[HUDI-4204] OCC with row writer path fails

• Type: Bug
• Status: Closed
• Priority: Major
• Resolution: Fixed
• Fix Version/s: 0.12.0
• Component/s: multi-writer
• Labels: pull-request-available
• Assignee: sivabalan narayanan
• Reporter: sivabalan narayanan
• Created: 07/Jun/22 21:03
• Updated: 09/Aug/22 16:34
• Resolved: 09/Aug/22 16:34

Description

Ref: https://github.com/apache/hudi/issues/5751

 

Caused by: org.apache.spark.SparkException: Writing job aborted
        at org.apache.spark.sql.errors.QueryExecutionErrors$.writingJobAbortedError(QueryExecutionErrors.scala:613)
        at org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:386)
        at org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2$(WriteToDataSourceV2Exec.scala:330)
        at org.apache.spark.sql.execution.datasources.v2.AppendDataExec.writeWithV2(WriteToDataSourceV2Exec.scala:236)
        at org.apache.spark.sql.execution.datasources.v2.V2ExistingTableWriteExec.run(WriteToDataSourceV2Exec.scala:309)
        at org.apache.spark.sql.execution.datasources.v2.V2ExistingTableWriteExec.run$(WriteToDataSourceV2Exec.scala:308)
        at org.apache.spark.sql.execution.datasources.v2.AppendDataExec.run(WriteToDataSourceV2Exec.scala:236)
        at org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result$lzycompute(V2CommandExec.scala:43)
        at org.apache.spark.sql.execution.datasources.v2.V2CommandExec.result(V2CommandExec.scala:43)
        at org.apache.spark.sql.execution.datasources.v2.V2CommandExec.executeCollect(V2CommandExec.scala:49)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:110)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
        at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
        at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
        at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:110)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:106)
        at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:481)
        at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:82)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:481)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
        at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
        at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:457)
        at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:106)
        at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:93)
        at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:91)
        at org.apache.spark.sql.execution.QueryExecution.assertCommandExecuted(QueryExecution.scala:128)
        at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:848)
        at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:311)
        at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:247)
        at org.apache.hudi.HoodieSparkSqlWriter$.bulkInsertAsRow(HoodieSparkSqlWriter.scala:559)
        at org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:176)
        at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:163)
        at org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:45)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:75)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:73)
        at org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:84)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:110)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:103)
        at org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:163)
        at org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:90)
        at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:775)
        at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:110)
        at org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:106)
        at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:481)
        at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:82)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:481)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
        at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
        at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
        at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
        at org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:457)
        at org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:106)
        at org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:93)
        at org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:91)
        at org.apache.spark.sql.execution.QueryExecution.assertCommandExecuted(QueryExecution.scala:128)
        at org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:848)
        at org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:382)
        at org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:303)
        at org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:239)
        ... 11 more
Caused by: org.apache.hudi.exception.HoodieException
        at org.apache.hudi.internal.DataSourceInternalWriterHelper.commit(DataSourceInternalWriterHelper.java:86)
        at org.apache.hudi.spark3.internal.HoodieDataSourceInternalBatchWrite.commit(HoodieDataSourceInternalBatchWrite.java:93)
        at org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:369)
        ... 78 more
Caused by: java.lang.NullPointerException
org.apache.hudi.client.utils.TransactionUtils.lambda$getCompletedInstantsDuringCurrentWriteOperation$1(TransactionUtils.java:159)
        at java.util.stream.ReferencePipeline$2$1.accept(ReferencePipeline.java:174)
        at java.util.ArrayList$ArrayListSpliterator.forEachRemaining(ArrayList.java:1384)
        at java.util.stream.AbstractPipeline.copyInto(AbstractPipeline.java:482)
        at java.util.stream.AbstractPipeline.wrapAndCopyInto(AbstractPipeline.java:472)
        at java.util.stream.StreamSpliterators$WrappingSpliterator.forEachRemaining(StreamSpliterators.java:313)
        at java.util.stream.Streams$ConcatSpliterator.forEachRemaining(Streams.java:743)
        at java.util.stream.ReferencePipeline$Head.forEach(ReferencePipeline.java:647)
        at org.apache.hudi.client.utils.TransactionUtils.resolveWriteConflictIfAny(TransactionUtils.java:79)
        at org.apache.hudi.client.SparkRDDWriteClient.preCommit(SparkRDDWriteClient.java:475)
        at org.apache.hudi.client.BaseHoodieWriteClient.commitStats(BaseHoodieWriteClient.java:233)
        at org.apache.hudi.client.BaseHoodieWriteClient.commitStats(BaseHoodieWriteClient.java:214)
        at org.apache.hudi.internal.DataSourceInternalWriterHelper.commit(DataSourceInternalWriterHelper.java:83)
        ... 80 more
 

Issue Links

• links to: GitHub Pull Request #5850
• links to: issue-5751