diff --git a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala index 2bb6d91d04b271ea137afbaf301461cdfa47632e..95224282f6d614d16d483fe89926a3a31ccacc44 100644 --- a/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala +++ b/streaming/src/main/scala/org/apache/spark/streaming/dstream/FileInputDStream.scala @@ -114,6 +114,13 @@ class FileInputDStream[K: ClassTag, V: ClassTag, F <: NewInputFormat[K,V] : Clas /** Generate one RDD from an array of files */ private def filesToRDD(files: Seq[String]): RDD[(K, V)] = { val fileRDDs = files.map(file => context.sparkContext.newAPIHadoopFile[K, V, F](file)) + files.zip(fileRDDs).foreach { case (file, rdd) => { + if (rdd.partitions.size == 0) { + logWarning("File " + file + " has no data in it. Are you sure you are following " + + "the move-based method of adding input files? Refer to the programming guide " + + "for more details.") + } + }} new UnionRDD(context.sparkContext, fileRDDs) }