Mingyu Kim created SPARK-3050:
---------------------------------
Summary: Spark program running with 1.0.2 jar cannot run against a
1.0.1 cluster
Key: SPARK-3050
URL: https://issues.apache.org/jira/browse/SPARK-3050
Project: Spark
Issue Type: Bug
Affects Versions: 1.0.2
Reporter: Mingyu Kim
Priority: Critical
I ran the following code with Spark 1.0.2 jar against a cluster that runs Spark
1.0.1 (i.e. localhost:7077 is running 1.0.1).
{code}
import java.util.ArrayList;
import java.util.List;
import org.apache.spark.api.java.JavaRDD;
import org.apache.spark.api.java.JavaSparkContext;
public class TestTest {
public static void main(String[] args) {
JavaSparkContext sc = new JavaSparkContext("spark://localhost:7077",
"Test");
List<Integer> list = new ArrayList<>();
list.add(1);
list.add(2);
list.add(3);
JavaRDD<Integer> rdd = sc.parallelize(list);
System.out.println(rdd.collect());
}
}
{code}
This throws InvalidClassException.
{code}
Exception in thread "main" org.apache.spark.SparkException: Job aborted due to
stage failure: Task 0.0:1 failed 4 times, most recent failure: Exception
failure in TID 6 on host 10.100.91.90: java.io.InvalidClassException:
org.apache.spark.rdd.RDD; local class incompatible: stream classdesc
serialVersionUID = -6766554341038829528, local class serialVersionUID =
385418487991259089
java.io.ObjectStreamClass.initNonProxy(ObjectStreamClass.java:604)
java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1620)
java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1515)
java.io.ObjectInputStream.readNonProxyDesc(ObjectInputStream.java:1620)
java.io.ObjectInputStream.readClassDesc(ObjectInputStream.java:1515)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1769)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:63)
org.apache.spark.scheduler.ResultTask$.deserializeInfo(ResultTask.scala:61)
org.apache.spark.scheduler.ResultTask.readExternal(ResultTask.scala:141)
java.io.ObjectInputStream.readExternalData(ObjectInputStream.java:1835)
java.io.ObjectInputStream.readOrdinaryObject(ObjectInputStream.java:1794)
java.io.ObjectInputStream.readObject0(ObjectInputStream.java:1348)
java.io.ObjectInputStream.readObject(ObjectInputStream.java:370)
org.apache.spark.serializer.JavaDeserializationStream.readObject(JavaSerializer.scala:63)
org.apache.spark.serializer.JavaSerializerInstance.deserialize(JavaSerializer.scala:85)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:165)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:722)
Driver stacktrace:
at
org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1049)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1033)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1031)
at
scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59)
at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47)
at
org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1031)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635)
at
org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:635)
at scala.Option.foreach(Option.scala:236)
at
org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:635)
at
org.apache.spark.scheduler.DAGSchedulerEventProcessActor$$anonfun$receive$2.applyOrElse(DAGScheduler.scala:1234)
at akka.actor.ActorCell.receiveMessage(ActorCell.scala:498)
at akka.actor.ActorCell.invoke(ActorCell.scala:456)
at akka.dispatch.Mailbox.processMailbox(Mailbox.scala:237)
at akka.dispatch.Mailbox.run(Mailbox.scala:219)
at
akka.dispatch.ForkJoinExecutorConfigurator$AkkaForkJoinTask.exec(AbstractDispatcher.scala:386)
at scala.concurrent.forkjoin.ForkJoinTask.doExec(ForkJoinTask.java:260)
at
scala.concurrent.forkjoin.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1339)
at
scala.concurrent.forkjoin.ForkJoinPool.runWorker(ForkJoinPool.java:1979)
at
scala.concurrent.forkjoin.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:107)
{code}
I thought minor version releases and patch releases should be
binary-compatible. Is that not true?
--
This message was sent by Atlassian JIRA
(v6.2#6252)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
