/** Process incoming heartbeat messages from the task trackers. */
public synchronized int emitHeartbeat(TaskTrackerStatus trackerStatus, boolean initialContact) {
String trackerName = trackerStatus.getTrackerName();
trackerStatus.setLastSeen(System.currentTimeMillis());
synchronized (taskTrackers) {
synchronized (trackerExpiryQueue) {
boolean seenBefore = updateTaskTrackerStatus(trackerName, trackerStatus);
if (initialContact) {
// If it's first contact, then clear out any state hanging around
if (seenBefore) {
lostTaskTracker(trackerName);
}
} else {
// If not first contact, there should be some record of the tracker
if (!seenBefore) {
return InterTrackerProtocol.UNKNOWN_TASKTRACKER;
}
}
if (initialContact) {
trackerExpiryQueue.add(trackerStatus);
}
}
}
updateTaskStatuses(trackerStatus);
// LOG.info("Got heartbeat from "+trackerName);
return InterTrackerProtocol.TRACKERS_OK;
}
@Override
public int run(String[] args) throws Exception {
if (args.length < 4) {
writeUsage();
return 1;
}
Path secretsPath = new Path(args[0]);
Path saltFilePath = new Path(args[1]);
Path inputPath = new Path(args[2]);
Path outputPath = new Path(args[3]);
// Make sure the salt file exists
generateSaltIfNeeded(saltFilePath, secretsPath);
// Configure the job
Job job = configureJob(secretsPath, saltFilePath, inputPath, outputPath);
// Run it
long startTime = System.currentTimeMillis();
job.submit();
if (job.waitForCompletion(true)) {
System.out.printf(
"Done obfuscating - took %d seconds.\n", (System.currentTimeMillis() - startTime) / 1000);
} else {
System.err.printf("Job finished with errors: %s\n", job.getStatus().getFailureInfo());
return 2;
}
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));
}
private static void run(Callable c, boolean read, int size) {
// Count all i/o time from here, including all retry overheads
long start_io_ms = System.currentTimeMillis();
while (true) {
try {
long start_ns = System.nanoTime(); // Blocking i/o call timing - without counting repeats
c.call();
TimeLine.record_IOclose(start_ns, start_io_ms, read ? 1 : 0, size, Value.HDFS);
break;
// Explicitly ignore the following exceptions but
// fail on the rest IOExceptions
} catch (EOFException e) {
ignoreAndWait(e, false);
} catch (SocketTimeoutException e) {
ignoreAndWait(e, false);
} catch (S3Exception e) {
// Preserve S3Exception before IOException
// Since this is tricky code - we are supporting different HDFS version
// New version declares S3Exception as IOException
// But old versions (0.20.xxx) declares it as RuntimeException
// So we have to catch it before IOException !!!
ignoreAndWait(e, false);
} catch (IOException e) {
ignoreAndWait(e, true);
} catch (Exception e) {
throw Log.errRTExcept(e);
}
}
}
/** Implements basic throttling capabilities. */
public static class Throttler {
double bytesPerSec;
long lastTime = System.currentTimeMillis();
public Throttler(double bytesPerSec) {
this.bytesPerSec = bytesPerSec;
}
public void incrementAndThrottle(int bytes) {
if (bytesPerSec < 1) { // no throttle at all
return;
}
long currentTime = System.currentTimeMillis();
long timeDiff = currentTime - lastTime;
if (timeDiff == 0) {
timeDiff = 1;
}
double bytesPerSec = (bytes / (double) timeDiff) * 1000;
if (bytesPerSec > this.bytesPerSec) {
// Throttle
double exceededByFactorOf = bytesPerSec / this.bytesPerSec;
try {
long mustSleep = (long) ((exceededByFactorOf - 1) * timeDiff);
Thread.sleep(mustSleep);
} catch (InterruptedException e) {
e.printStackTrace();
}
}
lastTime = System.currentTimeMillis();
}
}
/**
* The run method lives for the life of the JobTracker, and removes Jobs that are not still
* running, but which finished a long time ago.
*/
public void run() {
while (shouldRun) {
try {
Thread.sleep(RETIRE_JOB_CHECK_INTERVAL);
} catch (InterruptedException ie) {
}
synchronized (jobs) {
synchronized (jobInitQueue) {
synchronized (jobsByArrival) {
for (Iterator it = jobs.keySet().iterator(); it.hasNext(); ) {
String jobid = (String) it.next();
JobInProgress job = (JobInProgress) jobs.get(jobid);
if (job.getStatus().getRunState() != JobStatus.RUNNING
&& job.getStatus().getRunState() != JobStatus.PREP
&& (job.getFinishTime() + RETIRE_JOB_INTERVAL < System.currentTimeMillis())) {
it.remove();
jobInitQueue.remove(job);
jobsByArrival.remove(job);
}
}
}
}
}
}
}
public void configure(JobConf job) {
this.jobConf = job;
urlNormalizers = new URLNormalizers(job, URLNormalizers.SCOPE_INJECT);
interval = jobConf.getInt("db.fetch.interval.default", 2592000);
filters = new URLFilters(jobConf);
scfilters = new ScoringFilters(jobConf);
scoreInjected = jobConf.getFloat("db.score.injected", 1.0f);
curTime = job.getLong("injector.current.time", System.currentTimeMillis());
}
@Override
public int doWork() {
try {
setupProcedureStore();
ExecutorService executor = Executors.newFixedThreadPool(numThreads);
Future<?>[] futures = new Future<?>[numThreads];
// Start worker threads.
long start = System.currentTimeMillis();
for (int i = 0; i < numThreads; i++) {
futures[i] = executor.submit(this.new Worker(start));
}
boolean failure = false;
try {
for (Future<?> future : futures) {
long timeout = start + WORKER_THREADS_TIMEOUT_SEC * 1000 - System.currentTimeMillis();
failure |= (future.get(timeout, TimeUnit.MILLISECONDS).equals(EXIT_FAILURE));
}
} catch (Exception e) {
System.err.println("Exception in worker thread.");
e.printStackTrace();
return EXIT_FAILURE;
}
executor.shutdown();
if (failure) {
return EXIT_FAILURE;
}
long timeTaken = System.currentTimeMillis() - start;
System.out.println("******************************************");
System.out.println("Num threads : " + numThreads);
System.out.println("Num procedures : " + numProcs);
System.out.println("Sync type : " + syncType);
System.out.println("Time taken : " + (timeTaken / 1000.0f) + "sec");
System.out.println("******************************************");
return EXIT_SUCCESS;
} catch (IOException e) {
e.printStackTrace();
return EXIT_FAILURE;
} finally {
tearDownProcedureStore();
}
}
/**
* The run method lives for the life of the JobTracker, and removes TaskTrackers that have not
* checked in for some time.
*/
public void run() {
while (shouldRun) {
//
// Thread runs periodically to check whether trackers should be expired.
// The sleep interval must be no more than half the maximum expiry time
// for a task tracker.
//
try {
Thread.sleep(TASKTRACKER_EXPIRY_INTERVAL / 3);
} catch (InterruptedException ie) {
}
//
// Loop through all expired items in the queue
//
synchronized (taskTrackers) {
synchronized (trackerExpiryQueue) {
long now = System.currentTimeMillis();
TaskTrackerStatus leastRecent = null;
while ((trackerExpiryQueue.size() > 0)
&& ((leastRecent = (TaskTrackerStatus) trackerExpiryQueue.first()) != null)
&& (now - leastRecent.getLastSeen() > TASKTRACKER_EXPIRY_INTERVAL)) {
// Remove profile from head of queue
trackerExpiryQueue.remove(leastRecent);
String trackerName = leastRecent.getTrackerName();
// Figure out if last-seen time should be updated, or if tracker is dead
TaskTrackerStatus newProfile =
(TaskTrackerStatus) taskTrackers.get(leastRecent.getTrackerName());
// Items might leave the taskTracker set through other means; the
// status stored in 'taskTrackers' might be null, which means the
// tracker has already been destroyed.
if (newProfile != null) {
if (now - newProfile.getLastSeen() > TASKTRACKER_EXPIRY_INTERVAL) {
// Remove completely
updateTaskTrackerStatus(trackerName, null);
lostTaskTracker(leastRecent.getTrackerName());
} else {
// Update time by inserting latest profile
trackerExpiryQueue.add(newProfile);
}
}
}
}
}
}
}
/** Start the JobTracker process, listen on the indicated port */
JobTracker(Configuration conf) throws IOException {
//
// Grab some static constants
//
maxCurrentTasks = conf.getInt("mapred.tasktracker.tasks.maximum", 2);
RETIRE_JOB_INTERVAL = conf.getLong("mapred.jobtracker.retirejob.interval", 24 * 60 * 60 * 1000);
RETIRE_JOB_CHECK_INTERVAL = conf.getLong("mapred.jobtracker.retirejob.check", 60 * 1000);
TASK_ALLOC_EPSILON = conf.getFloat("mapred.jobtracker.taskalloc.loadbalance.epsilon", 0.2f);
PAD_FRACTION = conf.getFloat("mapred.jobtracker.taskalloc.capacitypad", 0.1f);
MIN_SLOTS_FOR_PADDING = 3 * maxCurrentTasks;
// This is a directory of temporary submission files. We delete it
// on startup, and can delete any files that we're done with
this.conf = conf;
JobConf jobConf = new JobConf(conf);
this.systemDir = jobConf.getSystemDir();
this.fs = FileSystem.get(conf);
FileUtil.fullyDelete(fs, systemDir);
fs.mkdirs(systemDir);
// Same with 'localDir' except it's always on the local disk.
jobConf.deleteLocalFiles(SUBDIR);
// Set ports, start RPC servers, etc.
InetSocketAddress addr = getAddress(conf);
this.localMachine = addr.getHostName();
this.port = addr.getPort();
this.interTrackerServer = RPC.getServer(this, addr.getPort(), 10, false, conf);
this.interTrackerServer.start();
Properties p = System.getProperties();
for (Iterator it = p.keySet().iterator(); it.hasNext(); ) {
String key = (String) it.next();
String val = (String) p.getProperty(key);
LOG.info("Property '" + key + "' is " + val);
}
this.infoPort = conf.getInt("mapred.job.tracker.info.port", 50030);
this.infoServer = new JobTrackerInfoServer(this, infoPort);
this.infoServer.start();
this.startTime = System.currentTimeMillis();
new Thread(this.expireTrackers).start();
new Thread(this.retireJobs).start();
new Thread(this.initJobs).start();
}
private static void run(Callable c, boolean read, int size) {
// Count all i/o time from here, including all retry overheads
long start_io_ms = System.currentTimeMillis();
while (true) {
try {
long start_ns = System.nanoTime(); // Blocking i/o call timing - without counting repeats
c.call();
TimeLine.record_IOclose(start_ns, start_io_ms, read ? 1 : 0, size, Value.HDFS);
break;
// Explicitly ignore the following exceptions but
// fail on the rest IOExceptions
} catch (EOFException e) {
ignoreAndWait(e, false);
} catch (SocketTimeoutException e) {
ignoreAndWait(e, false);
} catch (IOException e) {
ignoreAndWait(e, true);
} catch (Exception e) {
throw Log.errRTExcept(e);
}
}
}
// TODO: Can also collect #procs, time taken by each thread to measure fairness.
@Override
public Integer call() throws IOException {
while (true) {
if (workersFailed.get()) {
return EXIT_FAILURE;
}
long procId = procIds.getAndIncrement();
if (procId >= numProcs) {
break;
}
if (procId != 0 && procId % 10000 == 0) {
long ms = System.currentTimeMillis() - start;
System.out.println("Wrote " + procId + " procedures in " + StringUtils.humanTimeDiff(ms));
}
try {
if (procId > 0 && procId % numProcsPerWal == 0) {
store.rollWriterForTesting();
System.out.println(
"Starting new log : "
+ store.getActiveLogs().get(store.getActiveLogs().size() - 1));
}
} catch (IOException ioe) {
// Ask other threads to quit too.
workersFailed.set(true);
System.err.println("Exception when rolling log file. Current procId = " + procId);
ioe.printStackTrace();
return EXIT_FAILURE;
}
ProcedureTestingUtility.TestProcedure proc =
new ProcedureTestingUtility.TestProcedure(procId);
proc.setData(serializedState);
store.insert(proc, null);
store.update(proc);
}
return EXIT_SUCCESS;
}
