Java Code Examples for org.apache.hadoop.mapreduce.Job#addArchiveToClassPath()

The following examples show how to use org.apache.hadoop.mapreduce.Job#addArchiveToClassPath() . You can vote up the ones you like or vote down the ones you don't like, and go to the original project or source file by following the links above each example. You may check out the related API usage on the sidebar.
Example 1
Source File: TestMRWithDistributedCache.java    From hadoop with Apache License 2.0 5 votes vote down vote up
private void testWithConf(Configuration conf) throws IOException,
    InterruptedException, ClassNotFoundException, URISyntaxException {
  // Create a temporary file of length 1.
  Path first = createTempFile("distributed.first", "x");
  // Create two jars with a single file inside them.
  Path second =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.second.jar"), 2);
  Path third =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.third.jar"), 3);
  Path fourth =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.fourth.jar"), 4);


  Job job = Job.getInstance(conf);
  job.setMapperClass(DistributedCacheCheckerMapper.class);
  job.setReducerClass(DistributedCacheCheckerReducer.class);
  job.setOutputFormatClass(NullOutputFormat.class);
  FileInputFormat.setInputPaths(job, first);
  // Creates the Job Configuration
  job.addCacheFile(
    new URI(first.toUri().toString() + "#distributed.first.symlink"));
  job.addFileToClassPath(second);
  job.addArchiveToClassPath(third);
  job.addCacheArchive(fourth.toUri());
  job.setMaxMapAttempts(1); // speed up failures

  job.submit();
  assertTrue(job.waitForCompletion(false));
}
 
Example 2
Source File: TestMRWithDistributedCache.java    From big-c with Apache License 2.0 5 votes vote down vote up
private void testWithConf(Configuration conf) throws IOException,
    InterruptedException, ClassNotFoundException, URISyntaxException {
  // Create a temporary file of length 1.
  Path first = createTempFile("distributed.first", "x");
  // Create two jars with a single file inside them.
  Path second =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.second.jar"), 2);
  Path third =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.third.jar"), 3);
  Path fourth =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.fourth.jar"), 4);


  Job job = Job.getInstance(conf);
  job.setMapperClass(DistributedCacheCheckerMapper.class);
  job.setReducerClass(DistributedCacheCheckerReducer.class);
  job.setOutputFormatClass(NullOutputFormat.class);
  FileInputFormat.setInputPaths(job, first);
  // Creates the Job Configuration
  job.addCacheFile(
    new URI(first.toUri().toString() + "#distributed.first.symlink"));
  job.addFileToClassPath(second);
  job.addArchiveToClassPath(third);
  job.addCacheArchive(fourth.toUri());
  job.setMaxMapAttempts(1); // speed up failures

  job.submit();
  assertTrue(job.waitForCompletion(false));
}
 
Example 3
Source File: KDEJobRunner.java    From geowave with Apache License 2.0 5 votes vote down vote up
protected void addJobClasspathDependencies(final Job job, final Configuration conf)
    throws IOException, URISyntaxException {
  final String[] jars = conf.getTrimmedStrings(GEOWAVE_CLASSPATH_JARS);

  if (jars != null) {
    for (final String jarPath : jars) {
      job.addArchiveToClassPath(new Path(new URI(jarPath)));
    }
  }
}
 
Example 4
Source File: TestMRJobs.java    From hadoop with Apache License 2.0 4 votes vote down vote up
public void _testDistributedCache(String jobJarPath) throws Exception {
  if (!(new File(MiniMRYarnCluster.APPJAR)).exists()) {
    LOG.info("MRAppJar " + MiniMRYarnCluster.APPJAR
         + " not found. Not running test.");
    return;
  }

  // Create a temporary file of length 1.
  Path first = createTempFile("distributed.first", "x");
  // Create two jars with a single file inside them.
  Path second =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.second.jar"), 2);
  Path third =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.third.jar"), 3);
  Path fourth =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.fourth.jar"), 4);

  Job job = Job.getInstance(mrCluster.getConfig());
  
  // Set the job jar to a new "dummy" jar so we can check that its extracted 
  // properly
  job.setJar(jobJarPath);
  // Because the job jar is a "dummy" jar, we need to include the jar with
  // DistributedCacheChecker or it won't be able to find it
  Path distributedCacheCheckerJar = new Path(
          JarFinder.getJar(DistributedCacheChecker.class));
  job.addFileToClassPath(distributedCacheCheckerJar.makeQualified(
          localFs.getUri(), distributedCacheCheckerJar.getParent()));
  
  job.setMapperClass(DistributedCacheChecker.class);
  job.setOutputFormatClass(NullOutputFormat.class);

  FileInputFormat.setInputPaths(job, first);
  // Creates the Job Configuration
  job.addCacheFile(
      new URI(first.toUri().toString() + "#distributed.first.symlink"));
  job.addFileToClassPath(second);
  // The AppMaster jar itself
  job.addFileToClassPath(
          APP_JAR.makeQualified(localFs.getUri(), APP_JAR.getParent())); 
  job.addArchiveToClassPath(third);
  job.addCacheArchive(fourth.toUri());
  job.setMaxMapAttempts(1); // speed up failures

  job.submit();
  String trackingUrl = job.getTrackingURL();
  String jobId = job.getJobID().toString();
  Assert.assertTrue(job.waitForCompletion(false));
  Assert.assertTrue("Tracking URL was " + trackingUrl +
                    " but didn't Match Job ID " + jobId ,
        trackingUrl.endsWith(jobId.substring(jobId.lastIndexOf("_")) + "/"));
}
 
Example 5
Source File: TestMRJobs.java    From big-c with Apache License 2.0 4 votes vote down vote up
public void _testDistributedCache(String jobJarPath) throws Exception {
  if (!(new File(MiniMRYarnCluster.APPJAR)).exists()) {
    LOG.info("MRAppJar " + MiniMRYarnCluster.APPJAR
         + " not found. Not running test.");
    return;
  }

  // Create a temporary file of length 1.
  Path first = createTempFile("distributed.first", "x");
  // Create two jars with a single file inside them.
  Path second =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.second.jar"), 2);
  Path third =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.third.jar"), 3);
  Path fourth =
      makeJar(new Path(TEST_ROOT_DIR, "distributed.fourth.jar"), 4);

  Job job = Job.getInstance(mrCluster.getConfig());
  
  // Set the job jar to a new "dummy" jar so we can check that its extracted 
  // properly
  job.setJar(jobJarPath);
  // Because the job jar is a "dummy" jar, we need to include the jar with
  // DistributedCacheChecker or it won't be able to find it
  Path distributedCacheCheckerJar = new Path(
          JarFinder.getJar(DistributedCacheChecker.class));
  job.addFileToClassPath(distributedCacheCheckerJar.makeQualified(
          localFs.getUri(), distributedCacheCheckerJar.getParent()));
  
  job.setMapperClass(DistributedCacheChecker.class);
  job.setOutputFormatClass(NullOutputFormat.class);

  FileInputFormat.setInputPaths(job, first);
  // Creates the Job Configuration
  job.addCacheFile(
      new URI(first.toUri().toString() + "#distributed.first.symlink"));
  job.addFileToClassPath(second);
  // The AppMaster jar itself
  job.addFileToClassPath(
          APP_JAR.makeQualified(localFs.getUri(), APP_JAR.getParent())); 
  job.addArchiveToClassPath(third);
  job.addCacheArchive(fourth.toUri());
  job.setMaxMapAttempts(1); // speed up failures

  job.submit();
  String trackingUrl = job.getTrackingURL();
  String jobId = job.getJobID().toString();
  Assert.assertTrue(job.waitForCompletion(false));
  Assert.assertTrue("Tracking URL was " + trackingUrl +
                    " but didn't Match Job ID " + jobId ,
        trackingUrl.endsWith(jobId.substring(jobId.lastIndexOf("_")) + "/"));
}