/**
* Parse arguments and then runs a map/reduce job. Print output in standard out.
*
* @return a non-zero if there is an error. Otherwise, return 0.
*/
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.err.println("Usage: " + getClass().getName() + " <nMaps> <nSamples>");
ToolRunner.printGenericCommandUsage(System.err);
return 2;
}
final int nMaps = Integer.parseInt(args[0]);
final long nSamples = Long.parseLong(args[1]);
long now = System.currentTimeMillis();
int rand = new Random().nextInt(Integer.MAX_VALUE);
final Path tmpDir = new Path(TMP_DIR_PREFIX + "_" + now + "_" + rand);
System.out.println("Number of Maps = " + nMaps);
System.out.println("Samples per Map = " + nSamples);
System.out.println(
"Estimated value of Pi is " + estimatePi(nMaps, nSamples, tmpDir, getConf()));
return 0;
}
/**
* Run a map/reduce job for estimating Pi.
*
* @return the estimated value of Pi
*/
public static BigDecimal estimatePi(int numMaps, long numPoints, Path tmpDir, Configuration conf)
throws IOException, ClassNotFoundException, InterruptedException {
Job job = Job.getInstance(conf);
// setup job conf
job.setJobName(QuasiMonteCarlo.class.getSimpleName());
job.setJarByClass(QuasiMonteCarlo.class);
job.setInputFormatClass(SequenceFileInputFormat.class);
job.setOutputKeyClass(BooleanWritable.class);
job.setOutputValueClass(LongWritable.class);
job.setOutputFormatClass(SequenceFileOutputFormat.class);
job.setMapperClass(QmcMapper.class);
job.setReducerClass(QmcReducer.class);
job.setNumReduceTasks(1);
// turn off speculative execution, because DFS doesn't handle
// multiple writers to the same file.
job.setSpeculativeExecution(false);
// setup input/output directories
final Path inDir = new Path(tmpDir, "in");
final Path outDir = new Path(tmpDir, "out");
FileInputFormat.setInputPaths(job, inDir);
FileOutputFormat.setOutputPath(job, outDir);
final FileSystem fs = FileSystem.get(conf);
if (fs.exists(tmpDir)) {
throw new IOException(
"Tmp directory "
+ fs.makeQualified(tmpDir)
+ " already exists. Please remove it first.");
}
if (!fs.mkdirs(inDir)) {
throw new IOException("Cannot create input directory " + inDir);
}
try {
// generate an input file for each map task
for (int i = 0; i < numMaps; ++i) {
final Path file = new Path(inDir, "part" + i);
final LongWritable offset = new LongWritable(i * numPoints);
final LongWritable size = new LongWritable(numPoints);
final SequenceFile.Writer writer =
SequenceFile.createWriter(
fs, conf, file, LongWritable.class, LongWritable.class, CompressionType.NONE);
try {
writer.append(offset, size);
} finally {
writer.close();
}
System.out.println("Wrote input for Map #" + i);
}
// start a map/reduce job
System.out.println("Starting Job");
final long startTime = System.currentTimeMillis();
job.waitForCompletion(true);
final double duration = (System.currentTimeMillis() - startTime) / 1000.0;
System.out.println("Job Finished in " + duration + " seconds");
// read outputs
Path inFile = new Path(outDir, "reduce-out");
LongWritable numInside = new LongWritable();
LongWritable numOutside = new LongWritable();
SequenceFile.Reader reader = new SequenceFile.Reader(fs, inFile, conf);
try {
reader.next(numInside, numOutside);
} finally {
reader.close();
}
// compute estimated value
final BigDecimal numTotal =
BigDecimal.valueOf(numMaps).multiply(BigDecimal.valueOf(numPoints));
return BigDecimal.valueOf(4)
.setScale(20)
.multiply(BigDecimal.valueOf(numInside.get()))
.divide(numTotal, RoundingMode.HALF_UP);
} finally {
fs.delete(tmpDir, true);
}
}