You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "Ethan Guo (Jira)" <ji...@apache.org> on 2022/06/03 04:37:00 UTC
[jira] [Updated] (HUDI-4159) non existant partition field values has issues w/ partition pruning
[ https://issues.apache.org/jira/browse/HUDI-4159?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Ethan Guo updated HUDI-4159:
----------------------------
Fix Version/s: 0.11.1
(was: 0.11.0)
> non existant partition field values has issues w/ partition pruning
> -------------------------------------------------------------------
>
> Key: HUDI-4159
> URL: https://issues.apache.org/jira/browse/HUDI-4159
> Project: Apache Hudi
> Issue Type: Bug
> Components: reader-core
> Reporter: sivabalan narayanan
> Priority: Blocker
> Fix For: 0.11.1
>
>
> lets say some records don't have partition field values and are null. Based on our key gen code, we will set "Default" value for the same. But partition pruning may run into issues if original datatype of the partition field is non string (long/ integer) for instance. I ran into this for 0.10.0.
>
> {code:java}
> org.sparkproject.guava.util.concurrent.UncheckedExecutionException: java.lang.RuntimeException: Failed to cast value `default` to `IntegerType` for partition column `ss_sold_date_sk`
> at org.sparkproject.guava.cache.LocalCache$Segment.get(LocalCache.java:2263)
> at org.sparkproject.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.sparkproject.guava.cache.LocalCache$LocalManualCache.get(LocalCache.java:4789)
> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.getCachedPlan(SessionCatalog.scala:155)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.org$apache$spark$sql$execution$datasources$FindDataSourceTable$$readDataSourceTable(DataSourceStrategy.scala:249)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:288)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:278)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$2(AnalysisHelper.scala:108)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:73)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:108)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$4(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$mapChildren$1(TreeNode.scala:407)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:243)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:405)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:358)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.$anonfun$resolveOperatorsDown$1(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:221)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperatorsDown$(AnalysisHelper.scala:104)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperators(AnalysisHelper.scala:73)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.resolveOperators$(AnalysisHelper.scala:72)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:278)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:243)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:216)
> at scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
> at scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
> at scala.collection.immutable.List.foldLeft(List.scala:89)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:213)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:205)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:205)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:196)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:190)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:155)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:183)
> at org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:183)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.$anonfun$executeAndCheck$1(Analyzer.scala:174)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:228)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:173)
> at org.apache.spark.sql.execution.QueryExecution.$anonfun$analyzed$1(QueryExecution.scala:73)
> at org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
> at org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:143)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
> at org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:143)
> at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:73)
> at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:71)
> at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:63)
> at org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:98)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:96)
> at org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:615)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:772)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:610)
> at TPCDS.runQuery(TPCDS.scala:207)
> at TPCDS.runQuery(TPCDS.scala:219)
> ... 47 elided
> Caused by: java.lang.RuntimeException: Failed to cast value `default` to `IntegerType` for partition column `ss_sold_date_sk`
> at org.apache.spark.sql.execution.datasources.PartitioningUtils$.parsePartitionColumn(PartitioningUtils.scala:312)
> at org.apache.spark.sql.execution.datasources.PartitioningUtils$.parsePartition(PartitioningUtils.scala:250)
> at org.apache.spark.sql.execution.datasources.Spark3ParsePartitionUtil.parsePartition(Spark3ParsePartitionUtil.scala:37)
> at org.apache.hudi.HoodieFileIndex.$anonfun$getAllQueryPartitionPaths$3(HoodieFileIndex.scala:559)
> at scala.collection.TraversableLike.$anonfun$map$1(TraversableLike.scala:238)
> at scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
> at scala.collection.TraversableLike.map(TraversableLike.scala:238)
> at scala.collection.TraversableLike.map$(TraversableLike.scala:231)
> at scala.collection.AbstractTraversable.map(Traversable.scala:108)
> at org.apache.hudi.HoodieFileIndex.getAllQueryPartitionPaths(HoodieFileIndex.scala:511)
> at org.apache.hudi.HoodieFileIndex.loadPartitionPathFiles(HoodieFileIndex.scala:575)
> at org.apache.hudi.HoodieFileIndex.refresh0(HoodieFileIndex.scala:360)
> at org.apache.hudi.HoodieFileIndex.<init>(HoodieFileIndex.scala:157)
> at org.apache.hudi.DefaultSource.getBaseFileOnlyView(DefaultSource.scala:199)
> at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:119)
> at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:352)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.$anonfun$readDataSourceTable$1(DataSourceStrategy.scala:261)
> at org.sparkproject.guava.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4792)
> at org.sparkproject.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at org.sparkproject.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> at org.sparkproject.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.sparkproject.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> ... 178 more {code}
--
This message was sent by Atlassian Jira
(v8.20.7#820007)