DistributedCache - third party jar not found - hadoop

Question

I'm trying to get a hold of DistributedCache. I'm using Apache Hadoop 1.2.1 on two nodes.
I referred to the Cloudera post which is simply extended in the other posts that explain how to use third-party jars using -libjars
Note:
In my jar, I haven't included any jar libs. - neither Hadoop core nor commons lang.
The code :
public class WordCounter extends Configured implements Tool {
#Override
public int run(String[] args) throws Exception {
// TODO Auto-generated method stub
// Job job = new Job(getConf(), args[0]);
Job job = new Job(super.getConf(), args[0]);
job.setInputFormatClass(TextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setJarByClass(WordCounter.class);
FileInputFormat.setInputPaths(job, new Path(args[1]));
FileOutputFormat.setOutputPath(job, new Path(args[2]));
job.setMapperClass(WCMapper.class);
job.setReducerClass(WCReducer.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
int jobState = job.waitForCompletion(true) ? 0 : 1;
return jobState;
}
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
if (args == null || args.length < 3) {
System.out.println("The below three arguments are expected");
System.out
.println("<job name> <hdfs path of the input file> <hdfs path of the output file>");
return;
}
WordCounter wordCounter = new WordCounter();
// System.exit(ToolRunner.run(wordCounter, args));
System.exit(ToolRunner.run(new Configuration(), wordCounter, args));
}
}
The Mapper class is naive, its only attempting to use the StringUtils from Apache Commons(and NOT hadoop)
import java.io.IOException;
import java.util.StringTokenizer;
import org.apache.commons.lang3.StringUtils;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapreduce.Mapper;
/**
* #author 298790
*
*/
public class WCMapper extends Mapper<LongWritable, Text, Text, IntWritable> {
private static IntWritable one = new IntWritable(1);
#Override
protected void map(
LongWritable key,
Text value,
org.apache.hadoop.mapreduce.Mapper<LongWritable, Text, Text, IntWritable>.Context context)
throws IOException, InterruptedException {
// TODO Auto-generated method stub
StringTokenizer strTokenizer = new StringTokenizer(value.toString());
Text token = new Text();
while (strTokenizer.hasMoreTokens()) {
token.set(strTokenizer.nextToken());
context.write(token, one);
}
System.out.println("Converting " + value + " to upper case "
+ StringUtils.upperCase(value.toString()));
}
}
The commands that I use :
bigdata#slave3:~$ export HADOOP_CLASSPATH=dumphere/lib/commons-lang3-3.1.jar
bigdata#slave3:~$
bigdata#slave3:~$ echo $HADOOP_CLASSPATH
dumphere/lib/commons-lang3-3.1.jar
bigdata#slave3:~$
bigdata#slave3:~$ echo $LIBJARS
dumphere/lib/commons-lang3-3.1.jar
bigdata#slave3:~$ hadoop jar dumphere/code/jars/hdp_3rdparty.jar com.hadoop.basics.WordCounter "WordCount" "/input/dumphere/Childhood_days.txt" "/output/dumphere/wc" -libjars ${LIBJARS}
The exception I get :
Warning: $HADOOP_HOME is deprecated.
14/08/13 21:56:05 INFO input.FileInputFormat: Total input paths to process : 1
14/08/13 21:56:05 INFO util.NativeCodeLoader: Loaded the native-hadoop library
14/08/13 21:56:05 WARN snappy.LoadSnappy: Snappy native library not loaded
14/08/13 21:56:05 INFO mapred.JobClient: Running job: job_201408111719_0190
14/08/13 21:56:06 INFO mapred.JobClient: map 0% reduce 0%
14/08/13 21:56:37 INFO mapred.JobClient: Task Id : attempt_201408111719_0190_m_000000_0, Status : FAILED
Error: java.lang.ClassNotFoundException: org.apache.commons.lang3.StringUtils
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:424)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:357)
at com.hadoop.basics.WCMapper.map(WCMapper.java:40)
at com.hadoop.basics.WCMapper.map(WCMapper.java:1)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:764)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:364)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
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:1190)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
14/08/13 21:56:42 INFO mapred.JobClient: Task Id : attempt_201408111719_0190_m_000000_1, Status : FAILED
Error: java.lang.ClassNotFoundException: org.apache.commons.lang3.StringUtils
at java.net.URLClassLoader$1.run(URLClassLoader.java:366)
at java.net.URLClassLoader$1.run(URLClassLoader.java:355)
at java.security.AccessController.doPrivileged(Native Method)
at java.net.URLClassLoader.findClass(URLClassLoader.java:354)
at java.lang.ClassLoader.loadClass(ClassLoader.java:423)
at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:308)
at java.lang.ClassLoader.loadClass(ClassLoader.java:356)
at com.hadoop.basics.WCMapper.map(WCMapper.java:40)
at com.hadoop.basics.WCMapper.map(WCMapper.java:1)
at org.apache.hadoop.mapreduce.Mapper.run(Mapper.java:145)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:764)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:364)
at org.apache.hadoop.mapred.Child$4.run(Child.java:255)
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:1190)
at org.apache.hadoop.mapred.Child.main(Child.java:249)
The Cloudera post mentions :
The jar will be placed in distributed cache and will be made available to all of the job’s task attempts. More specifically, you will find the JAR in one of the ${mapred.local.dir}/taskTracker/archive/${user.name}/distcache/… subdirectories on local nodes.
But on that path, I'm not able to find the commons-lang3-3.1.jar
What am I missing?