Package org.apache.nutch.util

Class NutchJob

java.lang.Object

org.apache.hadoop.mapreduce.task.JobContextImpl

org.apache.hadoop.mapreduce.Job

org.apache.nutch.util.NutchJob

All Implemented Interfaces:

AutoCloseable, JobContext, MRJobConfig

public class NutchJob
extends Job

A Job for Nutch jobs.

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.hadoop.mapreduce.Job

Job.JobState, Job.TaskStatusFilter

Field Summary

Fields inherited from class org.apache.hadoop.mapreduce.Job

COMPLETION_POLL_INTERVAL_KEY, DEFAULT_SUBMIT_REPLICATION, DEFAULT_USE_WILDCARD_FOR_LIBJARS, OUTPUT_FILTER, PROGRESS_MONITOR_POLL_INTERVAL_KEY, SUBMIT_REPLICATION, USE_WILDCARD_FOR_LIBJARS, USED_GENERIC_PARSER

Fields inherited from class org.apache.hadoop.mapreduce.task.JobContextImpl

conf, credentials, ugi

Fields inherited from interface org.apache.hadoop.mapreduce.MRJobConfig

AM_NODE_LABEL_EXP, AM_STRICT_LOCALITY, APPLICATION_ATTEMPT_ID, APPLICATION_MASTER_CLASS, ARCHIVES_FOR_SHARED_CACHE, CACHE_ARCHIVES, CACHE_ARCHIVES_SHARED_CACHE_UPLOAD_POLICIES, CACHE_ARCHIVES_SIZES, CACHE_ARCHIVES_TIMESTAMPS, CACHE_ARCHIVES_VISIBILITIES, CACHE_FILE_TIMESTAMPS, CACHE_FILE_VISIBILITIES, CACHE_FILES, CACHE_FILES_SHARED_CACHE_UPLOAD_POLICIES, CACHE_FILES_SIZES, CACHE_LOCALARCHIVES, CACHE_LOCALFILES, CACHE_SYMLINK, CLASSPATH_ARCHIVES, CLASSPATH_FILES, COMBINE_CLASS_ATTR, COMBINE_RECORDS_BEFORE_PROGRESS, COMBINER_GROUP_COMPARATOR_CLASS, COMPLETED_MAPS_FOR_REDUCE_SLOWSTART, COUNTER_GROUP_NAME_MAX_DEFAULT, COUNTER_GROUP_NAME_MAX_KEY, COUNTER_GROUPS_MAX_DEFAULT, COUNTER_GROUPS_MAX_KEY, COUNTER_NAME_MAX_DEFAULT, COUNTER_NAME_MAX_KEY, COUNTERS_MAX_DEFAULT, COUNTERS_MAX_KEY, DEFAULT_FINISH_JOB_WHEN_REDUCERS_DONE, DEFAULT_HEAP_MEMORY_MB_RATIO, DEFAULT_IO_SORT_FACTOR, DEFAULT_IO_SORT_MB, DEFAULT_JOB_ACL_MODIFY_JOB, DEFAULT_JOB_ACL_VIEW_JOB, DEFAULT_JOB_AM_ACCESS_DISABLED, DEFAULT_JOB_DFS_STORAGE_CAPACITY_KILL_LIMIT_EXCEED, DEFAULT_JOB_MAX_MAP, DEFAULT_JOB_RUNNING_MAP_LIMIT, DEFAULT_JOB_RUNNING_REDUCE_LIMIT, DEFAULT_JOB_SINGLE_DISK_LIMIT_BYTES, DEFAULT_JOB_SINGLE_DISK_LIMIT_CHECK_INTERVAL_MS, DEFAULT_JOB_SINGLE_DISK_LIMIT_KILL_LIMIT_EXCEED, DEFAULT_JOB_TOKEN_TRACKING_IDS_ENABLED, DEFAULT_LOG_LEVEL, DEFAULT_MAP_CPU_VCORES, DEFAULT_MAP_MEMORY_MB, DEFAULT_MAPRED_ADMIN_JAVA_OPTS, DEFAULT_MAPRED_ADMIN_USER_ENV, DEFAULT_MAPREDUCE_APPLICATION_CLASSPATH, DEFAULT_MAPREDUCE_CROSS_PLATFORM_APPLICATION_CLASSPATH, DEFAULT_MAPREDUCE_JOB_EMIT_TIMELINE_DATA, DEFAULT_MAPREDUCE_JVM_SYSTEM_PROPERTIES_TO_LOG, DEFAULT_MAX_ALLOWED_FETCH_FAILURES_FRACTION, DEFAULT_MAX_FETCH_FAILURES_NOTIFICATIONS, DEFAULT_MAX_SHUFFLE_FETCH_HOST_FAILURES, DEFAULT_MAX_SHUFFLE_FETCH_RETRY_DELAY, DEFAULT_MR_AM_ADMIN_COMMAND_OPTS, DEFAULT_MR_AM_ADMIN_USER_ENV, DEFAULT_MR_AM_COMMAND_OPTS, DEFAULT_MR_AM_COMMIT_WINDOW_MS, DEFAULT_MR_AM_COMMITTER_CANCEL_TIMEOUT_MS, DEFAULT_MR_AM_CONTAINERLAUNCHER_THREAD_COUNT_LIMIT, DEFAULT_MR_AM_CONTAINERLAUNCHER_THREADPOOL_INITIAL_SIZE, DEFAULT_MR_AM_CPU_VCORES, DEFAULT_MR_AM_HARD_KILL_TIMEOUT_MS, DEFAULT_MR_AM_HISTORY_COMPLETE_EVENT_FLUSH_TIMEOUT_MS, DEFAULT_MR_AM_HISTORY_JOB_COMPLETE_UNFLUSHED_MULTIPLIER, DEFAULT_MR_AM_HISTORY_MAX_UNFLUSHED_COMPLETE_EVENTS, DEFAULT_MR_AM_HISTORY_USE_BATCHED_FLUSH_QUEUE_SIZE_THRESHOLD, DEFAULT_MR_AM_IGNORE_BLACKLISTING_BLACKLISTED_NODE_PERCENT, DEFAULT_MR_AM_JOB_CLIENT_THREAD_COUNT, DEFAULT_MR_AM_JOB_REDUCE_PREEMPTION_LIMIT, DEFAULT_MR_AM_JOB_REDUCE_RAMP_UP_LIMIT, DEFAULT_MR_AM_LOG_BACKUPS, DEFAULT_MR_AM_LOG_KB, DEFAULT_MR_AM_LOG_LEVEL, DEFAULT_MR_AM_MAX_ATTEMPTS, DEFAULT_MR_AM_NUM_PROGRESS_SPLITS, DEFAULT_MR_AM_PROFILE, DEFAULT_MR_AM_STAGING_DIR, DEFAULT_MR_AM_STAGING_ERASURECODING_ENABLED, DEFAULT_MR_AM_TASK_ESTIMATOR_SIMPLE_SMOOTH_INITIALS, DEFAULT_MR_AM_TASK_ESTIMATOR_SIMPLE_SMOOTH_LAMBDA_MS, DEFAULT_MR_AM_TASK_ESTIMATOR_SIMPLE_SMOOTH_STAGNATED_MS, DEFAULT_MR_AM_TASK_ESTIMATOR_SMOOTH_LAMBDA_MS, DEFAULT_MR_AM_TASK_LISTENER_THREAD_COUNT, DEFAULT_MR_AM_TO_RM_HEARTBEAT_INTERVAL_MS, DEFAULT_MR_AM_TO_RM_WAIT_INTERVAL_MS, DEFAULT_MR_AM_VMEM_MB, DEFAULT_MR_AM_WEBAPP_HTTPS_CLIENT_AUTH, DEFAULT_MR_AM_WEBAPP_HTTPS_ENABLED, DEFAULT_MR_CLIENT_JOB_MAX_RETRIES, DEFAULT_MR_CLIENT_JOB_RETRY_INTERVAL, DEFAULT_MR_CLIENT_MAX_RETRIES, DEFAULT_MR_CLIENT_TO_AM_IPC_MAX_RETRIES, DEFAULT_MR_CLIENT_TO_AM_IPC_MAX_RETRIES_ON_TIMEOUTS, DEFAULT_MR_ENCRYPTED_INTERMEDIATE_DATA, DEFAULT_MR_ENCRYPTED_INTERMEDIATE_DATA_BUFFER_KB, DEFAULT_MR_ENCRYPTED_INTERMEDIATE_DATA_KEY_SIZE_BITS, DEFAULT_MR_JOB_END_NOTIFICATION_TIMEOUT, DEFAULT_MR_JOB_REDUCER_PREEMPT_DELAY_SEC, DEFAULT_MR_JOB_REDUCER_UNCONDITIONAL_PREEMPT_DELAY_SEC, DEFAULT_MR_NUM_OPPORTUNISTIC_MAPS_PERCENT, DEFAULT_MR_TASK_ENABLE_PING_FOR_LIVELINESS_CHECK, DEFAULT_REDUCE_CPU_VCORES, DEFAULT_REDUCE_MEMORY_MB, DEFAULT_REDUCE_SEPARATE_SHUFFLE_LOG, DEFAULT_SHELL, DEFAULT_SHUFFLE_FETCH_RETRY_INTERVAL_MS, DEFAULT_SHUFFLE_INPUT_BUFFER_PERCENT, DEFAULT_SHUFFLE_KEY_LENGTH, DEFAULT_SHUFFLE_LOG_BACKUPS, DEFAULT_SHUFFLE_LOG_KB, DEFAULT_SHUFFLE_MERGE_PERCENT, DEFAULT_SPECULATIVE_MINIMUM_ALLOWED_TASKS, DEFAULT_SPECULATIVE_RETRY_AFTER_NO_SPECULATE, DEFAULT_SPECULATIVE_RETRY_AFTER_SPECULATE, DEFAULT_SPECULATIVECAP_RUNNING_TASKS, DEFAULT_SPECULATIVECAP_TOTAL_TASKS, DEFAULT_SPLIT_METAINFO_MAXSIZE, DEFAULT_TASK_ISMAP, DEFAULT_TASK_LOCAL_WRITE_LIMIT_BYTES, DEFAULT_TASK_LOG_BACKUPS, DEFAULT_TASK_PROFILE_PARAMS, DEFAULT_TASK_STUCK_TIMEOUT_MS, DEFAULT_TASK_TIMEOUT_MILLIS, FILES_FOR_CLASSPATH_AND_SHARED_CACHE, FILES_FOR_SHARED_CACHE, FINISH_JOB_WHEN_REDUCERS_DONE, GROUP_COMPARATOR_CLASS, HADOOP_WORK_DIR, HEAP_MEMORY_MB_RATIO, ID, INDEX_CACHE_MEMORY_LIMIT, INPUT_FILE_MANDATORY_PREFIX, INPUT_FILE_OPTION_PREFIX, INPUT_FORMAT_CLASS_ATTR, IO_SORT_FACTOR, IO_SORT_MB, JAR, JAR_UNPACK_PATTERN, JOB_ACL_MODIFY_JOB, JOB_ACL_VIEW_JOB, JOB_AM_ACCESS_DISABLED, JOB_CANCEL_DELEGATION_TOKEN, JOB_CONF_FILE, JOB_DFS_STORAGE_CAPACITY_KILL_LIMIT_EXCEED, JOB_JAR, JOB_JOBTRACKER_ID, JOB_LOCAL_DIR, JOB_MAX_MAP, JOB_NAME, JOB_NAMENODES, JOB_NAMENODES_TOKEN_RENEWAL_EXCLUDE, JOB_NODE_LABEL_EXP, JOB_RUNNING_MAP_LIMIT, JOB_RUNNING_REDUCE_LIMIT, JOB_SINGLE_DISK_LIMIT_BYTES, JOB_SINGLE_DISK_LIMIT_CHECK_INTERVAL_MS, JOB_SINGLE_DISK_LIMIT_KILL_LIMIT_EXCEED, JOB_SPLIT, JOB_SPLIT_METAINFO, JOB_SUBMIT_DIR, JOB_SUBMITHOST, JOB_SUBMITHOSTADDR, JOB_TAGS, JOB_TOKEN_TRACKING_IDS, JOB_TOKEN_TRACKING_IDS_ENABLED, JOB_UBERTASK_ENABLE, JOB_UBERTASK_MAXBYTES, JOB_UBERTASK_MAXMAPS, JOB_UBERTASK_MAXREDUCES, JOBJAR_SHARED_CACHE_UPLOAD_POLICY, JOBJAR_SHARED_CACHE_UPLOAD_POLICY_DEFAULT, JOBJAR_VISIBILITY, JOBJAR_VISIBILITY_DEFAULT, JVM_NUMTASKS_TORUN, KEY_COMPARATOR, MAP_CLASS_ATTR, MAP_COMBINE_MIN_SPILLS, MAP_CPU_VCORES, MAP_DEBUG_SCRIPT, MAP_ENV, MAP_FAILURES_MAX_PERCENT, MAP_INPUT_FILE, MAP_INPUT_PATH, MAP_INPUT_START, MAP_JAVA_OPTS, MAP_LOG_LEVEL, MAP_MAX_ATTEMPTS, MAP_MEMORY_MB, MAP_NODE_LABEL_EXP, MAP_OUTPUT_COLLECTOR_CLASS_ATTR, MAP_OUTPUT_COMPRESS, MAP_OUTPUT_COMPRESS_CODEC, MAP_OUTPUT_KEY_CLASS, MAP_OUTPUT_KEY_FIELD_SEPARATOR, MAP_OUTPUT_KEY_FIELD_SEPERATOR, MAP_OUTPUT_VALUE_CLASS, MAP_RESOURCE_TYPE_PREFIX, MAP_SKIP_INCR_PROC_COUNT, MAP_SKIP_MAX_RECORDS, MAP_SORT_CLASS, MAP_SORT_SPILL_PERCENT, MAP_SPECULATIVE, MAPRED_ADMIN_USER_ENV, MAPRED_ADMIN_USER_SHELL, MAPRED_MAP_ADMIN_JAVA_OPTS, MAPRED_REDUCE_ADMIN_JAVA_OPTS, MAPREDUCE_APPLICATION_CLASSPATH, MAPREDUCE_APPLICATION_FRAMEWORK_PATH, MAPREDUCE_JOB_CLASSLOADER, MAPREDUCE_JOB_CLASSLOADER_SYSTEM_CLASSES, MAPREDUCE_JOB_CREDENTIALS_BINARY, MAPREDUCE_JOB_DIR, MAPREDUCE_JOB_EMIT_TIMELINE_DATA, MAPREDUCE_JOB_LOG4J_PROPERTIES_FILE, MAPREDUCE_JOB_SHUFFLE_PROVIDER_SERVICES, MAPREDUCE_JOB_USER_CLASSPATH_FIRST, MAPREDUCE_JVM_ADD_OPENS_JAVA_OPT, MAPREDUCE_JVM_ADD_OPENS_JAVA_OPT_DEFAULT, MAPREDUCE_JVM_SYSTEM_PROPERTIES_TO_LOG, MAPREDUCE_V2_CHILD_CLASS, MAX_ALLOWED_FETCH_FAILURES_FRACTION, MAX_FETCH_FAILURES_NOTIFICATIONS, MAX_RESOURCES, MAX_RESOURCES_DEFAULT, MAX_RESOURCES_MB, MAX_RESOURCES_MB_DEFAULT, MAX_SHUFFLE_FETCH_HOST_FAILURES, MAX_SHUFFLE_FETCH_RETRY_DELAY, MAX_SINGLE_RESOURCE_MB, MAX_SINGLE_RESOURCE_MB_DEFAULT, MAX_TASK_FAILURES_PER_TRACKER, MR_AM_ADMIN_COMMAND_OPTS, MR_AM_ADMIN_USER_ENV, MR_AM_COMMAND_OPTS, MR_AM_COMMIT_WINDOW_MS, MR_AM_COMMITTER_CANCEL_TIMEOUT_MS, MR_AM_CONTAINERLAUNCHER_THREAD_COUNT_LIMIT, MR_AM_CONTAINERLAUNCHER_THREADPOOL_INITIAL_SIZE, MR_AM_CPU_VCORES, MR_AM_CREATE_JH_INTERMEDIATE_BASE_DIR, MR_AM_ENV, MR_AM_HARD_KILL_TIMEOUT_MS, MR_AM_HISTORY_COMPLETE_EVENT_FLUSH_TIMEOUT_MS, MR_AM_HISTORY_JOB_COMPLETE_UNFLUSHED_MULTIPLIER, MR_AM_HISTORY_MAX_UNFLUSHED_COMPLETE_EVENTS, MR_AM_HISTORY_USE_BATCHED_FLUSH_QUEUE_SIZE_THRESHOLD, MR_AM_IGNORE_BLACKLISTING_BLACKLISTED_NODE_PERECENT, MR_AM_JOB_CLIENT_PORT_RANGE, MR_AM_JOB_CLIENT_THREAD_COUNT, MR_AM_JOB_NODE_BLACKLISTING_ENABLE, MR_AM_JOB_RECOVERY_ENABLE, MR_AM_JOB_RECOVERY_ENABLE_DEFAULT, MR_AM_JOB_REDUCE_PREEMPTION_LIMIT, MR_AM_JOB_REDUCE_RAMPUP_UP_LIMIT, MR_AM_JOB_SPECULATOR, MR_AM_LOG_BACKUPS, MR_AM_LOG_KB, MR_AM_LOG_LEVEL, MR_AM_MAX_ATTEMPTS, MR_AM_NUM_PROGRESS_SPLITS, MR_AM_PREEMPTION_POLICY, MR_AM_PREFIX, MR_AM_PROFILE, MR_AM_PROFILE_PARAMS, MR_AM_RESOURCE_PREFIX, MR_AM_SECURITY_SERVICE_AUTHORIZATION_CLIENT, MR_AM_SECURITY_SERVICE_AUTHORIZATION_TASK_UMBILICAL, MR_AM_STAGING_DIR, MR_AM_STAGING_DIR_ERASURECODING_ENABLED, MR_AM_TASK_ESTIMATOR, MR_AM_TASK_ESTIMATOR_EXPONENTIAL_RATE_ENABLE, MR_AM_TASK_ESTIMATOR_SIMPLE_SMOOTH_LAMBDA_MS, MR_AM_TASK_ESTIMATOR_SIMPLE_SMOOTH_SKIP_INITIALS, MR_AM_TASK_ESTIMATOR_SIMPLE_SMOOTH_STAGNATED_MS, MR_AM_TASK_ESTIMATOR_SMOOTH_LAMBDA_MS, MR_AM_TASK_LISTENER_THREAD_COUNT, MR_AM_TO_RM_HEARTBEAT_INTERVAL_MS, MR_AM_TO_RM_WAIT_INTERVAL_MS, MR_AM_VMEM_MB, MR_AM_WEBAPP_HTTPS_CLIENT_AUTH, MR_AM_WEBAPP_HTTPS_ENABLED, MR_AM_WEBAPP_PORT_RANGE, MR_APPLICATION_TYPE, MR_CLIENT_JOB_MAX_RETRIES, MR_CLIENT_JOB_RETRY_INTERVAL, MR_CLIENT_MAX_RETRIES, MR_CLIENT_TO_AM_IPC_MAX_RETRIES, MR_CLIENT_TO_AM_IPC_MAX_RETRIES_ON_TIMEOUTS, MR_ENCRYPTED_INTERMEDIATE_DATA, MR_ENCRYPTED_INTERMEDIATE_DATA_BUFFER_KB, MR_ENCRYPTED_INTERMEDIATE_DATA_KEY_SIZE_BITS, MR_JOB_END_NOTIFICATION_CUSTOM_NOTIFIER_CLASS, MR_JOB_END_NOTIFICATION_MAX_ATTEMPTS, MR_JOB_END_NOTIFICATION_MAX_RETRY_INTERVAL, MR_JOB_END_NOTIFICATION_PROXY, MR_JOB_END_NOTIFICATION_TIMEOUT, MR_JOB_END_NOTIFICATION_URL, MR_JOB_END_RETRY_ATTEMPTS, MR_JOB_END_RETRY_INTERVAL, MR_JOB_REDACTED_PROPERTIES, MR_JOB_REDUCER_PREEMPT_DELAY_SEC, MR_JOB_REDUCER_UNCONDITIONAL_PREEMPT_DELAY_SEC, MR_JOB_SEND_TOKEN_CONF, MR_NUM_OPPORTUNISTIC_MAPS_PERCENT, MR_PREFIX, MR_TASK_ENABLE_PING_FOR_LIVELINESS_CHECK, NUM_MAP_PROFILES, NUM_MAPS, NUM_REDUCE_PROFILES, NUM_REDUCES, OUTPUT, OUTPUT_FORMAT_CLASS_ATTR, OUTPUT_KEY_CLASS, OUTPUT_VALUE_CLASS, PARTITIONER_CLASS_ATTR, PRESERVE_FAILED_TASK_FILES, PRESERVE_FILES_PATTERN, PRIORITY, QUEUE_NAME, RECORDS_BEFORE_PROGRESS, REDUCE_CLASS_ATTR, REDUCE_CPU_VCORES, REDUCE_DEBUG_SCRIPT, REDUCE_ENV, REDUCE_FAILURES_MAXPERCENT, REDUCE_INPUT_BUFFER_PERCENT, REDUCE_JAVA_OPTS, REDUCE_LOG_LEVEL, REDUCE_MARKRESET_BUFFER_PERCENT, REDUCE_MARKRESET_BUFFER_SIZE, REDUCE_MAX_ATTEMPTS, REDUCE_MEMORY_MB, REDUCE_MEMORY_TOTAL_BYTES, REDUCE_MEMTOMEM_ENABLED, REDUCE_MEMTOMEM_THRESHOLD, REDUCE_MERGE_INMEM_THRESHOLD, REDUCE_NODE_LABEL_EXP, REDUCE_RESOURCE_TYPE_PREFIX, REDUCE_SEPARATE_SHUFFLE_LOG, REDUCE_SKIP_INCR_PROC_COUNT, REDUCE_SKIP_MAXGROUPS, REDUCE_SPECULATIVE, RESERVATION_ID, RESOURCE_TYPE_ALTERNATIVE_NAME_MEMORY, RESOURCE_TYPE_NAME_MEMORY, RESOURCE_TYPE_NAME_VCORE, SETUP_CLEANUP_NEEDED, SHARED_CACHE_MODE, SHARED_CACHE_MODE_DEFAULT, SHUFFLE_CONNECT_TIMEOUT, SHUFFLE_FETCH_FAILURES, SHUFFLE_FETCH_RETRY_ENABLED, SHUFFLE_FETCH_RETRY_INTERVAL_MS, SHUFFLE_FETCH_RETRY_TIMEOUT_MS, SHUFFLE_INDEX_CACHE, SHUFFLE_INPUT_BUFFER_PERCENT, SHUFFLE_KEY_LENGTH, SHUFFLE_LOG_BACKUPS, SHUFFLE_LOG_KB, SHUFFLE_MEMORY_LIMIT_PERCENT, SHUFFLE_MERGE_PERCENT, SHUFFLE_NOTIFY_READERROR, SHUFFLE_PARALLEL_COPIES, SHUFFLE_READ_TIMEOUT, SKIP_OUTDIR, SKIP_RECORDS, SKIP_START_ATTEMPTS, SPECULATIVE_MINIMUM_ALLOWED_TASKS, SPECULATIVE_RETRY_AFTER_NO_SPECULATE, SPECULATIVE_RETRY_AFTER_SPECULATE, SPECULATIVE_SLOWNODE_THRESHOLD, SPECULATIVE_SLOWTASK_THRESHOLD, SPECULATIVECAP, SPECULATIVECAP_RUNNING_TASKS, SPECULATIVECAP_TOTAL_TASKS, SPILL_FILES_COUNT_LIMIT, SPLIT_FILE, SPLIT_METAINFO_MAXSIZE, STDERR_LOGFILE_ENV, STDOUT_LOGFILE_ENV, TASK_ATTEMPT_ID, TASK_CLEANUP_NEEDED, TASK_DEBUGOUT_LINES, TASK_EXIT_TIMEOUT, TASK_EXIT_TIMEOUT_CHECK_INTERVAL_MS, TASK_EXIT_TIMEOUT_CHECK_INTERVAL_MS_DEFAULT, TASK_EXIT_TIMEOUT_DEFAULT, TASK_ID, TASK_ISMAP, TASK_LOCAL_WRITE_LIMIT_BYTES, TASK_LOG_BACKUPS, TASK_LOG_PROGRESS_DELTA_THRESHOLD, TASK_LOG_PROGRESS_DELTA_THRESHOLD_DEFAULT, TASK_LOG_PROGRESS_WAIT_INTERVAL_SECONDS, TASK_LOG_PROGRESS_WAIT_INTERVAL_SECONDS_DEFAULT, TASK_MAP_PROFILE_PARAMS, TASK_OUTPUT_DIR, TASK_PARTITION, TASK_PREEMPTION, TASK_PROFILE, TASK_PROFILE_PARAMS, TASK_PROGRESS_REPORT_INTERVAL, TASK_REDUCE_PROFILE_PARAMS, TASK_STUCK_TIMEOUT_MS, TASK_TIMEOUT, TASK_TIMEOUT_CHECK_INTERVAL_MS, TASK_USERLOG_LIMIT, USER_NAME, WORKDIR, WORKFLOW_ADJACENCY_PREFIX_PATTERN, WORKFLOW_ADJACENCY_PREFIX_STRING, WORKFLOW_ID, WORKFLOW_NAME, WORKFLOW_NODE_NAME, WORKFLOW_TAGS, WORKING_DIR

Constructor Summary

Constructors

Constructor	Description
NutchJob(Configuration conf, String jobName)	Deprecated. , use instead Job.getInstance(Configuration) or Job.getInstance(Configuration, String).

Method Summary

Modifier and Type	Method	Description
static void	cleanupAfterFailure(Path tempDir, FileSystem fs)	Clean up the file system in case of a job failure.
static void	cleanupAfterFailure(Path tempDir, Path lock, FileSystem fs)	Clean up the file system in case of a job failure.
static String	getJobFailureLogMessage(String name, Job job)	Method to return job failure log message.

Methods inherited from class org.apache.hadoop.mapreduce.Job

addArchiveToClassPath, addArchiveToClassPath, addArchiveToSharedCache, addCacheArchive, addCacheArchive, addCacheFile, addCacheFile, addFileToClassPath, addFileToClassPath, addFileToClassPath, addFileToSharedCache, addFileToSharedCacheAndClasspath, cleanupProgress, close, createSymlink, failTask, getArchiveSharedCacheUploadPolicies, getCluster, getCompletionPollInterval, getCounters, getFileSharedCacheUploadPolicies, getFinishTime, getHistoryUrl, getInstance, getInstance, getInstance, getInstance, getInstance, getInstance, getInstance, getJobFile, getJobName, getJobState, getPriority, getProgressPollInterval, getReservationId, getSchedulingInfo, getStartTime, getStatus, getTaskCompletionEvents, getTaskCompletionEvents, getTaskDiagnostics, getTaskOutputFilter, getTaskReports, getTrackingURL, isComplete, isRetired, isSuccessful, isUber, killJob, killTask, killTask, mapProgress, monitorAndPrintJob, reduceProgress, setArchiveSharedCacheUploadPolicies, setCacheArchives, setCacheArchives, setCacheFiles, setCacheFiles, setCancelDelegationTokenUponJobCompletion, setCombinerClass, setCombinerKeyGroupingComparatorClass, setFileSharedCacheUploadPolicies, setGroupingComparatorClass, setInputFormatClass, setJar, setJarByClass, setJobName, setJobSetupCleanupNeeded, setMapOutputKeyClass, setMapOutputValueClass, setMapperClass, setMapSpeculativeExecution, setMaxMapAttempts, setMaxReduceAttempts, setNumReduceTasks, setOutputFormatClass, setOutputKeyClass, setOutputValueClass, setPartitionerClass, setPriority, setPriorityAsInteger, setProfileEnabled, setProfileParams, setProfileTaskRange, setReducerClass, setReduceSpeculativeExecution, setReservationId, setSortComparatorClass, setSpeculativeExecution, setTaskOutputFilter, setupProgress, setUser, setWorkingDirectory, submit, toString, waitForCompletion

Methods inherited from class org.apache.hadoop.mapreduce.task.JobContextImpl

getArchiveClassPaths, getArchiveClassPaths, getArchiveTimestamps, getArchiveTimestamps, getCacheArchives, getCacheArchives, getCacheFiles, getCacheFiles, getCombinerClass, getCombinerKeyGroupingComparator, getConfiguration, getCredentials, getFileClassPaths, getFileClassPaths, getFileTimestamps, getFileTimestamps, getGroupingComparator, getInputFormatClass, getJar, getJobID, getJobSetupCleanupNeeded, getLocalCacheArchives, getLocalCacheArchives, getLocalCacheFiles, getLocalCacheFiles, getMapOutputKeyClass, getMapOutputValueClass, getMapperClass, getMaxMapAttempts, getMaxReduceAttempts, getNumReduceTasks, getOutputFormatClass, getOutputKeyClass, getOutputValueClass, getPartitionerClass, getProfileEnabled, getProfileParams, getProfileTaskRange, getReducerClass, getSortComparator, getSymlink, getTaskCleanupNeeded, getUser, getWorkingDirectory, setJobID

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, wait

Methods inherited from interface org.apache.hadoop.mapreduce.JobContext

getArchiveClassPaths, getArchiveTimestamps, getCacheArchives, getCacheFiles, getCombinerClass, getCombinerKeyGroupingComparator, getConfiguration, getCredentials, getFileClassPaths, getFileTimestamps, getGroupingComparator, getInputFormatClass, getJar, getJobID, getJobSetupCleanupNeeded, getLocalCacheArchives, getLocalCacheFiles, getMapOutputKeyClass, getMapOutputValueClass, getMapperClass, getMaxMapAttempts, getMaxReduceAttempts, getNumReduceTasks, getOutputFormatClass, getOutputKeyClass, getOutputValueClass, getPartitionerClass, getProfileEnabled, getProfileParams, getProfileTaskRange, getReducerClass, getSortComparator, getSymlink, getTaskCleanupNeeded, getUser, getWorkingDirectory

Constructor Details

NutchJob

@Deprecated
public NutchJob(Configuration conf,
 String jobName)
         throws IOException

Deprecated.

, use instead Job.getInstance(Configuration) or Job.getInstance(Configuration, String).

Parameters:

conf - configuration for the job

jobName - name of the job

Throws:

IOException - see Job(Configuration, String)

Method Details

cleanupAfterFailure

public static void cleanupAfterFailure(Path tempDir,
 FileSystem fs)
                                throws IOException

Clean up the file system in case of a job failure.

Parameters:

tempDir - The temporary directory which needs to be deleted/cleaned-up.

fs - The FileSystem on which the tempDir resides.

Throws:

IOException - Occurs if there is fatal I/O error whilst performing the cleanup.

cleanupAfterFailure

public static void cleanupAfterFailure(Path tempDir,
 Path lock,
 FileSystem fs)
                                throws IOException

Clean up the file system in case of a job failure.

Parameters:

tempDir - The temporary directory which needs to be deleted/cleaned-up.

lock - A lockfile if one exists.

fs - The FileSystem on which the tempDir resides.

Throws:

IOException - Occurs if there is fatal I/O error whilst performing the cleanup.

See Also:

• LockUtil.removeLockFile(FileSystem, Path)

getJobFailureLogMessage

public static String getJobFailureLogMessage(String name,
 Job job)
                                      throws IOException,
InterruptedException

Method to return job failure log message. To be used across all Jobs

Parameters:

name - Name/Type of the job

job - Job Object for Job details

Returns:

job failure log message

Throws:

IOException - Can occur during fetching job status

InterruptedException - Can occur during fetching job status