for applying hive.fetch.task.conversion. If target table is native, input length @@ -2278,7 +2328,7 @@ - hive.fetch.task.aggr + hive.fetch.task.aggr false Aggregation queries with no group-by clause (for example, select count(*) from src) execute @@ -2287,7 +2337,7 @@ - hive.compute.query.using.stats + hive.compute.query.using.stats false When set to true Hive will answer a few queries like count(1) purely using stats @@ -2296,42 +2346,42 @@ - hive.fetch.output.serde + hive.fetch.output.serde org.apache.hadoop.hive.serde2.DelimitedJSONSerDe The SerDe used by FetchTask to serialize the fetch output. - hive.cache.expr.evaluation + hive.cache.expr.evaluation true If true, evaluation result of deterministic expression referenced twice or more will be cached. - hive.variable.substitute + hive.variable.substitute true This enables substitution using syntax like ${var} ${system:var} and ${env:var}. - hive.variable.substitute.depth + hive.variable.substitute.depth 40 The maximum replacements the substitution engine will do. - hive.conf.validation + hive.conf.validation true Enables type checking for registered Hive configurations - hive.semantic.analyzer.hook + hive.semantic.analyzer.hook - hive.security.authorization.enabled + hive.security.authorization.enabled false enable or disable the Hive client authorization - hive.security.authorization.manager + hive.security.authorization.manager org.apache.hadoop.hive.ql.security.authorization.DefaultHiveAuthorizationProvider The Hive client authorization manager class name. The user defined authorization class should implement @@ -2339,7 +2389,7 @@ - hive.security.authenticator.manager + hive.security.authenticator.manager org.apache.hadoop.hive.ql.security.HadoopDefaultAuthenticator hive client authenticator manager class name. The user defined authenticator should implement @@ -2347,7 +2397,7 @@ - hive.security.metastore.authorization.manager + hive.security.metastore.authorization.manager org.apache.hadoop.hive.ql.security.authorization.DefaultHiveMetastoreAuthorizationProvider authorization manager class name to be used in the metastore for authorization. @@ -2356,7 +2406,7 @@ - hive.security.metastore.authenticator.manager + hive.security.metastore.authenticator.manager org.apache.hadoop.hive.ql.security.HadoopDefaultMetastoreAuthenticator authenticator manager class name to be used in the metastore for authentication. @@ -2364,7 +2414,7 @@ - hive.security.authorization.createtable.user.grants + hive.security.authorization.createtable.user.grants the privileges automatically granted to some users whenever a table gets created. @@ -2373,7 +2423,7 @@ - hive.security.authorization.createtable.group.grants + hive.security.authorization.createtable.group.grants the privileges automatically granted to some groups whenever a table gets created. @@ -2382,7 +2432,7 @@ - hive.security.authorization.createtable.role.grants + hive.security.authorization.createtable.role.grants the privileges automatically granted to some roles whenever a table gets created. @@ -2391,7 +2441,7 @@ - hive.security.authorization.createtable.owner.grants + hive.security.authorization.createtable.owner.grants the privileges automatically granted to the owner whenever a table gets created. @@ -2399,32 +2449,32 @@ - hive.security.authorization.sqlstd.confwhitelist + hive.security.authorization.sqlstd.confwhitelist interal variable. List of modifiable configurations by user. - hive.cli.print.header + hive.cli.print.header false Whether to print the names of the columns in query output. - hive.error.on.empty.partition + hive.error.on.empty.partition false Whether to throw an exception if dynamic partition insert generates empty results. - hive.index.compact.file + hive.index.compact.file internal variable - hive.index.blockfilter.file + hive.index.blockfilter.file internal variable - hive.index.compact.file.ignore.hdfs + hive.index.compact.file.ignore.hdfs false When true the HDFS location stored in the index file will be ignored at runtime. @@ -2432,17 +2482,17 @@ - hive.exim.uri.scheme.whitelist + hive.exim.uri.scheme.whitelist hdfs,pfile A comma separated list of acceptable URI schemes for import and export. - hive.mapper.cannot.span.multiple.partitions + hive.mapper.cannot.span.multiple.partitions false - hive.rework.mapredwork + hive.rework.mapredwork false should rework the mapred work or not. @@ -2450,7 +2500,7 @@ - hive.exec.concatenate.check.index + hive.exec.concatenate.check.index true If this is set to true, Hive will throw error when doing @@ -2461,7 +2511,7 @@ - hive.io.exception.handlers + hive.io.exception.handlers A list of io exception handler class names. This is used @@ -2470,7 +2520,17 @@ - hive.log4j.file + hive.server2.logging.operation.enabled + true + When true, HS2 will save operation logs + + + hive.server2.logging.operation.log.location + ${system:java.io.tmpdir}/${system:user.name}/operation_logs + Top level directory where operation logs are stored if logging functionality is enabled + + + hive.log4j.file Hive log4j configuration file. @@ -2480,7 +2540,7 @@ - hive.exec.log4j.file + hive.exec.log4j.file Hive log4j configuration file for execution mode(sub command). @@ -2490,7 +2550,7 @@ - hive.server2.global.init.file.location + hive.server2.global.init.file.location ${env:HIVE_CONF_DIR} The location of HS2 global init file (.hiverc). @@ -2498,7 +2558,7 @@ - hive.autogen.columnalias.prefix.label + hive.autogen.columnalias.prefix.label _c String used as a prefix when auto generating column alias. @@ -2507,12 +2567,12 @@ - hive.autogen.columnalias.prefix.includefuncname + hive.autogen.columnalias.prefix.includefuncname false Whether to include function name in the column alias auto generated by Hive. - hive.exec.perf.logger + hive.exec.perf.logger org.apache.hadoop.hive.ql.log.PerfLogger The class responsible for logging client side performance metrics. @@ -2520,12 +2580,12 @@ - hive.start.cleanup.scratchdir + hive.start.cleanup.scratchdir false To cleanup the Hive scratchdir when starting the Hive Server - hive.insert.into.multilevel.dirs + hive.insert.into.multilevel.dirs false Where to insert into multilevel directories like @@ -2533,7 +2593,7 @@ - hive.warehouse.subdir.inherit.perms + hive.warehouse.subdir.inherit.perms false Set this to true if the the table directories should inherit the @@ -2542,17 +2602,17 @@ - hive.insert.into.external.tables + hive.insert.into.external.tables true whether insert into external tables is allowed - hive.exec.driver.run.hooks + hive.exec.driver.run.hooks A comma separated list of hooks which implement HiveDriverRunHook. Will be run at the beginning and end of Driver.run, these will be run in the order specified. - hive.ddl.output.format + hive.ddl.output.format The data format to use for DDL output. One of "text" (for human @@ -2560,12 +2620,12 @@ - hive.entity.separator + hive.entity.separator @ Separator used to construct names of tables and partitions. For example, dbname@tablename@partitionname - hive.display.partition.cols.separately + hive.display.partition.cols.separately true In older Hive version (0.10 and earlier) no distinction was made between @@ -2575,40 +2635,60 @@ - hive.server2.max.start.attempts + hive.server2.max.start.attempts 30 + Expects value bigger than 0. 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. - hive.server2.transport.mode + hive.server2.transport.mode binary - Server transport mode. "binary" or "http" + + Expects one of [binary, http]. + Transport mode of HiveServer2. + - hive.server2.thrift.http.port + hive.server2.thrift.http.port 10001 Port number when in HTTP mode. - hive.server2.thrift.http.path + hive.server2.thrift.http.path cliservice Path component of URL endpoint when in HTTP mode. - hive.server2.thrift.http.min.worker.threads + hive.server2.thrift.http.min.worker.threads 5 Minimum number of worker threads when in HTTP mode. - hive.server2.thrift.http.max.worker.threads + hive.server2.thrift.http.max.worker.threads 500 Maximum number of worker threads when in HTTP mode. - hive.server2.thrift.port + hive.server2.thrift.http.max.idle.time + 1800s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Maximum idle time for a connection on the server when in HTTP mode. + + + + hive.server2.thrift.http.worker.keepalive.time + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Keepalive time for an idle http worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval. + + + + hive.server2.thrift.port 10000 Port number of HiveServer2 Thrift interface. @@ -2616,7 +2696,7 @@ - hive.server2.thrift.bind.host + hive.server2.thrift.bind.host Bind host on which to run the HiveServer2 Thrift interface. @@ -2624,9 +2704,10 @@ - hive.server2.thrift.sasl.qop + hive.server2.thrift.sasl.qop auth + Expects one of [auth, auth-int, auth-conf]. Sasl QOP value; Set it to one of following values to enable higher levels of protection for HiveServer2 communication with clients. "auth" - authentication only (default) @@ -2636,27 +2717,38 @@ - hive.server2.thrift.min.worker.threads + hive.server2.thrift.min.worker.threads 5 Minimum number of Thrift worker threads - hive.server2.thrift.max.worker.threads + hive.server2.thrift.max.worker.threads 500 Maximum number of Thrift worker threads - hive.server2.async.exec.threads + hive.server2.thrift.worker.keepalive.time + 60s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Keepalive time (in seconds) for an idle worker thread. When the number of workers exceeds min workers, excessive threads are killed after this time interval. + + + + hive.server2.async.exec.threads 100 Number of threads in the async thread pool for HiveServer2 - hive.server2.async.exec.shutdown.timeout - 10 - Time (in seconds) for which HiveServer2 shutdown will wait for async + hive.server2.async.exec.shutdown.timeout + 10s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Maximum time for which HiveServer2 shutdown will wait for async + - hive.server2.async.exec.wait.queue.size + hive.server2.async.exec.wait.queue.size 100 Size of the wait queue for async thread pool in HiveServer2. @@ -2664,25 +2756,27 @@ - hive.server2.async.exec.keepalive.time - 10 + hive.server2.async.exec.keepalive.time + 10s - Time (in seconds) that an idle HiveServer2 async thread (from the thread pool) will wait - for a new task to arrive before terminating + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Time that an idle HiveServer2 async thread (from the thread pool) will wait for a new task + to arrive before terminating - hive.server2.long.polling.timeout - 5000 + hive.server2.long.polling.timeout + 5000ms - Time in milliseconds that HiveServer2 will wait, - before responding to asynchronous calls that use long polling + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time that HiveServer2 will wait before responding to asynchronous calls that use long polling - hive.server2.authentication + hive.server2.authentication NONE + Expects one of [nosasl, none, ldap, kerberos, pam, custom]. Client authentication types. NONE: no authentication check LDAP: LDAP/AD based authentication @@ -2692,22 +2786,22 @@ - hive.server2.allow.user.substitution + hive.server2.allow.user.substitution true Allow alternate user to be specified as part of HiveServer2 open connection request. - hive.server2.authentication.kerberos.keytab + hive.server2.authentication.kerberos.keytab Kerberos keytab file for server principal - hive.server2.authentication.kerberos.principal + hive.server2.authentication.kerberos.principal Kerberos server principal - hive.server2.authentication.spnego.keytab + hive.server2.authentication.spnego.keytab keytab file for SPNego principal, optional, @@ -2723,7 +2817,7 @@ - hive.server2.authentication.spnego.principal + hive.server2.authentication.spnego.principal SPNego service principal, optional, @@ -2734,22 +2828,22 @@ - hive.server2.authentication.ldap.url + hive.server2.authentication.ldap.url LDAP connection URL - hive.server2.authentication.ldap.baseDN + hive.server2.authentication.ldap.baseDN LDAP base DN - hive.server2.authentication.ldap.Domain + hive.server2.authentication.ldap.Domain - hive.server2.custom.authentication.class + hive.server2.custom.authentication.class Custom authentication class. Used when property @@ -2757,12 +2851,12 @@ must be a proper implementation of the interface org.apache.hive.service.auth.PasswdAuthenticationProvider. HiveServer2 will call its Authenticate(user, passed) method to authenticate requests. - The implementation may optionally extend Hadoop's - org.apache.hadoop.conf.Configured class to grab Hive's Configuration object. + The implementation may optionally implement Hadoop's + org.apache.hadoop.conf.Configurable class to grab Hive's Configuration object. - hive.server2.authentication.pam.services + hive.server2.authentication.pam.services List of the underlying pam services that should be used when auth type is PAM @@ -2770,7 +2864,7 @@ - hive.server2.enable.doAs + hive.server2.enable.doAs true Setting this property to true will have HiveServer2 execute @@ -2778,9 +2872,10 @@ - hive.server2.table.type.mapping + hive.server2.table.type.mapping CLASSIC + Expects one of [classic, hive]. This setting reflects how HiveServer2 will report the table types for JDBC and other client implementations that retrieve the available tables and supported table types HIVE : Exposes Hive's native table types like MANAGED_TABLE, EXTERNAL_TABLE, VIRTUAL_VIEW @@ -2788,37 +2883,64 @@ - hive.server2.session.hook + hive.server2.session.hook - hive.server2.use.SSL + hive.server2.use.SSL false - hive.server2.keystore.path + hive.server2.keystore.path - hive.server2.keystore.password + hive.server2.keystore.password - hive.security.command.whitelist + hive.security.command.whitelist set,reset,dfs,add,list,delete,compile Comma separated list of non-SQL Hive commands users are authorized to execute - hive.conf.restricted.list + hive.server2.session.check.interval + 0ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + The time should be bigger than or equal to 3000 msec. + The check interval for session/operation timeout, which can be disabled by setting to zero or negative value. + + + + hive.server2.idle.session.timeout + 0ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Session will be closed when it's not accessed for this duration, which can be disabled by setting to zero or negative value. + + + + hive.server2.idle.operation.timeout + 0ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Operation will be closed when it's not accessed for this duration of time, which can be disabled by setting to zero value. + With positive value, it's checked for operations in terminal state only (FINISHED, CANCELED, CLOSED, ERROR). + With negative value, it's checked for all of the operations regardless of state. + + + + hive.conf.restricted.list hive.security.authenticator.manager,hive.security.authorization.manager,hive.users.in.admin.role Comma separated list of configuration options which are immutable at runtime - hive.multi.insert.move.tasks.share.dependencies + hive.multi.insert.move.tasks.share.dependencies false If this is set all move tasks for tables/partitions (not directories) at the end of a @@ -2834,7 +2956,7 @@ - hive.exec.infer.bucket.sort + hive.exec.infer.bucket.sort false If this is set, when writing partitions, the metadata will include the bucketing/sorting @@ -2843,7 +2965,7 @@ - hive.exec.infer.bucket.sort.num.buckets.power.two + hive.exec.infer.bucket.sort.num.buckets.power.two false If this is set, when setting the number of reducers for the map reduce task which writes the @@ -2864,42 +2986,48 @@ - hive.merge.current.job.concatenate.list.bucketing + hive.merge.current.job.concatenate.list.bucketing true - hive.merge.current.job.concatenate.list.bucketing.depth + hive.merge.current.job.concatenate.list.bucketing.depth 0 - hive.optimize.listbucketing + hive.optimize.listbucketing false Enable list bucketing optimizer. Default value is false so that we disable it by default. - hive.server.read.socket.timeout - 10 - Timeout for the HiveServer to close the connection if no response from the client in N seconds, defaults to 10 seconds. + hive.server.read.socket.timeout + 10s + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is sec if not specified. + Timeout for the HiveServer to close the connection if no response from the client. By default, 10 seconds. + - hive.server.tcp.keepalive + hive.server.tcp.keepalive true Whether to enable TCP keepalive for the Hive Server. Keepalive will prevent accumulation of half-open connections. - hive.decode.partition.name + hive.decode.partition.name false Whether to show the unquoted partition names in query results. - hive.execution.engine + hive.execution.engine mr - Chooses execution engine. Options are: mr (Map reduce, default) or tez (hadoop 2 only) + + Expects one of [mr, tez]. + Chooses execution engine. Options are: mr (Map reduce, default) or tez (hadoop 2 only) + - hive.jar.directory + hive.jar.directory This is the location hive in tez mode will look for to find a site wide @@ -2907,7 +3035,7 @@ - hive.user.install.directory + hive.user.install.directory hdfs:///user/ If hive (in tez mode only) cannot find a usable hive jar in "hive.jar.directory", @@ -2916,7 +3044,7 @@ - hive.vectorized.execution.enabled + hive.vectorized.execution.enabled false This flag should be set to true to enable vectorized mode of query execution. @@ -2924,12 +3052,12 @@ - hive.vectorized.groupby.checkinterval + hive.vectorized.groupby.checkinterval 100000 Number of entries added to the group by aggregation hash before a recomputation of average entry size is performed. - hive.vectorized.groupby.maxentries + hive.vectorized.groupby.maxentries 1000000 Max number of entries in the vector group by aggregation hashtables. @@ -2937,52 +3065,54 @@ - hive.vectorized.groupby.flush.percent + hive.vectorized.groupby.flush.percent 0.1 Percent of entries in the group by aggregation hash flushed when the memory threshold is exceeded. - hive.typecheck.on.insert + hive.typecheck.on.insert true - hive.rpc.query.plan + hive.rpc.query.plan false Whether to send the query plan via local resource or RPC - hive.compute.splits.in.am + hive.compute.splits.in.am true Whether to generate the splits locally or in the AM (tez only) - hive.prewarm.enabled + hive.prewarm.enabled false Enables container prewarm for Tez (Hadoop 2 only) - hive.prewarm.numcontainers + hive.prewarm.numcontainers 10 Controls the number of containers to prewarm for Tez (Hadoop 2 only) - hive.stageid.rearrange + hive.stageid.rearrange none - + + Expects one of [none, idonly, traverse, execution]. + - hive.explain.dependency.append.tasktype + hive.explain.dependency.append.tasktype false - hive.counters.group.name + hive.counters.group.name HIVE The name of counter group for internal Hive variables (CREATED_FILE, FATAL_ERROR, etc.) - hive.server2.tez.default.queues + hive.server2.tez.default.queues A list of comma separated values corresponding to YARN queues of the same name. @@ -2991,7 +3121,7 @@ - hive.server2.tez.sessions.per.default.queue + hive.server2.tez.sessions.per.default.queue 1 A positive integer that determines the number of Tez sessions that should be @@ -3000,7 +3130,7 @@ - hive.server2.tez.initialize.default.sessions + hive.server2.tez.initialize.default.sessions false This flag is used in HiveServer2 to enable a user to use HiveServer2 without @@ -3009,16 +3139,17 @@ - hive.support.quoted.identifiers + hive.support.quoted.identifiers column - Whether to use quoted identifier. 'none' ot 'column' can be used. + Expects one of [none, column]. + Whether to use quoted identifier. 'none' or 'column' can be used. none: default(past) behavior. Implies only alphaNumeric and underscore are valid characters in identifiers. column: implies column names can contain any character. - hive.users.in.admin.role + hive.users.in.admin.role Comma separated list of users who are in admin role for bootstrapping. @@ -3026,7 +3157,7 @@ - hive.compat + hive.compat 0.12 Enable (configurable) deprecated behaviors by setting desired level of backward compatibility. @@ -3035,7 +3166,7 @@ - hive.convert.join.bucket.mapjoin.tez + hive.convert.join.bucket.mapjoin.tez false Whether joins can be automatically converted to bucket map joins in hive @@ -3043,22 +3174,25 @@ - hive.exec.check.crossproducts + hive.exec.check.crossproducts true Check if a plan contains a Cross Product. If there is one, output a warning to the Session's console. - hive.localize.resource.wait.interval - 5000 - Time in milliseconds to wait for another thread to localize the same resource for hive-tez. + hive.localize.resource.wait.interval + 5000ms + + Expects a time value with unit (d/day, h/hour, m/min, s/sec, ms/msec, us/usec, ns/nsec), which is msec if not specified. + Time to wait for another thread to localize the same resource for hive-tez. + - hive.localize.resource.num.wait.attempts + hive.localize.resource.num.wait.attempts 5 The number of attempts waiting for localizing a resource in hive-tez. - hive.tez.auto.reducer.parallelism + hive.tez.auto.reducer.parallelism false Turn on Tez' auto reducer parallelism feature. When enabled, Hive will still estimate data sizes @@ -3067,12 +3201,12 @@ - hive.tez.max.partition.factor + hive.tez.max.partition.factor 2.0 When auto reducer parallelism is enabled this factor will be used to over-partition data in shuffle edges. - hive.tez.min.partition.factor + hive.tez.min.partition.factor 0.25 When auto reducer parallelism is enabled this factor will be used to put a lower limit to the number diff --git a/data/conf/hive-site.xml b/data/conf/hive-site.xml index ed3ee42..50027de 100644 --- a/data/conf/hive-site.xml +++ b/data/conf/hive-site.xml @@ -25,6 +25,12 @@ Internal marker for test. Used for masking env-dependent values + + hive.cbo.enable + true + Enable CBO for Unit Tests + +