[
https://issues.apache.org/jira/browse/HUDI-5768?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Ethan Guo updated HUDI-5768:
----------------------------
Epic Link: HUDI-1292
> Fail to read metadata table in Spark Datasource
> -----------------------------------------------
>
> Key: HUDI-5768
> URL: https://issues.apache.org/jira/browse/HUDI-5768
> Project: Apache Hudi
> Issue Type: Bug
> Affects Versions: 0.12.0, 0.12.1, 0.12.2
> Reporter: Ethan Guo
> Assignee: Ethan Guo
> Priority: Blocker
> Labels: pull-request-available
> Fix For: 0.13.0
>
>
> Using Hudi 0.13.0 and Spark 3.3.0, reading a table created by 0.13.0:
> {code:java}
> scala> val df =
> spark.read.format("hudi").load("/Users/ethan/Work/tmp/20230127-test-cli-bundle/hudi_trips_cow_backup/.hoodie/metadata")
> scala> df.count
> scala.MatchError: HFILE (of class
> org.apache.hudi.common.model.HoodieFileFormat)
> at
> org.apache.hudi.HoodieBaseRelation.x$2$lzycompute(HoodieBaseRelation.scala:216)
> at org.apache.hudi.HoodieBaseRelation.x$2(HoodieBaseRelation.scala:215)
> at
> org.apache.hudi.HoodieBaseRelation.fileFormat$lzycompute(HoodieBaseRelation.scala:215)
> at
> org.apache.hudi.HoodieBaseRelation.fileFormat(HoodieBaseRelation.scala:215)
> at
> org.apache.hudi.HoodieBaseRelation.canPruneRelationSchema(HoodieBaseRelation.scala:295)
> at
> org.apache.hudi.BaseMergeOnReadSnapshotRelation.canPruneRelationSchema(MergeOnReadSnapshotRelation.scala:102)
> at
> org.apache.spark.sql.execution.datasources.Spark33NestedSchemaPruning$$anonfun$apply0$1.applyOrElse(Spark33NestedSchemaPruning.scala:56)
> at
> org.apache.spark.sql.execution.datasources.Spark33NestedSchemaPruning$$anonfun$apply0$1.applyOrElse(Spark33NestedSchemaPruning.scala:50)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:584)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:176)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:584)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
> at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$3(TreeNode.scala:589)
> at
> org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren(TreeNode.scala:1228)
> at
> org.apache.spark.sql.catalyst.trees.UnaryLike.mapChildren$(TreeNode.scala:1227)
> at
> org.apache.spark.sql.catalyst.plans.logical.Aggregate.mapChildren(basicLogicalOperators.scala:976)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:589)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$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:560)
> at
> org.apache.spark.sql.execution.datasources.Spark33NestedSchemaPruning.apply0(Spark33NestedSchemaPruning.scala:50)
> at
> org.apache.spark.sql.execution.datasources.Spark33NestedSchemaPruning.apply(Spark33NestedSchemaPruning.scala:44)
> at
> org.apache.spark.sql.execution.datasources.Spark33NestedSchemaPruning.apply(Spark33NestedSchemaPruning.scala:39)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$2(RuleExecutor.scala:211)
> at
> scala.collection.LinearSeqOptimized.foldLeft(LinearSeqOptimized.scala:126)
> at
> scala.collection.LinearSeqOptimized.foldLeft$(LinearSeqOptimized.scala:122)
> at scala.collection.immutable.List.foldLeft(List.scala:91)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1(RuleExecutor.scala:208)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$execute$1$adapted(RuleExecutor.scala:200)
> at scala.collection.immutable.List.foreach(List.scala:431)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:200)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.$anonfun$executeAndTrack$1(RuleExecutor.scala:179)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:88)
> at
> org.apache.spark.sql.catalyst.rules.RuleExecutor.executeAndTrack(RuleExecutor.scala:179)
> at
> org.apache.spark.sql.execution.QueryExecution.$anonfun$optimizedPlan$1(QueryExecution.scala:126)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker.measurePhase(QueryPlanningTracker.scala:111)
> at
> org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$2(QueryExecution.scala:185)
> at
> org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:510)
> at
> org.apache.spark.sql.execution.QueryExecution.$anonfun$executePhase$1(QueryExecution.scala:185)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.QueryExecution.executePhase(QueryExecution.scala:184)
> at
> org.apache.spark.sql.execution.QueryExecution.optimizedPlan$lzycompute(QueryExecution.scala:122)
> at
> org.apache.spark.sql.execution.QueryExecution.optimizedPlan(QueryExecution.scala:118)
> at
> org.apache.spark.sql.execution.QueryExecution.assertOptimized(QueryExecution.scala:136)
> at
> org.apache.spark.sql.execution.QueryExecution.executedPlan$lzycompute(QueryExecution.scala:154)
> at
> org.apache.spark.sql.execution.QueryExecution.executedPlan(QueryExecution.scala:151)
> at
> org.apache.spark.sql.execution.QueryExecution.simpleString(QueryExecution.scala:204)
> at
> org.apache.spark.sql.execution.QueryExecution.org$apache$spark$sql$execution$QueryExecution$$explainString(QueryExecution.scala:249)
> at
> org.apache.spark.sql.execution.QueryExecution.explainString(QueryExecution.scala:218)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:103)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:169)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:95)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:64)
> at org.apache.spark.sql.Dataset.withAction(Dataset.scala:3856)
> at org.apache.spark.sql.Dataset.count(Dataset.scala:3160)
> ... 47 elided{code}
> Using Hudi 0.12.0 and Spark 3.2.1 hit the same issue as above.
> Using Hudi 0.11.1 and Spark 3.2.1 can read the same metadata table.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
