Coordinator-wf-mr

通过coordinator调度一个wordcount例子，定时开启运行时间并且设置调度频率

job.properties

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

inputDir=cron/input
outputDir=cron/output

oozie.coord.application.path=${nameNode}/${oozieappsRoot}/cron/
start=2017-10-16T21:25+0800
end=2017-10-16T21:29+0800
workflowAppUri=${nameNode}/${oozieappsRoot}/cron/

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>

coordinator.xml

<coordinator-app name="cron-coord-mr" frequency="${coord:minutes(2)}" start="${start}" end="${end}" timezone="GMT+0800"
                 xmlns="uri:oozie:coordinator:0.2">
        <action>
        <workflow>
            <app-path>${workflowAppUri}</app-path>
            <configuration>
                <property>
                    <name>jobTracker</name>
                    <value>${jobTracker}</value>
                </property>
                <property>
                    <name>nameNode</name>
                    <value>${nameNode}</value>
                </property>
                <property>
                    <name>queueName</name>
                    <value>${queueName}</value>
                </property>
            </configuration>
        </workflow>
    </action>
</coordinator-app>