- 在/usr/local/module/oozie-4.0.0-cdh5.3.6/oozie-apps目录下创建map-reduce目录
- /usr/local/module/oozie-4.0.0-cdh5.3.6/oozie-apps/map-reduce下创建job.properties,workflow.xml文件,
以及lib文件夹 - 将/usr/local/module/hadoop-cdh5.3.6/hadoop-2.5.0-cdh5.3.6/share/hadoop/mapreduce/hadoop-mapreduce-examples-2.5.0-cdh5.3.6.jar拷贝到lib目录下
- 配置workflow.xml文件
<!-- 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. --> <workflow-app xmlns="uri:oozie:workflow:0.2" name="map-reduce-wf"> <start to="mr-node"/> <action name="mr-node"> <map-reduce> <job-tracker>${jobTracker}</job-tracker> <name-node>${nameNode}</name-node> <prepare> <!--对应的是hdfs上/output1目录,存在的话要先删除--> <delete path="${nameNode}/output1"/> </prepare> <configuration> <property> <name>mapred.job.queue.name</name> <value>${queueName}</value> </property> <!-- 配置调度MR任务时,使用新的API --> <property> <name>mapred.mapper.new-api</name> <value>true</value> </property> <property> <name>mapred.reducer.new-api</name> <value>true</value> </property> <!-- 指定Map类 --> <property> <name>mapreduce.job.map.class</name> <value>org.apache.hadoop.examples.WordCount$TokenizerMapper</value> </property> <!-- 指定Reduce类 --> <property> <name>mapreduce.job.reduce.class</name> <value>org.apache.hadoop.examples.WordCount$IntSumReducer</value> </property> <!-- 指定Job Key输出类型 --> <property> <name>mapreduce.job.output.key.class</name> <value>org.apache.hadoop.io.Text</value> </property> <!-- 指定Job Value输出类型 --> <property> <name>mapreduce.job.output.value.class</name> <value>org.apache.hadoop.io.IntWritable</value> </property> <property> <name>mapred.map.tasks</name> <value>1</value> </property> <!-- 指定输入输出路径 --> <property> <name>mapreduce.input.fileinputformat.inputdir</name> <value>/input1</value> </property> <property> <name>mapreduce.output.fileoutputformat.outputdir</name> <value>/output1</value> </property> </configuration> </map-reduce> <ok to="end"/> <error to="fail"/> </action> <kill name="fail"> <message>Map/Reduce failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message> </kill> <end name="end"/> </workflow-app>
- 修改job.properties文件
nameNode=hdfs://hadoop111:8020 jobTracker=hadoop112:8032 queueName=default examplesRoot=oozie-apps oozie.wf.application.path=${nameNode}/user/${user.name}/${examplesRoot}/map-reduce/workflow.xml
- 将文件上传到HDFS上
- 执行
- 效果
- 查看HDFS上输入和生成的输出文件
Oozie调度MapReduce任务
最新推荐文章于 2022-06-02 21:24:32 发布