Saving all output to "!!{outputDirectory}!!/skewjoinopt9.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/skewjoinopt9.q
>>>  set hive.internal.ddl.list.bucketing.enable=true;
No rows affected 
>>>  set hive.optimize.skewjoin.compiletime = true;
No rows affected 
>>>  
>>>  CREATE TABLE T1(key STRING, val STRING) 
SKEWED BY (key) ON ((2)) STORED AS TEXTFILE;
No rows affected 
>>>  
>>>  LOAD DATA LOCAL INPATH '../data/files/T1.txt' INTO TABLE T1;
No rows affected 
>>>  
>>>  CREATE TABLE T2(key STRING, val STRING) STORED AS TEXTFILE;
No rows affected 
>>>  
>>>  LOAD DATA LOCAL INPATH '../data/files/T2.txt' INTO TABLE T2;
No rows affected 
>>>  
>>>  -- no skew join compile time optimization would be performed if one of the
>>>  -- join sources is a sub-query consisting of a union all
>>>  -- adding a order by at the end to make the results deterministic
>>>  EXPLAIN 
select * from 
( 
select key, val from T1 
union all 
select key, val from T1 
) subq1 
join T2 b on subq1.key = b.key;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_TABLE_OR_COL val)))))) subq1) (TOK_TABREF (TOK_TABNAME T2) b) (= (. (TOK_TABLE_OR_COL subq1) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))))'
''
'STAGE DEPENDENCIES:'
'  Stage-1 is a root stage'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        b '
'          TableScan'
'            alias: b'
'            Reduce Output Operator'
'              key expressions:'
'                    expr: key'
'                    type: string'
'              sort order: +'
'              Map-reduce partition columns:'
'                    expr: key'
'                    type: string'
'              tag: 1'
'              value expressions:'
'                    expr: key'
'                    type: string'
'                    expr: val'
'                    type: string'
'        null-subquery1:subq1-subquery1:t1 '
'          TableScan'
'            alias: t1'
'            Select Operator'
'              expressions:'
'                    expr: key'
'                    type: string'
'                    expr: val'
'                    type: string'
'              outputColumnNames: _col0, _col1'
'              Union'
'                Reduce Output Operator'
'                  key expressions:'
'                        expr: _col0'
'                        type: string'
'                  sort order: +'
'                  Map-reduce partition columns:'
'                        expr: _col0'
'                        type: string'
'                  tag: 0'
'                  value expressions:'
'                        expr: _col0'
'                        type: string'
'                        expr: _col1'
'                        type: string'
'        null-subquery2:subq1-subquery2:t1 '
'          TableScan'
'            alias: t1'
'            Select Operator'
'              expressions:'
'                    expr: key'
'                    type: string'
'                    expr: val'
'                    type: string'
'              outputColumnNames: _col0, _col1'
'              Union'
'                Reduce Output Operator'
'                  key expressions:'
'                        expr: _col0'
'                        type: string'
'                  sort order: +'
'                  Map-reduce partition columns:'
'                        expr: _col0'
'                        type: string'
'                  tag: 0'
'                  value expressions:'
'                        expr: _col0'
'                        type: string'
'                        expr: _col1'
'                        type: string'
'      Reduce Operator Tree:'
'        Join Operator'
'          condition map:'
'               Inner Join 0 to 1'
'          condition expressions:'
'            0 {VALUE._col0} {VALUE._col1}'
'            1 {VALUE._col0} {VALUE._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col2, _col3'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col2'
'                  type: string'
'                  expr: _col3'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2, _col3'
'            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'
''
''
110 rows selected 
>>>  
>>>  select * from 
( 
select key, val from T1 
union all 
select key, val from T1 
) subq1 
join T2 b on subq1.key = b.key 
ORDER BY subq1.key, b.key, subq1.val, b.val;
'key','val','key','val'
'2','12','2','22'
'2','12','2','22'
'3','13','3','13'
'3','13','3','13'
'8','18','8','18'
'8','18','8','18'
'8','18','8','18'
'8','18','8','18'
'8','28','8','18'
'8','28','8','18'
'8','28','8','18'
'8','28','8','18'
12 rows selected 
>>>  
>>>  -- no skew join compile time optimization would be performed if one of the
>>>  -- join sources is a sub-query consisting of a group by
>>>  EXPLAIN 
select * from 
( 
select key, count(1) as cnt from T1 group by key 
) subq1 
join T2 b on subq1.key = b.key;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME T1))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_TABLE_OR_COL key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (TOK_TABLE_OR_COL key)))) subq1) (TOK_TABREF (TOK_TABNAME T2) b) (= (. (TOK_TABLE_OR_COL subq1) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR TOK_ALLCOLREF))))'
''
'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:'
'        subq1:t1 '
'          TableScan'
'            alias: t1'
'            Select Operator'
'              expressions:'
'                    expr: key'
'                    type: string'
'              outputColumnNames: key'
'              Group By Operator'
'                aggregations:'
'                      expr: count(1)'
'                bucketGroup: false'
'                keys:'
'                      expr: key'
'                      type: string'
'                mode: hash'
'                outputColumnNames: _col0, _col1'
'                Reduce Output Operator'
'                  key expressions:'
'                        expr: _col0'
'                        type: string'
'                  sort order: +'
'                  Map-reduce partition columns:'
'                        expr: _col0'
'                        type: string'
'                  tag: -1'
'                  value expressions:'
'                        expr: _col1'
'                        type: bigint'
'      Reduce Operator Tree:'
'        Group By Operator'
'          aggregations:'
'                expr: count(VALUE._col0)'
'          bucketGroup: false'
'          keys:'
'                expr: KEY._col0'
'                type: string'
'          mode: mergepartial'
'          outputColumnNames: _col0, _col1'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: bigint'
'            outputColumnNames: _col0, _col1'
'            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:'
'        $INTNAME '
'            Reduce Output Operator'
'              key expressions:'
'                    expr: _col0'
'                    type: string'
'              sort order: +'
'              Map-reduce partition columns:'
'                    expr: _col0'
'                    type: string'
'              tag: 0'
'              value expressions:'
'                    expr: _col0'
'                    type: string'
'                    expr: _col1'
'                    type: bigint'
'        b '
'          TableScan'
'            alias: b'
'            Reduce Output Operator'
'              key expressions:'
'                    expr: key'
'                    type: string'
'              sort order: +'
'              Map-reduce partition columns:'
'                    expr: key'
'                    type: string'
'              tag: 1'
'              value expressions:'
'                    expr: key'
'                    type: string'
'                    expr: val'
'                    type: string'
'      Reduce Operator Tree:'
'        Join Operator'
'          condition map:'
'               Inner Join 0 to 1'
'          condition expressions:'
'            0 {VALUE._col0} {VALUE._col1}'
'            1 {VALUE._col0} {VALUE._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col2, _col3'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: bigint'
'                  expr: _col2'
'                  type: string'
'                  expr: _col3'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2, _col3'
'            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'
''
''
132 rows selected 
>>>  
>>>  select * from 
( 
select key, count(1) as cnt from T1 group by key 
) subq1 
join T2 b on subq1.key = b.key 
ORDER BY subq1.key, b.key, subq1.cnt, b.val;
'key','cnt','key','val'
'2','1','2','22'
'3','1','3','13'
'8','2','8','18'
'8','2','8','18'
4 rows selected 
>>>  !record