select return error when filter string column in where clause

classic Classic list List threaded Threaded
4 messages Options
Reply | Threaded
Open this post in threaded view
|

select return error when filter string column in where clause

lionel061201
Hi Dev team,
I have loaded some data into carbondata table. But when I put the id
column(String type) in where clause it always return error as below:

cc.sql("select to_date(data_date),count(*) from default.carbontest_001
where id='LSJW26762FS044062' group by to_date(data_date)").show



===================================================================
WARN  06-12 09:02:13,763 - Lost task 5.0 in stage 44.0 (TID 687,
********.com): java.lang.RuntimeException: Exception occurred in query
execution.Please check logs.
at scala.sys.package$.error(package.scala:27)
at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$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 06-12 09:02:14,091 - Task 1 in stage 44.0 failed 4 times; aborting job
org.apache.spark.SparkException: Job aborted due to stage failure:
Task 1 in stage 44.0 failed 4 times, most recent failure: Lost task
1.3 in stage 44.0 (TID 694, scsp00258.saicdt.com):
java.lang.RuntimeException: Exception occurred in query
execution.Please check logs.
at scala.sys.package$.error(package.scala:27)
at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$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$$iwC.<init>(<console>:38)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
at $iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
at $iwC$$iwC$$iwC.<init>(<console>:56)
at $iwC$$iwC.<init>(<console>:58)
at $iwC.<init>(<console>:60)
at <init>(<console>:62)
at .<init>(<console>:66)
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$$runMain(SparkSubmit.scala:731)
at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
Caused by: java.lang.RuntimeException: Exception occurred in query
execution.Please check logs.
at scala.sys.package$.error(package.scala:27)
at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
at org.apache.spark.scheduler.Task.run(Task.scala:89)
at org.apache.spark.executor.Executor$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)

thanks,
lucao
Reply | Threaded
Open this post in threaded view
|

Re: select return error when filter string column in where clause

ravipesala
Hi,

Please provide table schema, load command and sample data to reproduce this
issue, you may create the JIRA for it.

Regards,
Ravi

On 6 December 2016 at 07:05, Lu Cao <[hidden email]> wrote:

> Hi Dev team,
> I have loaded some data into carbondata table. But when I put the id
> column(String type) in where clause it always return error as below:
>
> cc.sql("select to_date(data_date),count(*) from default.carbontest_001
> where id='LSJW26762FS044062' group by to_date(data_date)").show
>
>
>
> ===================================================================
> WARN  06-12 09:02:13,763 - Lost task 5.0 in stage 44.0 (TID 687,
> ********.com): java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
> at scala.sys.package$.error(package.scala:27)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<
> init>(CarbonScanRDD.scala:226)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(
> CarbonScanRDD.scala:192)
> 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.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.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 06-12 09:02:14,091 - Task 1 in stage 44.0 failed 4 times; aborting
> job
> org.apache.spark.SparkException: Job aborted due to stage failure:
> Task 1 in stage 44.0 failed 4 times, most recent failure: Lost task
> 1.3 in stage 44.0 (TID 694, scsp00258.saicdt.com):
> java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
> at scala.sys.package$.error(package.scala:27)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<
> init>(CarbonScanRDD.scala:226)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(
> CarbonScanRDD.scala:192)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(
> ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(
> ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$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$$iwC.<init>(<console>:38)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
> at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
> at $iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
> at $iwC$$iwC$$iwC.<init>(<console>:56)
> at $iwC$$iwC.<init>(<console>:58)
> at $iwC.<init>(<console>:60)
> at <init>(<console>:62)
> at .<init>(<console>:66)
> 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$$runMain(SparkSubmit.scala:731)
> at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
> at scala.sys.package$.error(package.scala:27)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<
> init>(CarbonScanRDD.scala:226)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(
> CarbonScanRDD.scala:192)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(
> MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(
> ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(
> ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$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)
>
> thanks,
> lucao
>



--
Thanks & Regards,
Ravi
Reply | Threaded
Open this post in threaded view
|

Re: select return error when filter string column in where clause

lionel061201
In reply to this post by lionel061201
Attach executor log:

#query successed
cc.sql("select count(*) from default.carbontest_003 where id =
'LSJW26761FS090787'").show

#and 'LSJW26760GS018559',  'LSJW26761ES064611' also successed

#query return error
cc.sql("select count(*) from default.carbontest_003 where id =
'LSJW26763FS088491'").show


===============================================================================================

INFO  06-12 12:20:54,821 - Got assigned task 651

INFO  06-12 12:20:54,822 - Running task 0.0 in stage 51.0 (TID 651)

INFO  06-12 12:20:54,830 - Updating epoch to 12 and clearing cache

INFO  06-12 12:20:54,830 - Started reading broadcast variable 43

INFO  06-12 12:20:54,837 - Block broadcast_43_piece0 stored as bytes
in memory (estimated size 8.6 KB, free 8.6 KB)

INFO  06-12 12:20:54,840 - Reading broadcast variable 43 took 10 ms

INFO  06-12 12:20:54,853 - Block broadcast_43 stored as values in
memory (estimated size 17.7 KB, free 26.3 KB)

INFO  06-12 12:20:54,868 - *************************carbon.properties

INFO  06-12 12:20:54,869 - [Executor task launch
worker-2][partitionID:003;queryID:4305874916432320_0] Query will be
executed on table: carbontest_003

ERROR 06-12 12:20:54,869 - [Executor task launch
worker-2][partitionID:003;queryID:4305874916432320_0]

java.lang.NullPointerException

        at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.intialiseInfos(AbstractDetailQueryResultIterator.java:117)

        at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.<init>(AbstractDetailQueryResultIterator.java:107)

        at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterator.<init>(DetailQueryResultIterator.java:43)

        at org.apache.carbondata.scan.executor.impl.DetailQueryExecutor.execute(DetailQueryExecutor.java:39)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:216)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)

        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.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.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 06-12 12:20:54,871 - Exception in task 0.0 in stage 51.0 (TID 651)

java.lang.RuntimeException: Exception occurred in query
execution.Please check logs.

        at scala.sys.package$.error(package.scala:27)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)

        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.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.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)

INFO  06-12 12:20:54,883 - Got assigned task 652

INFO  06-12 12:20:54,884 - Running task 0.1 in stage 51.0 (TID 652)

INFO  06-12 12:20:54,896 - *************************carbon.properties

INFO  06-12 12:20:54,896 - [Executor task launch
worker-2][partitionID:003;queryID:4305874916432320_0] Query will be
executed on table: carbontest_003

ERROR 06-12 12:20:54,897 - [Executor task launch
worker-2][partitionID:003;queryID:4305874916432320_0]

java.lang.NullPointerException

        at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.intialiseInfos(AbstractDetailQueryResultIterator.java:117)

        at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.<init>(AbstractDetailQueryResultIterator.java:107)

        at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterator.<init>(DetailQueryResultIterator.java:43)

        at org.apache.carbondata.scan.executor.impl.DetailQueryExecutor.execute(DetailQueryExecutor.java:39)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:216)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)

        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.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.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 06-12 12:20:54,897 - Exception in task 0.1 in stage 51.0 (TID 652)

java.lang.RuntimeException: Exception occurred in query
execution.Please check logs.

        at scala.sys.package$.error(package.scala:27)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)

        at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)

        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.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.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)

On Tue, Dec 6, 2016 at 9:35 AM, Lu Cao <[hidden email]> wrote:

> Hi Dev team,
> I have loaded some data into carbondata table. But when I put the id
> column(String type) in where clause it always return error as below:
>
> cc.sql("select to_date(data_date),count(*) from default.carbontest_001
> where id='LSJW26762FS044062' group by to_date(data_date)").show
>
>
>
> ===================================================================
> WARN  06-12 09:02:13,763 - Lost task 5.0 in stage 44.0 (TID 687,
> ********.com): java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
> at scala.sys.package$.error(package.scala:27)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
> 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.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.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 06-12 09:02:14,091 - Task 1 in stage 44.0 failed 4 times; aborting job
> org.apache.spark.SparkException: Job aborted due to stage failure:
> Task 1 in stage 44.0 failed 4 times, most recent failure: Lost task
> 1.3 in stage 44.0 (TID 694, scsp00258.saicdt.com):
> java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
> at scala.sys.package$.error(package.scala:27)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$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$$iwC.<init>(<console>:38)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
> at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
> at $iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
> at $iwC$$iwC$$iwC.<init>(<console>:56)
> at $iwC$$iwC.<init>(<console>:58)
> at $iwC.<init>(<console>:60)
> at <init>(<console>:62)
> at .<init>(<console>:66)
> 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$$runMain(SparkSubmit.scala:731)
> at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
> Caused by: java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
> at scala.sys.package$.error(package.scala:27)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
> at org.apache.spark.scheduler.Task.run(Task.scala:89)
> at org.apache.spark.executor.Executor$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)
>
> thanks,
> lucao
Reply | Threaded
Open this post in threaded view
|

Re: select return error when filter string column in where clause

lionel061201
Thank you Ravi! Qiang Cai has been working on this issue. Will let you
know the progress.
I have reduce the schema to only one column, but it still return the same error.

Thanks,
Lionel

On Tue, Dec 6, 2016 at 12:34 PM, Lu Cao <[hidden email]> wrote:

> Attach executor log:
>
> #query successed
> cc.sql("select count(*) from default.carbontest_003 where id =
> 'LSJW26761FS090787'").show
>
> #and 'LSJW26760GS018559',  'LSJW26761ES064611' also successed
>
> #query return error
> cc.sql("select count(*) from default.carbontest_003 where id =
> 'LSJW26763FS088491'").show
>
>
> ===============================================================================================
>
> INFO  06-12 12:20:54,821 - Got assigned task 651
>
> INFO  06-12 12:20:54,822 - Running task 0.0 in stage 51.0 (TID 651)
>
> INFO  06-12 12:20:54,830 - Updating epoch to 12 and clearing cache
>
> INFO  06-12 12:20:54,830 - Started reading broadcast variable 43
>
> INFO  06-12 12:20:54,837 - Block broadcast_43_piece0 stored as bytes
> in memory (estimated size 8.6 KB, free 8.6 KB)
>
> INFO  06-12 12:20:54,840 - Reading broadcast variable 43 took 10 ms
>
> INFO  06-12 12:20:54,853 - Block broadcast_43 stored as values in
> memory (estimated size 17.7 KB, free 26.3 KB)
>
> INFO  06-12 12:20:54,868 - *************************carbon.properties
>
> INFO  06-12 12:20:54,869 - [Executor task launch
> worker-2][partitionID:003;queryID:4305874916432320_0] Query will be
> executed on table: carbontest_003
>
> ERROR 06-12 12:20:54,869 - [Executor task launch
> worker-2][partitionID:003;queryID:4305874916432320_0]
>
> java.lang.NullPointerException
>
>         at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.intialiseInfos(AbstractDetailQueryResultIterator.java:117)
>
>         at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.<init>(AbstractDetailQueryResultIterator.java:107)
>
>         at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterator.<init>(DetailQueryResultIterator.java:43)
>
>         at org.apache.carbondata.scan.executor.impl.DetailQueryExecutor.execute(DetailQueryExecutor.java:39)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:216)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>
>         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.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.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 06-12 12:20:54,871 - Exception in task 0.0 in stage 51.0 (TID 651)
>
> java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
>
>         at scala.sys.package$.error(package.scala:27)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
>
>         at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>
>         at org.apache.spark.scheduler.Task.run(Task.scala:89)
>
>         at org.apache.spark.executor.Executor$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)
>
> INFO  06-12 12:20:54,883 - Got assigned task 652
>
> INFO  06-12 12:20:54,884 - Running task 0.1 in stage 51.0 (TID 652)
>
> INFO  06-12 12:20:54,896 - *************************carbon.properties
>
> INFO  06-12 12:20:54,896 - [Executor task launch
> worker-2][partitionID:003;queryID:4305874916432320_0] Query will be
> executed on table: carbontest_003
>
> ERROR 06-12 12:20:54,897 - [Executor task launch
> worker-2][partitionID:003;queryID:4305874916432320_0]
>
> java.lang.NullPointerException
>
>         at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.intialiseInfos(AbstractDetailQueryResultIterator.java:117)
>
>         at org.apache.carbondata.scan.result.iterator.AbstractDetailQueryResultIterator.<init>(AbstractDetailQueryResultIterator.java:107)
>
>         at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterator.<init>(DetailQueryResultIterator.java:43)
>
>         at org.apache.carbondata.scan.executor.impl.DetailQueryExecutor.execute(DetailQueryExecutor.java:39)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:216)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>
>         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.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.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 06-12 12:20:54,897 - Exception in task 0.1 in stage 51.0 (TID 652)
>
> java.lang.RuntimeException: Exception occurred in query
> execution.Please check logs.
>
>         at scala.sys.package$.error(package.scala:27)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
>
>         at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>
>         at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>
>         at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>
>         at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
>
>         at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>
>         at org.apache.spark.scheduler.Task.run(Task.scala:89)
>
>         at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214)
>
>         at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1145)
>
>         at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:615)
>
>         at java.lang.Thread.run(Thread.java:745)
>
> On Tue, Dec 6, 2016 at 9:35 AM, Lu Cao <[hidden email]> wrote:
>> Hi Dev team,
>> I have loaded some data into carbondata table. But when I put the id
>> column(String type) in where clause it always return error as below:
>>
>> cc.sql("select to_date(data_date),count(*) from default.carbontest_001
>> where id='LSJW26762FS044062' group by to_date(data_date)").show
>>
>>
>>
>> ===================================================================
>> WARN  06-12 09:02:13,763 - Lost task 5.0 in stage 44.0 (TID 687,
>> ********.com): java.lang.RuntimeException: Exception occurred in query
>> execution.Please check logs.
>> at scala.sys.package$.error(package.scala:27)
>> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
>> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>> 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.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.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 06-12 09:02:14,091 - Task 1 in stage 44.0 failed 4 times; aborting job
>> org.apache.spark.SparkException: Job aborted due to stage failure:
>> Task 1 in stage 44.0 failed 4 times, most recent failure: Lost task
>> 1.3 in stage 44.0 (TID 694, scsp00258.saicdt.com):
>> java.lang.RuntimeException: Exception occurred in query
>> execution.Please check logs.
>> at scala.sys.package$.error(package.scala:27)
>> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
>> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>> at org.apache.spark.scheduler.Task.run(Task.scala:89)
>> at org.apache.spark.executor.Executor$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$$iwC.<init>(<console>:38)
>> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:48)
>> at $iwC$$iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:50)
>> at $iwC$$iwC$$iwC$$iwC$$iwC.<init>(<console>:52)
>> at $iwC$$iwC$$iwC$$iwC.<init>(<console>:54)
>> at $iwC$$iwC$$iwC.<init>(<console>:56)
>> at $iwC$$iwC.<init>(<console>:58)
>> at $iwC.<init>(<console>:60)
>> at <init>(<console>:62)
>> at .<init>(<console>:66)
>> 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$$runMain(SparkSubmit.scala:731)
>> at org.apache.spark.deploy.SparkSubmit$.doRunMain$1(SparkSubmit.scala:181)
>> at org.apache.spark.deploy.SparkSubmit$.submit(SparkSubmit.scala:206)
>> at org.apache.spark.deploy.SparkSubmit$.main(SparkSubmit.scala:121)
>> at org.apache.spark.deploy.SparkSubmit.main(SparkSubmit.scala)
>> Caused by: java.lang.RuntimeException: Exception occurred in query
>> execution.Please check logs.
>> at scala.sys.package$.error(package.scala:27)
>> at org.apache.carbondata.spark.rdd.CarbonScanRDD$$anon$1.<init>(CarbonScanRDD.scala:226)
>> at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD.scala:192)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38)
>> at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
>> at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:73)
>> at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.scala:41)
>> at org.apache.spark.scheduler.Task.run(Task.scala:89)
>> at org.apache.spark.executor.Executor$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)
>>
>> thanks,
>> lucao