You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by sz...@apache.org on 2019/11/25 13:57:43 UTC
[hive] 01/02: Adam llap dev
This is an automated email from the ASF dual-hosted git repository.
szita pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
commit 2f2c4988ff3ccf92b78b0a8f9c0890d951309f21
Author: Adam Szita <sz...@cloudera.com>
AuthorDate: Thu Oct 31 11:08:17 2019 +0100
Adam llap dev
Change-Id: Ia14d2f0ad904de1d754e6b919954439e433e16db
---
data/conf/llap/hive-site.xml | 738 ++++++++++++++++++++++---------------------
1 file changed, 384 insertions(+), 354 deletions(-)
diff --git a/data/conf/llap/hive-site.xml b/data/conf/llap/hive-site.xml
index 0c5d030..3db7ea7 100644
--- a/data/conf/llap/hive-site.xml
+++ b/data/conf/llap/hive-site.xml
@@ -19,358 +19,388 @@
<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>${test.tmp.dir}/hadoop-tmp</value>
- <description>A base for other temporary directories.</description>
-</property>
-
-<property>
- <name>hive.tez.container.size</name>
- <value>128</value>
- <description></description>
-</property>
-
-<property>
- <name>hive.stats.fetch.column.stats</name>
- <value>true</value>
- <description>Use column stats to annotate stats for physical optimization phase</description>
-</property>
-
-<property>
- <name>hive.merge.tezfiles</name>
- <value>false</value>
- <description>Merge small files at the end of a Tez DAG</description>
-</property>
-
-<property>
- <name>hive.tez.input.format</name>
- <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
- <description>The default input format for tez. Tez groups splits in the AM.</description>
-</property>
-
-<property>
- <name>hive.exec.scratchdir</name>
- <value>${test.tmp.dir}/scratchdir</value>
- <description>Scratch space for Hive jobs</description>
-</property>
-
-<property>
- <name>hive.exec.local.scratchdir</name>
- <value>${test.tmp.dir}/localscratchdir/</value>
- <description>Local scratch space for Hive jobs</description>
-</property>
-
-<property>
- <name>datanucleus.schema.autoCreateAll</name>
- <value>true</value>
-</property>
-
-<property>
- <name>datanucleus.connectionPool.maxPoolSize</name>
- <value>4</value>
-</property>
-
-<property>
- <name>hive.metastore.schema.verification</name>
- <value>false</value>
-</property>
-
-<property>
- <name>javax.jdo.option.ConnectionURL</name>
- <value>jdbc:derby:memory:${test.tmp.dir}/junit_metastore_db;create=true</value>
-</property>
-
-<property>
- <name>javax.jdo.option.ConnectionDriverName</name>
- <value>org.apache.derby.jdbc.EmbeddedDriver</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>${test.warehouse.dir}</value>
- <description></description>
-</property>
-
-<property>
- <name>hive.metastore.metadb.dir</name>
- <value>file://${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, org.apache.hadoop.hive.ql.hooks.RuntimeStatsPersistenceCheckerHook, org.apache.hadoop.hive.ql.hooks.NoOperatorReuseCheckerHook</value>
- <description>Post Execute Hook for Tests</description>
-</property>
-
-<property>
- <name>hive.support.concurrency</name>
- <value>false</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>
- <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>true</value>
- <description>Whether Hive ignores the mapjoin hint</description>
-</property>
-
-<property>
- <name>io.sort.mb</name>
- <value>10</value>
-</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.dbclass</name>
- <value>fs</value>
- <description>The default storatge that stores temporary hive statistics. Currently, fs type is supported</description>
-</property>
-
-<property>
- <name>hive.execution.engine</name>
- <value>tez</value>
- <description>Whether to use MR or Tez</description>
-</property>
-
-<property>
- <name>tez.am.node-blacklisting.enabled</name>
- <value>false</value>
-</property>
-
-<property>
- <name>hive.prewarm.enabled</name>
- <value>false</value>
- <description>
- Enables container prewarm for tez (hadoop 2 only)
- </description>
-</property>
-<property>
- <name>hive.in.tez.test</name>
- <value>true</value>
- <description>
- Indicates that we are in tez testing mode.
- </description>
-</property>
-
-<property>
- <name>hive.execution.mode</name>
- <value>llap</value>
-</property>
-
-<!--property>
- This is determined by the cluster type, and is set in code - HadoopShims, etc.
- <name>hive.llap.execution.mode</name>
- <value>all</value>
-</property-->
-
-<property>
- <name>hive.tez.java.opts</name>
- <value> -Dlog4j.configurationFile=tez-container-log4j2.properties -Dtez.container.log.level=INFO -Dtez.container.root.logger=CLA </value>
-</property>
-
-<property>
- <name>tez.am.launch.cmd-opts</name>
- <value> -Dlog4j.configurationFile=tez-container-log4j2.properties -Dtez.container.log.level=INFO -Dtez.container.root.logger=CLA </value>
-</property>
-
-<property>
- <name>hive.llap.cache.allow.synthetic.fileid</name>
- <value>true</value>
-</property>
-
-<property>
- <name>hive.llap.io.allocator.direct</name>
- <value>false</value>
-</property>
-
-<property>
- <name>hive.explain.user</name>
- <value>false</value>
-</property>
-
-<property>
- <name>hive.join.inner.residual</name>
- <value>true</value>
-</property>
-
-<!-- llap properties -->
-
-<property>
- <name>hive.llap.daemon.service.hosts</name>
- <value>localhost</value>
-</property>
-
-<property>
- <name>hive.llap.daemon.service.port</name>
- <value>0</value>
-</property>
-
-<property>
- <name>hive.llap.daemon.num.executors</name>
- <value>4</value>
-</property>
-
-<property>
- <name>hive.llap.daemon.task.scheduler.wait.queue.size</name>
- <value>4</value>
-</property>
-
-<property>
- <name>hive.llap.cache.allow.synthetic.fileid</name>
- <value>true</value>
-</property>
-
-<!-- hadoop IPC options -->
-<property>
- <name>ipc.client.low-latency</name>
- <value>true</value>
- <description> </description>
-</property>
-<property>
- <name>ipc.client.tcpnodelay</name>
- <value>true</value>
- <description> </description>
-</property>
-<property>
- <name>ipc.clients-per-factory</name>
- <value>4</value>
- <description> </description>
-</property>
-<property>
- <name>hive.stats.fetch.bitvector</name>
- <value>true</value>
-</property>
-
-<property>
- <name>hive.tez.cartesian-product.enabled</name>
- <value>true</value>
-</property>
-
-<property>
- <name>yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage</name>
- <value>99</value>
-</property>
-
-<property>
- <name>hive.query.results.cache.enabled</name>
- <value>false</value>
-</property>
-
-<property>
- <name>tez.counters.max</name>
- <value>1024</value>
-</property>
-
-<property>
- <name>hive.query.reexecution.stats.persist.scope</name>
- <value>query</value>
-</property>
-
-<property>
- <name>hive.semantic.analyzer.hook</name>
- <value>org.apache.hadoop.hive.ql.hooks.ScheduledQueryCreationRegistryHook</value>
-</property>
-
+ <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.tez.container.size</name>
+ <value>128</value>
+ <description></description>
+ </property>
+
+ <property>
+ <name>hive.stats.fetch.column.stats</name>
+ <value>true</value>
+ <description>Use column stats to annotate stats for physical optimization phase</description>
+ </property>
+
+ <property>
+ <name>hive.merge.tezfiles</name>
+ <value>false</value>
+ <description>Merge small files at the end of a Tez DAG</description>
+ </property>
+
+ <property>
+ <name>hive.tez.input.format</name>
+ <value>org.apache.hadoop.hive.ql.io.HiveInputFormat</value>
+ <description>The default input format for tez. Tez groups splits in the AM.</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:;databaseName=/Users/szita/data/hive3/junit_metastore_db;create=true</value>
+ </property>
+
+ <property>
+ <name>javax.jdo.option.ConnectionDriverName</name>
+ <value>org.apache.derby.jdbc.EmbeddedDriver</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>${test.warehouse.dir}</value>
+ <description></description>
+ </property>
+
+ <property>
+ <name>hive.metastore.metadb.dir</name>
+ <value>file://${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, org.apache.hadoop.hive.ql.hooks.RuntimeStatsPersistenceCheckerHook, org.apache.hadoop.hive.ql.hooks.NoOperatorReuseCheckerHook</value>
+ <description>Post Execute Hook for Tests</description>
+ </property>
+
+ <property>
+ <name>hive.support.concurrency</name>
+ <value>false</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>
+ <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>true</value>
+ <description>Whether Hive ignores the mapjoin hint</description>
+ </property>
+
+ <property>
+ <name>io.sort.mb</name>
+ <value>10</value>
+ </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.dbclass</name>
+ <value>fs</value>
+ <description>The default storatge that stores temporary hive statistics. Currently, fs type is supported</description>
+ </property>
+
+ <property>
+ <name>hive.execution.engine</name>
+ <value>tez</value>
+ <description>Whether to use MR or Tez</description>
+ </property>
+
+ <property>
+ <name>tez.am.node-blacklisting.enabled</name>
+ <value>false</value>
+ </property>
+
+ <property>
+ <name>hive.prewarm.enabled</name>
+ <value>false</value>
+ <description>
+ Enables container prewarm for tez (hadoop 2 only)
+ </description>
+ </property>
+ <property>
+ <name>hive.in.tez.test</name>
+ <value>true</value>
+ <description>
+ Indicates that we are in tez testing mode.
+ </description>
+ </property>
+
+ <property>
+ <name>hive.execution.mode</name>
+ <value>llap</value>
+ </property>
+
+ <!--property>
+ This is determined by the cluster type, and is set in code - HadoopShims, etc.
+ <name>hive.llap.execution.mode</name>
+ <value>all</value>
+ </property-->
+
+ <property>
+ <name>hive.tez.java.opts</name>
+ <value> -Dlog4j.configurationFile=tez-container-log4j2.properties -Dtez.container.log.level=INFO -Dtez.container.root.logger=CLA </value>
+ </property>
+
+ <property>
+ <name>tez.am.launch.cmd-opts</name>
+ <value> -Dlog4j.configurationFile=tez-container-log4j2.properties -Dtez.container.log.level=INFO -Dtez.container.root.logger=CLA </value>
+ </property>
+
+ <property>
+ <name>hive.llap.cache.allow.synthetic.fileid</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <name>hive.llap.io.allocator.direct</name>
+ <value>false</value>
+ </property>
+
+ <property>
+ <name>hive.explain.user</name>
+ <value>false</value>
+ </property>
+
+ <property>
+ <name>hive.join.inner.residual</name>
+ <value>true</value>
+ </property>
+
+ <!-- llap properties -->
+
+ <property>
+ <name>hive.llap.daemon.service.hosts</name>
+ <value>localhost</value>
+ </property>
+
+ <property>
+ <name>hive.llap.daemon.service.port</name>
+ <value>0</value>
+ </property>
+
+ <property>
+ <name>hive.llap.daemon.num.executors</name>
+ <value>4</value>
+ </property>
+
+ <property>
+ <name>hive.llap.daemon.task.scheduler.wait.queue.size</name>
+ <value>4</value>
+ </property>
+
+ <property>
+ <name>hive.llap.cache.allow.synthetic.fileid</name>
+ <value>true</value>
+ </property>
+
+ <!-- hadoop IPC options -->
+ <property>
+ <name>ipc.client.low-latency</name>
+ <value>true</value>
+ <description> </description>
+ </property>
+ <property>
+ <name>ipc.client.tcpnodelay</name>
+ <value>true</value>
+ <description> </description>
+ </property>
+ <property>
+ <name>ipc.clients-per-factory</name>
+ <value>4</value>
+ <description> </description>
+ </property>
+ <property>
+ <name>hive.stats.fetch.bitvector</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <name>hive.tez.cartesian-product.enabled</name>
+ <value>true</value>
+ </property>
+
+ <property>
+ <name>yarn.nodemanager.disk-health-checker.max-disk-utilization-per-disk-percentage</name>
+ <value>99</value>
+ </property>
+
+ <property>
+ <name>hive.query.results.cache.enabled</name>
+ <value>false</value>
+ </property>
+
+ <property>
+ <name>tez.counters.max</name>
+ <value>1024</value>
+ </property>
+
+ <property>
+ <name>hive.query.reexecution.stats.persist.scope</name>
+ <value>query</value>
+ </property>
+
+ <property>
+ <name>hive.semantic.analyzer.hook</name>
+ <value>org.apache.hadoop.hive.ql.hooks.ScheduledQueryCreationRegistryHook</value>
+ </property>
+
+ <property>
+ <name>hive.llap.daemon.web.port</name>
+ <value>25002</value>
+ </property>
+ <property>
+ <name>hive.llap.io.memory.size</name>
+ <value>1024Mb</value>
+ </property>
+ <property>
+ <name>tez.grouping.max-size</name>
+ <value>512000000</value>
+ </property>
+
+ <property>
+ <name>tez.grouping.min-size</name>
+ <value>1024</value>
+ </property>
+
+ <property>
+ <name>mapreduce.input.fileinputformat.split.maxsize</name>
+ <value>40</value>
+ </property>
+
+ <property>
+ <name>mapreduce.input.fileinputformat.split.minsize</name>
+ <value>40</value>
+ </property>
+ <property>
+ <name>tez.am.launch.cmd-opts</name>
+ <value>-agentlib:jdwp=transport=dt_socket,server=y,suspend=n,address=5006,quiet=y</value>
+ </property>
+ <!--<property>-->
+ <!--<name>hive.llap.io.threadpool.size</name>-->
+ <!--<value>1</value>-->
+ <!--</property>-->
</configuration>