private String[] getActiveServersList(JobContext context) {
String[] servers = null;
try {
JobClient jc = new JobClient((JobConf) context.getConfiguration());
ClusterStatus status = jc.getClusterStatus(true);
Collection<String> atc = status.getActiveTrackerNames();
servers = new String[atc.size()];
int s = 0;
for (String serverInfo : atc) {
// System.out.println("serverInfo:" + serverInfo);
StringTokenizer st = new StringTokenizer(serverInfo, ":");
String trackerName = st.nextToken();
// System.out.println("trackerName:" + trackerName);
StringTokenizer st1 = new StringTokenizer(trackerName, "_");
st1.nextToken();
servers[s++] = st1.nextToken();
}
} catch (IOException e) {
e.printStackTrace();
}
return servers;
}
/**
* set up input file which has the list of input files.
*
* @return boolean
* @throws IOException
*/
private boolean setup() throws IOException {
estimateSavings();
final String randomId = getRandomId();
JobClient jClient = new JobClient(jobconf);
Path jobdir = new Path(jClient.getSystemDir(), NAME + "_" + randomId);
LOG.info(JOB_DIR_LABEL + "=" + jobdir);
jobconf.set(JOB_DIR_LABEL, jobdir.toString());
Path log = new Path(jobdir, "_logs");
// The control file should have small size blocks. This helps
// in spreading out the load from mappers that will be spawned.
jobconf.setInt("dfs.blocks.size", OP_LIST_BLOCK_SIZE);
FileOutputFormat.setOutputPath(jobconf, log);
LOG.info("log=" + log);
// create operation list
FileSystem fs = jobdir.getFileSystem(jobconf);
Path opList = new Path(jobdir, "_" + OP_LIST_LABEL);
jobconf.set(OP_LIST_LABEL, opList.toString());
int opCount = 0, synCount = 0;
SequenceFile.Writer opWriter = null;
try {
opWriter =
SequenceFile.createWriter(
fs, jobconf, opList, Text.class, PolicyInfo.class, SequenceFile.CompressionType.NONE);
for (RaidPolicyPathPair p : raidPolicyPathPairList) {
// If a large set of files are Raided for the first time, files
// in the same directory that tend to have the same size will end up
// with the same map. This shuffle mixes things up, allowing a better
// mix of files.
java.util.Collections.shuffle(p.srcPaths);
for (FileStatus st : p.srcPaths) {
opWriter.append(new Text(st.getPath().toString()), p.policy);
opCount++;
if (++synCount > SYNC_FILE_MAX) {
opWriter.sync();
synCount = 0;
}
}
}
} finally {
if (opWriter != null) {
opWriter.close();
}
fs.setReplication(opList, OP_LIST_REPLICATION); // increase replication for control file
}
raidPolicyPathPairList.clear();
jobconf.setInt(OP_COUNT_LABEL, opCount);
LOG.info("Number of files=" + opCount);
jobconf.setNumMapTasks(
getMapCount(opCount, new JobClient(jobconf).getClusterStatus().getTaskTrackers()));
LOG.info("jobName= " + jobName + " numMapTasks=" + jobconf.getNumMapTasks());
return opCount != 0;
}
public static void runSortJob(String... args) throws Exception {
Path input = new Path(args[0]);
Path output = new Path(args[1]);
JobConf job = new JobConf();
job.setNumReduceTasks(2);
job.setInputFormat(KeyValueTextInputFormat.class);
job.setOutputFormat(TextOutputFormat.class);
job.setMapOutputKeyClass(Text.class);
job.setMapOutputValueClass(Text.class);
FileInputFormat.setInputPaths(job, input);
FileOutputFormat.setOutputPath(job, output);
job.setJarByClass(SampleJob.class);
output.getFileSystem(job).delete(output, true);
JobClient jc = new JobClient(job);
JobClient.setTaskOutputFilter(job, JobClient.TaskStatusFilter.ALL);
RunningJob rj = jc.submitJob(job);
try {
if (!jc.monitorAndPrintJob(job, rj)) {
System.out.println("Job Failed: " + rj.getFailureInfo());
throw new IOException("Job failed!");
}
} catch (InterruptedException ie) {
Thread.currentThread().interrupt();
}
}
private RunningJob submitAction(Context context, Namespace ns) throws Exception {
Hive2ActionExecutor ae = new Hive2ActionExecutor();
WorkflowAction action = context.getAction();
ae.prepareActionDir(getFileSystem(), context);
ae.submitLauncher(getFileSystem(), context, action);
String jobId = action.getExternalId();
String jobTracker = action.getTrackerUri();
String consoleUrl = action.getConsoleUrl();
assertNotNull(jobId);
assertNotNull(jobTracker);
assertNotNull(consoleUrl);
Element e = XmlUtils.parseXml(action.getConf());
XConfiguration conf =
new XConfiguration(
new StringReader(XmlUtils.prettyPrint(e.getChild("configuration", ns)).toString()));
conf.set("mapred.job.tracker", e.getChildTextTrim("job-tracker", ns));
conf.set("fs.default.name", e.getChildTextTrim("name-node", ns));
conf.set("user.name", context.getProtoActionConf().get("user.name"));
conf.set("group.name", getTestGroup());
JobConf jobConf = Services.get().get(HadoopAccessorService.class).createJobConf(jobTracker);
XConfiguration.copy(conf, jobConf);
String user = jobConf.get("user.name");
JobClient jobClient =
Services.get().get(HadoopAccessorService.class).createJobClient(user, jobConf);
final RunningJob runningJob = jobClient.getJob(JobID.forName(jobId));
assertNotNull(runningJob);
return runningJob;
}
/**
* Generate the requested number of file splits, with the filename set to the filename of the
* output file.
*/
public InputSplit[] getSplits(JobConf job, int numSplits) throws IOException {
/** 设置输入分片的个数* */
JobClient client = new JobClient(job);
ClusterStatus cluster = client.getClusterStatus();
/** 如果属性不存在 则返回默认的值 * */
int numMapsPerHost = job.getInt("test.randomwriter.maps_per_host", 10);
long numBytesToWritePerMap =
job.getLong("test.randomwrite.bytes_per_map", 1 * 1024 * 1024 * 1024);
if (numBytesToWritePerMap == 0) {
System.err.println("Cannot have test.randomwrite.bytes_per_map set to 0");
}
long totalBytesToWrite =
job.getLong(
"test.randomwrite.total_bytes",
numMapsPerHost * numBytesToWritePerMap * cluster.getTaskTrackers());
int numMaps = (int) (totalBytesToWrite / numBytesToWritePerMap);
if (numMaps == 0 && totalBytesToWrite > 0) {
numMaps = 1;
}
System.out.println("numMaps-------" + numMaps);
InputSplit[] result = new InputSplit[numMaps];
Path outDir = FileOutputFormat.getOutputPath(job);
for (int i = 0; i < result.length; ++i) {
result[i] = new FileSplit(new Path(outDir, "dummy-split-" + i), 0, 1, (String[]) null);
}
return result;
}
public void testActionCheck() throws Exception {
JPAService jpaService = Services.get().get(JPAService.class);
WorkflowJobBean job =
this.addRecordToWfJobTable(WorkflowJob.Status.RUNNING, WorkflowInstance.Status.RUNNING);
WorkflowActionBean action =
this.addRecordToWfActionTable(job.getId(), "1", WorkflowAction.Status.PREP);
WorkflowActionGetJPAExecutor wfActionGetCmd = new WorkflowActionGetJPAExecutor(action.getId());
new ActionStartXCommand(action.getId(), "map-reduce").call();
action = jpaService.execute(wfActionGetCmd);
ActionExecutorContext context =
new ActionXCommand.ActionExecutorContext(job, action, false, false);
MapReduceActionExecutor actionExecutor = new MapReduceActionExecutor();
JobConf conf =
actionExecutor.createBaseHadoopConf(context, XmlUtils.parseXml(action.getConf()));
String user = conf.get("user.name");
JobClient jobClient =
Services.get().get(HadoopAccessorService.class).createJobClient(user, conf);
String launcherId = action.getExternalId();
final RunningJob launcherJob = jobClient.getJob(JobID.forName(launcherId));
waitFor(
120 * 1000,
new Predicate() {
public boolean evaluate() throws Exception {
return launcherJob.isComplete();
}
});
assertTrue(launcherJob.isSuccessful());
Map<String, String> actionData =
LauncherMapperHelper.getActionData(getFileSystem(), context.getActionDir(), conf);
assertTrue(LauncherMapperHelper.hasIdSwap(actionData));
new ActionCheckXCommand(action.getId()).call();
action = jpaService.execute(wfActionGetCmd);
String mapperId = action.getExternalId();
String childId = action.getExternalChildIDs();
assertTrue(launcherId.equals(mapperId));
final RunningJob mrJob = jobClient.getJob(JobID.forName(childId));
waitFor(
120 * 1000,
new Predicate() {
public boolean evaluate() throws Exception {
return mrJob.isComplete();
}
});
assertTrue(mrJob.isSuccessful());
new ActionCheckXCommand(action.getId()).call();
action = jpaService.execute(wfActionGetCmd);
assertEquals("SUCCEEDED", action.getExternalStatus());
}
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));
}
/**
* This is the main routine for launching a distributed random write job. It runs 10 maps/node and
* each node writes 1 gig of data to a DFS file. The reduce doesn't do anything.
*
* @throws IOException
*/
public int run(String[] args) throws Exception {
if (args.length == 0) {
System.out.println("Usage: writer <out-dir>");
ToolRunner.printGenericCommandUsage(System.out);
return -1;
}
Path outDir = new Path(args[0]);
JobConf job = new JobConf(getConf());
job.setJarByClass(RandomWriter.class);
job.setJobName("random-writer");
FileOutputFormat.setOutputPath(job, outDir);
job.setOutputKeyClass(BytesWritable.class);
job.setOutputValueClass(BytesWritable.class);
job.setInputFormat(RandomInputFormat.class);
job.setMapperClass(Map.class);
job.setReducerClass(IdentityReducer.class);
job.setOutputFormat(SequenceFileOutputFormat.class);
JobClient client = new JobClient(job);
ClusterStatus cluster = client.getClusterStatus();
/** 如果属性不存在 则返回默认的值 * */
int numMapsPerHost = job.getInt("test.randomwriter.maps_per_host", 10);
long numBytesToWritePerMap =
job.getLong("test.randomwrite.bytes_per_map", 1 * 1024 * 1024 * 1024);
if (numBytesToWritePerMap == 0) {
System.err.println("Cannot have test.randomwrite.bytes_per_map set to 0");
return -2;
}
long totalBytesToWrite =
job.getLong(
"test.randomwrite.total_bytes",
numMapsPerHost * numBytesToWritePerMap * cluster.getTaskTrackers());
int numMaps = (int) (totalBytesToWrite / numBytesToWritePerMap);
if (numMaps == 0 && totalBytesToWrite > 0) {
numMaps = 1;
job.setLong("test.randomwrite.bytes_per_map", totalBytesToWrite);
}
job.setNumMapTasks(numMaps);
/** 建议型的 * */
System.out.println("Running " + numMaps + " maps.");
// reducer NONE
job.setNumReduceTasks(0);
Date startTime = new Date();
System.out.println("Job started: " + startTime);
JobClient.runJob(job);
Date endTime = new Date();
System.out.println("Job ended: " + endTime);
System.out.println(
"The job took " + (endTime.getTime() - startTime.getTime()) / 1000 + " seconds.");
return 0;
}
private RunningJob _test(String... arg) throws Exception {
Path actionDir = getFsTestCaseDir();
File jar =
IOUtils.createJar(
new File(getTestCaseDir()),
"launcher.jar",
LauncherMapper.class,
LauncherSecurityManager.class,
LauncherException.class,
LauncherMainTester.class);
FileSystem fs = getFileSystem();
Path launcherJar = new Path(actionDir, "launcher.jar");
fs.copyFromLocalFile(new Path(jar.toString()), launcherJar);
JobConf jobConf = new JobConf();
jobConf.set("user.name", getTestUser());
jobConf.set("group.name", getTestGroup());
jobConf.setInt("mapred.map.tasks", 1);
jobConf.setInt("mapred.map.max.attempts", 1);
jobConf.setInt("mapred.reduce.max.attempts", 1);
jobConf.set("mapred.job.tracker", getJobTrackerUri());
jobConf.set("fs.default.name", getNameNodeUri());
injectKerberosInfo(jobConf);
LauncherMapper lm = new LauncherMapper();
lm.setupMainClass(jobConf, LauncherMainTester.class.getName());
lm.setupMainArguments(jobConf, arg);
Configuration actionConf = new XConfiguration();
lm.setupLauncherInfo(jobConf, "1", "1@a", actionDir, "1@a-0", actionConf);
assertEquals("1", actionConf.get("oozie.job.id"));
assertEquals("1@a", actionConf.get("oozie.action.id"));
DistributedCache.addFileToClassPath(new Path(launcherJar.toUri().getPath()), jobConf);
JobClient jobClient = createJobClient();
final RunningJob runningJob = jobClient.submitJob(jobConf);
System.out.println("Action Dir: " + actionDir);
System.out.println("LauncherMapper ID: " + runningJob.getJobID().toString());
waitFor(
180 * 1000,
new Predicate() {
public boolean evaluate() throws Exception {
return runningJob.isComplete();
}
});
return runningJob;
}
public static Token<
org.apache.hadoop.mapreduce.security.token.delegation.DelegationTokenIdentifier>
getJobTrackerDelegationToken(Configuration conf, String userName) throws Exception {
// LOG.info("getJobTrackerDelegationToken("+conf+","+userName+")");
JobClient jcl = new JobClient(new JobConf(conf, HCatOutputFormat.class));
Token<org.apache.hadoop.mapreduce.security.token.delegation.DelegationTokenIdentifier> t =
jcl.getDelegationToken(new Text(userName));
// LOG.info("got "+t);
return t;
// return null;
}
private void prepareDeleteIndex(String indexerName) {
// We do not have to take a lock on the indexer, since once in delete state the indexer cannot
// be modified anymore by ordinary users.
boolean canBeDeleted = false;
try {
// Read current situation of record and assure it is still actual
IndexerDefinition indexer = indexerModel.getFreshIndexer(indexerName);
if (indexer.getLifecycleState() == IndexerDefinition.LifecycleState.DELETE_REQUESTED) {
canBeDeleted = true;
String queueSubscriptionId = indexer.getSubscriptionId();
if (queueSubscriptionId != null) {
sepModel.removeSubscription(indexer.getSubscriptionId());
// We leave the subscription ID in the indexer definition FYI
}
if (indexer.getActiveBatchBuildInfo() != null) {
JobClient jobClient = getJobClient();
String jobId = indexer.getActiveBatchBuildInfo().getJobId();
RunningJob job = jobClient.getJob(jobId);
if (job != null) {
job.killJob();
log.info("Kill indexer build job for indexer " + indexerName + ", job ID = " + jobId);
}
// Just to be sure...
jobStatusWatcher.assureWatching(
indexer.getName(), indexer.getActiveBatchBuildInfo().getJobId());
canBeDeleted = false;
}
if (!canBeDeleted) {
indexer =
new IndexerDefinitionBuilder()
.startFrom(indexer)
.lifecycleState(IndexerDefinition.LifecycleState.DELETING)
.build();
indexerModel.updateIndexerInternal(indexer);
}
} else if (indexer.getLifecycleState() == IndexerDefinition.LifecycleState.DELETING) {
// Check if the build job is already finished, if so, allow delete
if (indexer.getActiveBatchBuildInfo() == null) {
canBeDeleted = true;
}
}
} catch (Throwable t) {
log.error("Error preparing deletion of indexer " + indexerName, t);
}
if (canBeDeleted) {
deleteIndexer(indexerName);
}
}
private void checkGeneratedDataAndJobStatus(long inputSize) throws IOException {
LOG.info("Verify the generated data size.");
long dataSizeInMB = getDataSizeInMB(new Path(gridmixDir, "input"));
Assert.assertTrue(
"Generate data has not matched with given size",
dataSizeInMB + 0.1 > inputSize || dataSizeInMB - 0.1 < inputSize);
JobClient jobClient = jtClient.getClient();
int len = jobClient.getAllJobs().length;
LOG.info("Verify the job status after completion of job.");
Assert.assertEquals(
"Job has not succeeded.",
JobStatus.SUCCEEDED,
jobClient.getAllJobs()[len - 1].getRunState());
}
@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;
}
@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;
}
/**
* Run the job
*
* @param params The Job parameters containing the gramSize, input output folders, defaultCat,
* encoding
*/
public static void runJob(Parameters params) throws IOException {
Configurable client = new JobClient();
JobConf conf = new JobConf(BayesClassifierDriver.class);
conf.setJobName("Bayes Classifier Driver running over input: " + params.get("testDirPath"));
conf.setOutputKeyClass(StringTuple.class);
conf.setOutputValueClass(DoubleWritable.class);
FileInputFormat.setInputPaths(conf, new Path(params.get("testDirPath")));
Path outPath = new Path(params.get("testDirPath") + "-output");
FileOutputFormat.setOutputPath(conf, outPath);
conf.setInputFormat(KeyValueTextInputFormat.class);
conf.setMapperClass(BayesClassifierMapper.class);
conf.setCombinerClass(BayesClassifierReducer.class);
conf.setReducerClass(BayesClassifierReducer.class);
conf.setOutputFormat(SequenceFileOutputFormat.class);
conf.set(
"io.serializations",
"org.apache.hadoop.io.serializer.JavaSerialization,"
+ "org.apache.hadoop.io.serializer.WritableSerialization");
HadoopUtil.overwriteOutput(outPath);
conf.set("bayes.parameters", params.toString());
client.setConf(conf);
JobClient.runJob(conf);
Path outputFiles = new Path(outPath, "part*");
FileSystem dfs = FileSystem.get(outPath.toUri(), conf);
ConfusionMatrix matrix = readResult(dfs, outputFiles, conf, params);
log.info("{}", matrix.summarize());
}
/**
* Driver to copy srcPath to destPath depending on required protocol.
*
* @param args arguments
*/
static void copy(final Configuration conf, final Arguments args) throws IOException {
LOG.info("srcPaths=" + args.srcs);
LOG.info("destPath=" + args.dst);
checkSrcPath(conf, args.srcs);
JobConf job = createJobConf(conf);
if (args.preservedAttributes != null) {
job.set(PRESERVE_STATUS_LABEL, args.preservedAttributes);
}
if (args.mapredSslConf != null) {
job.set("dfs.https.client.keystore.resource", args.mapredSslConf);
}
// Initialize the mapper
try {
setup(conf, job, args);
JobClient.runJob(job);
finalize(conf, job, args.dst, args.preservedAttributes);
} finally {
// delete tmp
fullyDelete(job.get(TMP_DIR_LABEL), job);
// delete jobDirectory
fullyDelete(job.get(JOB_DIR_LABEL), job);
}
}
public static void main(String[] args) throws Exception {
String input = "hdfs://centos:9000/access.log.10";
String output = "hdfs://centos:9000/out_kpitime";
JobConf conf = new JobConf(KPITime.class);
conf.setJobName("KPITime");
// conf.addResource("classpath:/hadoop/core-site.xml");
// conf.addResource("classpath:/hadoop/hdfs-site.xml");
// conf.addResource("classpath:/hadoop/mapred-site.xml");
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(KPITimeMapper.class);
conf.setCombinerClass(KPITimeReducer.class);
conf.setReducerClass(KPITimeReducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(input));
FileOutputFormat.setOutputPath(conf, new Path(output));
JobClient.runJob(conf);
System.exit(0);
}
public static void run(Map<String, String> path) throws IOException {
JobConf conf = Recommend.config();
String input = path.get("Step2Input");
String output = path.get("Step2Output");
HdfsDAO hdfs = new HdfsDAO(Recommend.HDFS, conf);
hdfs.rmr(output);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(Step2_UserVectorToCooccurrenceMapper.class);
// conf.setCombinerClass(Step2_UserVectorToConoccurrenceReducer.class);
// conf.setReducerClass(Step2_UserVectorToConoccurrenceReducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(input));
FileOutputFormat.setOutputPath(conf, new Path(output));
RunningJob job = JobClient.runJob(conf);
while (!job.isComplete()) {
job.waitForCompletion();
}
}
public RunningJob run(String inputPath, String outputPath) throws Exception {
sLogger.info("Tool name: BuildGraph");
sLogger.info(" - input: " + inputPath);
sLogger.info(" - output: " + outputPath);
JobConf conf = new JobConf(BuildGraph.class);
conf.setJobName("BuildGraph " + inputPath + " " + ContrailConfig.K);
ContrailConfig.initializeConfiguration(conf);
FileInputFormat.addInputPath(conf, new Path(inputPath));
FileOutputFormat.setOutputPath(conf, new Path(outputPath));
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
conf.setMapOutputKeyClass(Text.class);
conf.setMapOutputValueClass(Text.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(BuildGraphMapper.class);
conf.setReducerClass(BuildGraphReducer.class);
// delete the output directory if it exists already
FileSystem.get(conf).delete(new Path(outputPath), true);
return JobClient.runJob(conf);
}
public void runParseTest(
String fieldTerminator,
String lineTerminator,
String encloser,
String escape,
boolean encloseRequired)
throws IOException {
ClassLoader prevClassLoader = null;
String[] argv =
getArgv(true, fieldTerminator, lineTerminator, encloser, escape, encloseRequired);
runImport(argv);
try {
String tableClassName = getTableName();
argv = getArgv(false, fieldTerminator, lineTerminator, encloser, escape, encloseRequired);
SqoopOptions opts = new ImportTool().parseArguments(argv, null, null, true);
CompilationManager compileMgr = new CompilationManager(opts);
String jarFileName = compileMgr.getJarFilename();
// Make sure the user's class is loaded into our address space.
prevClassLoader = ClassLoaderStack.addJarFile(jarFileName, tableClassName);
JobConf job = new JobConf();
job.setJar(jarFileName);
// Tell the job what class we're testing.
job.set(ReparseMapper.USER_TYPE_NAME_KEY, tableClassName);
// use local mode in the same JVM.
ConfigurationHelper.setJobtrackerAddr(job, "local");
if (!BaseSqoopTestCase.isOnPhysicalCluster()) {
job.set(CommonArgs.FS_DEFAULT_NAME, CommonArgs.LOCAL_FS);
}
String warehouseDir = getWarehouseDir();
Path warehousePath = new Path(warehouseDir);
Path inputPath = new Path(warehousePath, getTableName());
Path outputPath = new Path(warehousePath, getTableName() + "-out");
job.setMapperClass(ReparseMapper.class);
job.setNumReduceTasks(0);
FileInputFormat.addInputPath(job, inputPath);
FileOutputFormat.setOutputPath(job, outputPath);
job.setOutputKeyClass(Text.class);
job.setOutputValueClass(NullWritable.class);
JobClient.runJob(job);
} catch (InvalidOptionsException ioe) {
fail(ioe.toString());
} catch (ParseException pe) {
fail(pe.toString());
} finally {
if (null != prevClassLoader) {
ClassLoaderStack.setCurrentClassLoader(prevClassLoader);
}
}
}
public static void main(String[] args) throws Exception {
String input = "hdfs://192.168.0.110:9000/input/access.log";
String output = "hdfs://192.168.0.110:9000/user/hdfs/pv";
JobConf conf = new JobConf(KPIPV.class);
conf.setJobName("KPIPV");
conf.setMapOutputKeyClass(Text.class);
conf.setMapOutputValueClass(IntWritable.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(IntWritable.class);
conf.setMapperClass(KPIPVMapper.class);
conf.setCombinerClass(KPIPVReducer.class);
conf.setReducerClass(KPIPVReducer.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(conf, new Path(input));
FileOutputFormat.setOutputPath(conf, new Path(output));
JobClient.runJob(conf);
System.exit(0);
}
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);
}
}
public int run(String[] args) throws Exception {
if (args.length < 2) {
printUsage();
return 1;
}
JobConf job = new JobConf(getConf(), MultiFileWordCount.class);
job.setJobName("MultiFileWordCount");
// set the InputFormat of the job to our InputFormat
job.setInputFormat(MyInputFormat.class);
// the keys are words (strings)
job.setOutputKeyClass(Text.class);
// the values are counts (ints)
job.setOutputValueClass(IntWritable.class);
// use the defined mapper
job.setMapperClass(MapClass.class);
// use the WordCount Reducer
job.setCombinerClass(LongSumReducer.class);
job.setReducerClass(LongSumReducer.class);
FileInputFormat.addInputPaths(job, args[0]);
FileOutputFormat.setOutputPath(job, new Path(args[1]));
JobClient.runJob(job);
return 0;
}
@Override
public int run(String[] args) throws Exception {
JobConf conf = JobBuilder.parseInputAndOutput(this, getConf(), args);
if (conf == null) {
return -1;
}
conf.setInputFormat(SequenceFileInputFormat.class);
conf.setOutputKeyClass(IntWritable.class);
conf.setOutputFormat(SequenceFileOutputFormat.class);
SequenceFileOutputFormat.setCompressOutput(conf, true);
SequenceFileOutputFormat.setOutputCompressorClass(conf, GzipCodec.class);
SequenceFileOutputFormat.setOutputCompressionType(conf, CompressionType.BLOCK);
conf.setPartitionerClass(TotalOrderPartitioner.class);
InputSampler.Sampler<IntWritable, Text> sampler =
new InputSampler.RandomSampler<IntWritable, Text>(0.1, 10000, 10);
Path input = FileInputFormat.getInputPaths(conf)[0];
input = input.makeQualified(input.getFileSystem(conf));
Path partitionFile = new Path(input, "_partitions");
TotalOrderPartitioner.setPartitionFile(conf, partitionFile);
InputSampler.writePartitionFile(conf, sampler);
// Add to DistributedCache
URI partitionUri = new URI(partitionFile.toString() + "#_partitions");
DistributedCache.addCacheFile(partitionUri, conf);
DistributedCache.createSymlink(conf);
JobClient.runJob(conf);
return 0;
}
public RunningJob run(String inputPath, String outputPath) throws Exception {
JobConf conf = new JobConf(BuildIndex.class);
conf.setJobName("BuildIndex");
FileInputFormat.addInputPath(conf, new Path(inputPath)); // multiple path
FileOutputFormat.setOutputPath(conf, new Path(outputPath));
conf.setOutputFormat(TextOutputFormat.class);
conf.setMapOutputKeyClass(LongWritable.class);
conf.setMapOutputValueClass(LongWritable.class);
conf.set("delim", delim);
conf.setOutputKeyClass(LongWritable.class);
conf.setOutputValueClass(LongWritable.class);
conf.setInt("keyFieldIndexTwo", keyFieldIndexTwo);
conf.setMapperClass(BuildIndexMapper.class);
conf.setNumReduceTasks(1);
conf.setReducerClass(BuildIndexReducer.class);
conf.setInputFormat(TextInputFormat.class);
// conf.setInputFormat(CustomInputFormat.class);
// FileOutputFormat.setCompressOutput(conf,true);
// delete the output directory if it exists already
FileSystem.get(conf).delete(new Path(outputPath), true);
return JobClient.runJob(conf);
}
public void runMR(String myMultiLocs, String sortKey)
throws ParseException, IOException, Exception, org.apache.hadoop.zebra.parser.ParseException {
JobConf jobConf = new JobConf(conf);
jobConf.setJobName("TestMultipleOutputs4");
jobConf.setJarByClass(TestMultipleOutputs4.class);
jobConf.set("table.output.tfile.compression", "gz");
jobConf.set("sortKey", sortKey);
// input settings
jobConf.setInputFormat(TextInputFormat.class);
jobConf.setMapperClass(TestMultipleOutputs4.MapClass.class);
jobConf.setMapOutputKeyClass(BytesWritable.class);
jobConf.setMapOutputValueClass(ZebraTuple.class);
FileInputFormat.setInputPaths(jobConf, inputPath);
jobConf.setNumMapTasks(1);
// output settings
jobConf.setOutputFormat(BasicTableOutputFormat.class);
BasicTableOutputFormat.setMultipleOutputs(
jobConf, myMultiLocs, TestMultipleOutputs4.OutputPartitionerClass.class);
// set the logical schema with 2 columns
BasicTableOutputFormat.setSchema(jobConf, "word:string, count:int");
// for demo purposes, create 2 physical column groups
BasicTableOutputFormat.setStorageHint(jobConf, "[word];[count]");
BasicTableOutputFormat.setSortInfo(jobConf, sortKey);
System.out.println("in runMR, sortkey: " + sortKey);
// set map-only job.
jobConf.setNumReduceTasks(1);
JobClient.runJob(jobConf);
BasicTableOutputFormat.close(jobConf);
}
/**
* {@inheritDoc}
*
* @see org.apache.hadoop.util.Tool#run(java.lang.String[])
*/
@Override
public int run(String[] args) throws Exception {
JobConf configuration = new JobConf(getConf(), WordCountExtended.class);
configuration.setJobName(JOB_NAME);
configuration.setOutputKeyClass(Text.class);
configuration.setOutputValueClass(IntWritable.class);
configuration.setMapperClass(Map.class);
configuration.setCombinerClass(Reduce.class);
configuration.setReducerClass(Reduce.class);
configuration.setInputFormat(TextInputFormat.class);
configuration.setOutputFormat(TextOutputFormat.class);
List<String> otherArgs = new ArrayList<String>();
for (int i = 0; i < args.length; ++i) {
if (JOB_SKIP_ARGUMENT.equals(args[i])) {
DistributedCache.addCacheFile(new Path(args[++i]).toUri(), configuration);
configuration.setBoolean(JOB_PARAMETER_SKIP_PATTERNS, true);
} else {
otherArgs.add(args[i]);
}
}
FileInputFormat.setInputPaths(configuration, new Path(otherArgs.get(0)));
FileOutputFormat.setOutputPath(configuration, new Path(otherArgs.get(1)));
JobClient.runJob(configuration);
return 0;
}
@Override
public void runStep(Path outputPathLocation) throws IOException {
ImmutableList<Path> pathList =
ImmutableList.of(
getOutputDirForStep(PartitionCrawlDBStep.class),
getOutputDirForStep(GenFeedUrlsStep.class),
getOutputDirForStep(GenHomepageUrlsStep.class),
getOutputDirForStep(GenBlogPlatformUrlsStep.class),
getOutputDirForStep(PartitionCrawlStatsStep.class),
getOutputDirForStep(PartitionRedirectDataStep.class));
JobConf jobConf =
new JobBuilder("BundleWriter Step", getConf())
.inputs(pathList)
.inputFormat(MultiFileMergeInputFormat.class)
.mapperKeyValue(IntWritable.class, Text.class)
.outputKeyValue(SegmentGeneratorBundleKey.class, SegmentGeneratorItemBundle.class)
.outputFormat(SequenceFileOutputFormat.class)
.reducer(GenBundlesStep.class, false)
.partition(MultiFileMergePartitioner.class)
.numReducers(CrawlListGeneratorTask.NUM_SHARDS)
.speculativeExecution(false)
.output(outputPathLocation)
.compressMapOutput(false)
.compressor(CompressionType.BLOCK, SnappyCodec.class)
.build();
LOG.info("Starting JOB");
JobClient.runJob(jobConf);
LOG.info("Finsihed JOB");
}
public RunningJob run(String inputPath, String outputPath) throws Exception {
sLogger.info("Tool name: Compressible");
sLogger.info(" - input: " + inputPath);
sLogger.info(" - output: " + outputPath);
// JobConf conf = new JobConf(Stats.class);
JobConf conf = new JobConf(Compressible.class);
conf.setJobName("Compressible " + inputPath);
BrushConfig.initializeConfiguration(conf);
FileInputFormat.addInputPath(conf, new Path(inputPath));
FileOutputFormat.setOutputPath(conf, new Path(outputPath));
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
conf.setMapOutputKeyClass(Text.class);
conf.setMapOutputValueClass(Text.class);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(CompressibleMapper.class);
conf.setReducerClass(CompressibleReducer.class);
// delete the output directory if it exists already
FileSystem.get(conf).delete(new Path(outputPath), true);
return JobClient.runJob(conf);
}
public static void main(String[] args) throws Exception {
JobConf conf = new JobConf(AccessProcessJob.class);
conf.set(nameNode, hdfsURL);
conf.setJobName("AccessProcessJob");
Job job = Job.getInstance(conf, "AccessProcessJob");
new Path(outputPath).getFileSystem(conf).delete(new Path(outputPath), true);
conf.setOutputKeyClass(Text.class);
conf.setOutputValueClass(Text.class);
conf.setMapperClass(AccessProcessMap.class);
conf.setReducerClass(AccessProcessReduce.class);
conf.setInputFormat(TextInputFormat.class);
conf.setOutputFormat(TextOutputFormat.class);
FileInputFormat.setInputPaths(job, new Path(inputPath));
FileOutputFormat.setOutputPath(job, new Path(outputPath));
conf.setNumMapTasks(1);
conf.setNumReduceTasks(1);
JobClient.runJob(conf);
}
