python pysparkStreaming.py

Ivy Default Cache set to: /Users/nlakshma/.ivy2/cache
The jars for the packages stored in: /Users/nlakshma/.ivy2/jars
:: loading settings :: url = jar:file:/usr/local/lib/python3.6/site-packages/pyspark/jars/ivy-2.4.0.jar!/org/apache/ivy/core/settings/ivysettings.xml
org.apache.spark#spark-streaming-kafka-0-8_2.11 added as a dependency
:: resolving dependencies :: org.apache.spark#spark-submit-parent;1.0
confs: [default]
found org.apache.spark#spark-streaming-kafka-0-8_2.11;2.0.2 in central
found org.apache.kafka#kafka_2.11;0.8.2.1 in central
found org.scala-lang.modules#scala-xml_2.11;1.0.2 in central
found com.yammer.metrics#metrics-core;2.2.0 in central
found org.slf4j#slf4j-api;1.7.16 in central
found org.scala-lang.modules#scala-parser-combinators_2.11;1.0.2 in central
found com.101tec#zkclient;0.3 in central
found log4j#log4j;1.2.17 in central
found org.apache.kafka#kafka-clients;0.8.2.1 in central
found net.jpountz.lz4#lz4;1.3.0 in central
found org.xerial.snappy#snappy-java;1.1.2.6 in central
found org.spark-project.spark#unused;1.0.0 in central
:: resolution report :: resolve 4729ms :: artifacts dl 16ms
:: modules in use:
com.101tec#zkclient;0.3 from central in [default]
com.yammer.metrics#metrics-core;2.2.0 from central in [default]
log4j#log4j;1.2.17 from central in [default]
net.jpountz.lz4#lz4;1.3.0 from central in [default]
org.apache.kafka#kafka-clients;0.8.2.1 from central in [default]
org.apache.kafka#kafka_2.11;0.8.2.1 from central in [default]
org.apache.spark#spark-streaming-kafka-0-8_2.11;2.0.2 from central in [default]
org.scala-lang.modules#scala-parser-combinators_2.11;1.0.2 from central in [default]
org.scala-lang.modules#scala-xml_2.11;1.0.2 from central in [default]
org.slf4j#slf4j-api;1.7.16 from central in [default]
org.spark-project.spark#unused;1.0.0 from central in [default]
org.xerial.snappy#snappy-java;1.1.2.6 from central in [default]
---------------------------------------------------------------------
| | modules || artifacts |
| conf | number| search|dwnlded|evicted|| number|dwnlded|
---------------------------------------------------------------------
| default | 12 | 1 | 1 | 0 || 12 | 0 |
---------------------------------------------------------------------
:: retrieving :: org.apache.spark#spark-submit-parent
confs: [default]
0 artifacts copied, 12 already retrieved (0kB/8ms)
2018-05-01 19:43:48 WARN NativeCodeLoader:62 - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable
Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
[Stage 0:> (0 + 1) / 1]2018-05-01 19:43:50 ERROR Executor:91 - Exception in task 0.0 in stage 0.0 (TID 0)
java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.streaming.kafka.KafkaReceiver.initializeLogIfNecessary(KafkaInputDStream.scala:68)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.streaming.kafka.KafkaReceiver.log(KafkaInputDStream.scala:68)
at org.apache.spark.internal.Logging$class.logInfo(Logging.scala:54)
at org.apache.spark.streaming.kafka.KafkaReceiver.logInfo(KafkaInputDStream.scala:68)
at org.apache.spark.streaming.kafka.KafkaReceiver.onStart(KafkaInputDStream.scala:90)
at org.apache.spark.streaming.receiver.ReceiverSupervisor.startReceiver(ReceiverSupervisor.scala:149)
at org.apache.spark.streaming.receiver.ReceiverSupervisor.start(ReceiverSupervisor.scala:131)
at org.apache.spark.streaming.scheduler.ReceiverTracker$ReceiverTrackerEndpoint$$anonfun$9.apply(ReceiverTracker.scala:600)
at org.apache.spark.streaming.scheduler.ReceiverTracker$ReceiverTrackerEndpoint$$anonfun$9.apply(ReceiverTracker.scala:590)
at org.apache.spark.SparkContext$$anonfun$34.apply(SparkContext.scala:2178)
at org.apache.spark.SparkContext$$anonfun$34.apply(SparkContext.scala:2178)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
2018-05-01 19:43:50 WARN TaskSetManager:66 - Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.streaming.kafka.KafkaReceiver.initializeLogIfNecessary(KafkaInputDStream.scala:68)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.streaming.kafka.KafkaReceiver.log(KafkaInputDStream.scala:68)
at org.apache.spark.internal.Logging$class.logInfo(Logging.scala:54)
at org.apache.spark.streaming.kafka.KafkaReceiver.logInfo(KafkaInputDStream.scala:68)
at org.apache.spark.streaming.kafka.KafkaReceiver.onStart(KafkaInputDStream.scala:90)
at org.apache.spark.streaming.receiver.ReceiverSupervisor.startReceiver(ReceiverSupervisor.scala:149)
at org.apache.spark.streaming.receiver.ReceiverSupervisor.start(ReceiverSupervisor.scala:131)
at org.apache.spark.streaming.scheduler.ReceiverTracker$ReceiverTrackerEndpoint$$anonfun$9.apply(ReceiverTracker.scala:600)
at org.apache.spark.streaming.scheduler.ReceiverTracker$ReceiverTrackerEndpoint$$anonfun$9.apply(ReceiverTracker.scala:590)
at org.apache.spark.SparkContext$$anonfun$34.apply(SparkContext.scala:2178)
at org.apache.spark.SparkContext$$anonfun$34.apply(SparkContext.scala:2178)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
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)

2018-05-01 19:43:50 ERROR TaskSetManager:70 - Task 0 in stage 0.0 failed 1 times; aborting job
2018-05-01 19:43:50 ERROR ReceiverTracker:91 - Receiver has been stopped. Try to restart it.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 0.0 failed 1 times, most recent failure: Lost task 0.0 in stage 0.0 (TID 0, localhost, executor driver): java.lang.AbstractMethodError
at org.apache.spark.internal.Logging$class.initializeLogIfNecessary(Logging.scala:99)
at org.apache.spark.streaming.kafka.KafkaReceiver.initializeLogIfNecessary(KafkaInputDStream.scala:68)
at org.apache.spark.internal.Logging$class.log(Logging.scala:46)
at org.apache.spark.streaming.kafka.KafkaReceiver.log(KafkaInputDStream.scala:68)
at org.apache.spark.internal.Logging$class.logInfo(Logging.scala:54)
at org.apache.spark.streaming.kafka.KafkaReceiver.logInfo(KafkaInputDStream.scala:68)
at org.apache.spark.streaming.kafka.KafkaReceiver.onStart(KafkaInputDStream.scala:90)
at org.apache.spark.streaming.receiver.ReceiverSupervisor.startReceiver(ReceiverSupervisor.scala:149)
at org.apache.spark.streaming.receiver.ReceiverSupervisor.start(ReceiverSupervisor.scala:131)
at org.apache.spark.streaming.scheduler.ReceiverTracker$ReceiverTrackerEndpoint$$anonfun$9.apply(ReceiverTracker.scala:600)
at org.apache.spark.streaming.scheduler.ReceiverTracker$ReceiverTrackerEndpoint$$anonfun$9.apply(ReceiverTracker.scala:590)
at org.apache.spark.SparkContext$$anonfun$34.apply(SparkContext.scala:2178)
at org.apache.spark.SparkContext$$anonfun$34.apply(SparkContext.scala:2178)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:87)
at org.apache.spark.scheduler.Task.run(Task.scala:109)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:345)
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)

Driver stacktrace:
at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1599)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1587)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1586)
at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48)
at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1586)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:831)
at scala.Option.foreach(Option.scala:257)
at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:831)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1820)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1769)
at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1758)
at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48)