Saving all output to "!!{outputDirectory}!!/auto_join24.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/auto_join24.q >>> set hive.auto.convert.join = true; No rows affected >>> >>> create table tst1(key STRING, cnt INT); No rows affected >>> >>> INSERT OVERWRITE TABLE tst1 SELECT a.key, count(1) FROM src a group by a.key; '_col0','_col1' No rows selected >>> >>> explain SELECT sum(a.cnt) FROM tst1 a JOIN tst1 b ON a.key = b.key; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME tst1) a) (TOK_TABREF (TOK_TABNAME tst1) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION sum (. (TOK_TABLE_OR_COL a) cnt))))))' '' '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:' ' b ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' b ' ' TableScan' ' alias: b' ' HashTable Sink Operator' ' condition expressions:' ' 0 {cnt}' ' 1 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' Position of Big Table: 0' '' ' Stage: Stage-4' ' Map Reduce' ' Alias -> Map Operator Tree:' ' a ' ' TableScan' ' alias: a' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {cnt}' ' 1 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' outputColumnNames: _col1' ' Position of Big Table: 0' ' Select Operator' ' expressions:' ' expr: _col1' ' type: int' ' outputColumnNames: _col1' ' Group By Operator' ' aggregations:' ' expr: sum(_col1)' ' 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:' ' a ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' a ' ' TableScan' ' alias: a' ' HashTable Sink Operator' ' condition expressions:' ' 0 {cnt}' ' 1 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' Position of Big Table: 1' '' ' Stage: Stage-5' ' Map Reduce' ' Alias -> Map Operator Tree:' ' b ' ' TableScan' ' alias: b' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {cnt}' ' 1 ' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[key]]' ' outputColumnNames: _col1' ' Position of Big Table: 1' ' Select Operator' ' expressions:' ' expr: _col1' ' type: int' ' outputColumnNames: _col1' ' Group By Operator' ' aggregations:' ' expr: sum(_col1)' ' 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:' ' 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: cnt' ' type: int' ' 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' ' Reduce Operator Tree:' ' Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {VALUE._col1}' ' 1 ' ' handleSkewJoin: false' ' outputColumnNames: _col1' ' Select Operator' ' expressions:' ' expr: _col1' ' type: int' ' outputColumnNames: _col1' ' Group By Operator' ' aggregations:' ' expr: sum(_col1)' ' 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' '' '' 224 rows selected >>> >>> SELECT sum(a.cnt) FROM tst1 a JOIN tst1 b ON a.key = b.key; '_c0' '500' 1 row selected >>> >>> >>> !record