You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@spark.apache.org by "Jianshi Huang (JIRA)" <ji...@apache.org> on 2014/10/08 11:41:33 UTC
[jira] [Updated] (SPARK-3846) KryoException when doing joins in
SparkSQL
[ https://issues.apache.org/jira/browse/SPARK-3846?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Jianshi Huang updated SPARK-3846:
---------------------------------
Description:
The error is reproducible when I join two tables manually. The error message is like follows.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 645 in stage 3.0 failed 4 times, most recent failure: Lost task 645.3 in stage 3.0 (TID 3802, lvshdc5dn0215.lvs.paypal.com): com.esotericsoftware.kryo.KryoException:
Unable to find class: __wrapper$1$18e31777385a452ba0bc030e899bf5d1.__wrapper$1$18e31777385a452ba0bc030e899bf5d1$SpecificRow$1
com.esotericsoftware.kryo.util.DefaultClassResolver.readName(DefaultClassResolver.java:138)
com.esotericsoftware.kryo.util.DefaultClassResolver.readClass(DefaultClassResolver.java:115)
com.esotericsoftware.kryo.Kryo.readClass(Kryo.java:610)
com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:721)
com.twitter.chill.Tuple2Serializer.read(TupleSerializers.scala:42)
com.twitter.chill.Tuple2Serializer.read(TupleSerializers.scala:34)
com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:732)
org.apache.spark.serializer.KryoDeserializationStream.readObject(KryoSerializer.scala:133)
org.apache.spark.serializer.DeserializationStream$$anon$1.getNext(Serializer.scala:133)
org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:30)
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
org.apache.spark.sql.execution.HashJoin$$anon$1.hasNext(joins.scala:101)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
org.apache.spark.sql.execution.GeneratedAggregate$$anonfun$8.apply(GeneratedAggregate.scala:198)
org.apache.spark.sql.execution.GeneratedAggregate$$anonfun$8.apply(GeneratedAggregate.scala:165)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:599)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:599)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:56)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:181)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:724)
was:
I built the latest Spark (1.2.0-SNAPSHOT) from master branch and found previous (1.1.0) successful jobs failed.
The error is reproducible when I join two tables manually. The error message is like follows.
org.apache.spark.SparkException: Job aborted due to stage failure: Task 645 in stage 3.0 failed 4 times, most recent failure: Lost task 645.3 in stage 3.0 (TID 3802, lvshdc5dn0215.lvs.paypal.com): com.esotericsoftware.kryo.KryoException:
Unable to find class: __wrapper$1$18e31777385a452ba0bc030e899bf5d1.__wrapper$1$18e31777385a452ba0bc030e899bf5d1$SpecificRow$1
com.esotericsoftware.kryo.util.DefaultClassResolver.readName(DefaultClassResolver.java:138)
com.esotericsoftware.kryo.util.DefaultClassResolver.readClass(DefaultClassResolver.java:115)
com.esotericsoftware.kryo.Kryo.readClass(Kryo.java:610)
com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:721)
com.twitter.chill.Tuple2Serializer.read(TupleSerializers.scala:42)
com.twitter.chill.Tuple2Serializer.read(TupleSerializers.scala:34)
com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:732)
org.apache.spark.serializer.KryoDeserializationStream.readObject(KryoSerializer.scala:133)
org.apache.spark.serializer.DeserializationStream$$anon$1.getNext(Serializer.scala:133)
org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:30)
org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
org.apache.spark.sql.execution.HashJoin$$anon$1.hasNext(joins.scala:101)
scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
org.apache.spark.sql.execution.GeneratedAggregate$$anonfun$8.apply(GeneratedAggregate.scala:198)
org.apache.spark.sql.execution.GeneratedAggregate$$anonfun$8.apply(GeneratedAggregate.scala:165)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:599)
org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:599)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
org.apache.spark.scheduler.Task.run(Task.scala:56)
org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:181)
java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
java.lang.Thread.run(Thread.java:724)
Affects Version/s: 1.1.0
> KryoException when doing joins in SparkSQL
> -------------------------------------------
>
> Key: SPARK-3846
> URL: https://issues.apache.org/jira/browse/SPARK-3846
> Project: Spark
> Issue Type: Bug
> Components: SQL
> Affects Versions: 1.1.0, 1.2.0
> Reporter: Jianshi Huang
>
> The error is reproducible when I join two tables manually. The error message is like follows.
> org.apache.spark.SparkException: Job aborted due to stage failure: Task 645 in stage 3.0 failed 4 times, most recent failure: Lost task 645.3 in stage 3.0 (TID 3802, lvshdc5dn0215.lvs.paypal.com): com.esotericsoftware.kryo.KryoException:
> Unable to find class: __wrapper$1$18e31777385a452ba0bc030e899bf5d1.__wrapper$1$18e31777385a452ba0bc030e899bf5d1$SpecificRow$1
> com.esotericsoftware.kryo.util.DefaultClassResolver.readName(DefaultClassResolver.java:138)
> com.esotericsoftware.kryo.util.DefaultClassResolver.readClass(DefaultClassResolver.java:115)
> com.esotericsoftware.kryo.Kryo.readClass(Kryo.java:610)
> com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:721)
> com.twitter.chill.Tuple2Serializer.read(TupleSerializers.scala:42)
> com.twitter.chill.Tuple2Serializer.read(TupleSerializers.scala:34)
> com.esotericsoftware.kryo.Kryo.readClassAndObject(Kryo.java:732)
> org.apache.spark.serializer.KryoDeserializationStream.readObject(KryoSerializer.scala:133)
> org.apache.spark.serializer.DeserializationStream$$anon$1.getNext(Serializer.scala:133)
> org.apache.spark.util.NextIterator.hasNext(NextIterator.scala:71)
> scala.collection.Iterator$$anon$13.hasNext(Iterator.scala:371)
> org.apache.spark.util.CompletionIterator.hasNext(CompletionIterator.scala:30)
> org.apache.spark.InterruptibleIterator.hasNext(InterruptibleIterator.scala:39)
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> org.apache.spark.sql.execution.HashJoin$$anon$1.hasNext(joins.scala:101)
> scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
> org.apache.spark.sql.execution.GeneratedAggregate$$anonfun$8.apply(GeneratedAggregate.scala:198)
> org.apache.spark.sql.execution.GeneratedAggregate$$anonfun$8.apply(GeneratedAggregate.scala:165)
> org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:599)
> org.apache.spark.rdd.RDD$$anonfun$13.apply(RDD.scala:599)
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
> org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:35)
> org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:262)
> org.apache.spark.rdd.RDD.iterator(RDD.scala:229)
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:68)
> org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> org.apache.spark.scheduler.Task.run(Task.scala:56)
> org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:181)
> java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
> java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
> java.lang.Thread.run(Thread.java:724)
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@spark.apache.org
For additional commands, e-mail: issues-help@spark.apache.org