[HIVE-6412] SMB join on Decimal columns causes cast exception in JoinUtil.computeKeys

• Type: Bug
• Status: Resolved
• Priority: Critical
• Resolution: Cannot Reproduce
• Assignee: Xuefu Zhang
• Reporter: Remus Rusanu
• Created: 12/Feb/14 11:52
• Updated: 25/Feb/14 14:59
• Resolved: 25/Feb/14 14:59

Description

Caused by: java.lang.ClassCastException: org.apache.hadoop.hive.serde2.io.HiveDecimalWritable cannot be cast to org.apache.hadoop.hive.common.type.HiveDecimal
        at org.apache.hadoop.hive.serde2.objectinspector.primitive.JavaHiveDecimalObjectInspector.getPrimitiveWritableObject(JavaHiveDecimalObjectInspector.java:49)
        at org.apache.hadoop.hive.serde2.objectinspector.primitive.JavaHiveDecimalObjectInspector.getPrimitiveWritableObject(JavaHiveDecimalObjectInspector.java:27)
        at org.apache.hadoop.hive.serde2.objectinspector.ObjectInspectorUtils.copyToStandardObject(ObjectInspectorUtils.java:281)
        at org.apache.hadoop.hive.ql.exec.JoinUtil.computeKeys(JoinUtil.java:143)
        at org.apache.hadoop.hive.ql.exec.SMBMapJoinOperator$MergeQueue.next(SMBMapJoinOperator.java:809)
        at org.apache.hadoop.hive.ql.exec.SMBMapJoinOperator$MergeQueue.nextHive(SMBMapJoinOperator.java:771)
        at org.apache.hadoop.hive.ql.exec.SMBMapJoinOperator$MergeQueue.setupContext(SMBMapJoinOperator.java:710)
        at org.apache.hadoop.hive.ql.exec.SMBMapJoinOperator.setUpFetchContexts(SMBMapJoinOperator.java:538)
        at org.apache.hadoop.hive.ql.exec.SMBMapJoinOperator.processOp(SMBMapJoinOperator.java:248)
        at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:790)
        at org.apache.hadoop.hive.ql.exec.TableScanOperator.processOp(TableScanOperator.java:92)
        at org.apache.hadoop.hive.ql.exec.Operator.forward(Operator.java:790)
        at org.apache.hadoop.hive.ql.exec.MapOperator.process(MapOperator.java:524)

Repro:

create table vsmb_bucket_1(key decimal(9,0), value decimal(38,10)) 
  CLUSTERED BY (key) 
  SORTED BY (key) INTO 1 BUCKETS 
  STORED AS ORC;
create table vsmb_bucket_2(key decimal(19,3), value decimal(28,0)) 
  CLUSTERED BY (key) 
  SORTED BY (key) INTO 1 BUCKETS 
  STORED AS ORC;
  
insert into table vsmb_bucket_1 
  select cast(cint as decimal(9,0)) as key, 
    cast(cfloat as decimal(38,10)) as value 
  from alltypesorc limit 2;
insert into table vsmb_bucket_2 
  select cast(cint as decimal(19,3)) as key, 
    cast(cfloat as decimal(28,0)) as value 
  from alltypesorc limit 2;

set hive.optimize.bucketmapjoin = true;
set hive.optimize.bucketmapjoin.sortedmerge = true;
set hive.auto.convert.sortmerge.join.noconditionaltask = true;
set hive.input.format = org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat;

explain
select /*+MAPJOIN(a)*/ * from vsmb_bucket_1 a join vsmb_bucket_2 b on a.key = b.key;
select /*+MAPJOIN(a)*/ * from vsmb_bucket_1 a join vsmb_bucket_2 b on a.key = b.key;