Workflow-Mapreduce Action

本workflow位于oozie目录下新创建的一个oozie-apps文件夹下的mr-wc-wf文件夹中。

mr-wc-wf：

1、job.properties

2、lib文件夹（其中包含了一个wordcount程序的jar包）

3、workflow.xml

将整个oozie-apps文件夹上传到hdfs的对应用户目录下

然后运行程序

bin/oozie job -config oozie-apps/mr-wc-wf/job.properties -run

job.properies:

nameNode=hdfs://BPF:9000
jobTracker=BPF:8032
queueName=default
oozie-appsRoot=user/bpf/oozie-apps
DataRoot=user/bpf/oozie/datas

oozie.wf.application.path=${nameNode}/${oozie-appsRoot}/mr-wc-wf/workflow.xml
inputDir=mr-wc-wf/input
outputDir=mr-wc-wf/output

workflow.xml:

<workflow-app xmlns="uri:oozie:workflow:0.5" name="map-wc-wf">
    <start to="mr-node-wc"/>
    <action name="mr-node-wc">
        <map-reduce>
            <job-tracker>${jobTracker}</job-tracker>
            <name-node>${nameNode}</name-node>
            <prepare>
                <delete path="${nameNode}/${DataRoot}/${outputDir}"/>
            </prepare>
            <configuration>
            	  <property>
                    <name>mapred.mapper.new-api</name>
                    <value>true</value>
                </property>
                <property>
                    <name>mapred.reducer.new-api</name>
                    <value>true</value>
                </property>
                <property>
                    <name>mapreduce.job.queuename</name>
                    <value>${queueName}</value>
                </property>
                <property>
                    <name>mapreduce.job.map.class</name>
                    <value>com.bpf.hadoop.WordCount$TokenizerMapper</value>
                </property>
                <property>
                    <name>mapreduce.job.reduce.class</name>
                    <value>com.bpf.hadoop.WordCount$IntSumReducer</value>
                </property>
                
		<property>
                    <name>mapreduce.map.output.key.class</name>
                    <value>org.apache.hadoop.io.Text</value>
                </property>
                <property>
                    <name>mapreduce.map.output.value.class</name>
                    <value>org.apache.hadoop.io.IntWritable</value>
                </property>
                <property>
                    <name>mapreduce.job.output.key.class</name>
                    <value>org.apache.hadoop.io.Text</value>
                </property>
                <property>
                    <name>mapreduce.job.output.value.class</name>
                    <value>org.apache.hadoop.io.IntWritable</value>
                </property>

                
                <property>
                    <name>mapreduce.input.fileinputformat.inputdir</name>
                    <value>${nameNode}/${DataRoot}/${inputDir}</value>
                </property>
                <property>
                    <name>mapreduce.output.fileoutputformat.outputdir</name>
                    <value>${nameNode}/${DataRoot}/${outputDir}</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>