public class Hadoop2TezFlow extends BaseFlow<org.apache.tez.dag.api.TezConfiguration>
Flow
.
HadoopFlow must be created through a Hadoop2TezFlowConnector
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.Hadoop2TezFlowConnector
BaseFlow.FlowHolder
completed, flowCanonicalHash, flowDescriptor, flowElementGraph, flowStats, flowStepGraph, platformInfo, sinks, sources, steps, stop, stopJobsOnExit, thread, throwable
CASCADING_FLOW_ID
NULL
Modifier | Constructor and Description |
---|---|
protected |
Hadoop2TezFlow() |
|
Hadoop2TezFlow(PlatformInfo platformInfo,
Map<Object,Object> properties,
org.apache.tez.dag.api.TezConfiguration flowConf,
FlowDef flowDef) |
Modifier and Type | Method and Description |
---|---|
org.apache.tez.dag.api.TezConfiguration |
getConfig() |
Map<Object,Object> |
getConfigAsProperties() |
org.apache.tez.dag.api.TezConfiguration |
getConfigCopy() |
FlowProcess<org.apache.tez.dag.api.TezConfiguration> |
getFlowProcess() |
String |
getFlowStagingPath() |
protected int |
getMaxNumParallelSteps() |
String |
getProperty(String key)
Method getProperty returns the value associated with the given key from the underlying properties system.
|
protected long |
getTotalSliceCPUMilliSeconds() |
protected void |
initConfig(Map<Object,Object> properties,
org.apache.tez.dag.api.TezConfiguration parentConfig) |
protected void |
initFromProperties(Map<Object,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.tez.dag.api.TezConfiguration |
newConfig(org.apache.tez.dag.api.TezConfiguration defaultConfig) |
protected void |
setConfigProperty(org.apache.tez.dag.api.TezConfiguration config,
Object key,
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, 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, writeStepsDOT
protected Hadoop2TezFlow()
public Hadoop2TezFlow(PlatformInfo platformInfo, Map<Object,Object> properties, org.apache.tez.dag.api.TezConfiguration flowConf, FlowDef flowDef)
protected void initFromProperties(Map<Object,Object> properties)
initFromProperties
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
protected void initConfig(Map<Object,Object> properties, org.apache.tez.dag.api.TezConfiguration parentConfig)
initConfig
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
public String getFlowStagingPath()
protected void setConfigProperty(org.apache.tez.dag.api.TezConfiguration config, Object key, Object value)
setConfigProperty
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
protected org.apache.tez.dag.api.TezConfiguration newConfig(org.apache.tez.dag.api.TezConfiguration defaultConfig)
@ProcessConfiguration public org.apache.tez.dag.api.TezConfiguration getConfig()
public org.apache.tez.dag.api.TezConfiguration getConfigCopy()
public Map<Object,Object> getConfigAsProperties()
public String getProperty(String key)
key
- of type Stringpublic FlowProcess<org.apache.tez.dag.api.TezConfiguration> getFlowProcess()
public boolean isPreserveTemporaryFiles()
protected void internalStart()
internalStart
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
public boolean stepsAreLocal()
protected void internalClean(boolean stop)
internalClean
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
protected void internalShutdown()
internalShutdown
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
protected int getMaxNumParallelSteps()
getMaxNumParallelSteps
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
protected long getTotalSliceCPUMilliSeconds()
getTotalSliceCPUMilliSeconds
in class BaseFlow<org.apache.tez.dag.api.TezConfiguration>
Copyright © 2007-2015 Xplenty, Inc. All Rights Reserved.