【Hadoop离线基础总结】oozie任务串联

---

• 需求

  执行shell脚本 → 执行MR程序 → 执行hive程序

• 1.准备工作目录

  cd /export/servers/oozie-4.1.0-cdh5.14.0/oozie_works
  mkdir -p sereval-actions
  

• 2.准备调度文件

  cd /export/servers/oozie-4.1.0-cdh5.14.0/oozie_works
  cp hive2/script.q sereval-actions/
  cp shell/hello.sh sereval-actions/
  cp -ra map-reduce/lib sereval-actions/
  

• 3.开发调度的配置文件

  cd /export/servers/oozie-4.1.0-cdh5.14.0/oozie_works/sereval-actions
  vim workflow.xml
  

  <workflow-app xmlns="uri:oozie:workflow:0.4" name="shell-wf">
  <start to="shell-node"/>
  <action name="shell-node">
      <shell xmlns="uri:oozie:shell-action:0.2">
          <job-tracker>${jobTracker}</job-tracker>
          <name-node>${nameNode}</name-node>
          <configuration>
              <property>
                  <name>mapred.job.queue.name</name>
                  <value>${queueName}</value>
              </property>
          </configuration>
          <exec>${EXEC}</exec>
          <!-- <argument>my_output=Hello Oozie</argument> -->
          <file>/user/root/oozie_works/sereval-actions/${EXEC}#${EXEC}</file>
  
          <capture-output/>
      </shell>
      <ok to="mr-node"/>
      <error to="mr-node"/>
  </action>
  
  
  
  
  <action name="mr-node">
          <map-reduce>
              <job-tracker>${jobTracker}</job-tracker>
              <name-node>${nameNode}</name-node>
              <prepare>
                  <delete path="${nameNode}/${outputDir}"/>
              </prepare>
              <configuration>
                  <property>
                      <name>mapred.job.queue.name</name>
                      <value>${queueName}</value>
                  </property>
  				<!--  
                  <property>
                      <name>mapred.mapper.class</name>
                      <value>org.apache.oozie.example.SampleMapper</value>
                  </property>
                  <property>
                      <name>mapred.reducer.class</name>
                      <value>org.apache.oozie.example.SampleReducer</value>
                  </property>
                  <property>
                      <name>mapred.map.tasks</name>
                      <value>1</value>
                  </property>
                  <property>
                      <name>mapred.input.dir</name>
                      <value>/user/${wf:user()}/${examplesRoot}/input-data/text</value>
                  </property>
                  <property>
                      <name>mapred.output.dir</name>
                      <value>/user/${wf:user()}/${examplesRoot}/output-data/${outputDir}</value>
                  </property>
  				-->
  				
  				   <!-- 开启使用新的API来进行配置 -->
                  <property>
                      <name>mapred.mapper.new-api</name>
                      <value>true</value>
                  </property>
  
                  <property>
                      <name>mapred.reducer.new-api</name>
                      <value>true</value>
                  </property>
  
                  <!-- 指定MR的输出key的类型 -->
                  <property>
                      <name>mapreduce.job.output.key.class</name>
                      <value>org.apache.hadoop.io.Text</value>
                  </property>
  
                  <!-- 指定MR的输出的value的类型-->
                  <property>
                      <name>mapreduce.job.output.value.class</name>
                      <value>org.apache.hadoop.io.IntWritable</value>
                  </property>
  
                  <!-- 指定输入路径 -->
                  <property>
                      <name>mapred.input.dir</name>
                      <value>${nameNode}/${inputdir}</value>
                  </property>
  
                  <!-- 指定输出路径 -->
                  <property>
                      <name>mapred.output.dir</name>
                      <value>${nameNode}/${outputDir}</value>
                  </property>
  
                  <!-- 指定执行的map类 -->
                  <property>
                      <name>mapreduce.job.map.class</name>
                      <value>org.apache.hadoop.examples.WordCount$TokenizerMapper</value>
                  </property>
  
                  <!-- 指定执行的reduce类 -->
                  <property>
                      <name>mapreduce.job.reduce.class</name>
                      <value>org.apache.hadoop.examples.WordCount$IntSumReducer</value>
                  </property>
  				<!--  配置map task的个数 -->
                  <property>
                      <name>mapred.map.tasks</name>
                      <value>1</value>
                  </property>
  
              </configuration>
          </map-reduce>
          <ok to="hive2-node"/>
          <error to="fail"/>
      </action>
  
  
  
  
  
  
   <action name="hive2-node">
          <hive2 xmlns="uri:oozie:hive2-action:0.1">
              <job-tracker>${jobTracker}</job-tracker>
              <name-node>${nameNode}</name-node>
              <prepare>
                  <delete path="${nameNode}/user/${wf:user()}/${examplesRoot}/output-data/hive2"/>
                  <mkdir path="${nameNode}/user/${wf:user()}/${examplesRoot}/output-data"/>
              </prepare>
              <configuration>
                  <property>
                      <name>mapred.job.queue.name</name>
                      <value>${queueName}</value>
                  </property>
              </configuration>
              <jdbc-url>${jdbcURL}</jdbc-url>
              <script>script.q</script>
              <param>INPUT=/user/${wf:user()}/${examplesRoot}/input-data/table</param>
              <param>OUTPUT=/user/${wf:user()}/${examplesRoot}/output-data/hive2</param>
          </hive2>
          <ok to="end"/>
          <error to="fail"/>
      </action>
  <decision name="check-output">
      <switch>
          <case to="end">
              ${wf:actionData('shell-node')['my_output'] eq 'Hello Oozie'}
          </case>
          <default to="fail-output"/>
      </switch>
  </decision>
  <kill name="fail">
      <message>Shell action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
  </kill>
  <kill name="fail-output">
      <message>Incorrect output, expected [Hello Oozie] but was [${wf:actionData('shell-node')['my_output']}]</message>
  </kill>
  <end name="end"/>
  </workflow-app>
  

  开发job.properties配置文件

  cd /export/servers/oozie-4.1.0-cdh5.14.0/oozie_works/sereval-actions
  vim  job.properties
  

  nameNode=hdfs://node01:8020
  jobTracker=node01:8032
  queueName=default
  examplesRoot=oozie_works
  EXEC=hello.sh
  outputDir=/oozie/output
  inputdir=/oozie/input
  jdbcURL=jdbc:hive2://node03:10000/default
  oozie.use.system.libpath=true
  # 配置我们文件上传到hdfs的保存路径 实际上就是在hdfs 的/user/root/oozie_works/sereval-actions这个路径下
  oozie.wf.application.path=${nameNode}/user/${user.name}/${examplesRoot}/sereval-actions/workflow.xml
  

• 4.上传资源文件夹到hdfs对应路径

  cd /export/servers/oozie-4.1.0-cdh5.14.0/oozie_works/
  hdfs dfs -put sereval-actions/ /user/root/oozie_works/
  

• 5.执行调度任务

  cd /export/servers/oozie-4.1.0-cdh5.14.0/
  bin/oozie job -oozie http://node03:11000/oozie -config oozie_works/serveral-actions/job.properties -run