Cao, Lionel created CARBONDATA-514:
-------------------------------------- Summary: Select string type columns will return error. Key: CARBONDATA-514 URL: https://issues.apache.org/jira/browse/CARBONDATA-514 Project: CarbonData Issue Type: Bug Components: sql Affects Versions: 1.0.0-incubating Reporter: Cao, Lionel The data successfully loaded and count(*) is OK, but when I tried to query the detail data, it returns below error: scala> cc.sql("desc carbontest_002").show +---------+---------+-------+ | col_name|data_type|comment| +---------+---------+-------+ | vin| string| | |data_date| string| | +---------+---------+-------+ scala> cc.sql("load data inpath 'hdfs://nameservice2/user/appuser/lucao/mydata4.csv' into table default.carbontest_002 OPTIONS('DELIMITER'=',')") WARN 07-12 16:30:30,241 - main skip empty input file: hdfs://nameservice2/user/appuser/lucao/mydata4.csv/_SUCCESS AUDIT 07-12 16:30:34,338 - [*.com][appuser][Thread-1]Data load request has been received for table default.carbontest_002 AUDIT 07-12 16:30:38,410 - [*.com][appuser][Thread-1]Data load is successful for default.carbontest_002 res12: org.apache.spark.sql.DataFrame = [] scala> cc.sql("select count(*) from carbontest_002") res14: org.apache.spark.sql.DataFrame = [_c0: bigint] scala> res14.show +-------+ | _c0| +-------+ |1000000| +-------+ scala> cc.sql("select vin, count(*) as cnt from carbontest_002 group by vin").show WARN 07-12 16:32:04,250 - Lost task 1.0 in stage 20.0 (TID 40, *.com): java.lang.ClassCastException: java.lang.String cannot be cast to java.lang.Integer at scala.runtime.BoxesRunTime.unboxToInt(BoxesRunTime.java:106) at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow$class.getInt(rows.scala:41) at org.apache.spark.sql.catalyst.expressions.GenericMutableRow.getInt(rows.scala:248) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown Source) at org.apache.spark.sql.CarbonScan$$anonfun$1$$anon$1.next(CarbonScan.scala:155) at org.apache.spark.sql.CarbonScan$$anonfun$1$$anon$1.next(CarbonScan.scala:149) at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:512) at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686) at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95) at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) ERROR 07-12 16:32:04,516 - Task 1 in stage 20.0 failed 4 times; aborting job WARN 07-12 16:32:04,600 - Lost task 0.1 in stage 20.0 (TID 45, *): TaskKilled (killed intentionally) ERROR 07-12 16:32:04,604 - Listener SQLListener threw an exception java.lang.NullPointerException at org.apache.spark.sql.execution.ui.SQLListener.onTaskEnd(SQLListener.scala:167) at org.apache.spark.scheduler.SparkListenerBus$class.onPostEvent(SparkListenerBus.scala:42) at org.apache.spark.scheduler.LiveListenerBus.onPostEvent(LiveListenerBus.scala:31) at org.apache.spark.scheduler.LiveListenerBus.onPostEvent(LiveListenerBus.scala:31) at org.apache.spark.util.ListenerBus$class.postToAll(ListenerBus.scala:55) at org.apache.spark.util.AsynchronousListenerBus.postToAll(AsynchronousListenerBus.scala:37) at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply$mcV$sp(AsynchronousListenerBus.scala:80) at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(AsynchronousListenerBus.scala:65) at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1$$anonfun$apply$mcV$sp$1.apply(AsynchronousListenerBus.scala:65) at scala.util.DynamicVariable.withValue(DynamicVariable.scala:57) at org.apache.spark.util.AsynchronousListenerBus$$anon$1$$anonfun$run$1.apply$mcV$sp(AsynchronousListenerBus.scala:64) at org.apache.spark.util.Utils$.tryOrStopSparkContext(Utils.scala:1181) at org.apache.spark.util.AsynchronousListenerBus$$anon$1.run(AsynchronousListenerBus.scala:63) org.apache.spark.SparkException: Job aborted due to stage failure: Task 1 in stage 20.0 failed 4 times, most recent failure: Lost task 1.3 in stage 20.0 (TID 44, *): java.lang.ClassCastException: java.lang.String cannot be cast to java.lang.Integer at scala.runtime.BoxesRunTime.unboxToInt(BoxesRunTime.java:106) at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow$class.getInt(rows.scala:41) at org.apache.spark.sql.catalyst.expressions.GenericMutableRow.getInt(rows.scala:248) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown Source) at org.apache.spark.sql.CarbonScan$$anonfun$1$$anon$1.next(CarbonScan.scala:155) at org.apache.spark.sql.CarbonScan$$anonfun$1$$anon$1.next(CarbonScan.scala:149) at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:512) at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686) at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95) at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) Driver stacktrace: at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1431) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1419) at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1418) at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:47) at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1418) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:799) at scala.Option.foreach(Option.scala:236) at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:799) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1640) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1599) at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1588) at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:620) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1843) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1856) at org.apache.spark.SparkContext.runJob(SparkContext.scala:1869) at org.apache.spark.sql.execution.SparkPlan.executeTake(SparkPlan.scala:212) at org.apache.spark.sql.execution.Limit.executeCollect(basicOperators.scala:165) at org.apache.spark.sql.execution.SparkPlan.executeCollectPublic(SparkPlan.scala:174) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) at org.apache.spark.sql.DataFrame$$anonfun$org$apache$spark$sql$DataFrame$$execute$1$1.apply(DataFrame.scala:1499) at org.apache.spark.sql.execution.SQLExecution$.withNewExecutionId(SQLExecution.scala:53) at org.apache.spark.sql.DataFrame.withNewExecutionId(DataFrame.scala:2086) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$execute$1(DataFrame.scala:1498) at org.apache.spark.sql.DataFrame.org$apache$spark$sql$DataFrame$$collect(DataFrame.scala:1505) at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1375) at org.apache.spark.sql.DataFrame$$anonfun$head$1.apply(DataFrame.scala:1374) at org.apache.spark.sql.DataFrame.withCallback(DataFrame.scala:2099) at org.apache.spark.sql.DataFrame.head(DataFrame.scala:1374) at org.apache.spark.sql.DataFrame.take(DataFrame.scala:1456) at org.apache.spark.sql.DataFrame.showString(DataFrame.scala:170) at org.apache.spark.sql.DataFrame.show(DataFrame.scala:350) at org.apache.spark.sql.DataFrame.show(DataFrame.scala:311) at org.apache.spark.sql.DataFrame.show(DataFrame.scala:319) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:35) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:40) at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:42) at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:44) at $iwC$$iwC$$iwC$$iwC.<init>(<console>:46) at $iwC$$iwC$$iwC.<init>(<console>:48) at $iwC$$iwC.<init>(<console>:50) at $iwC.<init>(<console>:52) at <init>(<console>:54) at .<init>(<console>:58) at .<clinit>(<console>) at .<init>(<console>:7) at .<clinit>(<console>) at $print(<console>) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.repl.SparkIMain$ReadEvalPrint.call(SparkIMain.scala:1045) at org.apache.spark.repl.SparkIMain$Request.loadAndRun(SparkIMain.scala:1326) at org.apache.spark.repl.SparkIMain.loadAndRunReq$1(SparkIMain.scala:821) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:852) at org.apache.spark.repl.SparkIMain.interpret(SparkIMain.scala:800) at org.apache.spark.repl.SparkILoop.reallyInterpret$1(SparkILoop.scala:857) at org.apache.spark.repl.SparkILoop.interpretStartingWith(SparkILoop.scala:902) at org.apache.spark.repl.SparkILoop.command(SparkILoop.scala:814) at org.apache.spark.repl.SparkILoop.processLine$1(SparkILoop.scala:657) at org.apache.spark.repl.SparkILoop.innerLoop$1(SparkILoop.scala:665) at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$loop(SparkILoop.scala:670) at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply$mcZ$sp(SparkILoop.scala:997) at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945) at org.apache.spark.repl.SparkILoop$$anonfun$org$apache$spark$repl$SparkILoop$$process$1.apply(SparkILoop.scala:945) at scala.tools.nsc.util.ScalaClassLoader$.savingContextLoader(ScalaClassLoader.scala:135) at org.apache.spark.repl.SparkILoop.org$apache$spark$repl$SparkILoop$$process(SparkILoop.scala:945) at org.apache.spark.repl.SparkILoop.process(SparkILoop.scala:1064) at org.apache.spark.repl.Main$.main(Main.scala:31) at org.apache.spark.repl.Main.main(Main.scala) at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method) at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:57) at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43) at java.lang.reflect.Method.invoke(Method.java:606) at org.apache.spark.deploy.SparkSubmit$.org$apache$spark$deploy$SparkSubmit$$runMain(SparkSubmit.scala:731) at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181) at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206) at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121) at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala) Caused by: java.lang.ClassCastException: java.lang.String cannot be cast to java.lang.Integer at scala.runtime.BoxesRunTime.unboxToInt(BoxesRunTime.java:106) at org.apache.spark.sql.catalyst.expressions.BaseGenericInternalRow$class.getInt(rows.scala:41) at org.apache.spark.sql.catalyst.expressions.GenericMutableRow.getInt(rows.scala:248) at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificUnsafeProjection.apply(Unknown Source) at org.apache.spark.sql.CarbonScan$$anonfun$1$$anon$1.next(CarbonScan.scala:155) at org.apache.spark.sql.CarbonScan$$anonfun$1$$anon$1.next(CarbonScan.scala:149) at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:512) at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.<init>(TungstenAggregationIterator.scala:686) at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:95) at org.apache.spark.sql.execution.aggregate.TungstenAggregate$$anonfun$doExecute$1$$anonfun$2.apply(TungstenAggregate.scala:86) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710) at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$20.apply(RDD.scala:710) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306) at org.apache.spark.rdd.RDD.iterator(RDD.scala:270) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73) at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41) at org.apache.spark.scheduler.Task.run(Task.scala:89) at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145) at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615) at java.lang.Thread.run(Thread.java:745) -- This message was sent by Atlassian JIRA (v6.3.4#6332) |
Free forum by Nabble | Edit this page |