Я начинаю с Hive, и мне нужна ваша помощь в ошибке. Это происходит после времени ожидания, когда я пытаюсь создать новую базу данных:
hive> CREATE DATABASE Test;
(редактировать: я получаю то же самое с "SHOW TABLES")
Я получаю это:
Exception in thread "main" java.lang.AssertionError: Source tables cannot be empty
at org.apache.hadoop.hive.ql.hooks.EnforceReadOnlyTables.<clinit>(EnforceReadOnlyTables.java:46)
at java.lang.Class.forName0(Native Method)
at java.lang.Class.forName(Class.java:348)
at org.apache.hadoop.hive.ql.hooks.HookUtils.getHooks(HookUtils.java:60)
at org.apache.hadoop.hive.ql.Driver.getHooks(Driver.java:1612)
at org.apache.hadoop.hive.ql.Driver.getHooks(Driver.java:1596)
at org.apache.hadoop.hive.ql.Driver.execute(Driver.java:1677)
at org.apache.hadoop.hive.ql.Driver.runInternal(Driver.java:1453)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1171)
at org.apache.hadoop.hive.ql.Driver.run(Driver.java:1161)
at org.apache.hadoop.hive.cli.CliDriver.processLocalCmd(CliDriver.java:232)
at org.apache.hadoop.hive.cli.CliDriver.processCmd(CliDriver.java:183)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:399)
at org.apache.hadoop.hive.cli.CliDriver.executeDriver(CliDriver.java:776)
at org.apache.hadoop.hive.cli.CliDriver.run(CliDriver.java:714)
at org.apache.hadoop.hive.cli.CliDriver.main(CliDriver.java:641)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.hadoop.util.RunJar.run(RunJar.java:234)
at org.apache.hadoop.util.RunJar.main(RunJar.java:148)
Вот мой куст-сайт.xml:
<configuration>
<property>
<name>hive.in.test</name>
<value>true</value>
<description>Internal marker for test. Used for masking env-dependent values</description>
</property>
<!-- Hive Configuration can either be stored in this file or in the hadoop configuration files -->
<!-- that are implied by Hadoop setup variables. -->
<!-- Aside from Hadoop setup variables - this file is provided as a convenience so that Hive -->
<!-- users do not have to edit hadoop configuration files (that may be managed as a centralized -->
<!-- resource). -->
<!-- Hive Execution Parameters -->
<property>
<name>hadoop.tmp.dir</name>
<value>${test.tmp.dir}/hadoop-tmp</value>
<description>A base for other temporary directories.</description>
</property>
<!--
<property>
<name>hive.exec.reducers.max</name>
<value>1</value>
<description>maximum number of reducers</description>
</property>
-->
<property>
<name>hive.exec.scratchdir</name>
<value>${test.tmp.dir}/scratchdir</value>
<description>Scratch space for Hive jobs</description>
</property>
<property>
<name>hive.exec.local.scratchdir</name>
<value>${test.tmp.dir}/localscratchdir/</value>
<description>Local scratch space for Hive jobs</description>
</property>
<property>
<name>datanucleus.schema.autoCreateAll</name>
<value>true</value>
</property>
<property>
<name>hive.metastore.schema.verification</name>
<value>false</value>
</property>
<property>
<name>javax.jdo.option.ConnectionURL</name>
<value>jdbc:derby://localhost:1527/metastore_db;create=true</value>
</property>
<property>
<name>javax.jdo.option.ConnectionDriverName</name>
<value>org.apache.derby.jdbc.ClientDriver</value>
</property>
<property>
<name>javax.jdo.option.ConnectionUserName</name>
<value>APP</value>
</property>
<property>
<name>javax.jdo.option.ConnectionPassword</name>
<value>mine</value>
</property>
<property>
<!-- this should eventually be deprecated since the metastore should supply this -->
<name>hive.metastore.warehouse.dir</name>
<value>/user/hive/warehouse</value>
<description></description>
</property>
<property>
<name>hive.metastore.metadb.dir</name>
<value>file://${test.tmp.dir}/metadb/</value>
<description>
Required by metastore server or if the uris argument below is not supplied
</description>
</property>
<property>
<name>test.log.dir</name>
<value>${test.tmp.dir}/log/</value>
<description></description>
</property>
<property>
<name>test.data.files</name>
<value>${hive.root}/data/files</value>
<description></description>
</property>
<property>
<name>test.data.scripts</name>
<value>${hive.root}/data/scripts</value>
<description></description>
</property>
<property>
<name>hive.jar.path</name>
<value>${maven.local.repository}/org/apache/hive/hive-exec/${hive.version}/hive-exec-${hive.version}.jar</value>
<description></description>
</property>
<property>
<name>hive.metastore.rawstore.impl</name>
<value>org.apache.hadoop.hive.metastore.ObjectStore</value>
<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>
</property>
<property>
<name>hive.querylog.location</name>
<value>${test.tmp.dir}/tmp</value>
<description>Location of the structured hive logs</description>
</property>
<property>
<name>hive.exec.pre.hooks</name>
<value>org.apache.hadoop.hive.ql.hooks.PreExecutePrinter, org.apache.hadoop.hive.ql.hooks.EnforceReadOnlyTables</value>
<description>Pre Execute Hook for Tests</description>
</property>
<property>
<name>hive.exec.post.hooks</name>
<value>org.apache.hadoop.hive.ql.hooks.PostExecutePrinter</value>
<description>Post Execute Hook for Tests</description>
</property>
<property>
<name>hive.support.concurrency</name>
<value>true</value>
<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>
</property>
<property>
<key>hive.unlock.numretries</key>
<value>2</value>
<description>The number of times you want to retry to do one unlock</description>
</property>
<property>
<key>hive.lock.sleep.between.retries</key>
<value>2</value>
<description>The sleep time (in seconds) between various retries</description>
</property>
<property>
<name>fs.pfile.impl</name>
<value>org.apache.hadoop.fs.ProxyLocalFileSystem</value>
<description>A proxy for local file system used for cross file system testing</description>
</property>
<property>
<name>hive.exec.mode.local.auto</name>
<value>false</value>
<description>
Let hive determine whether to run in local mode automatically
Disabling this for tests so that minimr is not affected
</description>
</property>
<property>
<name>hive.auto.convert.join</name>
<value>false</value>
<description>Whether Hive enable the optimization about converting common join into mapjoin based on the input file size</description>
</property>
<property>
<name>hive.ignore.mapjoin.hint</name>
<value>false</value>
<description>Whether Hive ignores the mapjoin hint</description>
</property>
<property>
<name>hive.input.format</name>
<value>org.apache.hadoop.hive.ql.io.CombineHiveInputFormat</value>
<description>The default input format, if it is not specified, the system assigns it. It is set to HiveInputFormat for hadoop versions 17, 18 and 19, whereas it is set to CombineHiveInputFormat for hadoop 20. The user can always overwrite it - if there is a bug in CombineHiveInputFormat, it can always be manually set to HiveInputFormat. </description>
</property>
<property>
<name>hive.default.rcfile.serde</name>
<value>org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe</value>
<description>The default SerDe hive will use for the rcfile format</description>
</property>
<property>
<name>hive.stats.key.prefix.reserve.length</name>
<value>0</value>
</property>
<property>
<name>hive.conf.restricted.list</name>
<value>dummy.config.value</value>
<description>Using dummy config value above because you cannot override config with empty value</description>
</property>
<property>
<name>hive.exec.submit.local.task.via.child</name>
<value>false</value>
</property>
<property>
<name>hive.dummyparam.test.server.specific.config.override</name>
<value>from.hive-site.xml</value>
<description>Using dummy param to test server specific configuration</description>
</property>
<property>
<name>hive.dummyparam.test.server.specific.config.hivesite</name>
<value>from.hive-site.xml</value>
<description>Using dummy param to test server specific configuration</description>
</property>
<property>
<name>test.var.hiveconf.property</name>
<value>${hive.exec.default.partition.name}</value>
<description>Test hiveconf property substitution</description>
</property>
<property>
<name>test.property1</name>
<value>value1</value>
<description>Test property defined in hive-site.xml only</description>
</property>
<property>
<name>hive.test.dummystats.aggregator</name>
<value>value2</value>
</property>
<property>
<name>hive.fetch.task.conversion</name>
<value>minimal</value>
</property>
<property>
<name>hive.users.in.admin.role</name>
<value>hive_admin_user</value>
</property>
<property>
<name>hive.security.authorization.manager</name>
<value>org.apache.hadoop.hive.ql.security.authorization.plugin.sqlstd.SQLStdHiveAuthorizerFactoryForTest</value>
<description>The Hive client authorization manager class name.</description>
</property>
<property>
<name>hive.llap.io.cache.orc.size</name>
<value>8388608</value>
</property>
<property>
<name>hive.llap.io.cache.orc.arena.size</name>
<value>8388608</value>
</property>
<property>
<name>hive.llap.io.cache.orc.alloc.max</name>
<value>2097152</value>
</property>
<property>
<name>hive.llap.io.cache.orc.alloc.min</name>
<value>32768</value>
</property>
<property>
<name>hive.llap.cache.allow.synthetic.fileid</name>
<value>true</value>
</property>
<property>
<name>hive.llap.io.use.lrfu</name>
<value>true</value>
</property>
<property>
<name>hive.llap.io.allocator.direct</name>
<value>false</value>
</property>
<property>
<name>hive.materializedview.rewriting</name>
<value>true</value>
</property>
</configuration>
Я более или менее выполнил следующие шаги: https://cwiki.apache.org/confluence/display/Hive/HiveDerbyServerMode. Что мне не хватает? Спасибо!
