/**
* Use the input splits to take samples of the input and generate sample keys. By default reads
* 100,000 keys from 10 locations in the input, sorts them and picks N-1 keys to generate N
* equally sized partitions.
*
* @param conf the job to sample
* @param partFile where to write the output file to
* @throws IOException if something goes wrong
*/
public static void writePartitionFile(JobConf conf, Path partFile) throws IOException {
TeraInputFormat inFormat = new TeraInputFormat();
TextSampler sampler = new TextSampler();
Text key = new Text();
Text value = new Text();
int partitions = conf.getNumReduceTasks();
long sampleSize = conf.getLong(SAMPLE_SIZE, 100000);
InputSplit[] splits = inFormat.getSplits(conf, conf.getNumMapTasks());
int samples = Math.min(10, splits.length);
long recordsPerSample = sampleSize / samples;
int sampleStep = splits.length / samples;
long records = 0;
// take N samples from different parts of the input
for (int i = 0; i < samples; ++i) {
RecordReader<Text, Text> reader =
inFormat.getRecordReader(splits[sampleStep * i], conf, null);
while (reader.next(key, value)) {
sampler.addKey(key);
records += 1;
if ((i + 1) * recordsPerSample <= records) {
break;
}
}
}
FileSystem outFs = partFile.getFileSystem(conf);
if (outFs.exists(partFile)) {
outFs.delete(partFile, false);
}
SequenceFile.Writer writer =
SequenceFile.createWriter(outFs, conf, partFile, Text.class, NullWritable.class);
NullWritable nullValue = NullWritable.get();
for (Text split : sampler.createPartitions(partitions)) {
writer.append(split, nullValue);
}
writer.close();
}
/**
* Use the input splits to take samples of the input and generate sample keys. By default reads
* 100,000 keys from 10 locations in the input, sorts them and picks N-1 keys to generate N
* equally sized partitions.
*
* @param job the job to sample
* @param partFile where to write the output file to
* @throws IOException if something goes wrong
*/
public static void writePartitionFile(final JobContext job, Path partFile)
throws IOException, InterruptedException {
long t1 = System.currentTimeMillis();
Configuration conf = job.getConfiguration();
final TeraInputFormat inFormat = new TeraInputFormat();
final TextSampler sampler = new TextSampler();
int partitions = job.getNumReduceTasks();
long sampleSize = conf.getLong(SAMPLE_SIZE, 100000);
final List<InputSplit> splits = inFormat.getSplits(job);
long t2 = System.currentTimeMillis();
System.out.println("Computing input splits took " + (t2 - t1) + "ms");
int samples = Math.min(conf.getInt(NUM_PARTITIONS, 10), splits.size());
System.out.println("Sampling " + samples + " splits of " + splits.size());
final long recordsPerSample = sampleSize / samples;
final int sampleStep = splits.size() / samples;
Thread[] samplerReader = new Thread[samples];
// take N samples from different parts of the input
for (int i = 0; i < samples; ++i) {
final int idx = i;
samplerReader[i] =
new Thread("Sampler Reader " + idx) {
{
setDaemon(true);
}
public void run() {
long records = 0;
try {
TaskAttemptContext context =
new TaskAttemptContextImpl(job.getConfiguration(), new TaskAttemptID());
RecordReader<Text, Text> reader =
inFormat.createRecordReader(splits.get(sampleStep * idx), context);
reader.initialize(splits.get(sampleStep * idx), context);
while (reader.nextKeyValue()) {
sampler.addKey(new Text(reader.getCurrentKey()));
records += 1;
if (recordsPerSample <= records) {
break;
}
}
} catch (IOException ie) {
System.err.println(
"Got an exception while reading splits " + StringUtils.stringifyException(ie));
System.exit(-1);
} catch (InterruptedException e) {
}
}
};
samplerReader[i].start();
}
FileSystem outFs = partFile.getFileSystem(conf);
DataOutputStream writer =
outFs.create(partFile, true, 64 * 1024, (short) 10, outFs.getDefaultBlockSize());
for (int i = 0; i < samples; i++) {
try {
samplerReader[i].join();
} catch (InterruptedException e) {
}
}
for (Text split : sampler.createPartitions(partitions)) {
split.write(writer);
}
writer.close();
long t3 = System.currentTimeMillis();
System.out.println("Computing parititions took " + (t3 - t2) + "ms");
}