getting error in oozie job

Question

I have a WordCount MapReduce job, when it runs from hadoop cli it runs well and given the output. but when I run the job through oozie it throwing me error 'Error: java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.Text, received org.apache.hadoop.io.LongWritable'

Here is the code

package Drivers;

import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.Reducer;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolRunner;

public class WordCount extends Configured implements Tool
{

    public static void main(String[] args) throws Exception 
    {
    int res = ToolRunner.run(new Configuration(), new WordCount(), args);
    System.exit(res);
    }

    @Override
    public int run(String[] args) throws Exception 
    {

    Job job = Job.getInstance(getConf(), "Tool Job");
    job.setJarByClass(WordCount.class);
    job.setMapperClass(WordMap.class);
    job.setReducerClass(RedForSum.class);
    job.setMapOutputKeyClass(Text.class);
    job.setMapOutputValueClass(IntWritable.class);
    job.setOutputKeyClass(Text.class);
    job.setOutputValueClass(IntWritable.class);
    FileInputFormat.addInputPath(job, new Path(args[0]));
    FileOutputFormat.setOutputPath(job, new Path(args[1]));
    return job.waitForCompletion(true) ? 0 : 1;
    }


    //map method
    public static class WordMap extends Mapper<LongWritable,Text,Text,IntWritable>
    {
        public void map(LongWritable k, Text v,Context con) throws IOException, InterruptedException
        {
            String line=v.toString();
            StringTokenizer t = new StringTokenizer(line);
            while(t.hasMoreTokens())
            {
                String word=t.nextToken();
                con.write(new Text(word),new IntWritable(1));
            }

        }
    }
    //reducer method
    public static class RedForSum extends Reducer<Text, IntWritable,Text,IntWritable>
    {
        public void reduce(Text k, Iterable<IntWritable> vlist, Context con) throws IOException, InterruptedException
        {
            int tot=0;
            for(IntWritable v:vlist)
             tot+=v.get();
            con.write(k, new IntWritable(tot));
        }
    }
}

my workflow.xml is here

    <workflow-app xmlns="uri:oozie:workflow:0.1" name="map-reduce-wf">
 <start to="mr-node"/>
 <action name="mr-node">
     <map-reduce>
       <job-tracker>${jobTracker}</job-tracker>
       <name-node>${nameNode}</name-node>
   <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>mapred.job.queue.name</name>
       <value>${queueName}</value>
     </property>
     <property>
       <name>mapreduce.mapper.class</name>
       <value>Drivers.WordCount$WordMap</value>
     </property>
     <property>
       <name>mapreduce.reducer.class</name>
       <value>Drivers.WordCount$RedForSum</value>
     </property>
     <property>
       <name>mapred.output.key.class</name>
       <value>org.apache.hadoop.io.Text</value>
     </property>
     <property>
       <name>mapred.output.value.class</name>
       <value>org.apache.hadoop.io.IntWritable</value>
     </property>
     <property>
       <name>mapred.input.dir</name>
       <value>${inputDir}</value>
     </property>
     <property>
       <name>mapred.output.dir</name>
       <value>${outputDir}</value>
     </property>
   </configuration>
  </map-reduce>
  <ok to="end"/>
  <error to="fail"/>
 </action>
   <kill name="fail">
   <message>Map/Reduce failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
   </kill>
   <end name="end"/>
</workflow-app>

When I run through oozie

oozie job -oozie http://localhost:11000/oozie -config /home/cloudera/job.properties -run

it throwing me the error

Error: java.io.IOException: Type mismatch in key from map: expected org.apache.hadoop.io.Text, received org.apache.hadoop.io.LongWritable at org.apache.hadoop.mapred.MapTask$MapOutputBuffer.collect(MapTask.java:1072) at org.apache.hadoop.mapred.MapTask$NewOutputCollector.write(MapTask.java:715) at org.apache.hadoop.mapreduce.task.TaskInputOutputContextImpl.write(TaskInputOutputContextImpl.java:89) at org.apache.hadoop.mapreduce.lib.map.WrappedMapper$Context.write(WrappedMapper.java:112) at org.apache.hadoop.mapreduce.Mapper.map(Mapper.java:124) at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145) at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:787) at org.apache.hadoop.mapred.MapTask.run(MapTask.java:341) at org.apache.hadoop.mapred.YarnChild$2.run(YarnChild.java:163) at java.security.AccessController.doPrivileged(Native Method) at javax.security.auth.Subject.doAs(Subject.java:415) at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1671) at org.apache.hadoop.mapred.YarnChild.main(YarnChild.java:158)

Can someone please let me know where I was mistaken.

Thanks in Advance.

Raju Sharma Raju Sharma · Accepted Answer · 2016-04-09T07:54:41

The problem seems to be in workflow xml. here the property name should be mapreduce.map.class and mapreduce.reduce.class instead of mapreduce.mapper.class and mapreduce.reducer.class correspondingly. So modified workflow should have these properties.

<property>
       <name>mapreduce.map.class</name>
       <value>Drivers.WordCount$WordMap</value>
     </property>
     <property>
       <name>mapreduce.reduce.class</name>
       <value>Drivers.WordCount$RedForSum</value>
     </property>

For more on this please refere here

getting error in oozie job

1 Answers