Saving all output to "!!{outputDirectory}!!/auto_join16.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/auto_join16.q >>> >>> set hive.auto.convert.join = true; No rows affected >>> >>> >>> explain SELECT sum(hash(subq.key, tab.value)) FROM (select a.key, a.value from src a where a.key > 10 ) subq JOIN src tab ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value) where tab.value < 200; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src) a)) (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) value))) (TOK_WHERE (> (. (TOK_TABLE_OR_COL a) key) 10)))) subq) (TOK_TABREF (TOK_TABNAME src) tab) (and (and (= (. (TOK_TABLE_OR_COL subq) key) (. (TOK_TABLE_OR_COL tab) key)) (> (. (TOK_TABLE_OR_COL subq) key) 20)) (= (. (TOK_TABLE_OR_COL subq) value) (. (TOK_TABLE_OR_COL tab) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL subq) key) (. (TOK_TABLE_OR_COL tab) value))))) (TOK_WHERE (< (. (TOK_TABLE_OR_COL tab) value) 200))))' '' 'STAGE DEPENDENCIES:' ' Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1' ' Stage-7 has a backup stage: Stage-1' ' Stage-4 depends on stages: Stage-7' ' Stage-2 depends on stages: Stage-1, Stage-4, Stage-5' ' Stage-8 has a backup stage: Stage-1' ' Stage-5 depends on stages: Stage-8' ' Stage-1' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-6' ' Conditional Operator' '' ' Stage: Stage-7' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' tab ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' tab ' ' TableScan' ' alias: tab' ' Filter Operator' ' predicate:' ' expr: ((key > 20) and (value < 200))' ' type: boolean' ' HashTable Sink Operator' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0], Column[_col1]]' ' 1 [Column[key], Column[value]]' ' Position of Big Table: 0' '' ' Stage: Stage-4' ' Map Reduce' ' Alias -> Map Operator Tree:' ' subq:a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (((key > 10) and (key > 20)) and (value < 200))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0], Column[_col1]]' ' 1 [Column[key], Column[value]]' ' outputColumnNames: _col0, _col3' ' Position of Big Table: 0' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col3' ' Group By Operator' ' aggregations:' ' expr: sum(hash(_col0,_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:' ' 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-8' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' subq:a ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' subq:a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (((key > 10) and (key > 20)) and (value < 200))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' HashTable Sink Operator' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0], Column[_col1]]' ' 1 [Column[key], Column[value]]' ' Position of Big Table: 1' '' ' Stage: Stage-5' ' Map Reduce' ' Alias -> Map Operator Tree:' ' tab ' ' TableScan' ' alias: tab' ' Filter Operator' ' predicate:' ' expr: ((key > 20) and (value < 200))' ' type: boolean' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[_col0], Column[_col1]]' ' 1 [Column[key], Column[value]]' ' outputColumnNames: _col0, _col3' ' Position of Big Table: 1' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col3' ' Group By Operator' ' aggregations:' ' expr: sum(hash(_col0,_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-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' subq:a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (((key > 10) and (key > 20)) and (value < 200))' ' type: boolean' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' outputColumnNames: _col0, _col1' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' tag: 0' ' value expressions:' ' expr: _col0' ' type: string' ' tab ' ' TableScan' ' alias: tab' ' Filter Operator' ' predicate:' ' expr: ((key > 20) and (value < 200))' ' type: boolean' ' Reduce Output Operator' ' key expressions:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' sort order: ++' ' Map-reduce partition columns:' ' expr: key' ' type: string' ' expr: value' ' type: string' ' tag: 1' ' value expressions:' ' expr: value' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col0}' ' 1 {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col3' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col3' ' Group By Operator' ' aggregations:' ' expr: sum(hash(_col0,_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-0' ' Fetch Operator' ' limit: -1' '' '' 286 rows selected >>> >>> SELECT sum(hash(subq.key, tab.value)) FROM (select a.key, a.value from src a where a.key > 10 ) subq JOIN src tab ON (subq.key = tab.key and subq.key > 20 and subq.value = tab.value) where tab.value < 200; '_c0' '' 1 row selected >>> !record