[
https://issues.apache.org/jira/browse/HUDI-3593?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17504719#comment-17504719
]
shibei edited comment on HUDI-3593 at 3/11/22, 4:10 AM:
--------------------------------------------------------
{code:java}
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:403)
at
org.apache.spark.util.ClosureCleaner$.org$apache$spark$util$ClosureCleaner$$clean(ClosureCleaner.scala:393)
at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
at org.apache.spark.SparkContext.clean(SparkContext.scala:2326)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:371)
at org.apache.spark.rdd.RDD$$anonfun$map$1.apply(RDD.scala:370)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
at org.apache.spark.rdd.RDD.withScope(RDD.scala:363)
at org.apache.spark.rdd.RDD.map(RDD.scala:370)
at org.apache.spark.api.java.JavaRDDLike$class.map(JavaRDDLike.scala:93)
at
org.apache.spark.api.java.AbstractJavaRDDLike.map(JavaRDDLike.scala:45)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.readRecordsForGroupBaseFiles(MultipleSparkJobExecutionStrategy.java:269)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.readRecordsForGroup(MultipleSparkJobExecutionStrategy.java:191)
at
org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.lambda$runClusteringForGroupAsync$4(MultipleSparkJobExecutionStrategy.java:171)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1604)
... 1 more
Caused by: java.util.ConcurrentModificationException
at
java.util.LinkedHashMap$LinkedHashIterator.nextNode(LinkedHashMap.java:719)
at
java.util.LinkedHashMap$LinkedKeyIterator.next(LinkedHashMap.java:742)
at java.util.HashSet.writeObject(HashSet.java:287)
at sun.reflect.GeneratedMethodAccessor19.invoke(Unknown Source)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:400)
... 16 more
{code}
was (Author: JIRAUSER279853):
Another failure
{code:java}
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at
java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1154)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at
java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
at
java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
at
java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
at
org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:43)
at
org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100)
at
org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:400)
... 16 more {code}
> AsyncClustering failed because of ConcurrentModificationException
> -----------------------------------------------------------------
>
> Key: HUDI-3593
> URL: https://issues.apache.org/jira/browse/HUDI-3593
> Project: Apache Hudi
> Issue Type: Bug
> Reporter: Hui An
> Assignee: Hui An
> Priority: Major
> Labels: pull-request-available
> Attachments: Screen Shot 2022-03-10 at 9.53.13 AM.png
>
>
> Following is the stacktrace I met,
> {code:java}
> ERROR AsyncClusteringService: Clustering executor failed
> java.util.concurrent.CompletionException: org.apache.spark.SparkException:
> Task not serializable
> at
> java.util.concurrent.CompletableFuture.encodeThrowable(CompletableFuture.java:273)
>
> at
> java.util.concurrent.CompletableFuture.completeThrowable(CompletableFuture.java:280)
>
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1606)
>
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.exec(CompletableFuture.java:1596)
>
> at java.util.concurrent.ForkJoinTask.doExec(ForkJoinTask.java:289)
> at
> java.util.concurrent.ForkJoinPool$WorkQueue.runTask(ForkJoinPool.java:1056)
> at java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
> at
> java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:157)
> Caused by: org.apache.spark.SparkException: Task not serializable
> at
> org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:416)
>
> at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:406)
> at org.apache.spark.util.ClosureCleaner$.clean(ClosureCleaner.scala:162)
> at org.apache.spark.SparkContext.clean(SparkContext.scala:2467)
> at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsWithIndex$1(RDD.scala:912)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
>
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
>
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
> at org.apache.spark.rdd.RDD.mapPartitionsWithIndex(RDD.scala:911)
> at
> org.apache.spark.api.java.JavaRDDLike.mapPartitionsWithIndex(JavaRDDLike.scala:103)
>
> at
> org.apache.spark.api.java.JavaRDDLike.mapPartitionsWithIndex$(JavaRDDLike.scala:99)
>
> at
> org.apache.spark.api.java.AbstractJavaRDDLike.mapPartitionsWithIndex(JavaRDDLike.scala:45)
>
> at
> org.apache.hudi.table.action.commit.SparkBulkInsertHelper.bulkInsert(SparkBulkInsertHelper.java:115)
>
> at
> org.apache.hudi.client.clustering.run.strategy.SparkSortAndSizeExecutionStrategy.performClusteringWithRecordsRDD(SparkSortAndSizeExecutionStrategy.java:68)
>
> at
> org.apache.hudi.client.clustering.run.strategy.MultipleSparkJobExecutionStrategy.lambda$runClusteringForGroupAsync$4(MultipleSparkJobExecutionStrategy.java:175)
>
> at
> java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1604)
> ... 5 more
> Caused by: java.util.ConcurrentModificationException
> at
> java.util.LinkedHashMap$LinkedHashIterator.nextNode(LinkedHashMap.java:719)
> at java.util.LinkedHashMap$LinkedKeyIterator.next(LinkedHashMap.java:742)
> at java.util.HashSet.writeObject(HashSet.java:287)
> at sun.reflect.GeneratedMethodAccessor54.invoke(Unknown Source)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
>
> at java.lang.reflect.Method.invoke(Method.java:498)
> at java.io.ObjectStreamClass.invokeWriteObject(ObjectStreamClass.java:1140)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1496)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeArray(ObjectOutputStream.java:1378)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1174)
> at
> java.io.ObjectOutputStream.defaultWriteFields(ObjectOutputStream.java:1548)
> at java.io.ObjectOutputStream.writeSerialData(ObjectOutputStream.java:1509)
> at
> java.io.ObjectOutputStream.writeOrdinaryObject(ObjectOutputStream.java:1432)
> at java.io.ObjectOutputStream.writeObject0(ObjectOutputStream.java:1178)
> at java.io.ObjectOutputStream.writeObject(ObjectOutputStream.java:348)
> at
> org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:44)
>
> at org.apache.spark.serializer.JavaSerializerInstance
> {code}
--
This message was sent by Atlassian Jira
(v8.20.1#820001)