|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object org.apache.hadoop.mapred.JobTracker
public class JobTracker
JobTracker is the central location for submitting and tracking MR jobs in a network environment.
Nested Class Summary | |
---|---|
static class |
JobTracker.IllegalStateException
A client tried to submit a job before the Job Tracker was ready. |
static class |
JobTracker.State
|
Field Summary | |
---|---|
static int |
CLUSTER_INCREMENT
|
static long |
COUNTER_UPDATE_INTERVAL
|
static int |
FILE_NOT_FOUND
|
static int |
HEARTBEAT_INTERVAL_MIN
|
static org.apache.commons.logging.Log |
LOG
|
static String |
MAP_OUTPUT_LENGTH
The custom http header used for the map output length. |
static float |
MAX_INMEM_FILESIZE_FRACTION
Constant denoting the max size (in terms of the fraction of the total size of the filesys) of a map output file that we will try to keep in mem. |
static float |
MAX_INMEM_FILESYS_USE
Constant denoting when a merge of in memory files will be triggered |
static String |
RAW_MAP_OUTPUT_LENGTH
The custom http header used for the "raw" map output length. |
static int |
SUCCESS
|
static String |
TEMP_DIR_NAME
Temporary directory name |
static int |
TRACKERS_OK
|
static int |
UNKNOWN_TASKTRACKER
|
static long |
versionID
version 3 introduced to replace emitHearbeat/pollForNewTask/pollForTaskWithClosedJob with heartbeat(TaskTrackerStatus, boolean, boolean, short)
version 4 changed TaskReport for HADOOP-549. |
static long |
versionID
|
static String |
WORKDIR
|
Method Summary | |
---|---|
Vector<org.apache.hadoop.mapred.JobInProgress> |
completedJobs()
|
Vector<org.apache.hadoop.mapred.JobInProgress> |
failedJobs()
|
static InetSocketAddress |
getAddress(Configuration conf)
|
JobStatus[] |
getAllJobs()
Get all the jobs submitted. |
String |
getAssignedTracker(String taskid)
Deprecated. |
String |
getAssignedTracker(TaskAttemptID taskId)
Get tracker name for a given task id. |
String |
getBuildVersion()
Returns the buildVersion of the JobTracker |
ClusterStatus |
getClusterStatus()
Get the current status of the cluster |
String |
getFilesystemName()
Grab the local fs name |
int |
getInfoPort()
|
org.apache.hadoop.mapred.JobInProgress |
getJob(JobID jobid)
|
org.apache.hadoop.mapred.JobInProgress |
getJob(String jobid)
Deprecated. |
Counters |
getJobCounters(JobID jobid)
Grab the current job counters |
Counters |
getJobCounters(String id)
Deprecated. |
JobProfile |
getJobProfile(JobID jobid)
Grab a handle to a job that is already known to the JobTracker. |
JobProfile |
getJobProfile(String id)
Deprecated. |
JobStatus |
getJobStatus(JobID jobid)
Grab a handle to a job that is already known to the JobTracker. |
JobStatus |
getJobStatus(String id)
Deprecated. |
String |
getJobTrackerMachine()
|
static String |
getLocalJobFilePath(JobID jobId)
Get the localized job file path on the job trackers local file system |
String |
getLocalJobFilePath(String jobid)
Deprecated. |
TaskReport[] |
getMapTaskReports(JobID jobid)
Grab a bunch of info on the map tasks that make up the job |
TaskReport[] |
getMapTaskReports(String jobid)
Deprecated. |
JobID |
getNewJobId()
Allocates a new JobId string. |
Node |
getNode(String name)
Return the Node in the network topology that corresponds to the hostname |
Collection<Node> |
getNodesAtMaxLevel()
Returns a collection of nodes at the max level |
int |
getNumResolvedTaskTrackers()
|
int |
getNumTaskCacheLevels()
|
static Node |
getParentNode(Node node,
int level)
|
long |
getProtocolVersion(String protocol,
long clientVersion)
Return protocol version corresponding to protocol interface. |
TaskReport[] |
getReduceTaskReports(JobID jobid)
Grab a bunch of info on the reduce tasks that make up the job |
TaskReport[] |
getReduceTaskReports(String jobid)
Deprecated. |
List<org.apache.hadoop.mapred.JobInProgress> |
getRunningJobs()
Version that is called from a timer thread, and therefore needs to be careful to synchronize. |
long |
getStartTime()
|
String |
getSystemDir()
Grab the jobtracker system directory path where job-specific files are to be placed. |
TaskCompletionEvent[] |
getTaskCompletionEvents(JobID jobid,
int fromEventId,
int maxEvents)
Get task completion events for the jobid, starting from fromEventId. |
TaskCompletionEvent[] |
getTaskCompletionEvents(String jobid,
int fromid,
int maxevents)
Deprecated. |
String[] |
getTaskDiagnostics(String jobid,
String tipid,
String taskid)
Deprecated. |
String[] |
getTaskDiagnostics(TaskAttemptID taskId)
Get the diagnostics for a given task |
org.apache.hadoop.mapred.TaskTrackerStatus |
getTaskTracker(String trackerID)
|
org.apache.hadoop.mapred.TaskInProgress |
getTip(TaskID tipid)
Returns specified TaskInProgress, or null. |
int |
getTotalSubmissions()
|
String |
getTrackerIdentifier()
Get the unique identifier (ie. |
int |
getTrackerPort()
|
org.apache.hadoop.mapred.HeartbeatResponse |
heartbeat(org.apache.hadoop.mapred.TaskTrackerStatus status,
boolean initialContact,
boolean acceptNewTasks,
short responseId)
The periodic heartbeat mechanism between the TaskTracker and
the JobTracker . |
JobStatus[] |
jobsToComplete()
Get the jobs that are not completed and not failed |
void |
killJob(JobID jobid)
Kill the indicated job |
void |
killJob(String id)
Deprecated. |
boolean |
killTask(String taskId,
boolean shouldFail)
Deprecated. |
boolean |
killTask(TaskAttemptID taskid,
boolean shouldFail)
Mark a Task to be killed |
static void |
main(String[] argv)
Start the JobTracker process. |
void |
offerService()
Run forever |
void |
reportTaskTrackerError(String taskTracker,
String errorClass,
String errorMessage)
Report a problem to the job tracker. |
Node |
resolveAndAddToTopology(String name)
|
Vector<org.apache.hadoop.mapred.JobInProgress> |
runningJobs()
|
static JobTracker |
startTracker(JobConf conf)
Start the JobTracker with given configuration. |
void |
stopTracker()
|
JobStatus |
submitJob(JobID jobId)
JobTracker.submitJob() kicks off a new job. |
JobStatus |
submitJob(String jobid)
Deprecated. |
Collection |
taskTrackers()
|
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
public static final org.apache.commons.logging.Log LOG
public static final int HEARTBEAT_INTERVAL_MIN
public static final int CLUSTER_INCREMENT
public static final long COUNTER_UPDATE_INTERVAL
public static final float MAX_INMEM_FILESYS_USE
public static final float MAX_INMEM_FILESIZE_FRACTION
public static final int SUCCESS
public static final int FILE_NOT_FOUND
public static final String MAP_OUTPUT_LENGTH
public static final String RAW_MAP_OUTPUT_LENGTH
public static final String TEMP_DIR_NAME
public static final String WORKDIR
public static final long versionID
heartbeat(TaskTrackerStatus, boolean, boolean, short)
version 4 changed TaskReport for HADOOP-549.
version 5 introduced that removes locateMapOutputs and instead uses
getTaskCompletionEvents to figure finished maps and fetch the outputs
version 6 adds maxTasks to TaskTrackerStatus for HADOOP-1245
version 7 replaces maxTasks by maxMapTasks and maxReduceTasks in
TaskTrackerStatus for HADOOP-1274
Version 8: HeartbeatResponse is added with the next heartbeat interval.
version 9 changes the counter representation for HADOOP-2248
version 10 changes the TaskStatus representation for HADOOP-2208
version 11 changes string to JobID in getTaskCompletionEvents().
version 12 changes the counters representation for HADOOP-1915
version 13 added call getBuildVersion() for HADOOP-236
Version 14: replaced getFilesystemName with getSystemDir for HADOOP-3135
public static final int TRACKERS_OK
public static final int UNKNOWN_TASKTRACKER
public static final long versionID
Method Detail |
---|
public static JobTracker startTracker(JobConf conf) throws IOException, InterruptedException
zero
.
conf
- configuration for the JobTracker.
IOException
InterruptedException
public void stopTracker() throws IOException
IOException
public long getProtocolVersion(String protocol, long clientVersion) throws IOException
VersionedProtocol
protocol
- The classname of the protocol interfaceclientVersion
- The version of the protocol that the client speaks
IOException
public static InetSocketAddress getAddress(Configuration conf)
public void offerService() throws InterruptedException
InterruptedException
public int getTotalSubmissions()
public String getJobTrackerMachine()
public String getTrackerIdentifier()
public int getTrackerPort()
public int getInfoPort()
public long getStartTime()
public Vector<org.apache.hadoop.mapred.JobInProgress> runningJobs()
public List<org.apache.hadoop.mapred.JobInProgress> getRunningJobs()
public Vector<org.apache.hadoop.mapred.JobInProgress> failedJobs()
public Vector<org.apache.hadoop.mapred.JobInProgress> completedJobs()
public Collection taskTrackers()
public org.apache.hadoop.mapred.TaskTrackerStatus getTaskTracker(String trackerID)
public Node resolveAndAddToTopology(String name)
public Collection<Node> getNodesAtMaxLevel()
public static Node getParentNode(Node node, int level)
public Node getNode(String name)
public int getNumTaskCacheLevels()
public int getNumResolvedTaskTrackers()
public String getBuildVersion() throws IOException
IOException
public org.apache.hadoop.mapred.HeartbeatResponse heartbeat(org.apache.hadoop.mapred.TaskTrackerStatus status, boolean initialContact, boolean acceptNewTasks, short responseId) throws IOException
TaskTracker
and
the JobTracker
.
The JobTracker
processes the status information sent by the
TaskTracker
and responds with instructions to start/stop
tasks or jobs, and also 'reset' instructions during contingencies.
status
- the status updateinitialContact
- true
if this is first interaction since
'refresh', false
otherwise.acceptNewTasks
- true
if the TaskTracker
is
ready to accept new tasks to run.responseId
- the last responseId successfully acted upon by the
TaskTracker
.
HeartbeatResponse
with
fresh instructions.
IOException
public String getFilesystemName() throws IOException
IOException
public void reportTaskTrackerError(String taskTracker, String errorClass, String errorMessage) throws IOException
taskTracker
- the name of the task trackererrorClass
- the kind of error (eg. the class that was thrown)errorMessage
- the human readable error message
IOException
- if there was a problem in communication or on the
remote sidepublic JobID getNewJobId() throws IOException
IOException
@Deprecated public JobStatus submitJob(String jobid) throws IOException
IOException
public JobStatus submitJob(JobID jobId) throws IOException
IOException
public ClusterStatus getClusterStatus()
@Deprecated public void killJob(String id)
public void killJob(JobID jobid)
@Deprecated public JobProfile getJobProfile(String id)
public JobProfile getJobProfile(JobID jobid)
@Deprecated public JobStatus getJobStatus(String id)
public JobStatus getJobStatus(JobID jobid)
@Deprecated public Counters getJobCounters(String id)
public Counters getJobCounters(JobID jobid)
@Deprecated public TaskReport[] getMapTaskReports(String jobid)
public TaskReport[] getMapTaskReports(JobID jobid)
@Deprecated public TaskReport[] getReduceTaskReports(String jobid)
public TaskReport[] getReduceTaskReports(JobID jobid)
@Deprecated public TaskCompletionEvent[] getTaskCompletionEvents(String jobid, int fromid, int maxevents) throws IOException
IOException
public TaskCompletionEvent[] getTaskCompletionEvents(JobID jobid, int fromEventId, int maxEvents) throws IOException
jobid
- job idfromEventId
- event id to start from.maxEvents
- the max number of events we want to look at
IOException
@Deprecated public String[] getTaskDiagnostics(String jobid, String tipid, String taskid) throws IOException
IOException
public String[] getTaskDiagnostics(TaskAttemptID taskId) throws IOException
taskId
- the id of the task
IOException
public org.apache.hadoop.mapred.TaskInProgress getTip(TaskID tipid)
@Deprecated public boolean killTask(String taskId, boolean shouldFail) throws IOException
IOException
public boolean killTask(TaskAttemptID taskid, boolean shouldFail) throws IOException
taskid
- the id of the task to kill.shouldFail
- if true the task is failed and added to failed tasks list, otherwise
it is just killed, w/o affecting job failure status.
IOException
@Deprecated public String getAssignedTracker(String taskid)
public String getAssignedTracker(TaskAttemptID taskId)
taskId
- the name of the task
public JobStatus[] jobsToComplete()
public JobStatus[] getAllJobs()
public String getSystemDir()
JobSubmissionProtocol.getSystemDir()
@Deprecated public org.apache.hadoop.mapred.JobInProgress getJob(String jobid)
public org.apache.hadoop.mapred.JobInProgress getJob(JobID jobid)
@Deprecated public String getLocalJobFilePath(String jobid)
public static String getLocalJobFilePath(JobID jobId)
jobId
- id of the job
public static void main(String[] argv) throws IOException, InterruptedException
IOException
InterruptedException
|
||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | |||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |