java on hadoop_在本地/远程集群上运行java hadoop作业 (Running java hadoop job on local/remote cluster)...

2011-09-30 15:04:23

1

I'm trying to run hadoop job on local/remote cluster. This job in future will be executed from web application. I'm trying to execute this piece of code from eclipse:

public class TestHadoop {

private final static String host = "localhost";

public static void main(String[] args) throws IOException, InterruptedException, ClassNotFoundException {

run();

}

static void run() throws IOException, InterruptedException, ClassNotFoundException {

Configuration conf = new Configuration();

// run on other machine/cluster

conf.set("fs.default.name", "hdfs://" + host + ":8020");

conf.set("mapred.job.tracker", "hdfs://" + host + ":8021");

Job job = new Job(conf, "Wordcount");

job.setJarByClass(TestHadoop.class);

FileInputFormat.addInputPath(job, new Path("/user/hue/jobsub/sample_data/midsummer.txt"));

FileOutputFormat.setOutputPath(job, new Path("/tmp/hadoop-out2"));

job.setMapperClass(Map.class);

job.setReducerClass(Reduce.class);

job.setOutputKeyClass(Text.class);

job.setOutputValueClass(IntWritable.class);

job.setInputFormatClass(TextInputFormat.class);

job.setOutputFormatClass(TextOutputFormat.class);

job.waitForCompletion(true);

}

static class Map extends Mapper {

private final static IntWritable one = new IntWritable(1);

private Text word = new Text();

@Override

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);

}

}

}

static class Reduce extends Reducer {

@Override

public void reduce(Text key, Iterable values, Context context) throws IOException,

InterruptedException {

int sum = 0;

for (IntWritable val : values) {

sum += val.get();

}

context.write(key, new IntWritable(sum));

}

}

}

However I get the following errors:

2011-09-30 16:32:39,000 WARN org.apache.hadoop.mapred.Child: Error running child

java.lang.RuntimeException: java.lang.ClassNotFoundException: org.mmm.hadoop.TestHadoop$Map

at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:996)

at org.apache.hadoop.mapreduce.JobContext.getMapperClass(JobContext.java:212)

at org.apache.hadoop.mapred.MapTask.runNewMapper(MapTask.java:602)

at org.apache.hadoop.mapred.MapTask.run(MapTask.java:323)

at org.apache.hadoop.mapred.Child$4.run(Child.java:270)

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:1127)

at org.apache.hadoop.mapred.Child.main(Child.java:264)

Caused by: java.lang.ClassNotFoundException: org.mmm.hadoop.TestHadoop$Map

at java.net.URLClassLoader$1.run(URLClassLoader.java:202)

at java.security.AccessController.doPrivileged(Native Method)

at java.net.URLClassLoader.findClass(URLClassLoader.java:190)

at java.lang.ClassLoader.loadClass(ClassLoader.java:306)

at sun.misc.Launcher$AppClassLoader.loadClass(Launcher.java:301)

at java.lang.ClassLoader.loadClass(ClassLoader.java:247)

at java.lang.Class.forName0(Native Method)

at java.lang.Class.forName(Class.java:247)

at org.apache.hadoop.conf.Configuration.getClassByName(Configuration.java:943)

at org.apache.hadoop.conf.Configuration.getClass(Configuration.java:994)

... 8 more

16:33:01.209 [LeaseChecker] DEBUG org.apache.hadoop.hdfs.DFSClient - LeaseChecker is interrupted.

java.lang.InterruptedException: sleep interrupted

at java.lang.Thread.sleep(Native Method) [na:1.7.0]

at org.apache.hadoop.hdfs.DFSClient$LeaseChecker.run(DFSClient.java:1167) ~[hadoop-core-0.20.2-cdh3u1.jar:na]

at java.lang.Thread.run(Thread.java:722) [na:1.7.0]

I'm using CDH3 with Hue. Jobs appears on job list with above running child error.