[
https://issues.apache.org/jira/browse/HUDI-6983?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Lin Liu updated HUDI-6983:
--------------------------
Summary: Error Report: more than one row returned by a subquery used as an
expression (was: Error: more than one row returned by a subquery used as an
expression)
> Error Report: more than one row returned by a subquery used as an expression
> ----------------------------------------------------------------------------
>
> Key: HUDI-6983
> URL: https://issues.apache.org/jira/browse/HUDI-6983
> Project: Apache Hudi
> Issue Type: Sub-task
> Reporter: Lin Liu
> Priority: Major
>
> {code:java}
> Exception in thread "main" java.lang.RuntimeException: Thread did not finish
> correctly
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor.checkResults(LSTBenchmarkExecutor.java:167)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor.execute(LSTBenchmarkExecutor.java:121)
> at com.microsoft.lst_bench.Driver.main(Driver.java:147)
> Caused by: java.util.concurrent.ExecutionException: java.sql.SQLException:
> org.apache.hive.service.cli.HiveSQLException: Error running query:
> java.lang.IllegalStateException: more than one row returned by a subquery
> used as an expression:
> Subquery subquery#40371, [id=#49903]
> +- AdaptiveSparkPlan isFinalPlan=true
> +- == Final Plan ==
> *(5) Project [d_week_seq#40616]
> +- *(5) Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- *(5) Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date>
> +- == Initial Plan ==
> Project [d_week_seq#40616]
> +- Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date> at
> org.apache.spark.sql.hive.thriftserver.HiveThriftServerErrors$.runningQueryError(HiveThriftServerErrors.scala:44)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:325)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2$$anon$3.$anonfun$run$2(SparkExecuteStatementOperation.scala:230)
> at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
> at
> org.apache.spark.sql.hive.thriftserver.SparkOperation.withLocalProperties(SparkOperation.scala:79)
> at
> org.apache.spark.sql.hive.thriftserver.SparkOperation.withLocalProperties$(SparkOperation.scala:63)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.withLocalProperties(SparkExecuteStatementOperation.scala:43)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2$$anon$3.run(SparkExecuteStatementOperation.scala:230)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2$$anon$3.run(SparkExecuteStatementOperation.scala:225)
> at java.base/java.security.AccessController.doPrivileged(Native Method)
> at java.base/javax.security.auth.Subject.doAs(Subject.java:423)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1878)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2.run(SparkExecuteStatementOperation.scala:239)
> at
> java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
> Caused by: java.lang.IllegalStateException: more than one row returned by a
> subquery used as an expression:
> Subquery subquery#40371, [id=#49903]
> +- AdaptiveSparkPlan isFinalPlan=true
> +- == Final Plan ==
> *(5) Project [d_week_seq#40616]
> +- *(5) Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- *(5) Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date>
> +- == Initial Plan ==
> Project [d_week_seq#40616]
> +- Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date> at
> org.apache.spark.sql.execution.ScalarSubquery.updateResult(subquery.scala:131)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$waitForSubqueries$1(SparkPlan.scala:281)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$waitForSubqueries$1$adapted(SparkPlan.scala:280)
> at
> scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at
> scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
> at
> org.apache.spark.sql.execution.SparkPlan.waitForSubqueries(SparkPlan.scala:280)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:250)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.FilterExec.produce(basicPhysicalOperators.scala:274)
> at
> org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:57)
> at
> org.apache.spark.sql.execution.CodegenSupport.$anonfun$produce$1(WholeStageCodegenExec.scala:101)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:251)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:43)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:816)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:918)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:213)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:251)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:209)
> at
> org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:359)
> at
> org.apache.spark.sql.execution.SparkPlan.executeCollectIterator(SparkPlan.scala:458)
> at
> org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.org$apache$spark$sql$execution$exchange$BroadcastExchangeExec$$doComputeRelation(BroadcastExchangeExec.scala:179)
> at
> org.apache.spark.sql.execution.exchange.BroadcastExchangeExec$$anon$1.doCompute(BroadcastExchangeExec.scala:172)
> at
> org.apache.spark.sql.execution.exchange.BroadcastExchangeExec$$anon$1.doCompute(BroadcastExchangeExec.scala:168)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.$anonfun$compute$1(AsyncDriverOperation.scala:73)
> 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$.withTracker(SQLExecution.scala:216)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withExecutionId$1(SQLExecution.scala:199)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
> at
> org.apache.spark.sql.execution.SQLExecution$.withExecutionId(SQLExecution.scala:196)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.compute(AsyncDriverOperation.scala:67)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.$anonfun$computeFuture$1(AsyncDriverOperation.scala:53)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:267)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.checkNoFailures(AdaptiveExecutor.scala:154)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.doRun(AdaptiveExecutor.scala:88)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.tryRunningAndGetFuture(AdaptiveExecutor.scala:66)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.execute(AdaptiveExecutor.scala:57)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.$anonfun$getFinalPhysicalPlan$1(AdaptiveSparkPlanExec.scala:249)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.getFinalPhysicalPlan(AdaptiveSparkPlanExec.scala:248)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.withFinalPlanUpdate(AdaptiveSparkPlanExec.scala:521)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.executeCollect(AdaptiveSparkPlanExec.scala:483)
> at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3932)
> at org.apache.spark.sql.Dataset.$anonfun$collect$1(Dataset.scala:3161)
> at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:3922)
> at
> org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:554)
> at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3920)
> 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.Dataset.withAction(Dataset.scala:3920)
> at org.apache.spark.sql.Dataset.collect(Dataset.scala:3161)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:300)
> ... 16 more
> at java.base/java.util.concurrent.FutureTask.report(FutureTask.java:122)
> at java.base/java.util.concurrent.FutureTask.get(FutureTask.java:191)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor.checkResults(LSTBenchmarkExecutor.java:165)
> ... 2 more
> Caused by: java.sql.SQLException:
> org.apache.hive.service.cli.HiveSQLException: Error running query:
> java.lang.IllegalStateException: more than one row returned by a subquery
> used as an expression:
> Subquery subquery#40371, [id=#49903]
> +- AdaptiveSparkPlan isFinalPlan=true
> +- == Final Plan ==
> *(5) Project [d_week_seq#40616]
> +- *(5) Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- *(5) Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date>
> +- == Initial Plan ==
> Project [d_week_seq#40616]
> +- Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date> at
> org.apache.spark.sql.hive.thriftserver.HiveThriftServerErrors$.runningQueryError(HiveThriftServerErrors.scala:44)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:325)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2$$anon$3.$anonfun$run$2(SparkExecuteStatementOperation.scala:230)
> at scala.runtime.java8.JFunction0$mcV$sp.apply(JFunction0$mcV$sp.java:23)
> at
> org.apache.spark.sql.hive.thriftserver.SparkOperation.withLocalProperties(SparkOperation.scala:79)
> at
> org.apache.spark.sql.hive.thriftserver.SparkOperation.withLocalProperties$(SparkOperation.scala:63)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.withLocalProperties(SparkExecuteStatementOperation.scala:43)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2$$anon$3.run(SparkExecuteStatementOperation.scala:230)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2$$anon$3.run(SparkExecuteStatementOperation.scala:225)
> at java.base/java.security.AccessController.doPrivileged(Native Method)
> at java.base/javax.security.auth.Subject.doAs(Subject.java:423)
> at
> org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1878)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation$$anon$2.run(SparkExecuteStatementOperation.scala:239)
> at
> java.base/java.util.concurrent.Executors$RunnableAdapter.call(Executors.java:515)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
> Caused by: java.lang.IllegalStateException: more than one row returned by a
> subquery used as an expression:
> Subquery subquery#40371, [id=#49903]
> +- AdaptiveSparkPlan isFinalPlan=true
> +- == Final Plan ==
> *(5) Project [d_week_seq#40616]
> +- *(5) Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- *(5) Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date>
> +- == Initial Plan ==
> Project [d_week_seq#40616]
> +- Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date> at
> org.apache.spark.sql.execution.ScalarSubquery.updateResult(subquery.scala:131)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$waitForSubqueries$1(SparkPlan.scala:281)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$waitForSubqueries$1$adapted(SparkPlan.scala:280)
> at
> scala.collection.mutable.ResizableArray.foreach(ResizableArray.scala:62)
> at
> scala.collection.mutable.ResizableArray.foreach$(ResizableArray.scala:55)
> at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:49)
> at
> org.apache.spark.sql.execution.SparkPlan.waitForSubqueries(SparkPlan.scala:280)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:250)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.FilterExec.produce(basicPhysicalOperators.scala:274)
> at
> org.apache.spark.sql.execution.ProjectExec.doProduce(basicPhysicalOperators.scala:57)
> at
> org.apache.spark.sql.execution.CodegenSupport.$anonfun$produce$1(WholeStageCodegenExec.scala:101)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:251)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.CodegenSupport.produce$(WholeStageCodegenExec.scala:96)
> at
> org.apache.spark.sql.execution.ProjectExec.produce(basicPhysicalOperators.scala:43)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec.doCodeGen(WholeStageCodegenExec.scala:816)
> at
> org.apache.spark.sql.execution.WholeStageCodegenExec.doExecute(WholeStageCodegenExec.scala:918)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$execute$1(SparkPlan.scala:213)
> at
> org.apache.spark.sql.execution.SparkPlan.$anonfun$executeQuery$1(SparkPlan.scala:251)
> at
> org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:151)
> at
> org.apache.spark.sql.execution.SparkPlan.executeQuery(SparkPlan.scala:248)
> at org.apache.spark.sql.execution.SparkPlan.execute(SparkPlan.scala:209)
> at
> org.apache.spark.sql.execution.SparkPlan.getByteArrayRdd(SparkPlan.scala:359)
> at
> org.apache.spark.sql.execution.SparkPlan.executeCollectIterator(SparkPlan.scala:458)
> at
> org.apache.spark.sql.execution.exchange.BroadcastExchangeExec.org$apache$spark$sql$execution$exchange$BroadcastExchangeExec$$doComputeRelation(BroadcastExchangeExec.scala:179)
> at
> org.apache.spark.sql.execution.exchange.BroadcastExchangeExec$$anon$1.doCompute(BroadcastExchangeExec.scala:172)
> at
> org.apache.spark.sql.execution.exchange.BroadcastExchangeExec$$anon$1.doCompute(BroadcastExchangeExec.scala:168)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.$anonfun$compute$1(AsyncDriverOperation.scala:73)
> 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$.withTracker(SQLExecution.scala:216)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withExecutionId$1(SQLExecution.scala:199)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
> at
> org.apache.spark.sql.execution.SQLExecution$.withExecutionId(SQLExecution.scala:196)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.compute(AsyncDriverOperation.scala:67)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.$anonfun$computeFuture$1(AsyncDriverOperation.scala:53)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:267)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.checkNoFailures(AdaptiveExecutor.scala:154)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.doRun(AdaptiveExecutor.scala:88)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.tryRunningAndGetFuture(AdaptiveExecutor.scala:66)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.execute(AdaptiveExecutor.scala:57)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.$anonfun$getFinalPhysicalPlan$1(AdaptiveSparkPlanExec.scala:249)
> at org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.getFinalPhysicalPlan(AdaptiveSparkPlanExec.scala:248)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.withFinalPlanUpdate(AdaptiveSparkPlanExec.scala:521)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.executeCollect(AdaptiveSparkPlanExec.scala:483)
> at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3932)
> at org.apache.spark.sql.Dataset.$anonfun$collect$1(Dataset.scala:3161)
> at org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:3922)
> at
> org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:554)
> at org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3920)
> 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.Dataset.withAction(Dataset.scala:3920)
> at org.apache.spark.sql.Dataset.collect(Dataset.scala:3161)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:300)
> ... 16 more at
> org.apache.hive.jdbc.HiveStatement.waitForOperationToComplete(HiveStatement.java:401)
> at org.apache.hive.jdbc.HiveStatement.execute(HiveStatement.java:266)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.executeTask(LSTBenchmarkExecutor.java:274)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.call(LSTBenchmarkExecutor.java:248)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.call(LSTBenchmarkExecutor.java:222)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> 2023-10-25T09:31:42,051 INFO [main] telemetry.JDBCTelemetryRegistry:
> Creating new logging tables...
> 2023-10-25T09:31:45,007 INFO [main] telemetry.JDBCTelemetryRegistry: Logging
> tables created.
> 2023-10-25T09:31:45,192 INFO [main] common.LSTBenchmarkExecutor: Running
> experiment: spark_hud_sf_1, run-id: d8a9deed-f145-4e19-a27c-8c7f9010cdb5
> 2023-10-25T09:31:45,194 INFO [main] common.LSTBenchmarkExecutor: Experiment
> start time: 2023_10_25_09_31_45_192
> 2023-10-25T09:31:45,194 INFO [main] common.LSTBenchmarkExecutor: Starting
> repetition: 0
> 2023-10-25T09:31:45,195 INFO [main] common.LSTBenchmarkExecutor: Running
> setup phase...
> 2023-10-25T09:31:52,929 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T09:32:00,776 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> 2023-10-25T09:32:00,786 INFO [main] common.LSTBenchmarkExecutor: Phase setup
> finished in 7 seconds.
> 2023-10-25T09:32:00,786 INFO [main] common.LSTBenchmarkExecutor: Running
> setup_data_maintenance phase...
> 2023-10-25T09:32:36,548 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T09:32:40,796 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> 2023-10-25T09:32:40,803 INFO [main] common.LSTBenchmarkExecutor: Phase
> setup_data_maintenance finished in 35 seconds.
> 2023-10-25T09:32:40,803 INFO [main] common.LSTBenchmarkExecutor: Running
> init phase...
> 2023-10-25T09:32:45,813 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T09:32:49,138 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> 2023-10-25T09:32:49,144 INFO [main] common.LSTBenchmarkExecutor: Phase init
> finished in 5 seconds.
> 2023-10-25T09:32:49,144 INFO [main] common.LSTBenchmarkExecutor: Running
> build phase...
> 2023-10-25T09:47:42,392 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T09:47:46,585 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> 2023-10-25T09:47:46,592 INFO [main] common.LSTBenchmarkExecutor: Phase build
> finished in 893 seconds.
> 2023-10-25T09:47:46,592 INFO [main] common.LSTBenchmarkExecutor: Running
> data_maintenance_1 phase...
> 2023-10-25T10:21:18,295 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T10:21:21,984 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> 2023-10-25T10:21:21,994 INFO [main] common.LSTBenchmarkExecutor: Phase
> data_maintenance_1 finished in 2011 seconds.
> 2023-10-25T10:21:21,994 INFO [main] common.LSTBenchmarkExecutor: Running
> single_user_2_0 phase...
> 2023-10-25T10:33:21,651 ERROR [pool-2-thread-1] common.LSTBenchmarkExecutor:
> Exception executing statement: query58.sql_0
> 2023-10-25T10:33:21,652 ERROR [pool-2-thread-1] common.LSTBenchmarkExecutor:
> Exception executing file: query58.sql
> 2023-10-25T10:33:21,652 ERROR [pool-2-thread-1] common.LSTBenchmarkExecutor:
> Exception executing task: single_user_0
> 2023-10-25T10:33:21,657 ERROR [pool-2-thread-1] common.LSTBenchmarkExecutor:
> Exception executing session: 0
> 2023-10-25T10:33:21,658 ERROR [main] common.LSTBenchmarkExecutor: Exception
> executing phase: single_user_2_0
> 2023-10-25T10:33:21,658 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T10:33:25,448 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> 2023-10-25T10:33:25,460 ERROR [main] common.LSTBenchmarkExecutor: Exception
> executing experiment: spark_hud_sf_1
> 2023-10-25T10:33:25,472 INFO [main] telemetry.JDBCTelemetryRegistry:
> Flushing events to database...
> 2023-10-25T10:33:28,343 INFO [main] telemetry.JDBCTelemetryRegistry: Events
> flushed to database.
> Exception in thread "main" java.lang.RuntimeException: Thread did not finish
> correctly
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor.checkResults(LSTBenchmarkExecutor.java:167)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor.execute(LSTBenchmarkExecutor.java:121)
> at com.microsoft.lst_bench.Driver.main(Driver.java:147)
> Caused by: java.util.concurrent.ExecutionException: java.sql.SQLException:
> org.apache.hive.service.cli.HiveSQLException: Error running query:
> java.lang.IllegalStateException: more than one row returned by a subquery
> used as an expression:
> Subquery subquery#40371, [id=#49903]
> +- AdaptiveSparkPlan isFinalPlan=true
> +- == Final Plan ==
> *(5) Project [d_week_seq#40616]
> +- *(5) Filter (isnotnull(d_date#40614) AND (d_date#40614 = 2000-02-12))
> +- *(5) Scan
> MergeOnReadSnapshotRelation(org.apache.spark.sql.SQLContext@1407eedc,Map(path
> -> s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim,
> hoodie.write.lock.zookeeper.url -> ip-10-0-86-217.us-west-2.compute.internal,
> hoodie.write.lock.zookeeper.base_path -> /hudi,
> hoodie.datasource.hive_sync.jdbcurl ->
> jdbc:hive2://ip-10-0-86-217.us-west-2.compute.internal:10000,
> hoodie.datasource.query.type -> snapshot, hoodie.cleaner.policy.failed.writes
> -> EAGER, hoodie.write.lock.zookeeper.port -> 2181,
> hoodie.write.lock.provider ->
> org.apache.hudi.client.transaction.lock.ZookeeperBasedLockProvider,
> hoodie.write.concurrency.mode ->
> single_writer),HoodieTableMetaClient{basePath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim',
>
> metaPath='s3a://rxusandbox-us-west-2/testcases/lstbench/hudi/sf_1/date_dim/.hoodie',
> tableType=MERGE_ON_READ},List(),None,None)
> hudi_tpcds.date_dim[d_week_seq#40616,d_date#40614] PushedFilters:
> [IsNotNull(d_date), EqualTo(d_date,2000-02-12)], ReadSchema:
> struct<d_week_seq:int,d_date:date>
> "1698226300.log" 291L, 33453B
> at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
> at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:216)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withExecutionId$1(SQLExecution.scala:199)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
> at
> org.apache.spark.sql.execution.SQLExecution$.withExecutionId(SQLExecution.scala:196)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.compute(AsyncDriverOperation.scala:67)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.$anonfun$computeFuture$1(AsyncDriverOperation.scala:53)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:267)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.checkNoFailures(AdaptiveExecutor.scala:154)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.doRun(AdaptiveExecutor.scala:88)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.tryRunningAndGetFuture(AdaptiveExecutor.scala:66)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.execute(AdaptiveExecutor.scala:57)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.$anonfun$getFinalPhysicalPlan$1(AdaptiveSparkPlanExec.scala:249)
> at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.getFinalPhysicalPlan(AdaptiveSparkPlanExec.scala:248)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.withFinalPlanUpdate(AdaptiveSparkPlanExec.scala:521)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.executeCollect(AdaptiveSparkPlanExec.scala:483)
> at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3932)
> at org.apache.spark.sql.Dataset.$anonfun$collect$1(Dataset.scala:3161)
> at
> org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:3922)
> at
> org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:554)
> at
> org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3920)
> at
> org.apache.spark.sql.catalyst.QueryPlanningTracker$.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.Dataset.withAction(Dataset.scala:3920)
> at org.apache.spark.sql.Dataset.collect(Dataset.scala:3161)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:300)
> ... 16 more at
> org.apache.hive.jdbc.HiveStatement.waitForOperationToComplete(HiveStatement.java:401)
> at org.apache.hive.jdbc.HiveStatement.execute(HiveStatement.java:266)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.executeTask(LSTBenchmarkExecutor.java:274)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.call(LSTBenchmarkExecutor.java:248)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.call(LSTBenchmarkExecutor.java:222)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
>
> at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:224)
> at
> org.apache.spark.sql.execution.SQLExecution$.withTracker(SQLExecution.scala:216)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withExecutionId$1(SQLExecution.scala:199)
> at
> org.apache.spark.sql.execution.SQLExecution$.withSQLConfPropagated(SQLExecution.scala:245)
> at
> org.apache.spark.sql.execution.SQLExecution$.withExecutionId(SQLExecution.scala:196)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.compute(AsyncDriverOperation.scala:67)
> at
> org.apache.spark.sql.execution.AsyncDriverOperation.$anonfun$computeFuture$1(AsyncDriverOperation.scala:53)
> at
> org.apache.spark.sql.execution.SQLExecution$.$anonfun$withThreadLocalCaptured$1(SQLExecution.scala:267)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.checkNoFailures(AdaptiveExecutor.scala:154)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.doRun(AdaptiveExecutor.scala:88)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.tryRunningAndGetFuture(AdaptiveExecutor.scala:66)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveExecutor.execute(AdaptiveExecutor.scala:57)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.$anonfun$getFinalPhysicalPlan$1(AdaptiveSparkPlanExec.scala:249)
> at
> org.apache.spark.sql.SparkSession.withActive(SparkSession.scala:779)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.getFinalPhysicalPlan(AdaptiveSparkPlanExec.scala:248)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.withFinalPlanUpdate(AdaptiveSparkPlanExec.scala:521)
> at
> org.apache.spark.sql.execution.adaptive.AdaptiveSparkPlanExec.executeCollect(AdaptiveSparkPlanExec.scala:483)
> at org.apache.spark.sql.Dataset.collectFromPlan(Dataset.scala:3932)
> at org.apache.spark.sql.Dataset.$anonfun$collect$1(Dataset.scala:3161)
> at
> org.apache.spark.sql.Dataset.$anonfun$withAction$2(Dataset.scala:3922)
> at
> org.apache.spark.sql.execution.QueryExecution$.withInternalError(QueryExecution.scala:554)
> at
> org.apache.spark.sql.Dataset.$anonfun$withAction$1(Dataset.scala:3920)
> 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.Dataset.withAction(Dataset.scala:3920)
> at org.apache.spark.sql.Dataset.collect(Dataset.scala:3161)
> at
> org.apache.spark.sql.hive.thriftserver.SparkExecuteStatementOperation.org$apache$spark$sql$hive$thriftserver$SparkExecuteStatementOperation$$execute(SparkExecuteStatementOperation.scala:300)
> ... 16 more at
> org.apache.hive.jdbc.HiveStatement.waitForOperationToComplete(HiveStatement.java:401)
> at org.apache.hive.jdbc.HiveStatement.execute(HiveStatement.java:266)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.executeTask(LSTBenchmarkExecutor.java:274)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.call(LSTBenchmarkExecutor.java:248)
> at
> com.microsoft.lst_bench.common.LSTBenchmarkExecutor$Worker.call(LSTBenchmarkExecutor.java:222)
> at java.base/java.util.concurrent.FutureTask.run(FutureTask.java:264)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1128)
> at
> java.base/java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:628)
> at java.base/java.lang.Thread.run(Thread.java:829) {code}
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
