public class HadoopFlow extends cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>
Flow.
HadoopFlow must be created through a FlowConnector sub-class instance.
If classpath paths are provided on the FlowDef, the Hadoop distributed cache mechanism will be used
to augment the remote classpath.
Any path elements that are relative will be uploaded to HDFS, and the HDFS URI will be used on the JobConf. Note all paths are added as "files" to the JobConf, not archives, so they aren't needlessly uncompressed cluster side.
FlowConnector| Modifier | Constructor and Description |
|---|---|
protected |
HadoopFlow() |
|
HadoopFlow(cascading.flow.planner.PlatformInfo platformInfo,
java.util.Map<java.lang.Object,java.lang.Object> properties,
org.apache.hadoop.mapred.JobConf jobConf,
cascading.flow.FlowDef flowDef) |
protected |
HadoopFlow(cascading.flow.planner.PlatformInfo platformInfo,
java.util.Map<java.lang.Object,java.lang.Object> properties,
org.apache.hadoop.mapred.JobConf jobConf,
java.lang.String name,
java.util.Map<java.lang.String,java.lang.String> flowDescriptor) |
| Modifier and Type | Method and Description |
|---|---|
protected void |
copyToDistributedCache() |
org.apache.hadoop.mapred.JobConf |
getConfig() |
java.util.Map<java.lang.Object,java.lang.Object> |
getConfigAsProperties() |
org.apache.hadoop.mapred.JobConf |
getConfigCopy() |
cascading.flow.FlowProcess<org.apache.hadoop.mapred.JobConf> |
getFlowProcess() |
protected int |
getMaxNumParallelSteps() |
java.lang.String |
getProperty(java.lang.String key)
Method getProperty returns the value associated with the given key from the underlying properties system.
|
protected long |
getTotalSliceCPUMilliSeconds() |
protected void |
initConfig(java.util.Map<java.lang.Object,java.lang.Object> properties,
org.apache.hadoop.mapred.JobConf parentConfig) |
protected void |
initFromProperties(java.util.Map<java.lang.Object,java.lang.Object> properties) |
protected void |
internalClean(boolean stop) |
protected void |
internalShutdown() |
protected void |
internalStart() |
boolean |
isPreserveTemporaryFiles()
Method isPreserveTemporaryFiles returns false if temporary files will be cleaned when this Flow completes.
|
protected org.apache.hadoop.mapred.JobConf |
newConfig(org.apache.hadoop.mapred.JobConf defaultConfig) |
protected void |
registerHadoopShutdownHook() |
protected void |
setConfigProperty(org.apache.hadoop.mapred.JobConf config,
java.lang.Object key,
java.lang.Object value) |
boolean |
stepsAreLocal() |
addListener, addPlannerProperties, addSessionProperties, addStepListener, areSinksStale, areSourcesNewer, cleanup, complete, createConfig, createFlowCanonicalHash, createFlowStats, createFlowThread, createPrepareFlowStats, deleteCheckpointsIfNotUpdate, deleteCheckpointsIfReplace, deleteSinks, deleteSinksIfNotUpdate, deleteSinksIfReplace, deleteTrapsIfNotUpdate, deleteTrapsIfReplace, fireOnCompleted, fireOnStarting, fireOnStopping, fireOnThrowable, fireOnThrowable, getCascadeID, getCascadingServices, getCheckpointNames, getCheckpoints, getCheckpointsCollection, getClassPath, getClientState, getEligibleJobsSize, getFieldsFor, getFlowCanonicalHash, getFlowDescriptor, getFlowElementGraph, getFlowSession, getFlowSkipStrategy, getFlowStats, getFlowStepGraph, getFlowSteps, getFlowStepStrategy, getHolder, getID, getJobMapCallables, getName, getPlannerInfo, getPlatformInfo, getRunID, getSink, getSink, getSinkModified, getSinkNames, getSinks, getSinksCollection, getSource, getSourceNames, getSources, getSourcesCollection, getSpawnStrategy, getStats, getSubmitPriority, getTags, getTrapNames, getTraps, getTrapsCollection, handleExecutorShutdown, hasListeners, hasStepListeners, ifStoppingBlockUntilComplete, initialize, initializeChildStats, initializeNewJobsMap, initSteps, internalStopAllJobs, isDebugEnabled, isInfoEnabled, isJobsMapInitialized, isSkipFlow, isStopJobsOnExit, logDebug, logError, logError, logInfo, logWarn, logWarn, logWarn, openSink, openSink, openSource, openSource, openTapForRead, openTapForWrite, openTrap, openTrap, prepare, presentSinkFields, presentSourceFields, registerShutdownHook, removeListener, removeListeners, removeStepListener, resourceExists, retrieveSinkFields, retrieveSourceFields, setCascade, setCheckpoints, setFlowElementGraph, setFlowSkipStrategy, setFlowStepGraph, setFlowStepStrategy, setName, setPlannerInfo, setSinks, setSources, setSpawnStrategy, setSubmitPriority, setTraps, spawnSteps, start, stop, toString, updateJobsMap, updateSchemes, writeDOT, writeStepsDOTclone, equals, finalize, getClass, hashCode, notify, notifyAll, wait, wait, waitgetSinkEntryStream, getSinkEntryStream, getSinkEntryStream, getSinkEntryStream, getSinkEntryStreamCopy, getSinkEntryStreamCopy, getSinkEntryStreamCopy, getSinkEntryStreamCopy, getSinkTupleStream, getSinkTupleStream, getSinkTupleStream, getSinkTupleStream, getSinkTupleStreamCopy, getSinkTupleStreamCopy, getSinkTupleStreamCopy, getSinkTupleStreamCopy, getSourceEntryStream, getSourceEntryStream, getSourceEntryStreamCopy, getSourceEntryStreamCopy, getSourceTupleStream, getSourceTupleStream, getSourceTupleStreamCopy, getSourceTupleStreamCopyprotected HadoopFlow()
protected HadoopFlow(cascading.flow.planner.PlatformInfo platformInfo, java.util.Map<java.lang.Object,java.lang.Object> properties, org.apache.hadoop.mapred.JobConf jobConf, java.lang.String name, java.util.Map<java.lang.String,java.lang.String> flowDescriptor)
public HadoopFlow(cascading.flow.planner.PlatformInfo platformInfo, java.util.Map<java.lang.Object,java.lang.Object> properties, org.apache.hadoop.mapred.JobConf jobConf, cascading.flow.FlowDef flowDef)
protected void initFromProperties(java.util.Map<java.lang.Object,java.lang.Object> properties)
initFromProperties in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected void initConfig(java.util.Map<java.lang.Object,java.lang.Object> properties, org.apache.hadoop.mapred.JobConf parentConfig)
initConfig in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected void setConfigProperty(org.apache.hadoop.mapred.JobConf config, java.lang.Object key, java.lang.Object value)
setConfigProperty in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected org.apache.hadoop.mapred.JobConf newConfig(org.apache.hadoop.mapred.JobConf defaultConfig)
newConfig in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>@ProcessConfiguration public org.apache.hadoop.mapred.JobConf getConfig()
public org.apache.hadoop.mapred.JobConf getConfigCopy()
public java.util.Map<java.lang.Object,java.lang.Object> getConfigAsProperties()
public java.lang.String getProperty(java.lang.String key)
key - of type Stringpublic cascading.flow.FlowProcess<org.apache.hadoop.mapred.JobConf> getFlowProcess()
public boolean isPreserveTemporaryFiles()
protected void internalStart()
internalStart in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected void registerHadoopShutdownHook()
protected void copyToDistributedCache()
public boolean stepsAreLocal()
protected void internalClean(boolean stop)
internalClean in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected void internalShutdown()
internalShutdown in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected int getMaxNumParallelSteps()
getMaxNumParallelSteps in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>protected long getTotalSliceCPUMilliSeconds()
getTotalSliceCPUMilliSeconds in class cascading.flow.BaseFlow<org.apache.hadoop.mapred.JobConf>Copyright © 2007-2021 Cascading Maintainers. All Rights Reserved.