You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "liujinhui (Jira)" <ji...@apache.org> on 2020/08/11 09:53:00 UTC

[jira] [Commented] (HUDI-1177) fix key generator bug

    [ https://issues.apache.org/jira/browse/HUDI-1177?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17175416#comment-17175416 ] 

liujinhui commented on HUDI-1177:
---------------------------------

Exception in thread "main" org.apache.spark.SparkException: Task not serializableException in thread "main" org.apache.spark.SparkException: Task not serializable 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$$anonfun$map$1.apply(RDD.scala:370) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112) at org.apache.spark.rdd.RDD.withScope(RDD.scala:363) at org.apache.spark.rdd.RDD.map(RDD.scala:370) at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:123) at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:126) at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70) at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68) at org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:86) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:131) at org.apache.spark.sql.execution.SparkPlan$$anonfun$execute$1.apply(SparkPlan.scala:127) at org.apache.spark.sql.execution.SparkPlan$$anonfun$executeQuery$1.apply(SparkPlan.scala:155) at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151) at org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:152) at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:127) at org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:80) at org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:80) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676) at org.apache.spark.sql.DataFrameWriter$$anonfun$runCommand$1.apply(DataFrameWriter.scala:676) at org.apache.spark.sql.execution.SQLExecution$$anonfun$withNewExecutionId$1.apply(SQLExecution.scala:78) at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:125) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:73) at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:676) at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:285) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:271) at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:229) at org.apache.hudi.utilities.TestDemo1.main(TestDemo1.java:101)Caused by: java.io.NotSerializableException: org.joda.time.format.DateTimeFormatterSerialization stack: - object not serializable (class: org.joda.time.format.DateTimeFormatter, value: org.joda.time.format.DateTimeFormatter@57d1edf0) - field (class: org.apache.hudi.keygen.parser.HoodieDateTimeParserImpl, name: inputFormatter, type: class org.joda.time.format.DateTimeFormatter) - object (class org.apache.hudi.keygen.parser.HoodieDateTimeParserImpl, org.apache.hudi.keygen.parser.HoodieDateTimeParserImpl@2f46bc25) - field (class: org.apache.hudi.keygen.TimestampBasedKeyGenerator, name: parser, type: interface org.apache.hudi.keygen.parser.HoodieDateTimeParser) - object (class org.apache.hudi.keygen.TimestampBasedKeyGenerator, org.apache.hudi.keygen.TimestampBasedKeyGenerator@581cb879) - field (class: org.apache.hudi.HoodieSparkSqlWriter$$anonfun$1, name: keyGenerator$1, type: class org.apache.hudi.keygen.KeyGenerator) - object (class org.apache.hudi.HoodieSparkSqlWriter$$anonfun$1, <function1>) at org.apache.spark.serializer.SerializationDebugger$.improveException(SerializationDebugger.scala:40) at org.apache.spark.serializer.JavaSerializationStream.writeObject(JavaSerializer.scala:46) at org.apache.spark.serializer.JavaSerializerInstance.serialize(JavaSerializer.scala:100) at org.apache.spark.util.ClosureCleaner$.ensureSerializable(ClosureCleaner.scala:400) ... 33 more

> fix key generator bug 
> ----------------------
>
>                 Key: HUDI-1177
>                 URL: https://issues.apache.org/jira/browse/HUDI-1177
>             Project: Apache Hudi
>          Issue Type: Bug
>            Reporter: liujinhui
>            Assignee: liujinhui
>            Priority: Major
>             Fix For: 0.6.0
>
>




--
This message was sent by Atlassian Jira
(v8.3.4#803005)