Details
-
Bug
-
Status: Closed
-
Major
-
Resolution: Fixed
-
None
-
None
-
None
-
Spark1.6
Description
When we execute Same query in hive, it is working fine but when we execute in carbondata "org.apache.hadoop.hive.ql.metadata.HiveException" occurs.
HIVE:
0: jdbc:hive2://hadoop-master:10000> create table Test_Boundary_h1 (c1_int int,c2_Bigint Bigint,c3_Decimal Decimal(38,30),c4_double double,c5_string string,c6_Timestamp Timestamp,c7_Datatype_Desc string) ROW FORMAT DELIMITED FIELDS TERMINATED BY ',' ;
---------+
result
---------+
---------+
No rows selected (1.177 seconds)
0: jdbc:hive2://hadoop-master:10000> load data local inpath '/opt/Carbon/CarbonData/TestData/Data/Test_Data1_h1.csv' OVERWRITE INTO TABLE Test_Boundary_h1 ;
---------+
Result
---------+
---------+
No rows selected (0.437 seconds)
0: jdbc:hive2://hadoop-master:10000> select min(c1_int),max(c1_int),sum(c1_int),avg(c1_int) , count(c1_int), variance(c1_int) from Test_Boundary_h1 where rand(c1_int)=0.6201007799387834 or rand(c1_int)=0.45540022789662593 ;
-------------------------------
| _c0 | _c1 | _c2 | _c3 | _c4 | _c5 |
-------------------------------
| NULL | NULL | NULL | NULL | 0 | NULL |
-------------------------------
1 row selected (0.996 seconds)
CARBONDATA:
0: jdbc:hive2://hadoop-master:10000> create table Test_Boundary (c1_int int,c2_Bigint Bigint,c3_Decimal Decimal(38,30),c4_double double,c5_string string,c6_Timestamp Timestamp,c7_Datatype_Desc string) STORED BY 'org.apache.carbondata.format' ;
---------+
Result
---------+
---------+
No rows selected (4.48 seconds)
0: jdbc:hive2://hadoop-master:10000> LOAD DATA INPATH 'hdfs://192.168.2.145:54310/BabuStore/Data/Test_Data1.csv' INTO table Test_Boundary OPTIONS('DELIMITER'=',','QUOTECHAR'='','BAD_RECORDS_ACTION'='FORCE','FILEHEADER'='') ;
---------+
Result
---------+
---------+
No rows selected (4.445 seconds)
0: jdbc:hive2://hadoop-master:10000> select min(c1_int),max(c1_int),sum(c1_int),avg(c1_int) , count(c1_int), variance(c1_int) from Test_Boundary where rand(c1_int)=0.6201007799387834 or rand(c1_int)=0.45540022789662593 ;
Error: org.apache.spark.SparkException: Job aborted due to stage failure: Task 0 in stage 19.0 failed 4 times, most recent failure: Lost task 0.3 in stage 19.0 (TID 826, hadoop-master): org.apache.hadoop.hive.ql.metadata.HiveException: Unable to execute method public org.apache.hadoop.hive.serde2.io.DoubleWritable org.apache.hadoop.hive.ql.udf.UDFRand.evaluate(org.apache.hadoop.io.LongWritable) on object org.apache.hadoop.hive.ql.udf.UDFRand@3152da1e of class org.apache.hadoop.hive.ql.udf.UDFRand with arguments
of size 1
at org.apache.hadoop.hive.ql.exec.FunctionRegistry.invoke(FunctionRegistry.java:981)
at org.apache.spark.sql.hive.HiveSimpleUDF.eval(hiveUDFs.scala:185)
at org.apache.spark.sql.catalyst.expressions.GeneratedClass$SpecificPredicate.eval(Unknown Source)
at org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$$anonfun$create$2.apply(GeneratePredicate.scala:68)
at org.apache.spark.sql.catalyst.expressions.codegen.GeneratePredicate$$anonfun$create$2.apply(GeneratePredicate.scala:68)
at org.apache.spark.sql.execution.Filter$$anonfun$2$$anonfun$apply$2.apply(basicOperators.scala:74)
at org.apache.spark.sql.execution.Filter$$anonfun$2$$anonfun$apply$2.apply(basicOperators.scala:72)
at scala.collection.Iterator$$anon$14.hasNext(Iterator.scala:390)
at scala.collection.Iterator$$anon$11.hasNext(Iterator.scala:327)
at org.apache.spark.sql.execution.aggregate.TungstenAggregationIterator.processInputs(TungstenAggregationIterator.scala:504)
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:227)
at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617)
at java.lang.Thread.run(Thread.java:745)
Caused by: java.lang.reflect.InvocationTargetException
at sun.reflect.GeneratedMethodAccessor46.invoke(Unknown Source)
at sun.reflect.DelegatingMethodAccessorImpl.invoke(DelegatingMethodAccessorImpl.java:43)
at java.lang.reflect.Method.invoke(Method.java:498)
at org.apache.hadoop.hive.ql.exec.FunctionRegistry.invoke(FunctionRegistry.java:957)
... 27 more
Caused by: java.lang.NullPointerException
at org.apache.hadoop.hive.ql.udf.UDFRand.evaluate(UDFRand.java:57)
... 31 more
Driver stacktrace: (state=,code=0)