Mailing-List: contact issues-help@carbondata.apache.org; run by ezmlm
Precedence: bulk
Reply-To: dev@carbondata.apache.org
Date: Tue, 9 May 2017 06:27:04 +0000 (UTC)
From: "Ravindra Pesala (JIRA)" <jira@apache.org>
To: issues@carbondata.apache.org
Message-ID: <JIRA.13036202.1484828700000.160811.1494311224181@Atlassian.JIRA>
In-Reply-To: <JIRA.13036202.1484828700000@Atlassian.JIRA>
References: <JIRA.13036202.1484828700000@Atlassian.JIRA> <JIRA.13036202.1484828700977@jira-lw-us.apache.org>
Subject: [jira] [Resolved] (CARBONDATA-664) Select queries fail when
 BAD_RECORDS_ACTION as FORCED is used in load query.
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: quoted-printable
archived-at: Tue, 09 May 2017 06:27:09 -0000


     [ https://issues.apache.org/jira/browse/CARBONDATA-664?page=3Dcom.atla=
ssian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Ravindra Pesala resolved CARBONDATA-664.
----------------------------------------
    Resolution: Duplicate

Duplicated to CARBONDATA-726

> Select queries fail when BAD_RECORDS_ACTION as FORCED is used in load que=
ry.
> -------------------------------------------------------------------------=
---
>
>                 Key: CARBONDATA-664
>                 URL: https://issues.apache.org/jira/browse/CARBONDATA-664
>             Project: CarbonData
>          Issue Type: Bug
>          Components: data-query
>    Affects Versions: 1.0.0-incubating
>         Environment: Spark 1.6
>            Reporter: Harsh Sharma
>              Labels: bug
>         Attachments: 100_olap_C20.csv, Driver Logs, Executor Logs
>
>          Time Spent: 50m
>  Remaining Estimate: 0h
>
> Below scenario is working on Spark 2.1, but not on Spark 1.6
> create table VMALL_DICTIONARY_INCLUDE (imei string,deviceInformationId in=
t,MAC string,deviceColor string,device_backColor string,modelId string,mark=
etName string,AMSize string,ROMSize string,CUPAudit string,CPIClocked strin=
g,series string,productionDate timestamp,bomCode string,internalModels stri=
ng, deliveryTime string, channelsId string, channelsName string , deliveryA=
reaId string, deliveryCountry string, deliveryProvince string, deliveryCity=
 string,deliveryDistrict string, deliveryStreet string, oxSingleNumber stri=
ng, ActiveCheckTime string, ActiveAreaId string, ActiveCountry string, Acti=
veProvince string, Activecity string, ActiveDistrict string, ActiveStreet s=
tring, ActiveOperatorId string, Active_releaseId string, Active_EMUIVersion=
 string, Active_operaSysVersion string, Active_BacVerNumber string, Active_=
BacFlashVer string, Active_webUIVersion string, Active_webUITypeCarrVer str=
ing,Active_webTypeDataVerNumber string, Active_operatorsVersion string, Act=
ive_phonePADPartitionedVersions string, Latest_YEAR int, Latest_MONTH int, =
Latest_DAY Decimal(30,10), Latest_HOUR string, Latest_areaId string, Latest=
_country string, Latest_province string, Latest_city string, Latest_distric=
t string, Latest_street string, Latest_releaseId string, Latest_EMUIVersion=
 string, Latest_operaSysVersion string, Latest_BacVerNumber string, Latest_=
BacFlashVer string, Latest_webUIVersion string, Latest_webUITypeCarrVer str=
ing, Latest_webTypeDataVerNumber string, Latest_operatorsVersion string, La=
test_phonePADPartitionedVersions string, Latest_operatorId string, gamePoin=
tDescription string,gamePointId double,contractNumber BigInt) STORED BY 'or=
g.apache.carbondata.format' TBLPROPERTIES('DICTIONARY_INCLUDE'=3D'imei,devi=
ceInformationId,productionDate,gamePointId,Latest_DAY,contractNumber');
> LOAD DATA INPATH 'hdfs://hadoop-master:54311/data/100_olap_C20.csv' INTO =
table VMALL_DICTIONARY_INCLUDE options('DELIMITER'=3D',','QUOTECHAR'=3D'"',=
'BAD_RECORDS_ACTION'=3D'FORCE','FILEHEADER'=3D'imei,deviceInformationId,MAC=
,deviceColor,device_backColor,modelId,marketName,AMSize,ROMSize,CUPAudit,CP=
IClocked,series,productionDate,bomCode,internalModels,deliveryTime,channels=
Id,channelsName,deliveryAreaId,deliveryCountry,deliveryProvince,deliveryCit=
y,deliveryDistrict,deliveryStreet,oxSingleNumber,contractNumber,ActiveCheck=
Time,ActiveAreaId,ActiveCountry,ActiveProvince,Activecity,ActiveDistrict,Ac=
tiveStreet,ActiveOperatorId,Active_releaseId,Active_EMUIVersion,Active_oper=
aSysVersion,Active_BacVerNumber,Active_BacFlashVer,Active_webUIVersion,Acti=
ve_webUITypeCarrVer,Active_webTypeDataVerNumber,Active_operatorsVersion,Act=
ive_phonePADPartitionedVersions,Latest_YEAR,Latest_MONTH,Latest_DAY,Latest_=
HOUR,Latest_areaId,Latest_country,Latest_province,Latest_city,Latest_distri=
ct,Latest_street,Latest_releaseId,Latest_EMUIVersion,Latest_operaSysVersion=
,Latest_BacVerNumber,Latest_BacFlashVer,Latest_webUIVersion,Latest_webUITyp=
eCarrVer,Latest_webTypeDataVerNumber,Latest_operatorsVersion,Latest_phonePA=
DPartitionedVersions,Latest_operatorId,gamePointId,gamePointDescription');
> select sum(deviceinformationId) from VMALL_DICTIONARY_INCLUDE where devic=
eColor =3D'5Device Color' and modelId !=3D '109' or Latest_DAY > '123456789=
0123540.0000000000' and contractNumber =3D=3D '92233720368547800' or Active=
_operaSysVersion like 'Operating System Version' and gamePointId <=3D> '8.1=
366141918611E39' and deviceInformationId < '1000000' and productionDate not=
 like '2016-07-01' and imei is null and Latest_HOUR is not null and channel=
sId <=3D '7' and Latest_releaseId >=3D '1' and Latest_MONTH between 6 and 8=
 and Latest_YEAR not between 2016 and 2017 and Latest_HOUR RLIKE '12' and g=
amePointDescription REGEXP 'Site' and imei in ('1AA1','1AA100','1AA10','1AA=
1000','1AA10000','1AA100000','1AA1000000','1AA100001','1AA100002','1AA10000=
4','','NULL') and Active_BacVerNumber not in ('Background version number1',=
'','null');
> This scenario results in the following exception,
> Error: org.apache.spark.SparkException: Job aborted due to stage failure:=
 Task 0 in stage 48.0 failed 4 times, most recent failure: Lost task 0.3 in=
 stage 48.0 (TID 152, hadoop-master): java.lang.RuntimeException: java.util=
.concurrent.ExecutionException: java.lang.NullPointerException
> =09at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterato=
r.next(DetailQueryResultIterator.java:65)
> =09at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterato=
r.next(DetailQueryResultIterator.java:35)
> =09at org.apache.carbondata.scan.result.iterator.ChunkRowIterator.<init>(=
ChunkRowIterator.java:43)
> =09at org.apache.carbondata.hadoop.CarbonRecordReader.initialize(CarbonRe=
cordReader.java:81)
> =09at org.apache.carbondata.spark.rdd.CarbonScanRDD.compute(CarbonScanRDD=
.scala:194)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scal=
a:38)
> =09at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:306)
> =09at org.apache.spark.rdd.RDD.iterator(RDD.scala:270)
> =09at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.sc=
ala:73)
> =09at org.apache.spark.scheduler.ShuffleMapTask.runTask(ShuffleMapTask.sc=
ala:41)
> =09at org.apache.spark.scheduler.Task.run(Task.scala:89)
> =09at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:22=
7)
> =09at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecuto=
r.java:1142)
> =09at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecut=
or.java:617)
> =09at java.lang.Thread.run(Thread.java:745)
> Caused by: java.util.concurrent.ExecutionException: java.lang.NullPointer=
Exception
> =09at java.util.concurrent.FutureTask.report(FutureTask.java:122)
> =09at java.util.concurrent.FutureTask.get(FutureTask.java:192)
> =09at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterato=
r.next(DetailQueryResultIterator.java:52)
> =09... 34 more
> Caused by: java.lang.NullPointerException
> =09at org.apache.carbondata.scan.result.AbstractScannedResult.getDictiona=
ryKeyIntegerArray(AbstractScannedResult.java:187)
> =09at org.apache.carbondata.scan.result.impl.FilterQueryScannedResult.get=
DictionaryKeyIntegerArray(FilterQueryScannedResult.java:53)
> =09at org.apache.carbondata.scan.collector.impl.DictionaryBasedResultColl=
ector.collectData(DictionaryBasedResultCollector.java:111)
> =09at org.apache.carbondata.scan.processor.impl.DataBlockIteratorImpl.nex=
t(DataBlockIteratorImpl.java:52)
> =09at org.apache.carbondata.scan.processor.impl.DataBlockIteratorImpl.nex=
t(DataBlockIteratorImpl.java:33)
> =09at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterato=
r$1.call(DetailQueryResultIterator.java:78)
> =09at org.apache.carbondata.scan.result.iterator.DetailQueryResultIterato=
r$1.call(DetailQueryResultIterator.java:72)
> =09at java.util.concurrent.FutureTask.run(FutureTask.java:266)
> =09... 3 more
> Driver stacktrace: (state=3D,code=3D0)


--
This message was sent by Atlassian JIRA
(v6.3.15#6346)