set hive.auto.convert.join = true


explain
select sum(hash(a.k1,a.v1,a.k2,a.v2,a.k3,a.v3))
from (
SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 , src3.key as k3, src3.value as v3 
FROM src src1 JOIN src src2 ON (src1.key = src2.key AND src1.key < 10) RIGHT OUTER JOIN src src3 ON (src1.key = src3.key AND src3.key < 20)
SORT BY k1,v1,k2,v2,k3,v3
)a
ABSTRACT SYNTAX TREE:
  (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) src1) (TOK_TABREF (TOK_TABNAME src) src2) (AND (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key)) (< (. (TOK_TABLE_OR_COL src1) key) 10))) (TOK_TABREF (TOK_TABNAME src) src3) (AND (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src3) key)) (< (. (TOK_TABLE_OR_COL src3) key) 20)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) key) k1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) value) v1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) key) k2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) value) v2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src3) key) k3) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src3) value) v3)) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL k1)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL v1)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL k2)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL v2)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL k3)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL v3))))) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL a) k1) (. (TOK_TABLE_OR_COL a) v1) (. (TOK_TABLE_OR_COL a) k2) (. (TOK_TABLE_OR_COL a) v2) (. (TOK_TABLE_OR_COL a) k3) (. (TOK_TABLE_OR_COL a) v3)))))))

STAGE DEPENDENCIES:
  Stage-7 is a root stage , consists of Stage-8, Stage-1
  Stage-8 has a backup stage: Stage-1
  Stage-6 depends on stages: Stage-8
  Stage-2 depends on stages: Stage-1, Stage-6
  Stage-3 depends on stages: Stage-2
  Stage-1
  Stage-0 is a root stage

STAGE PLANS:
  Stage: Stage-7
    Conditional Operator

  Stage: Stage-8
    Map Reduce Local Work
      Alias -> Map Local Tables:
        a:src1 
          Fetch Operator
            limit: -1
        a:src2 
          Fetch Operator
            limit: -1
      Alias -> Map Local Operator Tree:
        a:src1 
          TableScan
            alias: src1
            Filter Operator
              predicate:
                  expr: (key < 10.0)
                  type: boolean
              HashTable Sink Operator
                condition expressions:
                  0 {key} {value}
                  1 {key} {value}
                  2 {key} {value}
                filter predicates:
                  0 
                  1 
                  2 {(key < 20.0)}
                handleSkewJoin: false
                keys:
                  0 [Column[key]]
                  1 [Column[key]]
                  2 [Column[key]]
                Position of Big Table: 2
        a:src2 
          TableScan
            alias: src2
            Filter Operator
              predicate:
                  expr: (key < 10.0)
                  type: boolean
              HashTable Sink Operator
                condition expressions:
                  0 {key} {value}
                  1 {key} {value}
                  2 {key} {value}
                filter predicates:
                  0 
                  1 
                  2 {(key < 20.0)}
                handleSkewJoin: false
                keys:
                  0 [Column[key]]
                  1 [Column[key]]
                  2 [Column[key]]
                Position of Big Table: 2

  Stage: Stage-6
    Map Reduce
      Alias -> Map Operator Tree:
        a:src3 
          TableScan
            alias: src3
            Map Join Operator
              condition map:
                   Inner Join 0 to 1
                   Right Outer Join0 to 2
              condition expressions:
                0 {key} {value}
                1 {key} {value}
                2 {key} {value}
              filter predicates:
                0 
                1 
                2 {(key < 20.0)}
              handleSkewJoin: false
              keys:
                0 [Column[key]]
                1 [Column[key]]
                2 [Column[key]]
              outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9
              Position of Big Table: 2
              Select Operator
                expressions:
                      expr: _col0
                      type: string
                      expr: _col1
                      type: string
                      expr: _col4
                      type: string
                      expr: _col5
                      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.SequenceFileInputFormat
                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
      Local Work:
        Map Reduce Local Work

  Stage: Stage-2
    Map Reduce
      Alias -> Map Operator Tree:
        hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-35-58_309_5301659382942807999/-mr-10002 
            Reduce Output Operator
              key expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: string
                    expr: _col2
                    type: string
                    expr: _col3
                    type: string
                    expr: _col4
                    type: string
                    expr: _col5
                    type: string
              sort order: ++++++
              tag: -1
              value expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: string
                    expr: _col2
                    type: string
                    expr: _col3
                    type: string
                    expr: _col4
                    type: string
                    expr: _col5
                    type: string
      Reduce Operator Tree:
        Extract
          Select Operator
            expressions:
                  expr: _col0
                  type: string
                  expr: _col1
                  type: string
                  expr: _col2
                  type: string
                  expr: _col3
                  type: string
                  expr: _col4
                  type: string
                  expr: _col5
                  type: string
            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
            Group By Operator
              aggregations:
                    expr: sum(hash(_col0,_col1,_col2,_col3,_col4,_col5))
              bucketGroup: false
              mode: hash
              outputColumnNames: _col0
              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:
        hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-35-58_309_5301659382942807999/-mr-10003 
            Reduce Output Operator
              sort order: 
              tag: -1
              value expressions:
                    expr: _col0
                    type: bigint
      Reduce Operator Tree:
        Group By Operator
          aggregations:
                expr: sum(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-1
    Map Reduce
      Alias -> Map Operator Tree:
        a:src1 
          TableScan
            alias: src1
            Filter Operator
              predicate:
                  expr: (key < 10.0)
                  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: value
                      type: string
        a:src2 
          TableScan
            alias: src2
            Filter Operator
              predicate:
                  expr: (key < 10.0)
                  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: key
                      type: string
                      expr: value
                      type: string
        a:src3 
          TableScan
            alias: src3
            Reduce Output Operator
              key expressions:
                    expr: key
                    type: string
              sort order: +
              Map-reduce partition columns:
                    expr: key
                    type: string
              tag: 2
              value expressions:
                    expr: key
                    type: string
                    expr: value
                    type: string
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
               Right Outer Join0 to 2
          condition expressions:
            0 {VALUE._col0} {VALUE._col1}
            1 {VALUE._col0} {VALUE._col1}
            2 {VALUE._col0} {VALUE._col1}
          filter predicates:
            0 
            1 
            2 {(VALUE._col0 < 20.0)}
          handleSkewJoin: false
          outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9
          Select Operator
            expressions:
                  expr: _col0
                  type: string
                  expr: _col1
                  type: string
                  expr: _col4
                  type: string
                  expr: _col5
                  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.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

  Stage: Stage-0
    Fetch Operator
      limit: -1




select sum(hash(a.k1,a.v1,a.k2,a.v2,a.k3,a.v3))
from (
SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 , src3.key as k3, src3.value as v3 
FROM src src1 JOIN src src2 ON (src1.key = src2.key AND src1.key < 10) RIGHT OUTER JOIN src src3 ON (src1.key = src3.key AND src3.key < 20)
SORT BY k1,v1,k2,v2,k3,v3
)a
56157587016


explain
select sum(hash(a.k1,a.v1,a.k2,a.v2,a.k3,a.v3))
from (
SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 , src3.key as k3, src3.value as v3  
FROM src src1 JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key < 15) RIGHT OUTER JOIN src src3 ON (src1.key = src3.key AND src3.key < 20)
SORT BY k1,v1,k2,v2,k3,v3
)a
ABSTRACT SYNTAX TREE:
  (TOK_QUERY (TOK_FROM (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_RIGHTOUTERJOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) src1) (TOK_TABREF (TOK_TABNAME src) src2) (AND (AND (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key)) (< (. (TOK_TABLE_OR_COL src1) key) 10)) (< (. (TOK_TABLE_OR_COL src2) key) 15))) (TOK_TABREF (TOK_TABNAME src) src3) (AND (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src3) key)) (< (. (TOK_TABLE_OR_COL src3) key) 20)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) key) k1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) value) v1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) key) k2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) value) v2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src3) key) k3) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src3) value) v3)) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL k1)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL v1)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL k2)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL v2)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL k3)) (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL v3))))) a)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL a) k1) (. (TOK_TABLE_OR_COL a) v1) (. (TOK_TABLE_OR_COL a) k2) (. (TOK_TABLE_OR_COL a) v2) (. (TOK_TABLE_OR_COL a) k3) (. (TOK_TABLE_OR_COL a) v3)))))))

STAGE DEPENDENCIES:
  Stage-7 is a root stage , consists of Stage-8, Stage-1
  Stage-8 has a backup stage: Stage-1
  Stage-6 depends on stages: Stage-8
  Stage-2 depends on stages: Stage-1, Stage-6
  Stage-3 depends on stages: Stage-2
  Stage-1
  Stage-0 is a root stage

STAGE PLANS:
  Stage: Stage-7
    Conditional Operator

  Stage: Stage-8
    Map Reduce Local Work
      Alias -> Map Local Tables:
        a:src1 
          Fetch Operator
            limit: -1
        a:src2 
          Fetch Operator
            limit: -1
      Alias -> Map Local Operator Tree:
        a:src1 
          TableScan
            alias: src1
            Filter Operator
              predicate:
                  expr: ((key < 10.0) and (key < 15.0))
                  type: boolean
              HashTable Sink Operator
                condition expressions:
                  0 {key} {value}
                  1 {key} {value}
                  2 {key} {value}
                filter predicates:
                  0 
                  1 
                  2 {(key < 20.0)}
                handleSkewJoin: false
                keys:
                  0 [Column[key]]
                  1 [Column[key]]
                  2 [Column[key]]
                Position of Big Table: 2
        a:src2 
          TableScan
            alias: src2
            Filter Operator
              predicate:
                  expr: ((key < 15.0) and (key < 10.0))
                  type: boolean
              HashTable Sink Operator
                condition expressions:
                  0 {key} {value}
                  1 {key} {value}
                  2 {key} {value}
                filter predicates:
                  0 
                  1 
                  2 {(key < 20.0)}
                handleSkewJoin: false
                keys:
                  0 [Column[key]]
                  1 [Column[key]]
                  2 [Column[key]]
                Position of Big Table: 2

  Stage: Stage-6
    Map Reduce
      Alias -> Map Operator Tree:
        a:src3 
          TableScan
            alias: src3
            Map Join Operator
              condition map:
                   Inner Join 0 to 1
                   Right Outer Join0 to 2
              condition expressions:
                0 {key} {value}
                1 {key} {value}
                2 {key} {value}
              filter predicates:
                0 
                1 
                2 {(key < 20.0)}
              handleSkewJoin: false
              keys:
                0 [Column[key]]
                1 [Column[key]]
                2 [Column[key]]
              outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9
              Position of Big Table: 2
              Select Operator
                expressions:
                      expr: _col0
                      type: string
                      expr: _col1
                      type: string
                      expr: _col4
                      type: string
                      expr: _col5
                      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.SequenceFileInputFormat
                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
      Local Work:
        Map Reduce Local Work

  Stage: Stage-2
    Map Reduce
      Alias -> Map Operator Tree:
        hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-37-20_822_7360885266220174309/-mr-10002 
            Reduce Output Operator
              key expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: string
                    expr: _col2
                    type: string
                    expr: _col3
                    type: string
                    expr: _col4
                    type: string
                    expr: _col5
                    type: string
              sort order: ++++++
              tag: -1
              value expressions:
                    expr: _col0
                    type: string
                    expr: _col1
                    type: string
                    expr: _col2
                    type: string
                    expr: _col3
                    type: string
                    expr: _col4
                    type: string
                    expr: _col5
                    type: string
      Reduce Operator Tree:
        Extract
          Select Operator
            expressions:
                  expr: _col0
                  type: string
                  expr: _col1
                  type: string
                  expr: _col2
                  type: string
                  expr: _col3
                  type: string
                  expr: _col4
                  type: string
                  expr: _col5
                  type: string
            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
            Group By Operator
              aggregations:
                    expr: sum(hash(_col0,_col1,_col2,_col3,_col4,_col5))
              bucketGroup: false
              mode: hash
              outputColumnNames: _col0
              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:
        hdfs://mgrover-bigtop-centos-1.ent.cloudera.com:17020/tmp/hive-root/hive_2013-04-23_11-37-20_822_7360885266220174309/-mr-10003 
            Reduce Output Operator
              sort order: 
              tag: -1
              value expressions:
                    expr: _col0
                    type: bigint
      Reduce Operator Tree:
        Group By Operator
          aggregations:
                expr: sum(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-1
    Map Reduce
      Alias -> Map Operator Tree:
        a:src1 
          TableScan
            alias: src1
            Filter Operator
              predicate:
                  expr: ((key < 10.0) and (key < 15.0))
                  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: value
                      type: string
        a:src2 
          TableScan
            alias: src2
            Filter Operator
              predicate:
                  expr: ((key < 15.0) and (key < 10.0))
                  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: key
                      type: string
                      expr: value
                      type: string
        a:src3 
          TableScan
            alias: src3
            Reduce Output Operator
              key expressions:
                    expr: key
                    type: string
              sort order: +
              Map-reduce partition columns:
                    expr: key
                    type: string
              tag: 2
              value expressions:
                    expr: key
                    type: string
                    expr: value
                    type: string
      Reduce Operator Tree:
        Join Operator
          condition map:
               Inner Join 0 to 1
               Right Outer Join0 to 2
          condition expressions:
            0 {VALUE._col0} {VALUE._col1}
            1 {VALUE._col0} {VALUE._col1}
            2 {VALUE._col0} {VALUE._col1}
          filter predicates:
            0 
            1 
            2 {(VALUE._col0 < 20.0)}
          handleSkewJoin: false
          outputColumnNames: _col0, _col1, _col4, _col5, _col8, _col9
          Select Operator
            expressions:
                  expr: _col0
                  type: string
                  expr: _col1
                  type: string
                  expr: _col4
                  type: string
                  expr: _col5
                  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.SequenceFileInputFormat
                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

  Stage: Stage-0
    Fetch Operator
      limit: -1




select sum(hash(a.k1,a.v1,a.k2,a.v2,a.k3,a.v3))
from (
SELECT src1.key as k1, src1.value as v1, src2.key as k2, src2.value as v2 , src3.key as k3, src3.value as v3  
FROM src src1 JOIN src src2 ON (src1.key = src2.key AND src1.key < 10 AND src2.key < 15) RIGHT OUTER JOIN src src3 ON (src1.key = src3.key AND src3.key < 20)
SORT BY k1,v1,k2,v2,k3,v3
)a
56157587016
