問題：
Caused by: java.util.concurrent.ExecutionException: java.lang.IndexOutOfBoundsException: Index: 0
at java.util.concurrent.FutureTask.report(FutureTask.java:122)
at java.util.concurrent.FutureTask.get(FutureTask.java:192)
at org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.generateSplitsInfo(OrcInputFormat.java:1016)
... 65 more
Caused by: java.lang.IndexOutOfBoundsException: Index: 0
at java.util.Collections$EmptyList.get(Collections.java:4454)
at org.apache.hadoop.hive.ql.io.orc.OrcProto$Type.getSubtypes(OrcProto.java:12240)
at org.apache.hadoop.hive.ql.io.orc.ReaderImpl.getColumnIndicesFromNames(ReaderImpl.java:651)
at org.apache.hadoop.hive.ql.io.orc.ReaderImpl.getRawDataSizeOfColumns(ReaderImpl.java:634)
at org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$SplitGenerator.populateAndCacheStripeDetails(OrcInputFormat.java:927)
at org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$SplitGenerator.call(OrcInputFormat.java:836)
at org.apache.hadoop.hive.ql.io.orc.OrcInputFormat$SplitGenerator.call(OrcInputFormat.java:702)
at java.util.concurrent.FutureTask.run(FutureTask.java:266)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:748)
java.lang.RuntimeException: serious problem
at org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.generateSplitsInfo(OrcInputFormat.java:1021)
at org.apache.hadoop.hive.ql.io.orc.OrcInputFormat.getSplits(OrcInputFormat.java:1048)
at org.apache.spark.rdd.HadoopRDD.getPartitions(HadoopRDD.scala:200)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
at org.apache.spark.rdd.RDD.partitions(RDD.scala:251)
at org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:46)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:253)
at org.apache.spark.rdd.RDD$$anonfun$partitions$2.apply(RDD.scala:251)
at scala.Option.getOrElse(Option.scala:121)
原因：
sparksql生成的hive表有空文件，但是sparksql讀取空文件的時候，因為表示orc格式的，導致sparksql解析orc文件出錯。但是用hive卻可以正常讀取。
解決辦法：
設置set spark.sql.hive.convertMetastoreOrc=true
單純的設置以上參數還是會報錯：
java.lang.IndexOutOfBoundsException
at java.nio.Buffer.checkIndex(Buffer.java:540)
at java.nio.HeapByteBuffer.get(HeapByteBuffer.java:139)
at org.apache.hadoop.hive.ql.io.orc.ReaderImpl.extractMetaInfoFromFooter(ReaderImpl.java:374)
at org.apache.hadoop.hive.ql.io.orc.ReaderImpl.<init>(ReaderImpl.java:316)
at org.apache.hadoop.hive.ql.io.orc.OrcFile.createReader(OrcFile.java:187)
at org.apache.spark.sql.hive.orc.OrcFileOperator$$anonfun$getFileReader$2.apply(OrcFileOperator.scala:75)
at org.apache.spark.sql.hive.orc.OrcFileOperator$$anonfun$getFileReader$2.apply(OrcFileOperator.scala:73)
at scala.collection.Iterator$$anon$11.next(Iterator.scala:409)
at scala.collection.TraversableOnce$class.collectFirst(TraversableOnce.scala:145)
at scala.collection.AbstractIterator.collectFirst(Iterator.scala:1336)
at org.apache.spark.sql.hive.orc.OrcFileOperator$.getFileReader(OrcFileOperator.scala:86)
at org.apache.spark.sql.hive.orc.OrcFileOperator$$anonfun$readSchema$1.apply(OrcFileOperator.scala:95)
at org.apache.spark.sql.hive.orc.OrcFileOperator$$anonfun$readSchema$1.apply(OrcFileOperator.scala:95)
at scala.collection.immutable.Stream.flatMap(Stream.scala:489)
需要再設置set spark.sql.orc.impl=native
參考https://issues.apache.org/jira/browse/SPARK-19809