[
https://issues.apache.org/jira/browse/HUDI-6827?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Sagar Sumit closed HUDI-6827.
-----------------------------
Resolution: Fixed
> Exception would be thrown out if insert/insertOverWrite empty data into HUDI
> table using bulkInsert
> ---------------------------------------------------------------------------------------------------
>
> Key: HUDI-6827
> URL: https://issues.apache.org/jira/browse/HUDI-6827
> Project: Apache Hudi
> Issue Type: Bug
> Reporter: Jing Zhang
> Assignee: Jing Zhang
> Priority: Major
> Labels: pull-request-available
> Fix For: 1.0.0, 0.14.1
>
> Attachments: screenshot-1.png
>
>
> If run a spark job to insert/insertOverWrite empty data into HUDI table using
> bulkInsert, the exceptions like 'java.lang.IllegalArgumentException: Positive
> number of partitions required' would be thrown out.
> If using bulk insert overwrite, the exception stack is like
> {code:java}
> Positive number of partitions required
> java.lang.IllegalArgumentException: Positive number of partitions required
> at
> org.apache.spark.rdd.ParallelCollectionRDD$.slice(ParallelCollectionRDD.scala:118)
> at
> org.apache.spark.rdd.ParallelCollectionRDD.getPartitions(ParallelCollectionRDD.scala:96)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:300)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:296)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:300)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:296)
> at org.apache.spark.rdd.RDD.$anonfun$distinct$11(RDD.scala:470)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
> at org.apache.spark.rdd.RDD.distinct(RDD.scala:470)
> at org.apache.spark.api.java.JavaRDD.distinct(JavaRDD.scala:85)
> at org.apache.hudi.data.HoodieJavaRDD.distinct(HoodieJavaRDD.java:157)
> at
> org.apache.hudi.commit.DatasetBulkInsertOverwriteCommitActionExecutor.getPartitionToReplacedFileIds(DatasetBulkInsertOverwriteCommitActionExecutor.java:61)
> at
> org.apache.hudi.commit.BaseDatasetBulkInsertCommitActionExecutor.lambda$buildHoodieWriteMetadata$0(BaseDatasetBulkInsertCommitActionExecutor.java:83)
> at org.apache.hudi.common.util.Option.map(Option.java:108)
> at
> org.apache.hudi.commit.BaseDatasetBulkInsertCommitActionExecutor.buildHoodieWriteMetadata(BaseDatasetBulkInsertCommitActionExecutor.java:80)
> at
> org.apache.hudi.commit.BaseDatasetBulkInsertCommitActionExecutor.execute(BaseDatasetBulkInsertCommitActionExecutor.java:102)
> at
> org.apache.hudi.HoodieSparkSqlWriter$.bulkInsertAsRow(HoodieSparkSqlWriter.scala:908)
> at
> org.apache.hudi.HoodieSparkSqlWriter$.writeInternal(HoodieSparkSqlWriter.scala:407)
> at
> org.apache.hudi.HoodieSparkSqlWriter$.write(HoodieSparkSqlWriter.scala:132)
> at
> org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand$.run(InsertIntoHoodieTableCommand.scala:108)
> at
> org.apache.spark.sql.hudi.command.InsertIntoHoodieTableCommand.run(InsertIntoHoodieTableCommand.scala:61)
> {code}
> if using bulk insert,
> {code:java}
> Caused by: org.apache.hudi.exception.HoodieException: Failed to update
> metadata
> at
> org.apache.hudi.internal.DataSourceInternalWriterHelper.commit(DataSourceInternalWriterHelper.java:92)
> at
> org.apache.hudi.spark3.internal.HoodieDataSourceInternalBatchWrite.commit(HoodieDataSourceInternalBatchWrite.java:92)
> at
> org.apache.spark.sql.execution.datasources.v2.V2TableWriteExec.writeWithV2(WriteToDataSourceV2Exec.scala:369)
> ... 138 more
> Caused by: org.apache.hudi.exception.HoodieException: Failed to update
> metadata
> at
> org.apache.hudi.client.BaseHoodieWriteClient.writeTableMetadata(BaseHoodieWriteClient.java:367)
> at
> org.apache.hudi.client.BaseHoodieWriteClient.commit(BaseHoodieWriteClient.java:285)
> at
> org.apache.hudi.client.BaseHoodieWriteClient.commitStats(BaseHoodieWriteClient.java:236)
> at
> org.apache.hudi.client.BaseHoodieWriteClient.commitStats(BaseHoodieWriteClient.java:211)
> at
> org.apache.hudi.internal.DataSourceInternalWriterHelper.commit(DataSourceInternalWriterHelper.java:89)
> ... 140 more
> Caused by: java.lang.IllegalArgumentException: Positive number of partitions
> required
> at
> org.apache.spark.rdd.ParallelCollectionRDD$.slice(ParallelCollectionRDD.scala:118)
> at
> org.apache.spark.rdd.ParallelCollectionRDD.getPartitions(ParallelCollectionRDD.scala:96)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:300)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:296)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:300)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:296)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:300)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:296)
> at
> org.apache.spark.rdd.MapPartitionsRDD.getPartitions(MapPartitionsRDD.scala:49)
> at org.apache.spark.rdd.RDD.$anonfun$partitions$2(RDD.scala:300)
> at scala.Option.getOrElse(Option.scala:189)
> at org.apache.spark.rdd.RDD.partitions(RDD.scala:296)
> at
> org.apache.spark.SparkContext.$anonfun$union$2(SparkContext.scala:1410)
> at
> org.apache.spark.SparkContext.$anonfun$union$2$adapted(SparkContext.scala:1410)
> at scala.collection.TraversableLike.noneIn$1(TraversableLike.scala:271)
> at
> scala.collection.TraversableLike.filterImpl(TraversableLike.scala:337)
> at
> scala.collection.TraversableLike.filterImpl$(TraversableLike.scala:249)
> at
> scala.collection.AbstractTraversable.filterImpl(Traversable.scala:108)
> at scala.collection.TraversableLike.filter(TraversableLike.scala:347)
> at scala.collection.TraversableLike.filter$(TraversableLike.scala:347)
> at scala.collection.AbstractTraversable.filter(Traversable.scala:108)
> at
> org.apache.spark.SparkContext.$anonfun$union$1(SparkContext.scala:1410)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.SparkContext.withScope(SparkContext.scala:792)
> at org.apache.spark.SparkContext.union(SparkContext.scala:1409)
> at
> org.apache.spark.SparkContext.$anonfun$union$5(SparkContext.scala:1421)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.SparkContext.withScope(SparkContext.scala:792)
> at org.apache.spark.SparkContext.union(SparkContext.scala:1421)
> at org.apache.spark.rdd.RDD.$anonfun$union$1(RDD.scala:665)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:112)
> at org.apache.spark.rdd.RDD.withScope(RDD.scala:414)
> at org.apache.spark.rdd.RDD.union(RDD.scala:665)
> at org.apache.spark.api.java.JavaRDD.union(JavaRDD.scala:177)
> at org.apache.hudi.data.HoodieJavaRDD.union(HoodieJavaRDD.java:172)
> at
> org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.lambda$update$21(HoodieBackedTableMetadataWriter.java:918)
> at
> org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.processAndCommit(HoodieBackedTableMetadataWriter.java:853)
> at
> org.apache.hudi.metadata.HoodieBackedTableMetadataWriter.update(HoodieBackedTableMetadataWriter.java:910)
> at
> org.apache.hudi.client.BaseHoodieWriteClient.writeTableMetadata(BaseHoodieWriteClient.java:362)
> ... 144 more
> {code}
> And Similar exception would be thrown out using Spark 2.X.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
