[
https://issues.apache.org/jira/browse/HUDI-5615?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
victor updated HUDI-5615:
-------------------------
Description:
How to reproduce
Env EMR 6.9.0 HUDI 0.12.1
[https://docs.aws.amazon.com/emr/latest/ReleaseGuide/emr-690-release.html]
{code:java}
create external table databasename.table_name using hudi location
's3://my_bucket/attributes/table_name/'{code}
Run
{code:java}
23/01/25 04:57:32 WARN HoodieTableConfig: Run `table recover-configs` if config
update/delete failed midway. Falling back to backed up configs.23/01/25
04:57:32 ERROR SparkSQLDriver: Failed in [create external table
segp.pax_table_name_test using hudi location
's3://my_bucket/attributes/table_name/']org.apache.hudi.exception.HoodieIOException:
Could not load Hoodie properties from
s3://my_bucket/attributes/table_name/.hoodie/hoodie.properties at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:255)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:129)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient.newMetaClient(HoodieTableMetaClient.java:642)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient.access$000(HoodieTableMetaClient.java:80)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient$Builder.build(HoodieTableMetaClient.java:711)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient$lzycompute(HoodieCatalogTable.scala:81)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient(HoodieCatalogTable.scala:79)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig$lzycompute(HoodieCatalogTable.scala:87)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig(HoodieCatalogTable.scala:87)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand$.validateTblProperties(CreateHoodieTableCommand.scala:96)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand.run(CreateHoodieTableCommand.scala:66)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:75)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:73)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:84)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:103)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:114)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$7(SQLExecution.scala:139)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:139)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:138)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:100)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:96)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:615)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:177)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:615)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:591)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:96)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:83)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:81)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.Dataset.<init>(Dataset.scala:222)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:102)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:99)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:622)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:384)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:504)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:498)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
scala.collection.Iterator.foreach(Iterator.scala:943)
~[scala-library-2.12.15.jar:?] at
scala.collection.Iterator.foreach$(Iterator.scala:943)
~[scala-library-2.12.15.jar:?] at
scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
~[scala-library-2.12.15.jar:?] at
scala.collection.IterableLike.foreach(IterableLike.scala:74)
~[scala-library-2.12.15.jar:?] at
scala.collection.IterableLike.foreach$(IterableLike.scala:73)
~[scala-library-2.12.15.jar:?] at
scala.collection.AbstractIterable.foreach(Iterable.scala:56)
~[scala-library-2.12.15.jar:?] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:498)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:286)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) ~[?:1.8.0_352]
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
~[?:1.8.0_352] at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
~[?:1.8.0_352] at java.lang.reflect.Method.invoke(Method.java:498)
~[?:1.8.0_352] at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1006)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1095)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1104)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1]Caused by:
java.io.FileNotFoundException: No such file or directory
's3://my_bucket/attributes/table_name/.hoodie/hoodie.properties.backup' at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.getFileStatus(S3NativeFileSystem.java:524)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:935)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:927)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
org.apache.hadoop.fs.FileSystem.open(FileSystem.java:983)
~[hadoop-client-api-3.3.3-amzn-0.jar:?] at
com.amazon.ws.emr.hadoop.fs.EmrFileSystem.open(EmrFileSystem.java:197)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:468)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableConfig.fetchConfigs(HoodieTableConfig.java:309)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:245)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] ... 72
moreorg.apache.hudi.exception.HoodieIOException: Could not load Hoodie
properties from s3://my_bucket/attributes/table_name/.hoodie/hoodie.properties
at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:255)
at
org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:129)
at
org.apache.hudi.common.table.HoodieTableMetaClient.newMetaClient(HoodieTableMetaClient.java:642)
at
org.apache.hudi.common.table.HoodieTableMetaClient.access$000(HoodieTableMetaClient.java:80)
at
org.apache.hudi.common.table.HoodieTableMetaClient$Builder.build(HoodieTableMetaClient.java:711)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient$lzycompute(HoodieCatalogTable.scala:81)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient(HoodieCatalogTable.scala:79)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig$lzycompute(HoodieCatalogTable.scala:87)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig(HoodieCatalogTable.scala:87)
at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand$.validateTblProperties(CreateHoodieTableCommand.scala:96)
at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand.run(CreateHoodieTableCommand.scala:66)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$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$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:103)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:114)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$7(SQLExecution.scala:139)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:139)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:138)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:100)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:96)
at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:615)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:177)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:615)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$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:591)
at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:96)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:83)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:81)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:222) at
org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:102) at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779) at
org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:99) at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:622) at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779) at
org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617) at
org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651) at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:384)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:504)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:498)
at scala.collection.Iterator.foreach(Iterator.scala:943) at
scala.collection.Iterator.foreach$(Iterator.scala:943) at
scala.collection.AbstractIterator.foreach(Iterator.scala:1431) at
scala.collection.IterableLike.foreach(IterableLike.scala:74) at
scala.collection.IterableLike.foreach$(IterableLike.scala:73) at
scala.collection.AbstractIterable.foreach(Iterable.scala:56) at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:498)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:286)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1006)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203) at
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90) at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1095)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1104) at
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)Caused by:
java.io.FileNotFoundException: No such file or directory
's3://my_bucket/attributes/table_name/.hoodie/hoodie.properties.backup' at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.getFileStatus(S3NativeFileSystem.java:524)
at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:935)
at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:927)
at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:983) at
com.amazon.ws.emr.hadoop.fs.EmrFileSystem.open(EmrFileSystem.java:197) at
org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:468)
at
org.apache.hudi.common.table.HoodieTableConfig.fetchConfigs(HoodieTableConfig.java:309)
at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:245)
... 72 more {code}
was:
{code:java}
23/01/25 04:57:32 WARN HoodieTableConfig: Run `table recover-configs` if config
update/delete failed midway. Falling back to backed up configs.23/01/25
04:57:32 ERROR SparkSQLDriver: Failed in [create external table
segp.pax_table_name_test using hudi location
's3://my_bucket/attributes/table_name/']org.apache.hudi.exception.HoodieIOException:
Could not load Hoodie properties from
s3://my_bucket/attributes/table_name/.hoodie/hoodie.properties at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:255)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:129)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient.newMetaClient(HoodieTableMetaClient.java:642)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient.access$000(HoodieTableMetaClient.java:80)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableMetaClient$Builder.build(HoodieTableMetaClient.java:711)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient$lzycompute(HoodieCatalogTable.scala:81)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient(HoodieCatalogTable.scala:79)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig$lzycompute(HoodieCatalogTable.scala:87)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig(HoodieCatalogTable.scala:87)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand$.validateTblProperties(CreateHoodieTableCommand.scala:96)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand.run(CreateHoodieTableCommand.scala:66)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:75)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:73)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:84)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:103)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:114)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$7(SQLExecution.scala:139)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:139)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:138)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:100)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:96)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:615)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:177)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:615)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:591)
~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:96)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:83)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:81)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.Dataset.<init>(Dataset.scala:222)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:102)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:99)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:622)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651)
~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:384)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:504)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:498)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
scala.collection.Iterator.foreach(Iterator.scala:943)
~[scala-library-2.12.15.jar:?] at
scala.collection.Iterator.foreach$(Iterator.scala:943)
~[scala-library-2.12.15.jar:?] at
scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
~[scala-library-2.12.15.jar:?] at
scala.collection.IterableLike.foreach(IterableLike.scala:74)
~[scala-library-2.12.15.jar:?] at
scala.collection.IterableLike.foreach$(IterableLike.scala:73)
~[scala-library-2.12.15.jar:?] at
scala.collection.AbstractIterable.foreach(Iterable.scala:56)
~[scala-library-2.12.15.jar:?] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:498)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:286)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) ~[?:1.8.0_352]
at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
~[?:1.8.0_352] at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
~[?:1.8.0_352] at java.lang.reflect.Method.invoke(Method.java:498)
~[?:1.8.0_352] at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1006)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1095)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1104)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1]Caused by:
java.io.FileNotFoundException: No such file or directory
's3://my_bucket/attributes/table_name/.hoodie/hoodie.properties.backup' at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.getFileStatus(S3NativeFileSystem.java:524)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:935)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:927)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
org.apache.hadoop.fs.FileSystem.open(FileSystem.java:983)
~[hadoop-client-api-3.3.3-amzn-0.jar:?] at
com.amazon.ws.emr.hadoop.fs.EmrFileSystem.open(EmrFileSystem.java:197)
~[emrfs-hadoop-assembly-2.54.0.jar:?] at
org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:468)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableConfig.fetchConfigs(HoodieTableConfig.java:309)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:245)
~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] ... 72
moreorg.apache.hudi.exception.HoodieIOException: Could not load Hoodie
properties from s3://my_bucket/attributes/table_name/.hoodie/hoodie.properties
at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:255)
at
org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:129)
at
org.apache.hudi.common.table.HoodieTableMetaClient.newMetaClient(HoodieTableMetaClient.java:642)
at
org.apache.hudi.common.table.HoodieTableMetaClient.access$000(HoodieTableMetaClient.java:80)
at
org.apache.hudi.common.table.HoodieTableMetaClient$Builder.build(HoodieTableMetaClient.java:711)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient$lzycompute(HoodieCatalogTable.scala:81)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient(HoodieCatalogTable.scala:79)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig$lzycompute(HoodieCatalogTable.scala:87)
at
org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig(HoodieCatalogTable.scala:87)
at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand$.validateTblProperties(CreateHoodieTableCommand.scala:96)
at
org.apache.spark.sql.hudi.command.CreateHoodieTableCommand.run(CreateHoodieTableCommand.scala:66)
at
org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$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$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:103)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
at
org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:114)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$7(SQLExecution.scala:139)
at
org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
at
org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:139)
at
org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
at
org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:138)
at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
at
org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:100)
at
org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:96)
at
org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:615)
at
org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:177)
at
org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:615)
at
org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$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:591)
at
org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:96)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:83)
at
org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:81)
at org.apache.spark.sql.Dataset.<init>(Dataset.scala:222) at
org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:102) at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779) at
org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:99) at
org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:622) at
org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779) at
org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617) at
org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651) at
org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:384)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:504)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:498)
at scala.collection.Iterator.foreach(Iterator.scala:943) at
scala.collection.Iterator.foreach$(Iterator.scala:943) at
scala.collection.AbstractIterator.foreach(Iterator.scala:1431) at
scala.collection.IterableLike.foreach(IterableLike.scala:74) at
scala.collection.IterableLike.foreach$(IterableLike.scala:73) at
scala.collection.AbstractIterable.foreach(Iterable.scala:56) at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:498)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:286)
at
org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
at
sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498) at
org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at
org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1006)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203) at
org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90) at
org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1095)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1104) at
org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)Caused by:
java.io.FileNotFoundException: No such file or directory
's3://my_bucket/attributes/table_name/.hoodie/hoodie.properties.backup' at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.getFileStatus(S3NativeFileSystem.java:524)
at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:935)
at
com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:927)
at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:983) at
com.amazon.ws.emr.hadoop.fs.EmrFileSystem.open(EmrFileSystem.java:197) at
org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:468)
at
org.apache.hudi.common.table.HoodieTableConfig.fetchConfigs(HoodieTableConfig.java:309)
at
org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:245)
... 72 more {code}
> Fail to run create table on dataset
> -----------------------------------
>
> Key: HUDI-5615
> URL: https://issues.apache.org/jira/browse/HUDI-5615
> Project: Apache Hudi
> Issue Type: Task
> Reporter: victor
> Priority: Major
>
> How to reproduce
> Env EMR 6.9.0 HUDI 0.12.1
> [https://docs.aws.amazon.com/emr/latest/ReleaseGuide/emr-690-release.html]
>
> {code:java}
> create external table databasename.table_name using hudi location
> 's3://my_bucket/attributes/table_name/'{code}
>
>
> Run
> {code:java}
> 23/01/25 04:57:32 WARN HoodieTableConfig: Run `table recover-configs` if
> config update/delete failed midway. Falling back to backed up
> configs.23/01/25 04:57:32 ERROR SparkSQLDriver: Failed in [create external
> table segp.pax_table_name_test using hudi location
> 's3://my_bucket/attributes/table_name/']org.apache.hudi.exception.HoodieIOException:
> Could not load Hoodie properties from
> s3://my_bucket/attributes/table_name/.hoodie/hoodie.properties at
> org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:255)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:129)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.hudi.common.table.HoodieTableMetaClient.newMetaClient(HoodieTableMetaClient.java:642)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.hudi.common.table.HoodieTableMetaClient.access$000(HoodieTableMetaClient.java:80)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.hudi.common.table.HoodieTableMetaClient$Builder.build(HoodieTableMetaClient.java:711)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient$lzycompute(HoodieCatalogTable.scala:81)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient(HoodieCatalogTable.scala:79)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig$lzycompute(HoodieCatalogTable.scala:87)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig(HoodieCatalogTable.scala:87)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hudi.command.CreateHoodieTableCommand$.validateTblProperties(CreateHoodieTableCommand.scala:96)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.spark.sql.hudi.command.CreateHoodieTableCommand.run(CreateHoodieTableCommand.scala:66)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$lzycompute(commands.scala:75)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult(commands.scala:73)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.executeCollect(commands.scala:84)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:103)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:114)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$7(SQLExecution.scala:139)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:139)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:138)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:100)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:96)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:615)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:177)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:615)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$super$transformDownWithPruning(LogicalPlan.scala:30)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning(AnalysisHelper.scala:267)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper.transformDownWithPruning$(AnalysisHelper.scala:263)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.transformDownWithPruning(LogicalPlan.scala:30)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDown(TreeNode.scala:591)
> ~[spark-catalyst_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:96)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:83)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:81)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.Dataset.<init>(Dataset.scala:222)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:102)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:99)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:622)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651)
> ~[spark-sql_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:384)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:504)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:498)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> scala.collection.Iterator.foreach(Iterator.scala:943)
> ~[scala-library-2.12.15.jar:?] at
> scala.collection.Iterator.foreach$(Iterator.scala:943)
> ~[scala-library-2.12.15.jar:?] at
> scala.collection.AbstractIterator.foreach(Iterator.scala:1431)
> ~[scala-library-2.12.15.jar:?] at
> scala.collection.IterableLike.foreach(IterableLike.scala:74)
> ~[scala-library-2.12.15.jar:?] at
> scala.collection.IterableLike.foreach$(IterableLike.scala:73)
> ~[scala-library-2.12.15.jar:?] at
> scala.collection.AbstractIterable.foreach(Iterable.scala:56)
> ~[scala-library-2.12.15.jar:?] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:498)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:286)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> ~[spark-hive-thriftserver_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) ~[?:1.8.0_352]
> at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> ~[?:1.8.0_352] at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> ~[?:1.8.0_352] at java.lang.reflect.Method.invoke(Method.java:498)
> ~[?:1.8.0_352] at
> org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1006)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1095)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1104)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1] at
> org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> ~[spark-core_2.12-3.3.0-amzn-1.jar:3.3.0-amzn-1]Caused by:
> java.io.FileNotFoundException: No such file or directory
> 's3://my_bucket/attributes/table_name/.hoodie/hoodie.properties.backup' at
> com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.getFileStatus(S3NativeFileSystem.java:524)
> ~[emrfs-hadoop-assembly-2.54.0.jar:?] at
> com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:935)
> ~[emrfs-hadoop-assembly-2.54.0.jar:?] at
> com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:927)
> ~[emrfs-hadoop-assembly-2.54.0.jar:?] at
> org.apache.hadoop.fs.FileSystem.open(FileSystem.java:983)
> ~[hadoop-client-api-3.3.3-amzn-0.jar:?] at
> com.amazon.ws.emr.hadoop.fs.EmrFileSystem.open(EmrFileSystem.java:197)
> ~[emrfs-hadoop-assembly-2.54.0.jar:?] at
> org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:468)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.hudi.common.table.HoodieTableConfig.fetchConfigs(HoodieTableConfig.java:309)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] at
> org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:245)
> ~[hudi-spark3-bundle_2.12-0.12.1-amzn-0.jar:0.12.1-amzn-0] ... 72
> moreorg.apache.hudi.exception.HoodieIOException: Could not load Hoodie
> properties from
> s3://my_bucket/attributes/table_name/.hoodie/hoodie.properties at
> org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:255)
> at
> org.apache.hudi.common.table.HoodieTableMetaClient.<init>(HoodieTableMetaClient.java:129)
> at
> org.apache.hudi.common.table.HoodieTableMetaClient.newMetaClient(HoodieTableMetaClient.java:642)
> at
> org.apache.hudi.common.table.HoodieTableMetaClient.access$000(HoodieTableMetaClient.java:80)
> at
> org.apache.hudi.common.table.HoodieTableMetaClient$Builder.build(HoodieTableMetaClient.java:711)
> at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient$lzycompute(HoodieCatalogTable.scala:81)
> at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.metaClient(HoodieCatalogTable.scala:79)
> at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig$lzycompute(HoodieCatalogTable.scala:87)
> at
> org.apache.spark.sql.catalyst.catalog.HoodieCatalogTable.tableConfig(HoodieCatalogTable.scala:87)
> at
> org.apache.spark.sql.hudi.command.CreateHoodieTableCommand$.validateTblProperties(CreateHoodieTableCommand.scala:96)
> at
> org.apache.spark.sql.hudi.command.CreateHoodieTableCommand.run(CreateHoodieTableCommand.scala:66)
> at
> org.apache.spark.sql.execution.command.ExecutedCommandExec.sideEffectResult$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$$anonfun$eagerlyExecuteCommands$1.$anonfun$applyOrElse$1(QueryExecution.scala:103)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
> at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
> at
> org.apache.spark.sql.execution.SQLExecution$.executeQuery$1(SQLExecution.scala:114)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$7(SQLExecution.scala:139)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.withTracker(QueryPlanningTracker.scala:107)
> at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$6(SQLExecution.scala:139)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withNewExecutionId$1(SQLExecution.scala:138)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:68)
> at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:100)
> at
> org.apache.spark.sql.execution.QueryExecution$$anonfun$eagerlyExecuteCommands$1.applyOrElse(QueryExecution.scala:96)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.$anonfun$transformDownWithPruning$1(TreeNode.scala:615)
> at
> org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:177)
> at
> org.apache.spark.sql.catalyst.trees.TreeNode.transformDownWithPruning(TreeNode.scala:615)
> at
> org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.org$apache$spark$sql$catalyst$plans$logical$AnalysisHelper$$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:591)
> at
> org.apache.spark.sql.execution.QueryExecution.eagerlyExecuteCommands(QueryExecution.scala:96)
> at
> org.apache.spark.sql.execution.QueryExecution.commandExecuted$lzycompute(QueryExecution.scala:83)
> at
> org.apache.spark.sql.execution.QueryExecution.commandExecuted(QueryExecution.scala:81)
> at org.apache.spark.sql.Dataset.<init>(Dataset.scala:222) at
> org.apache.spark.sql.Dataset$.$anonfun$ofRows$2(Dataset.scala:102) at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779) at
> org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:99) at
> org.apache.spark.sql.SparkSession.$anonfun$sql$1(SparkSession.scala:622)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779) at
> org.apache.spark.sql.SparkSession.sql(SparkSession.scala:617) at
> org.apache.spark.sql.SQLContext.sql(SQLContext.scala:651) at
> org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:67)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:384)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1(SparkSQLCLIDriver.scala:504)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.$anonfun$processLine$1$adapted(SparkSQLCLIDriver.scala:498)
> at scala.collection.Iterator.foreach(Iterator.scala:943) at
> scala.collection.Iterator.foreach$(Iterator.scala:943) at
> scala.collection.AbstractIterator.foreach(Iterator.scala:1431) at
> scala.collection.IterableLike.foreach(IterableLike.scala:74) at
> scala.collection.IterableLike.foreach$(IterableLike.scala:73) at
> scala.collection.AbstractIterable.foreach(Iterable.scala:56) at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processLine(SparkSQLCLIDriver.scala:498)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:286)
> at
> org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at
> sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:62)
> at
> sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
> at java.lang.reflect.Method.invoke(Method.java:498) at
> org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at
> org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:1006)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:180)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:203) at
> org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:90) at
> org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:1095)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:1104) at
> org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)Caused by:
> java.io.FileNotFoundException: No such file or directory
> 's3://my_bucket/attributes/table_name/.hoodie/hoodie.properties.backup' at
> com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.getFileStatus(S3NativeFileSystem.java:524)
> at
> com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:935)
> at
> com.amazon.ws.emr.hadoop.fs.s3n.S3NativeFileSystem.open(S3NativeFileSystem.java:927)
> at org.apache.hadoop.fs.FileSystem.open(FileSystem.java:983) at
> com.amazon.ws.emr.hadoop.fs.EmrFileSystem.open(EmrFileSystem.java:197) at
> org.apache.hudi.common.fs.HoodieWrapperFileSystem.open(HoodieWrapperFileSystem.java:468)
> at
> org.apache.hudi.common.table.HoodieTableConfig.fetchConfigs(HoodieTableConfig.java:309)
> at
> org.apache.hudi.common.table.HoodieTableConfig.<init>(HoodieTableConfig.java:245)
> ... 72 more {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
