Saving all output to "!!{outputDirectory}!!/auto_join2.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/auto_join2.q >>> set hive.auto.convert.join = true; No rows affected >>> >>> CREATE TABLE dest_j2(key INT, value STRING) STORED AS TEXTFILE; No rows affected >>> >>> explain FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key) INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) src1) (TOK_TABREF (TOK_TABNAME src) src2) (= (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key))) (TOK_TABREF (TOK_TABNAME src) src3) (= (+ (. (TOK_TABLE_OR_COL src1) key) (. (TOK_TABLE_OR_COL src2) key)) (. (TOK_TABLE_OR_COL src3) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME dest_j2))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src3) value)))))' '' 'STAGE DEPENDENCIES:' ' Stage-11 is a root stage , consists of Stage-14, Stage-15, Stage-1' ' Stage-14 has a backup stage: Stage-1' ' Stage-9 depends on stages: Stage-14' ' Stage-8 depends on stages: Stage-1, Stage-9, Stage-10 , consists of Stage-12, Stage-13, Stage-2' ' Stage-12 has a backup stage: Stage-2' ' Stage-6 depends on stages: Stage-12' ' Stage-0 depends on stages: Stage-2, Stage-6, Stage-7' ' Stage-3 depends on stages: Stage-0' ' Stage-13 has a backup stage: Stage-2' ' Stage-7 depends on stages: Stage-13' ' Stage-2' ' Stage-15 has a backup stage: Stage-1' ' Stage-10 depends on stages: Stage-15' ' Stage-1' '' 'STAGE PLANS:' ' Stage: Stage-11' ' Conditional Operator' '' ' Stage: Stage-14' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' src2 ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' src2 ' ' TableScan' ' alias: src2' ' HashTable Sink Operator' ' condition expressions:' ' 0 {key}' ' 1 {key}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' Position of Big Table: 0' '' ' Stage: Stage-9' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src1 ' ' TableScan' ' alias: src1' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {key}' ' 1 {key}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' outputColumnNames: _col0, _col4' ' Position of Big Table: 0' ' 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-8' ' Conditional Operator' '' ' Stage: Stage-12' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' src3 ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' src3 ' ' TableScan' ' alias: src3' ' HashTable Sink Operator' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[_col0], Column[_col4]()]' ' 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]' ' Position of Big Table: 0' '' ' Stage: Stage-6' ' Map Reduce' ' Alias -> Map Operator Tree:' ' $INTNAME ' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[_col0], Column[_col4]()]' ' 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]' ' outputColumnNames: _col4, _col9' ' Position of Big Table: 0' ' Select Operator' ' expressions:' ' expr: _col4' ' type: string' ' expr: _col9' ' type: string' ' outputColumnNames: _col0, _col1' ' Select Operator' ' expressions:' ' expr: UDFToInteger(_col0)' ' type: int' ' expr: _col1' ' type: string' ' outputColumnNames: _col0, _col1' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: auto_join2.dest_j2' ' Local Work:' ' Map Reduce Local Work' '' ' Stage: Stage-0' ' Move Operator' ' tables:' ' replace: true' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: auto_join2.dest_j2' '' ' Stage: Stage-3' ' Stats-Aggr Operator' '' ' Stage: Stage-13' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' $INTNAME ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' $INTNAME ' ' HashTable Sink Operator' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[_col0], Column[_col4]()]' ' 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]' ' Position of Big Table: 1' '' ' Stage: Stage-7' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src3 ' ' TableScan' ' alias: src3' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {_col0}' ' 1 {value}' ' handleSkewJoin: false' ' keys:' ' 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[_col0], Column[_col4]()]' ' 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]' ' outputColumnNames: _col4, _col9' ' Position of Big Table: 1' ' Select Operator' ' expressions:' ' expr: _col4' ' type: string' ' expr: _col9' ' type: string' ' outputColumnNames: _col0, _col1' ' Select Operator' ' expressions:' ' expr: UDFToInteger(_col0)' ' type: int' ' expr: _col1' ' type: string' ' outputColumnNames: _col0, _col1' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: auto_join2.dest_j2' ' Local Work:' ' Map Reduce Local Work' '' ' Stage: Stage-2' ' Map Reduce' ' Alias -> Map Operator Tree:' ' $INTNAME ' ' Reduce Output Operator' ' key expressions:' ' expr: (_col0 + _col4)' ' type: double' ' sort order: +' ' Map-reduce partition columns:' ' expr: (_col0 + _col4)' ' type: double' ' tag: 0' ' value expressions:' ' expr: _col0' ' type: string' ' src3 ' ' TableScan' ' alias: src3' ' Reduce Output Operator' ' key expressions:' ' expr: UDFToDouble(key)' ' type: double' ' sort order: +' ' Map-reduce partition columns:' ' expr: UDFToDouble(key)' ' type: double' ' tag: 1' ' value expressions:' ' expr: value' ' type: string' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col4}' ' 1 {VALUE._col1}' ' handleSkewJoin: false' ' outputColumnNames: _col4, _col9' ' Select Operator' ' expressions:' ' expr: _col4' ' type: string' ' expr: _col9' ' type: string' ' outputColumnNames: _col0, _col1' ' Select Operator' ' expressions:' ' expr: UDFToInteger(_col0)' ' type: int' ' expr: _col1' ' type: string' ' outputColumnNames: _col0, _col1' ' File Output Operator' ' compressed: false' ' GlobalTableId: 1' ' table:' ' input format: org.apache.hadoop.mapred.TextInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat' ' serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe' ' name: auto_join2.dest_j2' '' ' Stage: Stage-15' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' src1 ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' src1 ' ' TableScan' ' alias: src1' ' HashTable Sink Operator' ' condition expressions:' ' 0 {key}' ' 1 {key}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' Position of Big Table: 1' '' ' Stage: Stage-10' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src2 ' ' TableScan' ' alias: src2' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {key}' ' 1 {key}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' outputColumnNames: _col0, _col4' ' Position of Big Table: 1' ' 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:' ' src1 ' ' TableScan' ' alias: src1' ' 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' ' src2 ' ' TableScan' ' alias: src2' ' 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' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col0}' ' 1 {VALUE._col0}' ' handleSkewJoin: false' ' outputColumnNames: _col0, _col4' ' File Output Operator' ' compressed: false' ' GlobalTableId: 0' ' table:' ' input format: org.apache.hadoop.mapred.SequenceFileInputFormat' ' output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat' '' '' 368 rows selected >>> >>> >>> FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key + src2.key = src3.key) INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value; '_col0','_col1' No rows selected >>> >>> SELECT sum(hash(dest_j2.key,dest_j2.value)) FROM dest_j2; '_c0' '33815990627' 1 row selected >>> !record