Saving all output to "!!{outputDirectory}!!/sort_merge_join_desc_2.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/sort_merge_join_desc_2.q
>>>  drop table table_desc1;
No rows affected 
>>>  drop table table_desc2;
No rows affected 
>>>  
>>>  set hive.enforce.sorting = true;
No rows affected 
>>>  
>>>  create table table_desc1(key string, value string) clustered by (key, value) 
sorted by (key DESC, value DESC) into 1 BUCKETS;
No rows affected 
>>>  create table table_desc2(key string, value string) clustered by (key, value) 
sorted by (key DESC, value DESC) into 1 BUCKETS;
No rows affected 
>>>  
>>>  insert overwrite table table_desc1 select key, value from src;
'key','value'
No rows selected 
>>>  insert overwrite table table_desc2 select key, value from src;
'key','value'
No rows selected 
>>>  
>>>  set hive.optimize.bucketmapjoin = true;
No rows affected 
>>>  set hive.optimize.bucketmapjoin.sortedmerge = true;
No rows affected 
>>>  set hive.input.format = org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat;
No rows affected 
>>>  
>>>  -- The columns of the tables above are sorted in same order.
>>>  -- descending followed by descending
>>>  -- So, sort merge join should be performed
>>>  
>>>  explain 
select /*+ mapjoin(b) */ count(*) from table_desc1 a join table_desc2 b 
on a.key=b.key and a.value=b.value where a.key < 10;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME table_desc1) a) (TOK_TABREF (TOK_TABNAME table_desc2) b) (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST b))) (TOK_SELEXPR (TOK_FUNCTIONSTAR count))) (TOK_WHERE (< (. (TOK_TABLE_OR_COL a) key) 10))))'
''
'STAGE DEPENDENCIES:'
'  Stage-1 is a root stage'
'  Stage-2 depends on stages: Stage-1'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (key < 10.0)'
'                  type: boolean'
'              Sorted Merge Bucket Map Join Operator'
'                condition map:'
'                     Inner Join 0 to 1'
'                condition expressions:'
'                  0 {key}'
'                  1 '
'                handleSkewJoin: false'
'                keys:'
'                  0 [Column[key], Column[value]]'
'                  1 [Column[key], Column[value]]'
'                outputColumnNames: _col0'
'                Position of Big Table: 0'
'                File Output Operator'
'                  compressed: false'
'                  GlobalTableId: 0'
'                  table:'
'                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat'
'                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat'
''
'  Stage: Stage-2'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'            outputColumnNames: _col0'
'            Select Operator'
'              Group By Operator'
'                aggregations:'
'                      expr: count()'
'                bucketGroup: false'
'                mode: hash'
'                outputColumnNames: _col0'
'                Reduce Output Operator'
'                  sort order: '
'                  tag: -1'
'                  value expressions:'
'                        expr: _col0'
'                        type: bigint'
'      Reduce Operator Tree:'
'        Group By Operator'
'          aggregations:'
'                expr: count(VALUE._col0)'
'          bucketGroup: false'
'          mode: mergepartial'
'          outputColumnNames: _col0'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: bigint'
'            outputColumnNames: _col0'
'            File Output Operator'
'              compressed: false'
'              GlobalTableId: 0'
'              table:'
'                  input format: org.apache.hadoop.mapred.TextInputFormat'
'                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
''
'  Stage: Stage-0'
'    Fetch Operator'
'      limit: -1'
''
''
84 rows selected 
>>>  
>>>  select /*+ mapjoin(b) */ count(*) from table_desc1 a join table_desc2 b 
on a.key=b.key and a.value=b.value where a.key < 10;
'_c1'
'22'
1 row selected 
>>>  
>>>  !record