http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/ql/src/test/results/clientpositive/perf/spark/query4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query4.q.out b/ql/src/test/results/clientpositive/perf/spark/query4.q.out index 5074d49..75c4fbb 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query4.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query4.q.out @@ -225,20 +225,20 @@ STAGE PLANS: Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) Reducer 11 <- Map 14 (PARTITION-LEVEL SORT, 975), Reducer 10 (PARTITION-LEVEL SORT, 975) Reducer 12 <- Reducer 11 (GROUP, 481) - Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 306), Map 19 (PARTITION-LEVEL SORT, 306) - Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 873), Reducer 16 (PARTITION-LEVEL SORT, 873) - Reducer 18 <- Reducer 17 (GROUP, 369) + Reducer 16 <- Map 15 (PARTITION-LEVEL SORT, 398), Map 19 (PARTITION-LEVEL SORT, 398) + Reducer 17 <- Map 20 (PARTITION-LEVEL SORT, 975), Reducer 16 (PARTITION-LEVEL SORT, 975) + Reducer 18 <- Reducer 17 (GROUP, 481) Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 7 (PARTITION-LEVEL SORT, 306) - Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 154), Map 25 (PARTITION-LEVEL SORT, 154) - Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 706), Reducer 22 (PARTITION-LEVEL SORT, 706) - Reducer 24 <- Reducer 23 (GROUP, 186) + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 306), Map 25 (PARTITION-LEVEL SORT, 306) + Reducer 23 <- Map 26 (PARTITION-LEVEL SORT, 873), Reducer 22 (PARTITION-LEVEL SORT, 873) + Reducer 24 <- Reducer 23 (GROUP, 369) Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 154), Map 31 (PARTITION-LEVEL SORT, 154) Reducer 29 <- Map 32 (PARTITION-LEVEL SORT, 706), Reducer 28 (PARTITION-LEVEL SORT, 706) Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 873), Reducer 2 (PARTITION-LEVEL SORT, 873) Reducer 30 <- Reducer 29 (GROUP, 186) - Reducer 34 <- Map 33 (PARTITION-LEVEL SORT, 398), Map 37 (PARTITION-LEVEL SORT, 398) - Reducer 35 <- Map 38 (PARTITION-LEVEL SORT, 975), Reducer 34 (PARTITION-LEVEL SORT, 975) - Reducer 36 <- Reducer 35 (GROUP, 481) + Reducer 34 <- Map 33 (PARTITION-LEVEL SORT, 154), Map 37 (PARTITION-LEVEL SORT, 154) + Reducer 35 <- Map 38 (PARTITION-LEVEL SORT, 706), Reducer 34 (PARTITION-LEVEL SORT, 706) + Reducer 36 <- Reducer 35 (GROUP, 186) Reducer 4 <- Reducer 3 (GROUP, 369) Reducer 5 <- Reducer 12 (PARTITION-LEVEL SORT, 690), Reducer 18 (PARTITION-LEVEL SORT, 690), Reducer 24 (PARTITION-LEVEL SORT, 690), Reducer 30 (PARTITION-LEVEL SORT, 690), Reducer 36 (PARTITION-LEVEL SORT, 690), Reducer 4 (PARTITION-LEVEL SORT, 690) Reducer 6 <- Reducer 5 (SORT, 1) @@ -300,20 +300,20 @@ STAGE PLANS: Map 15 Map Operator Tree: TableScan - alias: catalog_sales - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 19 Map Operator Tree: @@ -353,20 +353,20 @@ STAGE PLANS: Map 21 Map Operator Tree: TableScan - alias: web_sales - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) + expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_ext_discount_amt (type: decimal(7,2)), cs_ext_sales_price (type: decimal(7,2)), cs_ext_wholesale_cost (type: decimal(7,2)), cs_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 25 Map Operator Tree: @@ -374,7 +374,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -427,7 +427,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -459,20 +459,20 @@ STAGE PLANS: Map 33 Map Operator Tree: TableScan - alias: store_sales - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_sales_price (type: decimal(7,2)), ws_ext_wholesale_cost (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Map 37 Map Operator Tree: @@ -480,7 +480,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -515,7 +515,7 @@ STAGE PLANS: alias: date_dim Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + predicate: ((d_year = 2002) and d_date_sk is not null) (type: boolean) Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: d_date_sk (type: int) @@ -638,12 +638,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 17 Reduce Operator Tree: @@ -654,22 +654,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 18 Reduce Operator Tree: @@ -678,17 +678,17 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(24,6)) + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: decimal(24,6)) Reducer 2 Reduce Operator Tree: Join Operator @@ -714,12 +714,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 23 Reduce Operator Tree: @@ -730,22 +730,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 24 Reduce Operator Tree: @@ -754,17 +754,24 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(24,6)) + outputColumnNames: _col0, _col7 + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col7 > 0) (type: boolean) + Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(24,6)) Reducer 28 Reduce Operator Tree: Join Operator @@ -843,21 +850,14 @@ STAGE PLANS: Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col7 + outputColumnNames: _col0, _col1 Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(24,6)) + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(24,6)) Reducer 34 Reduce Operator Tree: Join Operator @@ -867,12 +867,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2)) Reducer 35 Reduce Operator Tree: @@ -883,22 +883,22 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col2, _col3, _col4, _col5, _col9, _col10, _col11, _col12, _col13, _col14, _col15 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col14 (type: string), _col15 (type: string), ((((_col5 - _col4) - _col2) + _col3) / 2) (type: decimal(14,6)) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col7) keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) sort order: +++++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE value expressions: _col7 (type: decimal(24,6)) Reducer 36 Reduce Operator Tree: @@ -907,42 +907,42 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col7 (type: decimal(24,6)) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: decimal(24,6)) - Reducer 4 - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col7 - Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (_col7 > 0) (type: boolean) - Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string), _col7 (type: decimal(24,6)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 58077952 Data size: 7864921389 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(24,6)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string), KEY._col5 (type: string), KEY._col6 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col7 (type: decimal(24,6)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(24,6)) Reducer 5 Reduce Operator Tree: Join Operator @@ -959,13 +959,13 @@ STAGE PLANS: 3 _col0 (type: string) 4 _col0 (type: string) 5 _col0 (type: string) - outputColumnNames: _col1, _col3, _col5, _col7, _col9, _col11, _col12 + outputColumnNames: _col1, _col3, _col5, _col6, _col8, _col10, _col12 Statistics: Num rows: 1916625598 Data size: 169085266687 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col5 / _col1) > (_col12 / _col3)) and ((_col5 / _col1) > (_col7 / _col9))) (type: boolean) + predicate: (((_col1 / _col8) > (_col10 / _col12)) and ((_col1 / _col8) > (_col6 / _col3))) (type: boolean) Statistics: Num rows: 212958399 Data size: 18787251785 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col11 (type: string) + expressions: _col5 (type: string) outputColumnNames: _col0 Statistics: Num rows: 212958399 Data size: 18787251785 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/ql/src/test/results/clientpositive/perf/spark/query40.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query40.q.out b/ql/src/test/results/clientpositive/perf/spark/query40.q.out index 5360385..f286294 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query40.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query40.q.out @@ -54,7 +54,8 @@ limit 100 POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-1 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -62,39 +63,44 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 8 + Map 9 Map Operator Tree: TableScan - alias: date_dim - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: warehouse + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-08 23:00:00.0' AND TIMESTAMP'1998-05-08 00:00:00.0' and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + predicate: w_warehouse_sk is not null (type: boolean) + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d_date_sk (type: int), d_date (type: string) + expressions: w_warehouse_sk (type: int), w_state (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work - Map 9 + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 7 Map Operator Tree: TableScan - alias: warehouse - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: w_warehouse_sk is not null (type: boolean) - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN TIMESTAMP'1998-03-08 23:00:00.0' AND TIMESTAMP'1998-05-08 00:00:00.0' and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: w_warehouse_sk (type: int), w_state (type: string) + expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) Local Work: Map Reduce Local Work @@ -103,7 +109,7 @@ STAGE PLANS: Spark Edges: Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 329), Map 6 (PARTITION-LEVEL SORT, 329) - Reducer 3 <- Map 7 (PARTITION-LEVEL SORT, 336), Reducer 2 (PARTITION-LEVEL SORT, 336) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 370), Reducer 2 (PARTITION-LEVEL SORT, 370) Reducer 4 <- Reducer 3 (GROUP, 447) Reducer 5 <- Reducer 4 (SORT, 1) #### A masked pattern was here #### @@ -144,7 +150,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: decimal(7,2)) - Map 7 + Map 8 Map Operator Tree: TableScan alias: item @@ -163,6 +169,8 @@ STAGE PLANS: Statistics: Num rows: 51333 Data size: 73728460 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Reducer 2 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: @@ -172,12 +180,22 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col4, _col7 Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col1 (type: int), _col4 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col4, _col7, _col9 + input vertices: + 1 Map 7 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col4 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string) Reducer 3 Local Work: Map Reduce Local Work @@ -188,45 +206,35 @@ STAGE PLANS: keys: 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col4, _col7, _col9 - Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col1, _col4, _col7, _col9, _col11 + Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col4, _col7, _col9, _col12 + outputColumnNames: _col4, _col7, _col9, _col11, _col14 input vertices: - 1 Map 8 - Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col7, _col9, _col12, _col14 - input vertices: - 1 Map 9 + 1 Map 9 + Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col14 (type: string), _col11 (type: string), CASE WHEN ((CAST( _col9 AS DATE) < DATE'1998-04-08')) THEN ((_col4 - COALESCE(_col7,0))) ELSE (0) END (type: decimal(13,2)), CASE WHEN ((CAST( _col9 AS DATE) >= DATE'1998-04-08')) THEN ((_col4 - COALESCE(_col7,0))) ELSE (0) END (type: decimal(13,2)) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col14 (type: string), _col9 (type: string), CASE WHEN ((CAST( _col12 AS DATE) < DATE'1998-04-08')) THEN ((_col4 - COALESCE(_col7,0))) ELSE (0) END (type: decimal(13,2)), CASE WHEN ((CAST( _col12 AS DATE) >= DATE'1998-04-08')) THEN ((_col4 - COALESCE(_col7,0))) ELSE (0) END (type: decimal(13,2)) + Group By Operator + aggregations: sum(_col2), sum(_col3) + keys: _col0 (type: string), _col1 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3) - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col2 (type: decimal(23,2)), _col3 (type: decimal(23,2)) + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(23,2)), _col3 (type: decimal(23,2)) Reducer 4 Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/244ca8e5/ql/src/test/results/clientpositive/perf/spark/query44.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query44.q.out b/ql/src/test/results/clientpositive/perf/spark/query44.q.out index b432c16..4ca41fb 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query44.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query44.q.out @@ -1,5 +1,5 @@ -Warning: Shuffle Join JOIN[33][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Work 'Reducer 4' is a cross product -Warning: Shuffle Join JOIN[78][tables = [$hdt$_3, $hdt$_4, $hdt$_2]] in Work 'Reducer 17' is a cross product +Warning: Shuffle Join JOIN[36][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Work 'Reducer 8' is a cross product +Warning: Shuffle Join JOIN[81][tables = [$hdt$_4, $hdt$_5, $hdt$_3]] in Work 'Reducer 19' is a cross product PREHOOK: query: explain select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing from(select * @@ -76,43 +76,65 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 20 (GROUP, 100) - Reducer 12 <- Map 11 (GROUP, 199) - Reducer 15 <- Map 1 (GROUP, 100) - Reducer 16 <- Reducer 15 (GROUP, 1) - Reducer 17 <- Reducer 16 (PARTITION-LEVEL SORT, 1), Reducer 21 (PARTITION-LEVEL SORT, 1), Reducer 23 (PARTITION-LEVEL SORT, 1) - Reducer 18 <- Reducer 17 (PARTITION-LEVEL SORT, 1009) - Reducer 19 <- Map 24 (PARTITION-LEVEL SORT, 1009), Reducer 18 (PARTITION-LEVEL SORT, 1009) - Reducer 21 <- Map 20 (GROUP, 100) - Reducer 23 <- Map 11 (GROUP, 199) - Reducer 4 <- Reducer 10 (PARTITION-LEVEL SORT, 1), Reducer 12 (PARTITION-LEVEL SORT, 1), Reducer 16 (PARTITION-LEVEL SORT, 1) - Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 1009) - Reducer 6 <- Map 13 (PARTITION-LEVEL SORT, 1009), Reducer 5 (PARTITION-LEVEL SORT, 1009) - Reducer 7 <- Reducer 19 (PARTITION-LEVEL SORT, 1009), Reducer 6 (PARTITION-LEVEL SORT, 1009) - Reducer 8 <- Reducer 7 (SORT, 1) + Reducer 11 <- Map 10 (GROUP, 100) + Reducer 13 <- Map 12 (GROUP, 199) + Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 1009), Reducer 20 (PARTITION-LEVEL SORT, 1009) + Reducer 17 <- Map 16 (GROUP, 100) + Reducer 18 <- Reducer 17 (GROUP, 1) + Reducer 19 <- Reducer 18 (PARTITION-LEVEL SORT, 1), Reducer 22 (PARTITION-LEVEL SORT, 1), Reducer 24 (PARTITION-LEVEL SORT, 1) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1009), Reducer 9 (PARTITION-LEVEL SORT, 1009) + Reducer 20 <- Reducer 19 (PARTITION-LEVEL SORT, 1009) + Reducer 22 <- Map 10 (GROUP, 100) + Reducer 24 <- Map 12 (GROUP, 199) + Reducer 3 <- Reducer 15 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 8 <- Reducer 11 (PARTITION-LEVEL SORT, 1), Reducer 13 (PARTITION-LEVEL SORT, 1), Reducer 18 (PARTITION-LEVEL SORT, 1) + Reducer 9 <- Reducer 8 (PARTITION-LEVEL SORT, 1009) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan + alias: i1 + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_product_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 10 + Map Operator Tree: + TableScan alias: store_sales Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: ss_net_profit (type: decimal(7,2)) + outputColumnNames: _col1 Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE Group By Operator + aggregations: sum(_col1), count(_col1) keys: 410 (type: int) mode: hash - outputColumnNames: _col0 + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - Map 11 + value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) + Map 12 Map Operator Tree: TableScan alias: ss1 @@ -136,7 +158,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 287997817 Data size: 25407250999 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) - Map 13 + Map 14 Map Operator Tree: TableScan alias: i2 @@ -154,7 +176,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) - Map 20 + Map 16 Map Operator Tree: TableScan alias: store_sales @@ -163,40 +185,18 @@ STAGE PLANS: predicate: ((ss_store_sk = 410) and ss_hdemo_sk is null) (type: boolean) Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_net_profit (type: decimal(7,2)) - outputColumnNames: _col1 Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col1), count(_col1) keys: 410 (type: int) mode: hash - outputColumnNames: _col0, _col1, _col2 + outputColumnNames: _col0 Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint) - Map 24 - Map Operator Tree: - TableScan - alias: i1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: i_item_sk is not null (type: boolean) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: i_item_sk (type: int), i_product_name (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 10 + Reducer 11 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) @@ -212,7 +212,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(37,22)) - Reducer 12 + Reducer 13 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) @@ -230,6 +230,22 @@ STAGE PLANS: value expressions: _col0 (type: int), _col1 (type: decimal(37,22)) Reducer 15 Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 17 + Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: int) mode: mergepartial @@ -246,7 +262,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Reducer 16 + Reducer 18 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -261,7 +277,7 @@ STAGE PLANS: Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reducer 17 + Reducer 19 Reduce Operator Tree: Join Operator condition map: @@ -278,12 +294,28 @@ STAGE PLANS: Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 0 (type: int), _col3 (type: decimal(37,22)) - sort order: ++ + sort order: +- Map-reduce partition columns: 0 (type: int) Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: int) - Reducer 18 + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 20 Reduce Operator Tree: Select Operator expressions: VALUE._col2 (type: int), KEY.reducesinkkey1 (type: decimal(37,22)) @@ -298,7 +330,7 @@ STAGE PLANS: Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col3 ASC NULLS FIRST + order by: _col3 DESC NULLS LAST partition by: 0 raw input shape: window functions: @@ -323,23 +355,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) - Reducer 19 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string) - Reducer 21 + Reducer 22 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) @@ -355,7 +371,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 71999454 Data size: 6351812727 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: decimal(37,22)) - Reducer 23 + Reducer 24 Reduce Operator Tree: Group By Operator aggregations: sum(VALUE._col0), count(VALUE._col1) @@ -371,8 +387,44 @@ STAGE PLANS: sort order: Statistics: Num rows: 143998908 Data size: 12703625455 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: decimal(37,22)) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col3, _col5 + Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: int), _col1 (type: string), _col5 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string), _col2 (type: string) Reducer 4 Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 18500 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 18500 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 8 + Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 @@ -388,12 +440,12 @@ STAGE PLANS: Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: 0 (type: int), _col3 (type: decimal(37,22)) - sort order: +- + sort order: ++ Map-reduce partition columns: 0 (type: int) Statistics: Num rows: 3455947584198744 Data size: 640872925954123264 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: int) - Reducer 5 + Reducer 9 Reduce Operator Tree: Select Operator expressions: VALUE._col2 (type: int), KEY.reducesinkkey1 (type: decimal(37,22)) @@ -408,7 +460,7 @@ STAGE PLANS: Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col3 DESC NULLS LAST + order by: _col3 ASC NULLS FIRST partition by: 0 raw input shape: window functions: @@ -433,58 +485,6 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1151982528066248 Data size: 213624308651374400 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) - Reducer 6 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col3 - Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 1267180808338276 Data size: 234986744609712256 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string) - Reducer 7 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col3, _col5, _col7 - Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col5 (type: int), _col7 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col1 (type: string), _col2 (type: string) - Reducer 8 - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1393898919384048 Data size: 258485424673204064 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 100 - Statistics: Num rows: 100 Data size: 18500 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 100 Data size: 18500 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator