Answered my own question: http://stackoverflow.com/questions/33030559/hadoop-2-6-1-java-lang-nullpointerexception-at-org-apache-hadoop-hdfs-dfsoutputs
Versioning inconsistency between Hadoop versions was causing this. On 3/17/16, 10:52 AM, "Ganelin, Ilya" <[email protected]> wrote: >Hi all , would appreciate some insight into the below error when attempting to >stream data out to HDFS. The output operator is pasted below the error. > >2016-03-17 10:48:02,197 [8/DurabilityOut_HDHT:HdfsFileOutputOperator] ERROR >engine.StreamingContainer run - Operator set >[OperatorDeployInfo[id=8,name=DurabilityOut_HDHT,type=GENERIC,checkpoint={ffffffffffffffff, > 0, >0},inputs=[OperatorDeployInfo.InputDeployInfo[portName=input,streamId=Records >-:- >Durability_HDHT,sourceNodeId=2,sourcePortName=recordHash,locality=<null>,partitionMask=0,partitionKeys=<null>]],outputs=[]]] > stopped running due to an exception. >com.google.common.util.concurrent.UncheckedExecutionException: >java.lang.NullPointerException >at com.google.common.cache.LocalCache$Segment.get(LocalCache.java:2234) >at com.google.common.cache.LocalCache.get(LocalCache.java:3965) >at com.google.common.cache.LocalCache.getOrLoad(LocalCache.java:3969) >at >com.google.common.cache.LocalCache$LocalManualCache.get(LocalCache.java:4829) >at >com.datatorrent.lib.io.fs.AbstractFileOutputOperator.processTuple(AbstractFileOutputOperator.java:796) >at >com.datatorrent.lib.io.fs.AbstractFileOutputOperator$1.process(AbstractFileOutputOperator.java:270) >at com.datatorrent.api.DefaultInputPort.put(DefaultInputPort.java:70) >at >com.datatorrent.stram.stream.BufferServerSubscriber$BufferReservoir.sweep(BufferServerSubscriber.java:265) >at com.datatorrent.stram.engine.GenericNode.run(GenericNode.java:229) >at >com.datatorrent.stram.engine.StreamingContainer$2.run(StreamingContainer.java:1380) >Caused by: java.lang.NullPointerException >at >org.apache.hadoop.hdfs.DFSOutputStream.isLazyPersist(DFSOutputStream.java:1709) >at >org.apache.hadoop.hdfs.DFSOutputStream.getChecksum4Compute(DFSOutputStream.java:1550) >at org.apache.hadoop.hdfs.DFSOutputStream.<init>(DFSOutputStream.java:1560) >at org.apache.hadoop.hdfs.DFSOutputStream.<init>(DFSOutputStream.java:1667) >at >org.apache.hadoop.hdfs.DFSOutputStream.newStreamForAppend(DFSOutputStream.java:1694) >at org.apache.hadoop.hdfs.DFSClient.callAppend(DFSClient.java:1824) >at org.apache.hadoop.hdfs.DFSClient.append(DFSClient.java:1885) >at org.apache.hadoop.hdfs.DFSClient.append(DFSClient.java:1855) >at >org.apache.hadoop.hdfs.DistributedFileSystem$4.doCall(DistributedFileSystem.java:340) >at >org.apache.hadoop.hdfs.DistributedFileSystem$4.doCall(DistributedFileSystem.java:336) >at >org.apache.hadoop.fs.FileSystemLinkResolver.resolve(FileSystemLinkResolver.java:81) >at >org.apache.hadoop.hdfs.DistributedFileSystem.append(DistributedFileSystem.java:348) >at >org.apache.hadoop.hdfs.DistributedFileSystem.append(DistributedFileSystem.java:318) >at org.apache.hadoop.fs.FileSystem.append(FileSystem.java:1164) >at >com.datatorrent.lib.io.fs.AbstractFileOutputOperator.openStream(AbstractFileOutputOperator.java:641) >at >com.datatorrent.lib.io.fs.AbstractFileOutputOperator$2.load(AbstractFileOutputOperator.java:550) >at >com.datatorrent.lib.io.fs.AbstractFileOutputOperator$2.load(AbstractFileOutputOperator.java:504) >at >com.google.common.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3568) >at com.google.common.cache.LocalCache$Segment.loadSync(LocalCache.java:2350) >at >com.google.common.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2313) >at com.google.common.cache.LocalCache$Segment.get(LocalCache.java:2228) > >package com.capitalone.vault8.citadel.operators.impl; > >import com.datatorrent.api.Context; >import com.datatorrent.lib.io.fs.AbstractFileOutputOperator; > >import org.apache.hadoop.conf.Configuration; >import org.apache.hadoop.fs.FileSystem; >import org.apache.hadoop.fs.LocalFileSystem; >import org.apache.hadoop.fs.Path; >import org.slf4j.Logger; >import org.slf4j.LoggerFactory; > >import java.io.BufferedReader; >import java.io.IOException; > >/** > * Ingest a file, and emit it timestamped (line-by-line) into Apex. <p/> <a > * href="mailto:[email protected]";>Vault 8</a> > * > * @author Vault 8 > */ >public class HdfsFileOutputOperator extends AbstractFileOutputOperator<String> >{ > transient BufferedReader br = null; > private static Logger LOG = > LoggerFactory.getLogger(HdfsFileOutputOperator.class.toString()); > > private static String idDelim = "@"; > private String coreSite; > private String hdfsSite; > private String outputFileName; > > private transient int operatorId; > > // Because every operator may have multiple physical partitions, we should > organize the data by > // partition > private transient String operatorUniquePath; > > public String getHdfsSite() { > return hdfsSite; > } > > public void setHdfsSite(String hdfsSite) { > this.hdfsSite = hdfsSite; > } > > public String getCoreSite() { > return coreSite; > } > > public void setCoreSite(String coreSite) { > this.coreSite = coreSite; > } > > // Set the actual name of the file on HDFS > public void setOutputFileName(String outputFileName) { > this.outputFileName = outputFileName; > } > > // Get the name of of the file > public String getOutputFileName() { > return outputFileName; > } > > // Override method to get the absolute path for the output > @Override > protected String getFileName(String tuple) { > return operatorUniquePath; > } > > @Override > public void setup(Context.OperatorContext context) { > super.setup(context); > operatorId = context.getId(); > operatorUniquePath = new Path(getOutputFileName() + idDelim + operatorId + > ".txt").toString(); > } > > /** > * This method is used to provide the FileSystem for the operator. This > allows us to use HDFS > */ > @Override > protected FileSystem getFSInstance() throws IOException { > Configuration config = new Configuration(); > // Update the configuration here > try { > config.addResource(new Path(getCoreSite())); > config.addResource(new Path(getHdfsSite())); > } catch (IllegalArgumentException e) { > LOG.warn("Tried to create an empty path ", e); > } > > FileSystem tempFS = FileSystem.newInstance(new Path(filePath).toUri(), > config); > > if (tempFS instanceof LocalFileSystem) { > tempFS = ((LocalFileSystem) tempFS).getRaw(); > } > > return tempFS; > } > > > @Override > protected byte[] getBytesForTuple(String tuple) { > return tuple.getBytes(); > } >} >________________________________________________________ > >The information contained in this e-mail is confidential and/or proprietary to >Capital One and/or its affiliates and may only be used solely in performance >of work or services for Capital One. The information transmitted herewith is >intended only for use by the individual or entity to which it is addressed. If >the reader of this message is not the intended recipient, you are hereby >notified that any review, retransmission, dissemination, distribution, copying >or other use of, or taking of any action in reliance upon this information is >strictly prohibited. If you have received this communication in error, please >contact the sender and delete the material from your computer. ________________________________________________________ The information contained in this e-mail is confidential and/or proprietary to Capital One and/or its affiliates and may only be used solely in performance of work or services for Capital One. The information transmitted herewith is intended only for use by the individual or entity to which it is addressed. If the reader of this message is not the intended recipient, you are hereby notified that any review, retransmission, dissemination, distribution, copying or other use of, or taking of any action in reliance upon this information is strictly prohibited. If you have received this communication in error, please contact the sender and delete the material from your computer.
