@Override
public int run(String[] args) throws Exception {
if (args.length != 2) {
System.err.printf(
"Usage: %s [generic options] <input> <output>\n", getClass().getSimpleName());
ToolRunner.printGenericCommandUsage(System.err);
return -1;
}
JobConf conf = new JobConf(getConf(), getClass());
conf.setJobName("Max temperature");
FileInputFormat.addInputPath(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(MaxTemperatureMapper.class);
conf.setCombinerClass(MaxTemperatureReducer.class);
conf.setReducerClass(MaxTemperatureReducer.class);
// vv MaxTemperatureDriverV6
conf.setProfileEnabled(true);
conf.setProfileParams(
"-agentlib:hprof=cpu=samples,heap=sites,depth=6," + "force=n,thread=y,verbose=n,file=%s");
conf.setProfileTaskRange(true, "0-2");
// ^^ MaxTemperatureDriverV6
JobClient.runJob(conf);
return 0;
}
public void testComplexNameWithRegex() throws Exception {
OutputStream os = getFileSystem().create(new Path(getInputDir(), "text.txt"));
Writer wr = new OutputStreamWriter(os);
wr.write("b a\n");
wr.close();
JobConf conf = createJobConf();
conf.setJobName("name \\Evalue]");
conf.setInputFormat(TextInputFormat.class);
conf.setOutputKeyClass(LongWritable.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(IdentityMapper.class);
FileInputFormat.setInputPaths(conf, getInputDir());
FileOutputFormat.setOutputPath(conf, getOutputDir());
JobClient.runJob(conf);
Path[] outputFiles =
FileUtil.stat2Paths(getFileSystem().listStatus(getOutputDir(), new OutputLogFilter()));
assertEquals(1, outputFiles.length);
InputStream is = getFileSystem().open(outputFiles[0]);
BufferedReader reader = new BufferedReader(new InputStreamReader(is));
assertEquals("0\tb a", reader.readLine());
assertNull(reader.readLine());
reader.close();
}
public static void runJob(String[] args) {
JobConf conf = new JobConf(CassandraBulkLoader.class);
if (args.length >= 4) {
conf.setNumReduceTasks(new Integer(args[3]));
}
try {
// We store the cassandra storage-conf.xml on the HDFS cluster
DistributedCache.addCacheFile(new URI("/cassandra/storage-conf.xml#storage-conf.xml"), conf);
} catch (URISyntaxException e) {
throw new RuntimeException(e);
}
conf.setInputFormat(KeyValueTextInputFormat.class);
conf.setJobName("CassandraBulkLoader_v2");
conf.setMapperClass(Map.class);
conf.setReducerClass(Reduce.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
FileInputFormat.setInputPaths(conf, new Path(args[1]));
FileOutputFormat.setOutputPath(conf, new Path(args[2]));
try {
JobClient.runJob(conf);
} catch (IOException e) {
throw new RuntimeException(e);
}
}
private String runJob() throws Exception {
OutputStream os = getFileSystem().create(new Path(getInputDir(), "text.txt"));
Writer wr = new OutputStreamWriter(os);
wr.write("hello1\n");
wr.write("hello2\n");
wr.write("hello3\n");
wr.close();
JobConf conf = createJobConf();
conf.setJobName("mr");
conf.setJobPriority(JobPriority.HIGH);
conf.setInputFormat(TextInputFormat.class);
conf.setMapOutputKeyClass(LongWritable.class);
conf.setMapOutputValueClass(Text.class);
conf.setOutputFormat(TextOutputFormat.class);
conf.setOutputKeyClass(LongWritable.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(org.apache.hadoop.mapred.lib.IdentityMapper.class);
conf.setReducerClass(org.apache.hadoop.mapred.lib.IdentityReducer.class);
FileInputFormat.setInputPaths(conf, getInputDir());
FileOutputFormat.setOutputPath(conf, getOutputDir());
return JobClient.runJob(conf).getID().toString();
}
@Override
public int run(String[] args) throws Exception {
JobConf conf = new JobConf(getConf(), getClass());
conf.setJobName("UFO count");
String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
if (otherArgs.length != 2) {
System.err.println("Usage: avro UFO counter <in> <out>");
System.exit(2);
}
FileInputFormat.addInputPath(conf, new Path(otherArgs[0]));
Path outputPath = new Path(otherArgs[1]);
FileOutputFormat.setOutputPath(conf, outputPath);
outputPath.getFileSystem(conf).delete(outputPath);
Schema input_schema = Schema.parse(getClass().getResourceAsStream("ufo.avsc"));
AvroJob.setInputSchema(conf, input_schema);
AvroJob.setMapOutputSchema(
conf,
Pair.getPairSchema(Schema.create(Schema.Type.STRING), Schema.create(Schema.Type.LONG)));
AvroJob.setOutputSchema(conf, OUTPUT_SCHEMA);
AvroJob.setMapperClass(conf, AvroRecordMapper.class);
AvroJob.setReducerClass(conf, AvroRecordReducer.class);
conf.setInputFormat(AvroInputFormat.class);
JobClient.runJob(conf);
return 0;
}
public void inject(Path crawlDb, Path urlDir) throws IOException {
SimpleDateFormat sdf = new SimpleDateFormat("yyyy-MM-dd HH:mm:ss");
long start = System.currentTimeMillis();
if (LOG.isInfoEnabled()) {
LOG.info("Injector: starting at " + sdf.format(start));
LOG.info("Injector: crawlDb: " + crawlDb);
LOG.info("Injector: urlDir: " + urlDir);
}
Path tempDir =
new Path(
getConf().get("mapred.temp.dir", ".")
+ "/inject-temp-"
+ Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
// map text input file to a <url,CrawlDatum> file
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Converting injected urls to crawl db entries.");
}
JobConf sortJob = new NutchJob(getConf());
sortJob.setJobName("inject " + urlDir);
FileInputFormat.addInputPath(sortJob, urlDir);
sortJob.setMapperClass(InjectMapper.class);
FileOutputFormat.setOutputPath(sortJob, tempDir);
sortJob.setOutputFormat(SequenceFileOutputFormat.class);
sortJob.setOutputKeyClass(Text.class);
sortJob.setOutputValueClass(CrawlDatum.class);
sortJob.setLong("injector.current.time", System.currentTimeMillis());
RunningJob mapJob = JobClient.runJob(sortJob);
long urlsInjected = mapJob.getCounters().findCounter("injector", "urls_injected").getValue();
long urlsFiltered = mapJob.getCounters().findCounter("injector", "urls_filtered").getValue();
LOG.info("Injector: total number of urls rejected by filters: " + urlsFiltered);
LOG.info(
"Injector: total number of urls injected after normalization and filtering: "
+ urlsInjected);
// merge with existing crawl db
if (LOG.isInfoEnabled()) {
LOG.info("Injector: Merging injected urls into crawl db.");
}
JobConf mergeJob = CrawlDb.createJob(getConf(), crawlDb);
FileInputFormat.addInputPath(mergeJob, tempDir);
mergeJob.setReducerClass(InjectReducer.class);
JobClient.runJob(mergeJob);
CrawlDb.install(mergeJob, crawlDb);
// clean up
FileSystem fs = FileSystem.get(getConf());
fs.delete(tempDir, true);
long end = System.currentTimeMillis();
LOG.info(
"Injector: finished at "
+ sdf.format(end)
+ ", elapsed: "
+ TimingUtil.elapsedTime(start, end));
}
// Job configuration
private static JobConf createJobConf(Configuration conf) {
JobConf jobconf = new JobConf(conf, DistCp.class);
jobconf.setJobName(NAME);
// turn off speculative execution, because DFS doesn't handle
// multiple writers to the same file.
jobconf.setMapSpeculativeExecution(false);
jobconf.setInputFormat(CopyInputFormat.class);
jobconf.setOutputKeyClass(Text.class);
jobconf.setOutputValueClass(Text.class);
jobconf.setMapperClass(CopyFilesMapper.class);
jobconf.setNumReduceTasks(0);
return jobconf;
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(Add1.class);
conf.setJobName("sumar1");
conf.setOutputKeyClass(IntWritable.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
// Main function
public static void main(String[] args) throws Exception {
// TODO Auto-generated method stub
JobConf conf = new JobConf(ProcessUnits.class);
conf.setJobName("max_eletricityunits");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(EE_Mapper.class);
conf.setCombinerClass(EE_Reducer.class);
conf.setReducerClass(EE_Reducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public int run(String[] args) throws Exception {
if (args.length < 4) {
System.out.println("ERROR: Please Enter args : input output type(text|seq) splitChar(9=\t)");
return JobClient.SUCCESS;
}
String input = args[0];
String output = args[1];
String type = args[2];
String splitChar = args[3];
JobConf config = new JobConf(getConf(), getClass());
config.set("user.split", splitChar);
config.setJobName("File Filter -" + System.currentTimeMillis());
config.setNumReduceTasks(10);
config.setReducerClass(IdentityReducer.class);
config.setMapperClass(FileTestMapper.class);
if ("text".equals(type)) {
config.setInputFormat(TextInputFormat.class);
TextInputFormat.addInputPath(config, new Path(input));
} else {
config.setInputFormat(SequenceFileInputFormat.class);
SequenceFileInputFormat.addInputPath(config, new Path(input));
}
config.setMapOutputKeyClass(Text.class);
config.setMapOutputValueClass(Text.class);
config.setOutputKeyClass(Text.class);
config.setOutputValueClass(Text.class);
// if output path exists then return
FileSystem fs = FileSystem.get(config);
Path outputPath = new Path(output);
FileOutputFormat.setOutputPath(config, outputPath);
if (!fs.exists(outputPath)) {
JobClient.runJob(config);
} else {
System.out.println("You has finished this job today ! " + outputPath);
}
return JobClient.SUCCESS;
}
public static void main(String args[]) throws IOException {
JobConf job = new JobConf(WordCountJob.class);
job.setJobName("Word Count Example");
FileInputFormat.setInputPaths(job, args[0]);
job.setInputFormat(TextInputFormat.class);
job.setMapperClass(MapTask.class);
job.setCombinerClass(ReduceTask.class);
job.setReducerClass(ReduceTask.class);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(IntWritable.class);
job.setOutputFormat(TextOutputFormat.class);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
JobClient.runJob(job);
}
public int run(String[] args) throws Exception {
if (args.length < 1) {
args = new String[] {DateStringUtils.now()};
System.out.println(
"ERROR: Please Enter Date , eg. 20101010 ! now use default => " + DateStringUtils.now());
}
JobConf config = new JobConf(getConf(), getClass());
config.set("user.args", Utils.asString(args));
config.setJobName(getClass() + "-" + System.currentTimeMillis());
config.setNumReduceTasks(100);
config.setMapperClass(getClass());
config.setReducerClass(getClass());
config.setInputFormat(getInputFormat());
config.setMapOutputKeyClass(Text.class);
config.setMapOutputValueClass(Text.class);
// add input paths
for (String path : getInputPath(args)) {
if (TextInputFormat.class.equals(getInputFormat())) {
TextInputFormat.addInputPath(config, new Path(path));
} else if (SequenceFileInputFormat.class.equals(getInputFormat())) {
SequenceFileInputFormat.addInputPath(config, new Path(path));
}
}
config.setOutputKeyClass(Text.class);
config.setOutputValueClass(Text.class);
// if output path exists then return
FileSystem fs = FileSystem.get(config);
Path outputPath = new Path(getOutputPath(args));
FileOutputFormat.setOutputPath(config, outputPath);
if (!fs.exists(outputPath)) {
JobClient.runJob(config);
} else {
System.out.println("You has finished this job today ! " + outputPath);
}
return JobClient.SUCCESS;
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(WordCount.class);
conf.setJobName("wordcount");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public static void main(String[] args) throws IOException {
if (args.length != 2) {
System.err.println("Usage: OldMaxTemperature <input path> <output path>");
System.exit(-1);
}
/*[*/ JobConf conf = new JobConf(OldMaxTemperature.class); /*]*/
/*[*/ conf /*]*/.setJobName("Max temperature");
FileInputFormat.addInputPath(/*[*/ conf /*]*/, new Path(args[0]));
FileOutputFormat.setOutputPath(/*[*/ conf /*]*/, new Path(args[1]));
/*[*/ conf /*]*/.setMapperClass(OldMaxTemperatureMapper.class);
/*[*/ conf /*]*/.setReducerClass(OldMaxTemperatureReducer.class);
/*[*/ conf /*]*/.setOutputKeyClass(Text.class);
/*[*/ conf /*]*/.setOutputValueClass(IntWritable.class);
/*[*/ JobClient.runJob(conf); /*]*/
}
public int run(String[] args) throws Exception {
JobConf conf = new JobConf(getConf(), XiangLi1_exercise3.class);
conf.setJobName("xiangli1_exercise3");
conf.setNumReduceTasks(0);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(Map.class);
// conf.setCombinerClass(Reduce.class);
// conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
return 0;
}
@Override
public int run(String[] args) throws Exception {
JobConf conf = new JobConf(getConf(), Sqrt2.class);
conf.setJobName("sqrt2");
conf.setOutputKeyClass(DoubleWritable.class);
conf.setOutputValueClass(DoubleWritable.class);
conf.setMapperClass(Map.class);
/*conf.setCombinerClass(Reduce.class);*/
conf.setReducerClass(Reduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
return 0;
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(Main.class);
conf.setJobName("feels-analysis");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(TheOutputClass.class);
conf.setMapperClass(Map.class);
conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
conf.setNumReduceTasks(1);
conf.setInputFormat(CSVTextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
// TODO: determine whether we need extra output
MultipleOutputs.addMultiNamedOutput(
conf, SECOND_OUTPUT, TextOutputFormat.class, Text.class, TheOutputClass.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(NeighborSearch.class);
conf.setJobName("star searching");
conf.setOutputKeyClass(BlockIDWritable.class);
conf.setOutputValueClass(PairWritable.class);
conf.setMapperClass(Map.class);
// conf.setCombinerClass(Reduce.class);
conf.setReducerClass(Reduce.class);
// conf.setPartitionerClass(BlockPartitioner.class);
// conf.setFloat("mapred.reduce.slowstart.completed.maps", (float) 1.0);
conf.setInputFormat(StarInputFormat.class);
conf.setOutputFormat(StarOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(args[0]));
FileOutputFormat.setOutputPath(conf, new Path(args[1]));
JobClient.runJob(conf);
}
static void checkRecords(
Configuration defaults, int noMaps, int noReduces, Path sortInput, Path sortOutput)
throws IOException {
JobConf jobConf = new JobConf(defaults, RecordChecker.class);
jobConf.setJobName("sortvalidate-record-checker");
jobConf.setInputFormat(SequenceFileInputFormat.class);
jobConf.setOutputFormat(SequenceFileOutputFormat.class);
jobConf.setOutputKeyClass(BytesWritable.class);
jobConf.setOutputValueClass(IntWritable.class);
jobConf.setMapperClass(Map.class);
jobConf.setReducerClass(Reduce.class);
JobClient client = new JobClient(jobConf);
ClusterStatus cluster = client.getClusterStatus();
if (noMaps == -1) {
noMaps = cluster.getTaskTrackers() * jobConf.getInt("test.sortvalidate.maps_per_host", 10);
}
if (noReduces == -1) {
noReduces = (int) (cluster.getMaxReduceTasks() * 0.9);
String sortReduces = jobConf.get("test.sortvalidate.reduces_per_host");
if (sortReduces != null) {
noReduces = cluster.getTaskTrackers() * Integer.parseInt(sortReduces);
}
}
jobConf.setNumMapTasks(noMaps);
jobConf.setNumReduceTasks(noReduces);
FileInputFormat.setInputPaths(jobConf, sortInput);
FileInputFormat.addInputPath(jobConf, sortOutput);
Path outputPath = new Path("/tmp/sortvalidate/recordchecker");
FileSystem fs = FileSystem.get(defaults);
if (fs.exists(outputPath)) {
fs.delete(outputPath, true);
}
FileOutputFormat.setOutputPath(jobConf, outputPath);
// Uncomment to run locally in a single process
// job_conf.set("mapred.job.tracker", "local");
Path[] inputPaths = FileInputFormat.getInputPaths(jobConf);
System.out.println(
"\nSortValidator.RecordChecker: Running on "
+ cluster.getTaskTrackers()
+ " nodes to validate sort from "
+ inputPaths[0]
+ ", "
+ inputPaths[1]
+ " into "
+ FileOutputFormat.getOutputPath(jobConf)
+ " with "
+ noReduces
+ " reduces.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
JobClient.runJob(jobConf);
Date end_time = new Date();
System.out.println("Job ended: " + end_time);
System.out.println(
"The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds.");
}
/** Check refreshNodes for decommissioning blacklisted nodes. */
public void testBlacklistedNodeDecommissioning() throws Exception {
LOG.info("Testing blacklisted node decommissioning");
MiniMRCluster mr = null;
JobTracker jt = null;
try {
// start mini mr
JobConf jtConf = new JobConf();
jtConf.set("mapred.max.tracker.blacklists", "1");
mr = new MiniMRCluster(0, 0, 2, "file:///", 1, null, null, null, jtConf);
jt = mr.getJobTrackerRunner().getJobTracker();
assertEquals("Trackers not up", 2, jt.taskTrackers().size());
// validate the total tracker count
assertEquals(
"Active tracker count mismatch", 2, jt.getClusterStatus(false).getTaskTrackers());
// validate blacklisted count
assertEquals(
"Blacklisted tracker count mismatch",
0,
jt.getClusterStatus(false).getBlacklistedTrackers());
// run a failing job to blacklist the tracker
JobConf jConf = mr.createJobConf();
jConf.set("mapred.max.tracker.failures", "1");
jConf.setJobName("test-job-fail-once");
jConf.setMapperClass(FailOnceMapper.class);
jConf.setReducerClass(IdentityReducer.class);
jConf.setNumMapTasks(1);
jConf.setNumReduceTasks(0);
RunningJob job =
UtilsForTests.runJob(jConf, new Path(TEST_DIR, "in"), new Path(TEST_DIR, "out"));
job.waitForCompletion();
// validate the total tracker count
assertEquals(
"Active tracker count mismatch", 1, jt.getClusterStatus(false).getTaskTrackers());
// validate blacklisted count
assertEquals(
"Blacklisted tracker count mismatch",
1,
jt.getClusterStatus(false).getBlacklistedTrackers());
// find the blacklisted tracker
String trackerName = null;
for (TaskTrackerStatus status : jt.taskTrackers()) {
if (jt.isBlacklisted(status.getTrackerName())) {
trackerName = status.getTrackerName();
break;
}
}
// get the hostname
String hostToDecommission = JobInProgress.convertTrackerNameToHostName(trackerName);
LOG.info("Decommissioning tracker " + hostToDecommission);
// decommission the node
HashSet<String> decom = new HashSet<String>(1);
decom.add(hostToDecommission);
jt.decommissionNodes(decom);
// validate
// check the cluster status and tracker size
assertEquals(
"Tracker is not lost upon host decommissioning",
1,
jt.getClusterStatus(false).getTaskTrackers());
assertEquals(
"Blacklisted tracker count incorrect in cluster status " + "after decommissioning",
0,
jt.getClusterStatus(false).getBlacklistedTrackers());
assertEquals("Tracker is not lost upon host decommissioning", 1, jt.taskTrackers().size());
} finally {
if (mr != null) {
mr.shutdown();
mr = null;
jt = null;
FileUtil.fullyDelete(new File(TEST_DIR.toString()));
}
}
}
/**
* The main driver for word count map/reduce program. Invoke this method to submit the map/reduce
* job.
*
* @throws IOException When there is communication problems with the job tracker.
*/
public void testOldJobWithMapAndReducers() throws Exception {
JobConf conf = new JobConf(TestJobCounters.class);
conf.setJobName("wordcount-map-reducers");
// the keys are words (strings)
conf.setOutputKeyClass(Text.class);
// the values are counts (ints)
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(WordCount.MapClass.class);
conf.setCombinerClass(WordCount.Reduce.class);
conf.setReducerClass(WordCount.Reduce.class);
conf.setNumMapTasks(3);
conf.setNumReduceTasks(1);
conf.setInt("io.sort.mb", 1);
conf.setInt("io.sort.factor", 2);
conf.set("io.sort.record.percent", "0.05");
conf.set("io.sort.spill.percent", "0.80");
FileSystem fs = FileSystem.get(conf);
Path testDir = new Path(TEST_ROOT_DIR, "countertest");
conf.set("test.build.data", testDir.toString());
try {
if (fs.exists(testDir)) {
fs.delete(testDir, true);
}
if (!fs.mkdirs(testDir)) {
throw new IOException("Mkdirs failed to create " + testDir.toString());
}
String inDir = testDir + File.separator + "genins" + File.separator;
String outDir = testDir + File.separator;
Path wordsIns = new Path(inDir);
if (!fs.mkdirs(wordsIns)) {
throw new IOException("Mkdirs failed to create " + wordsIns.toString());
}
long inputSize = 0;
// create 3 input files each with 5*2k words
File inpFile = new File(inDir + "input5_2k_1");
createWordsFile(inpFile);
inputSize += inpFile.length();
inpFile = new File(inDir + "input5_2k_2");
createWordsFile(inpFile);
inputSize += inpFile.length();
inpFile = new File(inDir + "input5_2k_3");
createWordsFile(inpFile);
inputSize += inpFile.length();
FileInputFormat.setInputPaths(conf, inDir);
Path outputPath1 = new Path(outDir, "output5_2k_3");
FileOutputFormat.setOutputPath(conf, outputPath1);
RunningJob myJob = JobClient.runJob(conf);
Counters c1 = myJob.getCounters();
// 3maps & in each map, 4 first level spills --- So total 12.
// spilled records count:
// Each Map: 1st level:2k+2k+2k+2k=8k;2ndlevel=4k+4k=8k;
// 3rd level=2k(4k from 1st level & 4k from 2nd level & combineAndSpill)
// So total 8k+8k+2k=18k
// For 3 Maps, total = 3*18=54k
// Reduce: each of the 3 map o/p's(2k each) will be spilled in shuffleToDisk()
// So 3*2k=6k in 1st level; 2nd level:4k(2k+2k);
// 3rd level directly given to reduce(4k+2k --- combineAndSpill => 2k.
// So 0 records spilled to disk in 3rd level)
// So total of 6k+4k=10k
// Total job counter will be 54k+10k = 64k
// 3 maps and 2.5k lines --- So total 7.5k map input records
// 3 maps and 10k words in each --- So total of 30k map output recs
validateMapredCounters(c1, 64000, 7500, 30000);
validateMapredFileCounters(c1, inputSize, inputSize, 0, 0, 0);
// create 4th input file each with 5*2k words and test with 4 maps
inpFile = new File(inDir + "input5_2k_4");
createWordsFile(inpFile);
inputSize += inpFile.length();
conf.setNumMapTasks(4);
Path outputPath2 = new Path(outDir, "output5_2k_4");
FileOutputFormat.setOutputPath(conf, outputPath2);
myJob = JobClient.runJob(conf);
c1 = myJob.getCounters();
// 4maps & in each map 4 first level spills --- So total 16.
// spilled records count:
// Each Map: 1st level:2k+2k+2k+2k=8k;2ndlevel=4k+4k=8k;
// 3rd level=2k(4k from 1st level & 4k from 2nd level & combineAndSpill)
// So total 8k+8k+2k=18k
// For 3 Maps, total = 4*18=72k
// Reduce: each of the 4 map o/p's(2k each) will be spilled in shuffleToDisk()
// So 4*2k=8k in 1st level; 2nd level:4k+4k=8k;
// 3rd level directly given to reduce(4k+4k --- combineAndSpill => 2k.
// So 0 records spilled to disk in 3rd level)
// So total of 8k+8k=16k
// Total job counter will be 72k+16k = 88k
// 4 maps and 2.5k words in each --- So 10k map input records
// 4 maps and 10k unique words --- So 40k map output records
validateMapredCounters(c1, 88000, 10000, 40000);
validateMapredFileCounters(c1, inputSize, inputSize, 0, 0, 0);
// check for a map only job
conf.setNumReduceTasks(0);
Path outputPath3 = new Path(outDir, "output5_2k_5");
FileOutputFormat.setOutputPath(conf, outputPath3);
myJob = JobClient.runJob(conf);
c1 = myJob.getCounters();
// 4 maps and 2.5k words in each --- So 10k map input records
// 4 maps and 10k unique words --- So 40k map output records
validateMapredCounters(c1, 0, 10000, 40000);
validateMapredFileCounters(c1, inputSize, inputSize, 0, -1, -1);
} finally {
// clean up the input and output files
if (fs.exists(testDir)) {
fs.delete(testDir, true);
}
}
}
static void checkRecords(Configuration defaults, Path sortInput, Path sortOutput)
throws IOException {
FileSystem inputfs = sortInput.getFileSystem(defaults);
FileSystem outputfs = sortOutput.getFileSystem(defaults);
FileSystem defaultfs = FileSystem.get(defaults);
JobConf jobConf = new JobConf(defaults, RecordStatsChecker.class);
jobConf.setJobName("sortvalidate-recordstats-checker");
int noSortReduceTasks = outputfs.listStatus(sortOutput, sortPathsFilter).length;
jobConf.setInt("sortvalidate.sort.reduce.tasks", noSortReduceTasks);
int noSortInputpaths = inputfs.listStatus(sortInput).length;
jobConf.setInputFormat(NonSplitableSequenceFileInputFormat.class);
jobConf.setOutputFormat(SequenceFileOutputFormat.class);
jobConf.setOutputKeyClass(IntWritable.class);
jobConf.setOutputValueClass(RecordStatsChecker.RecordStatsWritable.class);
jobConf.setMapperClass(Map.class);
jobConf.setCombinerClass(Reduce.class);
jobConf.setReducerClass(Reduce.class);
jobConf.setNumMapTasks(noSortReduceTasks);
jobConf.setNumReduceTasks(1);
FileInputFormat.setInputPaths(jobConf, sortInput);
FileInputFormat.addInputPath(jobConf, sortOutput);
Path outputPath = new Path("/tmp/sortvalidate/recordstatschecker");
if (defaultfs.exists(outputPath)) {
defaultfs.delete(outputPath, true);
}
FileOutputFormat.setOutputPath(jobConf, outputPath);
// Uncomment to run locally in a single process
// job_conf.set("mapred.job.tracker", "local");
Path[] inputPaths = FileInputFormat.getInputPaths(jobConf);
System.out.println(
"\nSortValidator.RecordStatsChecker: Validate sort "
+ "from "
+ inputPaths[0]
+ " ("
+ noSortInputpaths
+ " files), "
+ inputPaths[1]
+ " ("
+ noSortReduceTasks
+ " files) into "
+ FileOutputFormat.getOutputPath(jobConf)
+ " with 1 reducer.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
JobClient.runJob(jobConf);
Date end_time = new Date();
System.out.println("Job ended: " + end_time);
System.out.println(
"The job took " + (end_time.getTime() - startTime.getTime()) / 1000 + " seconds.");
// Check to ensure that the statistics of the
// framework's sort-input and sort-output match
SequenceFile.Reader stats =
new SequenceFile.Reader(defaultfs, new Path(outputPath, "part-00000"), defaults);
IntWritable k1 = new IntWritable();
IntWritable k2 = new IntWritable();
RecordStatsWritable v1 = new RecordStatsWritable();
RecordStatsWritable v2 = new RecordStatsWritable();
if (!stats.next(k1, v1)) {
throw new IOException("Failed to read record #1 from reduce's output");
}
if (!stats.next(k2, v2)) {
throw new IOException("Failed to read record #2 from reduce's output");
}
if ((v1.getBytes() != v2.getBytes())
|| (v1.getRecords() != v2.getRecords())
|| v1.getChecksum() != v2.getChecksum()) {
throw new IOException(
"("
+ v1.getBytes()
+ ", "
+ v1.getRecords()
+ ", "
+ v1.getChecksum()
+ ") v/s ("
+ v2.getBytes()
+ ", "
+ v2.getRecords()
+ ", "
+ v2.getChecksum()
+ ")");
}
}
