Saving all output to "!!{outputDirectory}!!/skewjoinopt13.q.raw". Enter "record" with no arguments to stop it.
>>>  !run !!{qFileDirectory}!!/skewjoinopt13.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) 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 
>>>  
>>>  CREATE TABLE T3(key STRING, val STRING) 
SKEWED BY (val) ON ((12)) STORED AS TEXTFILE;
No rows affected 
>>>  
>>>  LOAD DATA LOCAL INPATH '../data/files/T3.txt' INTO TABLE T3;
No rows affected 
>>>  
>>>  -- This test is for skewed join compile time optimization for more than 2 tables.
>>>  -- The join key for table 3 is different from the join key used for joining
>>>  -- tables 1 and 2. Table 3 is skewed, but since one of the join sources for table
>>>  -- 3 consist of a sub-query which contains a join, the compile time skew join
>>>  -- optimization is not performed
>>>  -- adding a order by at the end to make the results deterministic
>>>  
>>>  EXPLAIN 
select * 
from 
T1 a join T2 b on a.key = b.key 
join T3 c on a.val = c.val;
'Explain'
'ABSTRACT SYNTAX TREE:'
'  (TOK_QUERY (TOK_FROM (TOK_JOIN (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_TABREF (TOK_TABNAME T3) c) (= (. (TOK_TABLE_OR_COL a) val) (. (TOK_TABLE_OR_COL c) val)))) (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:'
'        a '
'          TableScan'
'            alias: a'
'            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'
'        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, _col4, _col5'
'          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: _col1'
'                    type: string'
'              sort order: +'
'              Map-reduce partition columns:'
'                    expr: _col1'
'                    type: string'
'              tag: 0'
'              value expressions:'
'                    expr: _col4'
'                    type: string'
'                    expr: _col5'
'                    type: string'
'                    expr: _col0'
'                    type: string'
'                    expr: _col1'
'                    type: string'
'        c '
'          TableScan'
'            alias: c'
'            Reduce Output Operator'
'              key expressions:'
'                    expr: val'
'                    type: string'
'              sort order: +'
'              Map-reduce partition columns:'
'                    expr: val'
'                    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} {VALUE._col4} {VALUE._col5}'
'            1 {VALUE._col0} {VALUE._col1}'
'          handleSkewJoin: false'
'          outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9'
'          Select Operator'
'            expressions:'
'                  expr: _col4'
'                  type: string'
'                  expr: _col5'
'                  type: string'
'                  expr: _col0'
'                  type: string'
'                  expr: _col1'
'                  type: string'
'                  expr: _col8'
'                  type: string'
'                  expr: _col9'
'                  type: string'
'            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5'
'            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'
''
''
137 rows selected 
>>>  
>>>  select * 
from 
T1 a join T2 b on a.key = b.key 
join T3 c on a.val = c.val 
order by a.key, b.key, c.key, a.val, b.val, c.val;
'key','val','key','val','key','val'
'2','12','2','22','2','12'
1 row selected 
>>>  
>>>  !record