You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hudi.apache.org by "Raymond Xu (Jira)" <ji...@apache.org> on 2022/01/13 03:58:00 UTC
[jira] [Updated] (HUDI-3240) ALTER TABLE rename breaks with managed table in Spark 2.4
[ https://issues.apache.org/jira/browse/HUDI-3240?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Raymond Xu updated HUDI-3240:
-----------------------------
Description:
{code:sql}
create table if not exists cow_nonpt_nonpcf_tbl (
id int,
name string,
price double
) using hudi
options (
type = 'cow',
primaryKey = 'id'
);
insert into cow_nonpt_nonpcf_tbl select 1, 'a1', 20;
ALTER TABLE cow_nonpt_nonpcf_tbl RENAME TO cow_nonpt_nonpcf_tbl_2;
desc cow_nonpt_nonpcf_tbl_2;
-- desc works fine
select * from desc cow_nonpt_nonpcf_tbl_2;
-- throws exception{code}
{code:java}
22/01/13 03:48:18 ERROR SparkSQLDriver: Failed in [select * from cow_nonpt_nonpcf_tbl_2]
java.util.concurrent.ExecutionException: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306)
at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293)
at org.spark_project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116)
at org.spark_project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135)
at org.spark_project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410)
at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380)
at org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
at org.spark_project.guava.cache.LocalCache$LocalManualCache.get(LocalCache.java:4789)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.getCachedPlan(SessionCatalog.scala:141)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable.org$apache$spark$sql$execution$datasources$FindDataSourceTable$$readDataSourceTable(DataSourceStrategy.scala:227)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:264)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:255)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:107)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperators(AnalysisHelper.scala:73)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:255)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:223)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:274)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:845)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:161)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:920)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:929)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:611)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:824)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:601)
at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:421)
at org.apache.hudi.common.util.TablePathUtils.getTablePath(TablePathUtils.java:50)
at org.apache.hudi.DataSourceUtils.getTablePath(DataSourceUtils.java:76)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:103)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:316)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:242)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:227)
at org.spark_project.guava.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4792)
at org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
... 77 more
java.util.concurrent.ExecutionException: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306)
at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293)
at org.spark_project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116)
at org.spark_project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135)
at org.spark_project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410)
at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380)
at org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
at org.spark_project.guava.cache.LocalCache$LocalManualCache.get(LocalCache.java:4789)
at org.apache.spark.sql.catalyst.catalog.SessionCatalog.getCachedPlan(SessionCatalog.scala:141)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable.org$apache$spark$sql$execution$datasources$FindDataSourceTable$$readDataSourceTable(DataSourceStrategy.scala:227)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:264)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:255)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:107)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperators(AnalysisHelper.scala:73)
at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:255)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:223)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
at scala.collection.immutable.List.foldLeft(List.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
at scala.collection.immutable.List.foreach(List.scala:392)
at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:274)
at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
at java.lang.reflect.Method.invoke(Unknown Source)
at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:845)
at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:161)
at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)
at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:920)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:929)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:611)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:824)
at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:601)
at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:421)
at org.apache.hudi.common.util.TablePathUtils.getTablePath(TablePathUtils.java:50)
at org.apache.hudi.DataSourceUtils.getTablePath(DataSourceUtils.java:76)
at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:103)
at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:316)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:242)
at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:227)
at org.spark_project.guava.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4792)
at org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
... 77 more
{code}
table created in /opt/spark-warehouse but it's looking for `File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2`
{code:java}
spark.serializer org.apache.spark.serializer.KryoSerializer
spark.sql.extensions org.apache.spark.sql.hudi.HoodieSparkSessionExtension
spark.sql.hive.convertMetastoreParquet false
spark.sql.catalogImplementation in-memory
spark.sql.warehouse.dir /opt/spark-warehouse
{code}
reported while testing on 0.10.1-rc1 (spark 2.4.4), not an issue in spark 3.0.3 and 3.1.2
was:
{code:sql}
create table if not exists cow_nonpt_nonpcf_tbl (
id int,
name string,
price double
) using hudi
options (
type = 'cow',
primaryKey = 'id'
);
insert into cow_nonpt_nonpcf_tbl select 1, 'a1', 20;
DESC cow_nonpt_nonpcf_tbl;
-- shows id int
ALTER TABLE cow_nonpt_nonpcf_tbl change column id id bigint;
DESC cow_nonpt_nonpcf_tbl;
-- shows id bigint
-- this works fine so far
select * from cow_nonpt_nonpcf_tbl;
-- throws exception
{code}
{code}
org.apache.spark.sql.execution.QueryExecutionException: Parquet column cannot be converted in file file:///opt/spark-warehouse/cow_nonpt_nonpcf_tbl/ff3c68e6-84d4-4a8a-8bc8-cc58736847aa-0_0-7-7_20220112182401452.parquet. Column: [id], Expected: bigint, Found: INT32
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:179)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
at org.apache.spark.sql.execution.FileSourceScanExec$$anon$1.hasNext(DataSourceScanExec.scala:503)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.columnartorow_nextBatch_0$(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$GeneratedIteratorForCodegenStage1.processNext(Unknown Source)
at org.apache.spark.sql.execution.BufferedRowIterator.hasNext(BufferedRowIterator.java:43)
at org.apache.spark.sql.execution.WholeStageCodegenExec$$anon$1.hasNext(WholeStageCodegenExec.scala:755)
at org.apache.spark.sql.execution.SparkPlan.$anonfun$getByteArrayRdd$1(SparkPlan.scala:345)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2(RDD.scala:898)
at org.apache.spark.rdd.RDD.$anonfun$mapPartitionsInternal$2$adapted(RDD.scala:898)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:52)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:373)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:337)
at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:90)
at org.apache.spark.scheduler.Task.run(Task.scala:131)
at org.apache.spark.executor.Executor$TaskRunner.$anonfun$run$3(Executor.scala:497)
at org.apache.spark.util.Utils$.tryWithSafeFinally(Utils.scala:1439)
at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:500)
at java.util.concurrent.ThreadPoolExecutor.runWorker(Unknown Source)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(Unknown Source)
at java.lang.Thread.run(Unknown Source)
Caused by: org.apache.spark.sql.execution.datasources.SchemaColumnConvertNotSupportedException
at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.constructConvertNotSupportedException(VectorizedColumnReader.java:339)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readIntBatch(VectorizedColumnReader.java:571)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedColumnReader.readBatch(VectorizedColumnReader.java:294)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextBatch(VectorizedParquetRecordReader.java:283)
at org.apache.spark.sql.execution.datasources.parquet.VectorizedParquetRecordReader.nextKeyValue(VectorizedParquetRecordReader.java:181)
at org.apache.spark.sql.execution.datasources.RecordReaderIterator.hasNext(RecordReaderIterator.scala:37)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.hasNext(FileScanRDD.scala:93)
at org.apache.spark.sql.execution.datasources.FileScanRDD$$anon$1.nextIterator(FileScanRDD.scala:173)
... 20 more
{code}
reported while testing on 0.10.1-rc1 (spark 3.0.3, 3.1.2)
> ALTER TABLE rename breaks with managed table in Spark 2.4
> ---------------------------------------------------------
>
> Key: HUDI-3240
> URL: https://issues.apache.org/jira/browse/HUDI-3240
> Project: Apache Hudi
> Issue Type: Bug
> Affects Versions: 0.10.1
> Reporter: Raymond Xu
> Assignee: Yann Byron
> Priority: Major
> Fix For: 0.11.0
>
>
> {code:sql}
> create table if not exists cow_nonpt_nonpcf_tbl (
> id int,
> name string,
> price double
> ) using hudi
> options (
> type = 'cow',
> primaryKey = 'id'
> );
> insert into cow_nonpt_nonpcf_tbl select 1, 'a1', 20;
> ALTER TABLE cow_nonpt_nonpcf_tbl RENAME TO cow_nonpt_nonpcf_tbl_2;
> desc cow_nonpt_nonpcf_tbl_2;
> -- desc works fine
> select * from desc cow_nonpt_nonpcf_tbl_2;
> -- throws exception{code}
> {code:java}
> 22/01/13 03:48:18 ERROR SparkSQLDriver: Failed in [select * from cow_nonpt_nonpcf_tbl_2]
> java.util.concurrent.ExecutionException: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
> at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306)
> at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293)
> at org.spark_project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116)
> at org.spark_project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135)
> at org.spark_project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410)
> at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380)
> at org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache$LocalManualCache.get(LocalCache.java:4789)
> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.getCachedPlan(SessionCatalog.scala:141)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.org$apache$spark$sql$execution$datasources$FindDataSourceTable$$readDataSourceTable(DataSourceStrategy.scala:227)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:264)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:255)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:107)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperators(AnalysisHelper.scala:73)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:255)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:223)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
> at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
> at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
> at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
> at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:274)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
> at java.lang.reflect.Method.invoke(Unknown Source)
> at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:845)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:161)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
> at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:920)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:929)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
> at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:611)
> at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:824)
> at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:601)
> at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:421)
> at org.apache.hudi.common.util.TablePathUtils.getTablePath(TablePathUtils.java:50)
> at org.apache.hudi.DataSourceUtils.getTablePath(DataSourceUtils.java:76)
> at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:103)
> at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:316)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:242)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:227)
> at org.spark_project.guava.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4792)
> at org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> ... 77 more
> java.util.concurrent.ExecutionException: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
> at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.getValue(AbstractFuture.java:306)
> at org.spark_project.guava.util.concurrent.AbstractFuture$Sync.get(AbstractFuture.java:293)
> at org.spark_project.guava.util.concurrent.AbstractFuture.get(AbstractFuture.java:116)
> at org.spark_project.guava.util.concurrent.Uninterruptibles.getUninterruptibly(Uninterruptibles.java:135)
> at org.spark_project.guava.cache.LocalCache$Segment.getAndRecordStats(LocalCache.java:2410)
> at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2380)
> at org.spark_project.guava.cache.LocalCache$Segment.lockedGetOrLoad(LocalCache.java:2342)
> at org.spark_project.guava.cache.LocalCache$Segment.get(LocalCache.java:2257)
> at org.spark_project.guava.cache.LocalCache.get(LocalCache.java:4000)
> at org.spark_project.guava.cache.LocalCache$LocalManualCache.get(LocalCache.java:4789)
> at org.apache.spark.sql.catalyst.catalog.SessionCatalog.getCachedPlan(SessionCatalog.scala:141)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.org$apache$spark$sql$execution$datasources$FindDataSourceTable$$readDataSourceTable(DataSourceStrategy.scala:227)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:264)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anonfun$apply$2.applyOrElse(DataSourceStrategy.scala:255)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$2.apply(AnalysisHelper.scala:108)
> at org.apache.spark.sql.catalyst.trees.CurrentOrigin$.withOrigin(TreeNode.scala:70)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:107)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1$$anonfun$apply$6.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.trees.TreeNode$$anonfun$4.apply(TreeNode.scala:329)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapProductIterator(TreeNode.scala:187)
> at org.apache.spark.sql.catalyst.trees.TreeNode.mapChildren(TreeNode.scala:327)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:113)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$$anonfun$resolveOperatorsDown$1.apply(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.allowInvokingTransformsInAnalyzer(AnalysisHelper.scala:194)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperatorsDown(AnalysisHelper.scala:106)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperatorsDown(LogicalPlan.scala:29)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$class.resolveOperators(AnalysisHelper.scala:73)
> at org.apache.spark.sql.catalyst.plans.logical.LogicalPlan.resolveOperators(LogicalPlan.scala:29)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:255)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable.apply(DataSourceStrategy.scala:223)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:87)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1$$anonfun$apply$1.apply(RuleExecutor.scala:84)
> at scala.collection.LinearSeqOptimized$class.foldLeft(LinearSeqOptimized.scala:124)
> at scala.collection.immutable.List.foldLeft(List.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:84)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor$$anonfun$execute$1.apply(RuleExecutor.scala:76)
> at scala.collection.immutable.List.foreach(List.scala:392)
> at org.apache.spark.sql.catalyst.rules.RuleExecutor.execute(RuleExecutor.scala:76)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.org$apache$spark$sql$catalyst$analysis$Analyzer$$executeSameContext(Analyzer.scala:127)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.execute(Analyzer.scala:121)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:106)
> at org.apache.spark.sql.catalyst.analysis.Analyzer$$anonfun$executeAndCheck$1.apply(Analyzer.scala:105)
> at org.apache.spark.sql.catalyst.plans.logical.AnalysisHelper$.markInAnalyzer(AnalysisHelper.scala:201)
> at org.apache.spark.sql.catalyst.analysis.Analyzer.executeAndCheck(Analyzer.scala:105)
> at org.apache.spark.sql.execution.QueryExecution.analyzed$lzycompute(QueryExecution.scala:57)
> at org.apache.spark.sql.execution.QueryExecution.analyzed(QueryExecution.scala:55)
> at org.apache.spark.sql.execution.QueryExecution.assertAnalyzed(QueryExecution.scala:47)
> at org.apache.spark.sql.Dataset$.ofRows(Dataset.scala:78)
> at org.apache.spark.sql.SparkSession.sql(SparkSession.scala:642)
> at org.apache.spark.sql.SQLContext.sql(SQLContext.scala:694)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLDriver.run(SparkSQLDriver.scala:62)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.processCmd(SparkSQLCLIDriver.scala:371)
> at org.apache.hadoop.hive.cli.CliDriver.processLine(CliDriver.java:376)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver$.main(SparkSQLCLIDriver.scala:274)
> at org.apache.spark.sql.hive.thriftserver.SparkSQLCLIDriver.main(SparkSQLCLIDriver.scala)
> at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
> at sun.reflect.NativeMethodAccessorImpl.invoke(Unknown Source)
> at sun.reflect.DelegatingMethodAccessorImpl.invoke(Unknown Source)
> at java.lang.reflect.Method.invoke(Unknown Source)
> at org.apache.spark.deploy.JavaMainApplication.start(SparkApplication.scala:52)
> at org.apache.spark.deploy.SparkSubmit.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:845)
> at org.apache.spark.deploy.SparkSubmit.doRunMain$1(SparkSubmit.scala:161)
> at org.apache.spark.deploy.SparkSubmit.submit(SparkSubmit.scala:184)
> at org.apache.spark.deploy.SparkSubmit.doSubmit(SparkSubmit.scala:86)
> at org.apache.spark.deploy.SparkSubmit$$anon$2.doSubmit(SparkSubmit.scala:920)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:929)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.io.FileNotFoundException: File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2 does not exist
> at org.apache.hadoop.fs.RawLocalFileSystem.deprecatedGetFileStatus(RawLocalFileSystem.java:611)
> at org.apache.hadoop.fs.RawLocalFileSystem.getFileLinkStatusInternal(RawLocalFileSystem.java:824)
> at org.apache.hadoop.fs.RawLocalFileSystem.getFileStatus(RawLocalFileSystem.java:601)
> at org.apache.hadoop.fs.FilterFileSystem.getFileStatus(FilterFileSystem.java:421)
> at org.apache.hudi.common.util.TablePathUtils.getTablePath(TablePathUtils.java:50)
> at org.apache.hudi.DataSourceUtils.getTablePath(DataSourceUtils.java:76)
> at org.apache.hudi.DefaultSource.createRelation(DefaultSource.scala:103)
> at org.apache.spark.sql.execution.datasources.DataSource.resolveRelation(DataSource.scala:316)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:242)
> at org.apache.spark.sql.execution.datasources.FindDataSourceTable$$anon$1.call(DataSourceStrategy.scala:227)
> at org.spark_project.guava.cache.LocalCache$LocalManualCache$1.load(LocalCache.java:4792)
> at org.spark_project.guava.cache.LocalCache$LoadingValueReference.loadFuture(LocalCache.java:3599)
> at org.spark_project.guava.cache.LocalCache$Segment.loadSync(LocalCache.java:2379)
> ... 77 more
> {code}
>
> table created in /opt/spark-warehouse but it's looking for `File file:/user/hive/warehouse/cow_nonpt_nonpcf_tbl_2`
>
> {code:java}
> spark.serializer org.apache.spark.serializer.KryoSerializer
> spark.sql.extensions org.apache.spark.sql.hudi.HoodieSparkSessionExtension
> spark.sql.hive.convertMetastoreParquet false
> spark.sql.catalogImplementation in-memory
> spark.sql.warehouse.dir /opt/spark-warehouse
> {code}
>
> reported while testing on 0.10.1-rc1 (spark 2.4.4), not an issue in spark 3.0.3 and 3.1.2
--
This message was sent by Atlassian Jira
(v8.20.1#820001)