Saving all output to "!!{outputDirectory}!!/auto_join31.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/auto_join31.q >>> set hive.auto.convert.join = true; No rows affected >>> >>> explain FROM (SELECT src.* FROM src sort by key) x RIGHT OUTER JOIN (SELECT src.* FROM src sort by value) Y ON (x.key = Y.key) JOIN (SELECT src.* FROM src sort by value) Z ON (x.key = Z.key) select sum(hash(Y.key,Y.value)); 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_RIGHTOUTERJOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL key))))) x) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Y) key))) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_ALLCOLREF (TOK_TABNAME src)))) (TOK_SORTBY (TOK_TABSORTCOLNAMEASC (TOK_TABLE_OR_COL value))))) Z) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL Z) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL Y) key) (. (TOK_TABLE_OR_COL Y) value)))))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-8 depends on stages: Stage-1, Stage-4, Stage-5 , consists of Stage-9, Stage-10, Stage-2' ' Stage-9 has a backup stage: Stage-2' ' Stage-6 depends on stages: Stage-9' ' Stage-3 depends on stages: Stage-2, Stage-6, Stage-7' ' Stage-10 has a backup stage: Stage-2' ' Stage-7 depends on stages: Stage-10' ' Stage-2' ' Stage-4 is a root stage' ' Stage-5 is a root stage' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' z:src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Reduce Output Operator' ' key expressions:' ' expr: _col1' ' type: string' ' sort order: +' ' tag: -1' ' value expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' Reduce Operator Tree:' ' Extract' ' 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' ' Conditional Operator' '' ' Stage: Stage-9' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' $INTNAME ' ' Fetch Operator' ' limit: -1' ' $INTNAME1 ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' $INTNAME ' ' HashTable Sink Operator' ' condition expressions:' ' 0 ' ' 1 {_col0} {_col1}' ' 2 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' 2 [Column[_col0]]' ' Position of Big Table: 1' ' $INTNAME1 ' ' HashTable Sink Operator' ' condition expressions:' ' 0 ' ' 1 {_col0} {_col1}' ' 2 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' 2 [Column[_col0]]' ' Position of Big Table: 1' '' ' Stage: Stage-6' ' Map Reduce' ' Alias -> Map Operator Tree:' ' $INTNAME2 ' ' Map Join Operator' ' condition map:' ' Right Outer Join0 to 1' ' Inner Join 0 to 2' ' condition expressions:' ' 0 ' ' 1 {_col0} {_col1}' ' 2 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' 2 [Column[_col0]]' ' outputColumnNames: _col2, _col3' ' Position of Big Table: 1' ' Select Operator' ' expressions:' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col2, _col3' ' Group By Operator' ' aggregations:' ' expr: sum(hash(_col2,_col3))' ' 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' ' Local Work:' ' Map Reduce Local Work' '' ' Stage: Stage-3' ' Map Reduce' ' Alias -> Map Operator Tree:' ' file:!!{hive.exec.scratchdir}!! ' ' 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-10' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' $INTNAME1 ' ' Fetch Operator' ' limit: -1' ' $INTNAME2 ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' $INTNAME1 ' ' HashTable Sink Operator' ' condition expressions:' ' 0 ' ' 1 {_col0} {_col1}' ' 2 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' 2 [Column[_col0]]' ' Position of Big Table: 2' ' $INTNAME2 ' ' HashTable Sink Operator' ' condition expressions:' ' 0 ' ' 1 {_col0} {_col1}' ' 2 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' 2 [Column[_col0]]' ' Position of Big Table: 2' '' ' Stage: Stage-7' ' Map Reduce' ' Alias -> Map Operator Tree:' ' $INTNAME ' ' Map Join Operator' ' condition map:' ' Right Outer Join0 to 1' ' Inner Join 0 to 2' ' condition expressions:' ' 0 ' ' 1 {_col0} {_col1}' ' 2 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0]]' ' 1 [Column[_col0]]' ' 2 [Column[_col0]]' ' outputColumnNames: _col2, _col3' ' Position of Big Table: 2' ' Select Operator' ' expressions:' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col2, _col3' ' Group By Operator' ' aggregations:' ' expr: sum(hash(_col2,_col3))' ' 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' ' Local Work:' ' Map Reduce Local Work' '' ' 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: 2' ' $INTNAME1 ' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 0' ' $INTNAME2 ' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 1' ' value expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Right Outer Join0 to 1' ' Inner Join 0 to 2' ' condition expressions:' ' 0 ' ' 1 {VALUE._col0} {VALUE._col1}' ' 2 ' ' handleSkewJoin: false' ' outputColumnNames: _col2, _col3' ' Select Operator' ' expressions:' ' expr: _col2' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col2, _col3' ' Group By Operator' ' aggregations:' ' expr: sum(hash(_col2,_col3))' ' 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-4' ' Map Reduce' ' Alias -> Map Operator Tree:' ' x:src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' tag: -1' ' value expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' Reduce Operator Tree:' ' Extract' ' 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-5' ' Map Reduce' ' Alias -> Map Operator Tree:' ' y:src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Reduce Output Operator' ' key expressions:' ' expr: _col1' ' type: string' ' sort order: +' ' tag: -1' ' value expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' Reduce Operator Tree:' ' Extract' ' 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' '' '' 374 rows selected >>> >>> FROM (SELECT src.* FROM src sort by key) x RIGHT OUTER JOIN (SELECT src.* FROM src sort by value) Y ON (x.key = Y.key) JOIN (SELECT src.* FROM src sort by value) Z ON (x.key = Z.key) select sum(hash(Y.key,Y.value)); '_c0' '348019368476' 1 row selected >>> !record