db_name="orcl" #(數據庫名:不允許修改) 
db_domain=dbcenter.toys.com 
instance_name=orcl #(數據庫實例名:可以修改,可以與db_name相同也可不同) 
service_names=orcl.dbcenter.toys.com 
control_file=(............... 
.........

格式二: Oracle JDBC Thin using an SID: 
jdbc:oracle:thin:@<host>:<port>:<SID> 
Example: jdbc:oracle:thin:@192.168.2.1:1521:X01A 
Note: 
Support for SID is being phased out. Oracle recommends that users switch over to usingservice names. 
 
格式三：Oracle JDBC Thin using a TNSName: 
jdbc:oracle:thin:@<TNSName> 
Example: jdbc:oracle:thin:@GL 
Note: 
Support for TNSNames was added in the driver release 10.2.0.1``

[atguigu@hadoop102 conf]$ hadoop dfs -mkdir /directory
[atguigu@hadoop102 conf]$ start-history-server.sh

[atguigu@hadoop102 hadoop]$ start-thriftserver.sh

set hive.exec.dynamic.partition=true;
set hive.exec.dynamic.partition.mode=nostrick;

[atguigu@hadoop102 conf]$ cat /opt/module/spark-3.0.0-bin-hadoop3.2/conf/hive-site.xml 
<?xml version="1.0"?>
<?xml-stylesheet type="text/xsl" href="configuration.xsl"?>
<configuration>
    <!-- 修改Hive的計算引擎 -->
    <property>
        <name>hive.execution.engine</name>
        <value>tez</value>
    </property>
    <property>
        <name>hive.tez.container.size</name>
        <value>1024</value>
    </property>

    <!-- hive窗口打印默認庫和表頭 -->
    <property>
        <name>hive.cli.print.header</name>
        <value>true</value>
    </property>
    <property>
        <name>hive.cli.print.current.db</name>
        <value>true</value>
    </property>

    <!-- 指定hiveserver2連接的host -->
    <property>
        <name>hive.server2.thrift.bind.host</name>
        <value>hadoop102</value>
    </property>

    <!-- 指定hiveserver2連接的端口號 -->
    <property>
        <name>hive.server2.thrift.port</name>
        <value>10000</value>
    </property>

    <!-- jdbc連接的URL -->
    <property>
        <name>javax.jdo.option.ConnectionURL</name>
        <value>jdbc:mysql://hadoop102:3306/metastore?useSSL=false</value>
    </property>

    <!-- jdbc連接的Driver-->
    <property>
        <name>javax.jdo.option.ConnectionDriverName</name>
        <value>com.mysql.jdbc.Driver</value>
    </property>

    <!-- jdbc連接的username-->
    <property>
        <name>javax.jdo.option.ConnectionUserName</name>
        <value>root</value>
    </property>

    <!-- jdbc連接的password -->
    <property>
        <name>javax.jdo.option.ConnectionPassword</name>
        <value>root</value>
    </property>

    <!-- Hive默認在HDFS的工作目錄 -->
    <property>
        <name>hive.metastore.warehouse.dir</name>
        <value>/user/hive/warehouse</value>
    </property>
    
   <!-- Hive元數據存儲的驗證 -->
    <property>
        <name>hive.metastore.schema.verification</name>
        <value>false</value>
    </property>
   
    <!-- 元數據存儲授權  -->
    <property>
        <name>hive.metastore.event.db.notification.api.auth</name>
        <value>false</value>
    </property>
  
    <!-- 開啓動態分區 -->
    <property>
    	<name>hive.exec.dynamic.partition.mode</name>
    	<value>nonstrict</value>
    </property>

</configuration>

[atguigu@hadoop102 conf]$ cat /opt/module/spark-3.0.0-bin-hadoop3.2/conf/spark-defaults.conf 
#
# Licensed to the Apache Software Foundation (ASF) under one or more
# contributor license agreements.  See the NOTICE file distributed with
# this work for additional information regarding copyright ownership.
# The ASF licenses this file to You under the Apache License, Version 2.0
# (the "License"); you may not use this file except in compliance with
# the License.  You may obtain a copy of the License at
#
#    http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
#

# Default system properties included when running spark-submit.
# This is useful for setting default environmental settings.

# Example:
# spark.master                     spark://master:7077
#是否記錄Spark任務日誌
spark.eventLog.enabled           true
#Spark任務日誌的存儲路徑
spark.eventLog.dir               hdfs://hadoop102:9820/directory
# spark.serializer                 org.apache.spark.serializer.KryoSerializer
# spark.driver.memory              5g
# spark.executor.extraJavaOptions  -XX:+PrintGCDetails -Dkey=value -Dnumbers="one two three"
#Spark歷史服務器地址
spark.yarn.historyServer.address=hadoop102:18080
spark.history.ui.port=18080
#------------------------------------
#指定Spark master為yarn
spark.master=yarn
#Spark歷史服務器讀取歷史任務日誌的路徑
spark.history.fs.logDirectory=hdfs://hadoop102:9820/directory
#開啓Spark-sql自適應優化
spark.sql.adaptive.enabled=true
#開啓Spark-sql中Reduce階段分區數自適應
spark.sql.adaptive.coalescePartitions.enabled=true
#使用Hive提供的Parquet文件的序列化和反序列化工具，以兼容Hive
spark.sql.hive.convertMetastoreParquet=false
#使用老版的Parquet文件格式，以兼容Hive
spark.sql.parquet.writeLegacyFormat=true
#解決SPARK-21725問題
spark.hadoop.fs.hdfs.impl.disable.cache=true
#降低Spark-sql中類型檢查級別，兼容Hive
spark.sql.storeAssignmentPolicy=LEGACY

Unless required by applicable law or agreed to in writing, software
  distributed under the License is distributed on an "AS IS" BASIS,
  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
  See the License for the specific language governing permissions and
  limitations under the License. See accompanying LICENSE file.
-->
<configuration>

  <property>
    <name>yarn.scheduler.capacity.maximum-applications</name>
    <value>10000</value>
    <description>
      Maximum number of applications that can be pending and running.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.maximum-am-resource-percent</name>
    <!-- 學習環境調大Application Master可以獲得的最大資源百分比，生產使用默認的0.1就可以 -->
    <value>0.8</value>
    <description>
      Maximum percent of resources in the cluster which can be used to run 
      application masters i.e. controls number of concurrent running
      applications.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.resource-calculator</name>
    <value>org.apache.hadoop.yarn.util.resource.DefaultResourceCalculator</value>
    <description>
      The ResourceCalculator implementation to be used to compare 
      Resources in the scheduler.
      The default i.e. DefaultResourceCalculator only uses Memory while
      DominantResourceCalculator uses dominant-resource to compare 
      multi-dimensional resources such as Memory, CPU etc.
    </description>
  </property>
  
  <!-- 指定hive隊列的資源額定容量 -->
<property>
    <name>yarn.scheduler.capacity.root.hive.capacity</name>
    <value>50</value>
</property>
<!-- 指定隊列中，用户提交job佔用集羣資源的百分比-->
<property>
    <name>yarn.scheduler.capacity.root.hive.user-limit-factor</name>
    <value>2</value>
</property>
<!-- 指定hive隊列的資源最大容量 -->
<property>
    <name>yarn.scheduler.capacity.root.hive.maximum-capacity</name>
    <value>100</value>
</property>
<!--指定隊列的工作狀態-->
<property>
    <name>yarn.scheduler.capacity.root.hive.state</name>
    <value>RUNNING</value>
</property>
<!--訪問權限，設定那些用户可以提交應用，*表示所有用户-->
<property>
    <name>yarn.scheduler.capacity.root.hive.acl_submit_applications</name>
    <value>*</value>
</property>
<!--訪問權限，設定那些用户是管理者，*表示所有用户-->
<property>
    <name>yarn.scheduler.capacity.root.hive.acl_administer_queue</name>
    <value>*</value>
</property>
<!--訪問權限，設定那些用户有優先，*表示所有用户平等-->
<property>
    <name>yarn.scheduler.capacity.root.hive.acl_application_max_priority</name>
    <value>*</value>
</property>
<!--訪問權限，設定job的最大存活時間，-1表示沒有限定-->
<property>
    <name>yarn.scheduler.capacity.root.hive.maximum-application-lifetime</name>
    <value>-1</value>
</property>
<!--訪問權限，設定job的默認存活時間，-1表示沒有限定-->
<property>
    <name>yarn.scheduler.capacity.root.hive.default-application-lifetime</name>
    <value>-1</value>
</property>

  <property>
    <name>yarn.scheduler.capacity.root.queues</name>
    <value>default,hive</value>
    <description>
      The queues at the this level (root is the root queue).
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.capacity</name>
    <value>50</value>
    <description>Default queue target capacity.</description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.user-limit-factor</name>
    <value>1</value>
    <description>
      Default queue user limit a percentage from 0.0 to 1.0.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.maximum-capacity</name>
    <value>60</value>
    <description>
      The maximum capacity of the default queue. 
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.state</name>
    <value>RUNNING</value>
    <description>
      The state of the default queue. State can be one of RUNNING or STOPPED.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.acl_submit_applications</name>
    <value>*</value>
    <description>
      The ACL of who can submit jobs to the default queue.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.acl_administer_queue</name>
    <value>*</value>
    <description>
      The ACL of who can administer jobs on the default queue.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.root.default.acl_application_max_priority</name>
    <value>*</value>
    <description>
      The ACL of who can submit applications with configured priority.
      For e.g, [user={name} group={name} max_priority={priority} default_priority={priority}]
    </description>
  </property>

   <property>
     <name>yarn.scheduler.capacity.root.default.maximum-application-lifetime
     </name>
     <value>-1</value>
     <description>
        Maximum lifetime of an application which is submitted to a queue
        in seconds. Any value less than or equal to zero will be considered as
        disabled.
        This will be a hard time limit for all applications in this
        queue. If positive value is configured then any application submitted
        to this queue will be killed after exceeds the configured lifetime.
        User can also specify lifetime per application basis in
        application submission context. But user lifetime will be
        overridden if it exceeds queue maximum lifetime. It is point-in-time
        configuration.
        Note : Configuring too low value will result in killing application
        sooner. This feature is applicable only for leaf queue.
     </description>
   </property>

   <property>
     <name>yarn.scheduler.capacity.root.default.default-application-lifetime
     </name>
     <value>-1</value>
     <description>
        Default lifetime of an application which is submitted to a queue
        in seconds. Any value less than or equal to zero will be considered as
        disabled.
        If the user has not submitted application with lifetime value then this
        value will be taken. It is point-in-time configuration.
        Note : Default lifetime can't exceed maximum lifetime. This feature is
        applicable only for leaf queue.
     </description>
   </property>

  <property>
    <name>yarn.scheduler.capacity.node-locality-delay</name>
    <value>40</value>
    <description>
      Number of missed scheduling opportunities after which the CapacityScheduler 
      attempts to schedule rack-local containers.
      When setting this parameter, the size of the cluster should be taken into account.
      We use 40 as the default value, which is approximately the number of nodes in one rack.
      Note, if this value is -1, the locality constraint in the container request
      will be ignored, which disables the delay scheduling.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.rack-locality-additional-delay</name>
    <value>-1</value>
    <description>
      Number of additional missed scheduling opportunities over the node-locality-delay
      ones, after which the CapacityScheduler attempts to schedule off-switch containers,
      instead of rack-local ones.
      Example: with node-locality-delay=40 and rack-locality-delay=20, the scheduler will
      attempt rack-local assignments after 40 missed opportunities, and off-switch assignments
      after 40+20=60 missed opportunities.
      When setting this parameter, the size of the cluster should be taken into account.
      We use -1 as the default value, which disables this feature. In this case, the number
      of missed opportunities for assigning off-switch containers is calculated based on
      the number of containers and unique locations specified in the resource request,
      as well as the size of the cluster.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.queue-mappings</name>
    <value></value>
    <description>
      A list of mappings that will be used to assign jobs to queues
      The syntax for this list is [u|g]:[name]:[queue_name][,next mapping]*
      Typically this list will be used to map users to queues,
      for example, u:%user:%user maps all users to queues with the same name
      as the user.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.queue-mappings-override.enable</name>
    <value>false</value>
    <description>
      If a queue mapping is present, will it override the value specified
      by the user? This can be used by administrators to place jobs in queues
      that are different than the one specified by the user.
      The default is false.
    </description>
  </property>

  <property>
    <name>yarn.scheduler.capacity.per-node-heartbeat.maximum-offswitch-assignments</name>
    <value>1</value>
    <description>
      Controls the number of OFF_SWITCH assignments allowed
      during a node's heartbeat. Increasing this value can improve
      scheduling rate for OFF_SWITCH containers. Lower values reduce
      "clumping" of applications on particular nodes. The default is 1.
      Legal values are 1-MAX_INT. This config is refreshable.
    </description>
  </property>


  <property>
    <name>yarn.scheduler.capacity.application.fail-fast</name>
    <value>false</value>
    <description>
      Whether RM should fail during recovery if previous applications'
      queue is no longer valid.
    </description>
  </property>

</configuration>