Saving all output to "!!{outputDirectory}!!/skewjoinopt11.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/skewjoinopt11.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 
>>>  
>>>  -- This test is to verify the skew join compile optimization when the join is followed
>>>  -- by a union. Both sides of a union consist of a join, which should have used
>>>  -- skew join compile time optimization.
>>>  -- adding a order by at the end to make the results deterministic
>>>  
>>>  EXPLAIN 
select * from 
( 
select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key 
union all 
select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key 
) subq1;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) val) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) val) val2)))) (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME T1) a) (TOK_TABREF (TOK_TABNAME T2) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) val) val1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) val) val2))))) subq1)) (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-5'
'  Stage-3 depends on stages: Stage-2, Stage-8'
'  Stage-5 is a root stage'
'  Stage-7 is a root stage'
'  Stage-8 depends on stages: Stage-7, Stage-9'
'  Stage-9 is a root stage'
'  Stage-0 is a root stage'
''
'STAGE PLANS:'
'  Stage: Stage-1'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        subquery1:a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (not (key = '2'))'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 0'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: val'
'                      type: string'
'        subquery1:b '
'          TableScan'
'            alias: b'
'            Filter Operator'
'              predicate:'
'                  expr: (not (key = '2'))'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 1'
'                value expressions:'
'                      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._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col5'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2'
'            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}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                SELECT * : (no compute)'
'                File Output Operator'
'                  compressed: false'
'                  GlobalTableId: 0'
'                  table:'
'                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat'
'                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                SELECT * : (no compute)'
'                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-3'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                expressions:'
'                      expr: _col0'
'                      type: string'
'                      expr: _col1'
'                      type: string'
'                      expr: _col2'
'                      type: string'
'                outputColumnNames: _col0, _col1, _col2'
'                File Output Operator'
'                  compressed: false'
'                  GlobalTableId: 0'
'                  table:'
'                      input format: org.apache.hadoop.mapred.TextInputFormat'
'                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                expressions:'
'                      expr: _col0'
'                      type: string'
'                      expr: _col1'
'                      type: string'
'                      expr: _col2'
'                      type: string'
'                outputColumnNames: _col0, _col1, _col2'
'                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-5'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        null-subquery2:subq1-subquery2:a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (key = '2')'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 0'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: val'
'                      type: string'
'        null-subquery2:subq1-subquery2:b '
'          TableScan'
'            alias: b'
'            Filter Operator'
'              predicate:'
'                  expr: (key = '2')'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 1'
'                value expressions:'
'                      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._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col5'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2'
'            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-7'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        null-subquery1:subq1-subquery1:a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (key = '2')'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 0'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: val'
'                      type: string'
'        null-subquery1:subq1-subquery1:b '
'          TableScan'
'            alias: b'
'            Filter Operator'
'              predicate:'
'                  expr: (key = '2')'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 1'
'                value expressions:'
'                      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._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col5'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2'
'            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-8'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                SELECT * : (no compute)'
'                File Output Operator'
'                  compressed: false'
'                  GlobalTableId: 0'
'                  table:'
'                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat'
'                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat'
'        file:!!{hive.exec.scratchdir}!! '
'          TableScan'
'            Union'
'              Select Operator'
'                SELECT * : (no compute)'
'                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-9'
'    Map Reduce'
'      Alias -> Map Operator Tree:'
'        subquery2:a '
'          TableScan'
'            alias: a'
'            Filter Operator'
'              predicate:'
'                  expr: (not (key = '2'))'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 0'
'                value expressions:'
'                      expr: key'
'                      type: string'
'                      expr: val'
'                      type: string'
'        subquery2:b '
'          TableScan'
'            alias: b'
'            Filter Operator'
'              predicate:'
'                  expr: (not (key = '2'))'
'                  type: boolean'
'              Reduce Output Operator'
'                key expressions:'
'                      expr: key'
'                      type: string'
'                sort order: +'
'                Map-reduce partition columns:'
'                      expr: key'
'                      type: string'
'                tag: 1'
'                value expressions:'
'                      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._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col5'
'          Select Operator'
'            expressions:'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2'
'            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-0'
'    Fetch Operator'
'      limit: -1'
''
''
383 rows selected 
>>>  
>>>  select * from 
( 
select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key 
union all 
select a.key, a.val as val1, b.val as val2 from T1 a join T2 b on a.key = b.key 
) subq1 
ORDER BY key, val1, val2;
'key','val1','val2'
'2','12','22'
'2','12','22'
'3','13','13'
'3','13','13'
'8','18','18'
'8','18','18'
'8','18','18'
'8','18','18'
'8','28','18'
'8','28','18'
'8','28','18'
'8','28','18'
12 rows selected 
>>>  !record