I am facing issues while trying to run a job from windows (through eclipse) on
my hadoop cluster on my RHEL VM's. When I run it as "run on hadoop" it works
fine, but when I run it as a java application, it throws classnotfound exception
INFO: Task Id : attempt_201201101527_0037_m_000000_0, Status : FAILED
java.lang.RuntimeException: java.lang.ClassNotFoundException: TestHadoop$Map
at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:866)
at
org.apache.hadoop.mapreduce.JobContext.getMapperClass(JobContext.java:195)
at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:718)
at org.apache.hadoop.mapred.MapTask.run(MapTask.java:369)
at org.apache.hadoop.mapred.Child$4.run(Child.java:259)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:396)
at
org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1059)
at org.apache.hadoop.mapred.Child.main(Child.java:253)
Below is the stub:
public class TestHadoop extends Configured {
public static class Map extends Mapper<LongWritable, Text, Text,
IntWritable> {
private final static IntWritable one = new IntWritable(1);
private Text word = new Text();
public void map(LongWritable key, Text value, Context context)
throws IOException, InterruptedException {
String line = value.toString();
StringTokenizer tokenizer = new StringTokenizer(line);
while (tokenizer.hasMoreTokens()) {
word.set(tokenizer.nextToken());
context.write(word, one);
}
}
}
public static class Reduce extends Reducer<Text, IntWritable, Text,
IntWritable> {
public void reduce(Text key, Iterable<IntWritable> values,
Context context) throws IOException, InterruptedException {
int sum = 0;
for (IntWritable val:values) {
sum += val.get();
}
context.write(key, new IntWritable(sum));
}
}
public static void main(String[] args) throws Exception {
Configuration conf = new Configuration(true);
conf.set("fs.default.name","hdfs://vm-acd2-4c51:54310/");
conf.set("mapred.job.tracker","hdfs://vm-acd2-4c51:54311/");
conf.set("mapreduce.jobtracker.staging.root.dir","/app/hadoop/mapred/staging");
Job jobconf = new Job(conf,"TestHadoop");
jobconf.setJarByClass(TestHadoop.class);
jobconf.setOutputKeyClass(Text.class);
jobconf.setOutputValueClass(IntWritable.class);
jobconf.setMapperClass(Map.class);
jobconf.setCombinerClass(Reduce.class);
jobconf.setReducerClass(Reduce.class);
jobconf.setInputFormatClass(TextInputFormat.class);
jobconf.setOutputFormatClass(TextOutputFormat.class);
FileInputFormat.setInputPaths(jobconf, new
Path("/tmp/Hadoop_Temp_Data/Input/"));
FileOutputFormat.setOutputPath(jobconf, new
Path("/tmp/Hadoop_Temp_Data/Output1/"));
jobconf.waitForCompletion(true);
}
}
Any help will be greatly appreciated!
Thanks
Hema Subramanian
