Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 1.0 failed 4 times,
most recent failure: Lost task 0.3 in stage 1.0 (TID 7, node3): java.lang.RuntimeException: native snappy library not available: this version of libhadoop was built without snappy support.
at org.apache.hadoop.io.compress.SnappyCodec.checkNativeCodeLoaded(SnappyCodec.java:65)
at org.apache.hadoop.io.compress.SnappyCodec.getDecompressorType(SnappyCodec.java:193)
at org.apache.hadoop.io.compress.CodecPool.getDecompressor(CodecPool.java:178)
at org.apache.hadoop.io.SequenceFile$Reader.init(SequenceFile.java:1918)
at org.apache.hadoop.io.SequenceFile$Reader.initialize(SequenceFile.java:1813)
at org.apache.hadoop.io.SequenceFile$Reader.<init>(SequenceFile.java:1762)
at org.apache.hadoop.io.SequenceFile$Reader.<init>(SequenceFile.java:1776)
at org.apache.hadoop.mapred.SequenceFileRecordReader.<init>(SequenceFileRecordReader.java:49)
at org.apache.hadoop.mapred.SequenceFileInputFormat.getRecordReader(SequenceFileInputFormat.java:64)
at org.apache.spark.rdd.HadoopRDD$$anon$1.<init>(HadoopRDD.scala:239)
at org.apache.spark.rdd.HadoopRDD.compute(HadoopRDD.scala:216)
at org.apache.spark.rdd.HadoopRDD.compute(HadoopRDD.scala:101)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:277)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:244)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
.........