Saving all output to "!!{outputDirectory}!!/ppd_random.q.raw". Enter "record" with no arguments to stop it. >>> !run !!{qFileDirectory}!!/ppd_random.q >>> set hive.optimize.ppd=true; No rows affected >>> set hive.ppd.remove.duplicatefilters=false; No rows affected >>> >>> EXPLAIN SELECT src1.c1, src2.c4 FROM (SELECT src.key as c1, src.value as c2 from src ) src1 JOIN (SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 ON src1.c1 = src2.c3 WHERE rand() > 0.5; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (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_TABLE_OR_COL src) key) c1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value) c2)))) src1) (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_TABLE_OR_COL src) key) c3) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value) c4)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL src) key) '2')))) src2) (= (. (TOK_TABLE_OR_COL src1) c1) (. (TOK_TABLE_OR_COL src2) c3)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) c1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) c4))) (TOK_WHERE (> (TOK_FUNCTION rand) 0.5))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src1:src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' outputColumnNames: _col0' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 0' ' value expressions:' ' expr: _col0' ' type: string' ' src2:src ' ' TableScan' ' alias: src' ' Filter Operator' ' predicate:' ' expr: (key > '2')' ' type: boolean' ' Filter Operator' ' predicate:' ' expr: (key > '2')' ' 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' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 1' ' value expressions:' ' expr: _col1' ' 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' ' Filter Operator' ' predicate:' ' expr: (rand() > 0.5)' ' type: boolean' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1' ' 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' '' '' 93 rows selected >>> >>> set hive.ppd.remove.duplicatefilters=true; No rows affected >>> >>> EXPLAIN SELECT src1.c1, src2.c4 FROM (SELECT src.key as c1, src.value as c2 from src ) src1 JOIN (SELECT src.key as c3, src.value as c4 from src where src.key > '2' ) src2 ON src1.c1 = src2.c3 WHERE rand() > 0.5; 'Explain' 'ABSTRACT SYNTAX TREE:' ' (TOK_QUERY (TOK_FROM (TOK_JOIN (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_TABLE_OR_COL src) key) c1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value) c2)))) src1) (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_TABLE_OR_COL src) key) c3) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value) c4)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL src) key) '2')))) src2) (= (. (TOK_TABLE_OR_COL src1) c1) (. (TOK_TABLE_OR_COL src2) c3)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src1) c1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src2) c4))) (TOK_WHERE (> (TOK_FUNCTION rand) 0.5))))' '' 'STAGE DEPENDENCIES:' ' Stage-1 is a root stage' ' Stage-0 is a root stage' '' 'STAGE PLANS:' ' Stage: Stage-1' ' Map Reduce' ' Alias -> Map Operator Tree:' ' src1:src ' ' TableScan' ' alias: src' ' Select Operator' ' expressions:' ' expr: key' ' type: string' ' outputColumnNames: _col0' ' Reduce Output Operator' ' key expressions:' ' expr: _col0' ' type: string' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 0' ' value expressions:' ' expr: _col0' ' type: string' ' src2:src ' ' TableScan' ' alias: src' ' Filter Operator' ' predicate:' ' expr: (key > '2')' ' 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' ' sort order: +' ' Map-reduce partition columns:' ' expr: _col0' ' type: string' ' tag: 1' ' value expressions:' ' expr: _col1' ' 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' ' Filter Operator' ' predicate:' ' expr: (rand() > 0.5)' ' type: boolean' ' Select Operator' ' expressions:' ' expr: _col0' ' type: string' ' expr: _col3' ' type: string' ' outputColumnNames: _col0, _col1' ' 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' '' '' 89 rows selected >>> !record