@Override
public int run(String[] args) throws Exception {
Job job = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (job == null) {
return -1;
}
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputKeyClass(IntWritable.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
SequenceFileOutputFormat.setCompressOutput(job, true);
SequenceFileOutputFormat.setOutputCompressorClass(job, GzipCodec.class);
SequenceFileOutputFormat.setOutputCompressionType(job, CompressionType.BLOCK);
job.setPartitionerClass(TotalOrderPartitioner.class);
InputSampler.Sampler<IntWritable, Text> sampler =
new InputSampler.RandomSampler<IntWritable, Text>(0.1, 10000, 10);
InputSampler.writePartitionFile(job, sampler);
// Add to DistributedCache
Configuration conf = job.getConfiguration();
String partitionFile = TotalOrderPartitioner.getPartitionFile(conf);
URI partitionUri = new URI(partitionFile);
job.addCacheFile(partitionUri);
return job.waitForCompletion(true) ? 0 : 1;
}
@Override
public int run(String[] arg0) throws Exception {
Job job = Job.getInstance(getConf(), "PopulationJob");
Configuration conf = job.getConfiguration();
job.setJarByClass(Population.class);
Path out = new Path("totalorder");
FileInputFormat.setInputPaths(job, "populations");
FileOutputFormat.setOutputPath(job, out);
out.getFileSystem(conf).delete(out, true);
job.setMapperClass(PopulationMapper.class);
job.setReducerClass(PopulationReducer.class);
job.setInputFormatClass(KeyValueTextInputFormat.class);
job.setOutputFormatClass(TextOutputFormat.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(Text.class);
job.setNumReduceTasks(5);
// Configure the TotalOrderPartitioner here...
job.setPartitionerClass(TotalOrderPartitioner.class);
InputSampler.Sampler<Text, Text> sampler =
new InputSampler.RandomSampler<Text, Text>(0.1, 200, 3);
InputSampler.writePartitionFile(job, sampler);
String partitionFile = TotalOrderPartitioner.getPartitionFile(conf);
URI partitionURI = new URI(partitionFile + "#" + TotalOrderPartitioner.DEFAULT_PATH);
job.addCacheFile(partitionURI);
return job.waitForCompletion(true) ? 0 : 1;
}
/**
* Configure <code>job</code> with a TotalOrderPartitioner, partitioning against <code>splitPoints
* </code>. Cleans up the partitions file after job exists.
*/
static void configurePartitioner(Job job, List<ImmutableBytesWritable> splitPoints)
throws IOException {
Configuration conf = job.getConfiguration();
// create the partitions file
FileSystem fs = FileSystem.get(conf);
Path partitionsPath = new Path(conf.get("hbase.fs.tmp.dir"), "partitions_" + UUID.randomUUID());
fs.makeQualified(partitionsPath);
writePartitions(conf, partitionsPath, splitPoints);
fs.deleteOnExit(partitionsPath);
// configure job to use it
job.setPartitionerClass(TotalOrderPartitioner.class);
TotalOrderPartitioner.setPartitionFile(conf, partitionsPath);
}
/**
* Configure <code>job</code> with a TotalOrderPartitioner, partitioning against <code>splitPoints
* </code>. Cleans up the partitions file after job exists.
*/
static void configurePartitioner(Job job, List<ImmutableBytesWritable> splitPoints)
throws IOException {
Configuration conf = job.getConfiguration();
// create the partitions file
FileSystem fs = FileSystem.get(conf);
String hbaseTmpFsDir =
conf.get(
HConstants.TEMPORARY_FS_DIRECTORY_KEY, HConstants.DEFAULT_TEMPORARY_HDFS_DIRECTORY);
Path partitionsPath = new Path(hbaseTmpFsDir, "partitions_" + UUID.randomUUID());
fs.makeQualified(partitionsPath);
writePartitions(conf, partitionsPath, splitPoints);
fs.deleteOnExit(partitionsPath);
// configure job to use it
job.setPartitionerClass(TotalOrderPartitioner.class);
TotalOrderPartitioner.setPartitionFile(conf, partitionsPath);
}
