Saving all output to "!!{outputDirectory}!!/join38.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/join38.q >>> >>> >>> create table tmp(col0 string, col1 string,col2 string,col3 string,col4 string,col5 string,col6 string,col7 string,col8 string,col9 string,col10 string,col11 string); No rows affected >>> >>> insert overwrite table tmp select key, cast(key + 1 as int), key +2, key+3, key+4, cast(key+5 as int), key+6, key+7, key+8, key+9, key+10, cast(key+11 as int) from src where key = 100; 'key','_c1','_c2','_c3','_c4','_c5','_c6','_c7','_c8','_c9','_c10','_c11' No rows selected >>> >>> select * from tmp; 'col0','col1','col2','col3','col4','col5','col6','col7','col8','col9','col10','col11' '100','101','102.0','103.0','104.0','105','106.0','107.0','108.0','109.0','110.0','111' '100','101','102.0','103.0','104.0','105','106.0','107.0','108.0','109.0','110.0','111' 2 rows selected >>> >>> explain FROM src a JOIN tmp b ON (a.key = b.col11) SELECT /*+ MAPJOIN(a) */ a.value, b.col5, count(1) as count where b.col11 = 111 group by a.value, b.col5; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME src) a) (TOK_TABREF (TOK_TABNAME tmp) b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) col11)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) col5)) (TOK_SELEXPR (TOK_FUNCTION count 1) count)) (TOK_WHERE (= (. (TOK_TABLE_OR_COL b) col11) 111)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL a) value) (. (TOK_TABLE_OR_COL b) col5))))' '' 'STAGE DEPENDENCIES:' ' Stage-4 is a root stage' ' Stage-1 depends on stages: Stage-4' ' Stage-2 depends on stages: Stage-1' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-4' ' Map Reduce Local Work' ' Alias -> Map Local Tables:' ' a ' ' Fetch Operator' ' limit: -1' ' Alias -> Map Local Operator Tree:' ' a ' ' TableScan' ' alias: a' ' Filter Operator' ' predicate:' ' expr: (key = 111.0)' ' type: boolean' ' HashTable Sink Operator' ' condition expressions:' ' 0 {value}' ' 1 {col5} {col11}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[col11]]' ' Position of Big Table: 1' '' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' b ' ' TableScan' ' alias: b' ' Filter Operator' ' predicate:' ' expr: (col11 = 111.0)' ' type: boolean' ' Map Join Operator' ' condition map:' ' Inner Join 0 to 1' ' condition expressions:' ' 0 {value}' ' 1 {col5} {col11}' ' handleSkewJoin: false' ' keys:' ' 0 [Column[key]]' ' 1 [Column[col11]]' ' outputColumnNames: _col1, _col9, _col15' ' 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-2' ' Map Reduce' ' Alias -> Map Operator Tree:' ' file:!!{hive.exec.scratchdir}!! ' ' Select Operator' ' expressions:' ' expr: _col1' ' type: string' ' expr: _col9' ' type: string' ' expr: _col15' ' type: string' ' outputColumnNames: _col1, _col9, _col15' ' Select Operator' ' expressions:' ' expr: _col1' ' type: string' ' expr: _col9' ' type: string' ' outputColumnNames: _col1, _col9' ' Group By Operator' ' aggregations:' ' expr: count(1)' ' bucketGroup: false' ' keys:' ' expr: _col1' ' type: string' ' expr: _col9' ' type: string' ' mode: hash' ' outputColumnNames: _col0, _col1, _col2' ' 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: -1' ' value expressions:' ' expr: _col2' ' type: bigint' ' Reduce Operator Tree:' ' Group By Operator' ' aggregations:' ' expr: count(VALUE._col0)' ' bucketGroup: false' ' keys:' ' expr: KEY._col0' ' type: string' ' expr: KEY._col1' ' type: string' ' mode: mergepartial' ' outputColumnNames: _col0, _col1, _col2' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col1' ' type: string' ' expr: _col2' ' type: bigint' ' outputColumnNames: _col0, _col1, _col2' ' 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-0' ' Fetch Operator' ' limit: -1' '' '' 145 rows selected >>> >>> FROM src a JOIN tmp b ON (a.key = b.col11) SELECT /*+ MAPJOIN(a) */ a.value, b.col5, count(1) as count where b.col11 = 111 group by a.value, b.col5; 'value','col5','count' 'val_111','105','2' 1 row selected >>> >>> >>> !record