Hi All,
I'm getting the following Error in between a sapcrk job is running. actually I'm trying to migrate data from Hadoop cluster-A and Hadoop cluster-B. Im migrating Around 10000 Partitions per Job, the problem here is my job is throwing Error when it crossed half way. please find the following Error and let me know how to Resolve this.
18/07/09 20:49:54 WARN TaskSetManager: Lost task 1.0 in stage 882.0 (TID 1902, DNSName, executor 1): java.net.UnknownHostException: HostName:50075: HostName
at java.net.AbstractPlainSocketImpl.connect(AbstractPlainSocketImpl.java:184)
at java.net.SocksSocketImpl.connect(SocksSocketImpl.java:392)
at java.net.Socket.connect(Socket.java:589)
at sun.net.NetworkClient.doConnect(NetworkClient.java:175)
at sun.net.www.http.HttpClient.openServer(HttpClient.java:432)
at sun.net.www.http.HttpClient.openServer(HttpClient.java:527)
at sun.net.www.http.HttpClient.<init>(HttpClient.java:211)
at sun.net.www.http.HttpClient.New(HttpClient.java:308)
at sun.net.www.http.HttpClient.New(HttpClient.java:326)
at sun.net.www.protocol.http.HttpURLConnection.getNewHttpClient(HttpURLConnection.java:1168)
at sun.net.www.protocol.http.HttpURLConnection.plainConnect0(HttpURLConnection.java:1104)
at sun.net.www.protocol.http.HttpURLConnection.plainConnect(HttpURLConnection.java:998)
at sun.net.www.protocol.http.HttpURLConnection.connect(HttpURLConnection.java:932)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$AbstractRunner.connect(WebHdfsFileSystem.java:595)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$AbstractRunner.connect(WebHdfsFileSystem.java:552)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$ReadRunner.connect(WebHdfsFileSystem.java:1710)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$AbstractRunner.runWithRetry(WebHdfsFileSystem.java:620)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$AbstractRunner.access$100(WebHdfsFileSystem.java:472)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$AbstractRunner$1.run(WebHdfsFileSystem.java:502)
at java.security.AccessController.doPrivileged(Native Method)
at javax.security.auth.Subject.doAs(Subject.java:422)
at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1698)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$AbstractRunner.run(WebHdfsFileSystem.java:498)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$ReadRunner.read(WebHdfsFileSystem.java:1659)
at org.apache.hadoop.hdfs.web.WebHdfsFileSystem$WebHdfsInputStream.read(WebHdfsFileSystem.java:1520)
at java.io.DataInputStream.readFully(DataInputStream.java:195)
at java.io.DataInputStream.readFully(DataInputStream.java:169)
at org.apache.hadoop.io.SequenceFile$Reader.init(SequenceFile.java:1915)
at org.apache.hadoop.io.SequenceFile$Reader.initialize(SequenceFile.java:1880)
at org.apache.hadoop.io.SequenceFile$Reader.<init>(SequenceFile.java:1829)
at org.apache.hadoop.io.SequenceFile$Reader.<init>(SequenceFile.java:1843)
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.liftedTree1$1(HadoopRDD.scala:251)
at org.apache.spark.rdd.HadoopRDD$anon$1.<init>(HadoopRDD.scala:250)
at org.apache.spark.rdd.HadoopRDD.compute(HadoopRDD.scala:208)
at org.apache.spark.rdd.HadoopRDD.compute(HadoopRDD.scala:94)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:323)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:287)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:96)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:53)
at org.apache.spark.scheduler.Task.run(Task.scala:108)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:338)
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:745)
Tanx and Regards,
MJ
