16/11/04 11:05:52 ERROR Executor: Exception in task 0.0 in stage 0.0 (TID 0) java.lang.OutOfMemoryError: GC overhead limit exceeded at java.util.Arrays.copyOfRange(Arrays.java:3664) at java.lang.String.<init>(String.java:201) at org.apache.xerces.xni.XMLString.toString(Unknown Source) at org.apache.xerces.parsers.AbstractDOMParser.characters(Unknown Source) at org.apache.xerces.xinclude.XIncludeHandler.characters(Unknown Source) at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl.scanContent(Unknown Source) at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl$FragmentContentDispatcher.dispatch(Unknown Source) at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl.scanDocument(Unknown Source) at org.apache.xerces.parsers.XML11Configuration.parse(Unknown Source) at org.apache.xerces.parsers.XML11Configuration.parse(Unknown Source) at org.apache.xerces.parsers.XMLParser.parse(Unknown Source) at org.apache.xerces.parsers.DOMParser.parse(Unknown Source) at org.apache.xerces.jaxp.DocumentBuilderImpl.parse(Unknown Source) at javax.xml.parsers.DocumentBuilder.parse(DocumentBuilder.java:150) at org.apache.hadoop.conf.Configuration.parse(Configuration.java:2352) at org.apache.hadoop.conf.Configuration.parse(Configuration.java:2340) at org.apache.hadoop.conf.Configuration.loadResource(Configuration.java:2411) at org.apache.hadoop.conf.Configuration.loadResources(Configuration.java:2364) at org.apache.hadoop.conf.Configuration.getProps(Configuration.java:2281) at org.apache.hadoop.conf.Configuration.get(Configuration.java:888) at org.apache.hadoop.io.compress.CompressionCodecFactory.getCodecClasses(CompressionCodecFactory.java:121) at org.apache.hadoop.io.compress.CompressionCodecFactory.<init>(CompressionCodecFactory.java:175) at org.apache.spark.input.WholeTextFileRecordReader.nextKeyValue(WholeTextFileRecordReader.scala:77) at org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader.nextKeyValue(CombineFileRecordReader.java:69) at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:168) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) 16/11/04 11:05:56 ERROR SparkUncaughtExceptionHandler: Uncaught exception in thread Thread[Executor task launch worker-0,5,main] java.lang.OutOfMemoryError: GC overhead limit exceeded at java.util.Arrays.copyOfRange(Arrays.java:3664) at java.lang.String.<init>(String.java:201) at org.apache.xerces.xni.XMLString.toString(Unknown Source) at org.apache.xerces.parsers.AbstractDOMParser.characters(Unknown Source) at org.apache.xerces.xinclude.XIncludeHandler.characters(Unknown Source) at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl.scanContent(Unknown Source) at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl$FragmentContentDispatcher.dispatch(Unknown Source) at org.apache.xerces.impl.XMLDocumentFragmentScannerImpl.scanDocument(Unknown Source) at org.apache.xerces.parsers.XML11Configuration.parse(Unknown Source) at org.apache.xerces.parsers.XML11Configuration.parse(Unknown Source) at org.apache.xerces.parsers.XMLParser.parse(Unknown Source) at org.apache.xerces.parsers.DOMParser.parse(Unknown Source) at org.apache.xerces.jaxp.DocumentBuilderImpl.parse(Unknown Source) at javax.xml.parsers.DocumentBuilder.parse(DocumentBuilder.java:150) at org.apache.hadoop.conf.Configuration.parse(Configuration.java:2352) at org.apache.hadoop.conf.Configuration.parse(Configuration.java:2340) at org.apache.hadoop.conf.Configuration.loadResource(Configuration.java:2411) at org.apache.hadoop.conf.Configuration.loadResources(Configuration.java:2364) at org.apache.hadoop.conf.Configuration.getProps(Configuration.java:2281) at org.apache.hadoop.conf.Configuration.get(Configuration.java:888) at org.apache.hadoop.io.compress.CompressionCodecFactory.getCodecClasses(CompressionCodecFactory.java:121) at org.apache.hadoop.io.compress.CompressionCodecFactory.<init>(CompressionCodecFactory.java:175) at org.apache.spark.input.WholeTextFileRecordReader.nextKeyValue(WholeTextFileRecordReader.scala:77) at org.apache.hadoop.mapreduce.lib.input.CombineFileRecordReader.nextKeyValue(CombineFileRecordReader.java:69) at org.apache.spark.rdd.NewHadoopRDD$$anon$1.hasNext(NewHadoopRDD.scala:168) at org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327) at scala.collection.Iterator$class.foreach(Iterator.scala:727) at scala.collection.AbstractIterator.foreach(Iterator.scala:1157) at scala.collection.generic.Growable$class.$plus$plus$eq(Growable.scala:48) 16/11/04 11:05:56 INFO DiskBlockManager: Shutdown hook called