"; from file=" + jobTokenFile);
Token<JobTokenIdentifier> jt = TokenCache.getJobToken(credentials);
jt.setService(new Text(address.getAddress().getHostAddress() + ":"
+ address.getPort()));
UserGroupInformation current = UserGroupInformation.getCurrentUser();
current.addToken(jt);
UserGroupInformation taskOwner
= UserGroupInformation.createRemoteUser(firstTaskid.getJobID().toString());
taskOwner.addToken(jt);
// Set the credentials
defaultConf.setCredentials(credentials);
final TaskUmbilicalProtocol umbilical =
taskOwner.doAs(new PrivilegedExceptionAction<TaskUmbilicalProtocol>() {
@Override
public TaskUmbilicalProtocol run() throws Exception {
return (TaskUmbilicalProtocol)RPC.getProxy(TaskUmbilicalProtocol.class,
TaskUmbilicalProtocol.versionID,
address,
defaultConf);
}
});
int numTasksToExecute = -1; //-1 signifies "no limit"
int numTasksExecuted = 0;
Runtime.getRuntime().addShutdownHook(new Thread() {
public void run() {
try {
if (taskid != null) {
TaskLog.syncLogs(logLocation, taskid, isCleanup);
}
} catch (Throwable throwable) {
}
}
});
Thread t = new Thread() {
public void run() {
//every so often wake up and syncLogs so that we can track
//logs of the currently running task
while (true) {
try {
Thread.sleep(5000);
if (taskid != null) {
TaskLog.syncLogs(logLocation, taskid, isCleanup);
}
} catch (InterruptedException ie) {
} catch (IOException iee) {
LOG.error("Error in syncLogs: " + iee);
System.exit(-1);
}
}
}
};
t.setName("Thread for syncLogs");
t.setDaemon(true);
t.start();
String pid = "";
if (!Shell.WINDOWS) {
pid = System.getenv().get("JVM_PID");
}
JvmContext context = new JvmContext(jvmId, pid);
int idleLoopCount = 0;
Task task = null;
UserGroupInformation childUGI = null;
try {
while (true) {
taskid = null;
JvmTask myTask = umbilical.getTask(context);
if (myTask.shouldDie()) {
break;
} else {
if (myTask.getTask() == null) {
taskid = null;
if (++idleLoopCount >= SLEEP_LONGER_COUNT) {
//we sleep for a bigger interval when we don't receive
//tasks for a while
Thread.sleep(1500);
} else {
Thread.sleep(500);
}
continue;
}
}
idleLoopCount = 0;
task = myTask.getTask();
taskid = task.getTaskID();
isCleanup = task.isTaskCleanupTask();
// reset the statistics for the task
FileSystem.clearStatistics();
//create the index file so that the log files
//are viewable immediately
TaskLog.syncLogs(logLocation, taskid, isCleanup);
// Create the job-conf and set credentials
final JobConf job = new JobConf(task.getJobFile());
job.setCredentials(defaultConf.getCredentials());
// set the jobTokenFile into task
task.setJobTokenSecret(JobTokenSecretManager.
createSecretKey(jt.getPassword()));
// setup the child's mapred-local-dir. The child is now sandboxed and
// can only see files down and under attemtdir only.
TaskRunner.setupChildMapredLocalDirs(task, job);
//setupWorkDir actually sets up the symlinks for the distributed
//cache. After a task exits we wipe the workdir clean, and hence
//the symlinks have to be rebuilt.
TaskRunner.setupWorkDir(job, new File(".").getAbsoluteFile());
numTasksToExecute = job.getNumTasksToExecutePerJvm();
assert(numTasksToExecute != 0);
task.setConf(job);
// Initiate Java VM metrics
JvmMetrics.init(task.getPhase().toString(), job.getSessionId());
LOG.debug("Creating remote user to execute task: " + job.get("user.name"));
childUGI = UserGroupInformation.createRemoteUser(job.get("user.name"));
// Add tokens to new user so that it may execute its task correctly.
for(Token<?> token : UserGroupInformation.getCurrentUser().getTokens()) {
childUGI.addToken(token);
}
// Create a final reference to the task for the doAs block
final Task taskFinal = task;
childUGI.doAs(new PrivilegedExceptionAction<Object>() {
@Override
public Object run() throws Exception {
try {
// use job-specified working directory
FileSystem.get(job).setWorkingDirectory(job.getWorkingDirectory());
taskFinal.run(job, umbilical); // run the task
} finally {
TaskLog.syncLogs(logLocation, taskid, isCleanup);
}
return null;
}
});
if (numTasksToExecute > 0 && ++numTasksExecuted == numTasksToExecute) {
break;
}
}
} catch (FSError e) {
LOG.fatal("FSError from child", e);
umbilical.fsError(taskid, e.getMessage());
} catch (Exception exception) {
LOG.warn("Error running child", exception);
try {
if (task != null) {
// do cleanup for the task
if(childUGI == null) {
task.taskCleanup(umbilical);
} else {
final Task taskFinal = task;
childUGI.doAs(new PrivilegedExceptionAction<Object>() {
@Override
public Object run() throws Exception {
taskFinal.taskCleanup(umbilical);
return null;
}