mikeashley87 commented on issue #6819: URL: https://github.com/apache/hudi/issues/6819#issuecomment-1270450572
I am getting the same error when using https://mvnrepository.com/artifact/org.apache.hudi/hudi-spark2.4-bundle_2.11/0.12.0 ``` py4j.protocol.Py4JJavaError: An error occurred while calling o1011.save. : org.apache.spark.SparkException: Job aborted due to stage failure: Failed to serialize task 3847, not attempting to retry it. Exception during serialization: java.io.NotSerializableException: org.apache.hadoop.fs.Path Serialization stack: - object not serializable (class: org.apache.hadoop.fs.Path, value: s3://somebucket/someprefix) - element of array (index: 0) - array (class [Ljava.lang.Object;, size 1) - field (class: scala.collection.mutable.WrappedArray$ofRef, name: array, type: class [Ljava.lang.Object;) - object (class scala.collection.mutable.WrappedArray$ofRef, WrappedArray(s3://somebucket/someprefix)) - writeObject data (class: org.apache.spark.rdd.ParallelCollectionPartition) - object (class org.apache.spark.rdd.ParallelCollectionPartition, org.apache.spark.rdd.ParallelCollectionPartition@3488) - field (class: org.apache.spark.scheduler.ResultTask, name: partition, type: interface org.apache.spark.Partition) - object (class org.apache.spark.scheduler.ResultTask, ResultTask(114, 0)) at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1889) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1877) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1876) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1876) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:926) at scala.Option.foreach(Option.scala:257) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:926) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:2110) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2059) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:2048) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:49) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:737) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2061) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2082) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2101) at org.apache.spark.SparkContext.runJob(SparkContext.scala:2126) at org.apache.spark.rdd.RDD$$anonfun$collect$1.apply(RDD.scala:945) 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.collect(RDD.scala:944) at org.apache.spark.api.java.JavaRDDLike$class.collect(JavaRDDLike.scala:361) at org.apache.spark.api.java.AbstractJavaRDDLike.collect(JavaRDDLike.scala:45) at org.apache.hudi.client.common.HoodieSparkEngineContext.map(HoodieSparkEngineContext.java:103) at org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.listAllPartitions(HoodieBackedTableMetadataWriter.java:631) at org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.initialCommit(HoodieBackedTableMetadataWriter.java:1064) at org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.initializeFromFilesystem(HoodieBackedTableMetadataWriter.java:557) at org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.initializeIfNeeded(HoodieBackedTableMetadataWriter.java:390) at org.apache.hudi.metadata.SparkHoodieBackedTableMetadataWriter.initialize(SparkHoodieBackedTableMetadataWriter.java:120) at org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.<init>(HoodieBackedTableMetadataWriter.java:171) at org.apache.hudi.metadata.SparkHoodieBackedTableMetadataWriter.<init>(SparkHoodieBackedTableMetadataWriter.java:89) at org.apache.hudi.metadata.SparkHoodieBackedTableMetadataWriter.create(SparkHoodieBackedTableMetadataWriter.java:75) at org.apache.hudi.client.SparkRDDWriteClient.initializeMetadataTable(SparkRDDWriteClient.java:446) at org.apache.hudi.client.SparkRDDWriteClient.doInitTable(SparkRDDWriteClient.java:431) at org.apache.hudi.client.BaseHoodieWriteClient.initTable(BaseHoodieWriteClient.java:1459) at org.apache.hudi.client.BaseHoodieWriteClient.initTable(BaseHoodieWriteClient.java:1491) at org.apache.hudi.client.SparkRDDWriteClient.upsert(SparkRDDWriteClient.java:152) at org.apache.hudi.DataSourceUtils.doWriteOperation(DataSourceUtils.java:206) at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:329) at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:183) 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 sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:498) at py4j.reflection.MethodInvoker.invoke(MethodInvoker.java:244) at py4j.reflection.ReflectionEngine.invoke(ReflectionEngine.java:357) at py4j.Gateway.invoke(Gateway.java:282) at py4j.commands.AbstractCommand.invokeMethod(AbstractCommand.java:132) at py4j.commands.CallCommand.execute(CallCommand.java:79) at py4j.GatewayConnection.run(GatewayConnection.java:238) at java.lang.Thread.run(Thread.java:750) ``` -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: commits-unsubscr...@hudi.apache.org For queries about this service, please contact Infrastructure at: us...@infra.apache.org
