aznwarmonkey commented on issue #4541:
URL: https://github.com/apache/hudi/issues/4541#issuecomment-1009432117
Hi,
After making the above changes I let job process multiple days, after the
3rd day of process I get the below exception. It looks like it is error out
during the clustering process. Any ideas as to why this is occuring?
```python
park.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220)
at
org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133)
at
org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989)
at
org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:370)
at
org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:301)
at
org.apache.hudi.HoodieSparkSqlWriter$.bulkInsertAsRow(HoodieSparkSqlWriter.scala:302)
at
org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:127)
at
org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:134)
at
org.apache.spark.sql.execution.datasources.SaveIntoDataSourceCommand.run(SaveIntoDataSourceCommand.scala:46)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:70)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:68)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.doExecute(commands.scala:90)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:185)
at
org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:223)
at
org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
at
org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:220)
at
org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:181)
at
org.apache.spark.sql.execution.QueryExecution.toRdd$lzycompute(QueryExecution.scala:134)
at
org.apache.spark.sql.execution.QueryExecution.toRdd(QueryExecution.scala:133)
at
org.apache.spark.sql.DataFrameWriter.$anonfun$runCommand$1(DataFrameWriter.scala:989)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:110)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:135)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:232)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$5(SQLExecution.scala:135)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:253)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:134)
at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at
org.apache.spark.sql.DataFrameWriter.runCommand(DataFrameWriter.scala:989)
at
org.apache.spark.sql.DataFrameWriter.saveToV1Source(DataFrameWriter.scala:438)
at
org.apache.spark.sql.DataFrameWriter.saveInternal(DataFrameWriter.scala:415)
at
org.apache.spark.sql.DataFrameWriter.save(DataFrameWriter.scala:293)
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:748)
Caused by: org.apache.hudi.exception.HoodieException:
java.lang.NullPointerException
at
org.apache.hudi.internal.DataSourceInternalWriterHelper.commit(DataSourceInternalWriterHelper.java:83)
at
org.apache.hudi.spark3.internal.HoodieDataSourceInternalBatchWrite.commit(HoodieDataSourceInternalBatchWrite.java:84)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:371)
... 69 more
Suppressed: org.apache.hudi.exception.HoodieRollbackException:
Failed to rollback s3://snag-dev-test/data/hudi/COW_ALL_KEYS/country/ commits
20220109003243
at
org.apache.hudi.client.AbstractHoodieWriteClient.rollback(AbstractHoodieWriteClient.java:563)
at
org.apache.hudi.internal.DataSourceInternalWriterHelper.abort(DataSourceInternalWriterHelper.java:91)
at
org.apache.hudi.spark3.internal.HoodieDataSourceInternalBatchWrite.abort(HoodieDataSourceInternalBatchWrite.java:89)
at
org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:378)
... 69 more
Caused by: org.apache.hudi.exception.HoodieRollbackException: Found
in-flight commits after time :20220109003243, please rollback greater commits
first
at
org.apache.hudi.table.action.rollback.BaseRollbackActionExecutor.validateRollbackCommitSequence(BaseRollbackActionExecutor.java:148)
at
org.apache.hudi.table.action.rollback.BaseRollbackActionExecutor.doRollbackAndGetStats(BaseRollbackActionExecutor.java:166)
at
org.apache.hudi.table.action.rollback.BaseRollbackActionExecutor.execute(BaseRollbackActionExecutor.java:103)
at
org.apache.hudi.table.HoodieSparkCopyOnWriteTable.rollback(HoodieSparkCopyOnWriteTable.java:230)
at
org.apache.hudi.client.AbstractHoodieWriteClient.rollback(AbstractHoodieWriteClient.java:552)
... 72 more
Caused by: java.util.concurrent.CompletionException:
java.lang.NullPointerException
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$WorkQueue.runTask(ForkJoinPool.java:1056)
at
java.util.concurrent.ForkJoinPool.runWorker(ForkJoinPool.java:1692)
at
java.util.concurrent.ForkJoinWorkerThread.run(ForkJoinWorkerThread.java:175)
Caused by: java.lang.NullPointerException
at java.io.StringReader.<init>(StringReader.java:50)
at org.apache.avro.Schema$Parser.parse(Schema.java:1020)
at
org.apache.hudi.table.action.cluster.SparkExecuteClusteringCommitActionExecutor.lambda$runClusteringForGroupAsync$3(SparkExecuteClusteringCommitActionExecutor.java:118)
at
java.util.concurrent.CompletableFuture$AsyncSupply.run(CompletableFuture.java:1604)
... 5 more
```
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
