http://git-wip-us.apache.org/repos/asf/hive/blob/0f7163fa/ql/src/test/results/clientpositive/perf/spark/query54.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query54.q.out b/ql/src/test/results/clientpositive/perf/spark/query54.q.out index 241d6d8..a66ad45 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query54.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query54.q.out @@ -1,7 +1,7 @@ -Warning: Shuffle Join JOIN[84][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Work 'Reducer 4' is a cross product -Warning: Shuffle Join JOIN[115][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 5' is a cross product -Warning: Map Join MAPJOIN[145][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[83][tables = [$hdt$_1, $hdt$_2, $hdt$_3, $hdt$_0, $hdt$_4, $hdt$_5, $hdt$_6]] in Work 'Reducer 5' is a cross product +Warning: Shuffle Join JOIN[114][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 6' is a cross product Warning: Map Join MAPJOIN[144][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[143][bigTable=?] in task 'Stage-1:MAPRED' is a cross product PREHOOK: query: explain with my_customers as ( select distinct c_customer_sk @@ -193,11 +193,11 @@ STAGE PLANS: Stage: Stage-3 Spark Edges: - Reducer 23 <- Map 22 (GROUP, 2) - Reducer 24 <- Reducer 23 (GROUP, 1) + Reducer 22 <- Map 21 (GROUP, 2) + Reducer 23 <- Reducer 22 (GROUP, 1) #### A masked pattern was here #### Vertices: - Map 22 + Map 21 Map Operator Tree: TableScan alias: date_dim @@ -221,7 +221,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Reducer 23 + Reducer 22 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -240,7 +240,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Reducer 24 + Reducer 23 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -264,7 +264,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 12 + Map 10 Map Operator Tree: TableScan alias: store @@ -288,45 +288,25 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 654), Reducer 17 (PARTITION-LEVEL SORT, 654) - Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 458), Map 18 (PARTITION-LEVEL SORT, 458), Map 19 (PARTITION-LEVEL SORT, 458) - Reducer 15 <- Map 20 (PARTITION-LEVEL SORT, 505), Reducer 14 (PARTITION-LEVEL SORT, 505) - Reducer 16 <- Map 21 (PARTITION-LEVEL SORT, 1009), Reducer 15 (PARTITION-LEVEL SORT, 1009) - Reducer 17 <- Reducer 16 (GROUP, 610) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 458), Map 16 (PARTITION-LEVEL SORT, 458), Map 17 (PARTITION-LEVEL SORT, 458) + Reducer 13 <- Map 18 (PARTITION-LEVEL SORT, 505), Reducer 12 (PARTITION-LEVEL SORT, 505) + Reducer 14 <- Map 19 (PARTITION-LEVEL SORT, 1009), Reducer 13 (PARTITION-LEVEL SORT, 1009) + Reducer 15 <- Reducer 14 (GROUP, 610) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 654), Reducer 15 (PARTITION-LEVEL SORT, 654) Reducer 26 <- Map 25 (GROUP, 2) - Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 772), Reducer 2 (PARTITION-LEVEL SORT, 772) + Reducer 3 <- Map 20 (PARTITION-LEVEL SORT, 733), Reducer 2 (PARTITION-LEVEL SORT, 733) Reducer 31 <- Map 30 (GROUP, 2) - Reducer 4 <- Reducer 26 (PARTITION-LEVEL SORT, 1), Reducer 3 (PARTITION-LEVEL SORT, 1) - Reducer 5 <- Reducer 31 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1) - Reducer 6 <- Reducer 5 (GROUP, 1009) + Reducer 4 <- Map 24 (PARTITION-LEVEL SORT, 482), Reducer 3 (PARTITION-LEVEL SORT, 482) + Reducer 5 <- Reducer 26 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1) + Reducer 6 <- Reducer 31 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1) Reducer 7 <- Reducer 6 (GROUP, 1009) - Reducer 8 <- Reducer 7 (SORT, 1) + Reducer 8 <- Reducer 7 (GROUP, 1009) + Reducer 9 <- Reducer 8 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: store_sales - filterExpr: (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 - 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 - Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 - 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) - Execution mode: vectorized - Map 10 - Map Operator Tree: - TableScan alias: customer_address filterExpr: (ca_address_sk is not null and ca_county is not null and ca_state is not null) (type: boolean) Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE @@ -345,7 +325,7 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 input vertices: - 1 Map 12 + 1 Map 10 Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) @@ -355,7 +335,7 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 13 + Map 11 Map Operator Tree: TableScan alias: catalog_sales @@ -375,7 +355,7 @@ STAGE PLANS: Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized - Map 18 + Map 16 Map Operator Tree: TableScan alias: web_sales @@ -395,7 +375,7 @@ STAGE PLANS: Statistics: Num rows: 431992504 Data size: 58579807164 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int) Execution mode: vectorized - Map 19 + Map 17 Map Operator Tree: TableScan alias: date_dim @@ -414,7 +394,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 20 + Map 18 Map Operator Tree: TableScan alias: item @@ -433,7 +413,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 21 + Map 19 Map Operator Tree: TableScan alias: customer @@ -453,6 +433,46 @@ STAGE PLANS: Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) Execution mode: vectorized + Map 20 + Map Operator Tree: + TableScan + alias: store_sales + filterExpr: (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 + 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 + Select Operator + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) + Execution mode: vectorized + Map 24 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_month_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) + Execution mode: vectorized Map 25 Map Operator Tree: TableScan @@ -501,42 +521,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 9 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_month_seq (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int) - Execution mode: vectorized - Reducer 11 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col1 (type: int) - outputColumnNames: _col5 - Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col5 (type: int) - sort order: + - Map-reduce partition columns: _col5 (type: int) - Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE - Reducer 14 + Reducer 12 Reduce Operator Tree: Join Operator condition map: @@ -552,7 +537,7 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: int) Statistics: Num rows: 475191764 Data size: 64437789277 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int) - Reducer 15 + Reducer 13 Reduce Operator Tree: Join Operator condition map: @@ -567,7 +552,7 @@ STAGE PLANS: sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 522710951 Data size: 70881569741 Basic stats: COMPLETE Column stats: NONE - Reducer 16 + Reducer 14 Reduce Operator Tree: Join Operator condition map: @@ -587,7 +572,7 @@ STAGE PLANS: sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) Statistics: Num rows: 574982058 Data size: 77969728405 Basic stats: COMPLETE Column stats: NONE - Reducer 17 + Reducer 15 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -612,15 +597,14 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + 1 _col1 (type: int) + outputColumnNames: _col5 + Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int) + key expressions: _col5 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int) + Map-reduce partition columns: _col5 (type: int) + Statistics: Num rows: 316240138 Data size: 42883351551 Basic stats: COMPLETE Column stats: NONE Reducer 26 Execution mode: vectorized Reduce Operator Tree: @@ -641,24 +625,26 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) - 1 _col5 (type: int) - outputColumnNames: _col2, _col4, _col10 - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + 0 _col5 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col5, _col7, _col9 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 1 - outputColumnNames: _col2, _col4, _col10 + outputColumnNames: _col5, _col7, _col9 input vertices: - 1 Reducer 24 - Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE + 1 Reducer 23 + Statistics: Num rows: 633595212 Data size: 61598310416 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 696954748 Data size: 67758142923 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col4 (type: int), _col10 (type: int) + key expressions: _col7 (type: int) + sort order: + + Map-reduce partition columns: _col7 (type: int) + Statistics: Num rows: 633595212 Data size: 61598310416 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: int), _col9 (type: decimal(7,2)) Reducer 31 Execution mode: vectorized Reduce Operator Tree: @@ -672,6 +658,20 @@ STAGE PLANS: Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col7 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col9, _col12 + Statistics: Num rows: 696954748 Data size: 67758142926 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 696954748 Data size: 67758142926 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: int), _col9 (type: decimal(7,2)), _col12 (type: int) + Reducer 5 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -681,12 +681,12 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col2, _col4, _col10, _col13 - Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col5, _col9, _col12, _col13 + Statistics: Num rows: 6363893803988 Data size: 7746260663523866 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col10 (type: int), _col2 (type: decimal(7,2)), _col4 (type: int), _col13 (type: int) + expressions: _col5 (type: int), _col9 (type: decimal(7,2)), _col12 (type: int), _col13 (type: int) outputColumnNames: _col0, _col4, _col11, _col13 - Statistics: Num rows: 6363893803988 Data size: 7746260663496473 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6363893803988 Data size: 7746260663523866 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -696,16 +696,16 @@ STAGE PLANS: outputColumnNames: _col0, _col4, _col11, _col13 input vertices: 1 Reducer 29 - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6363893803988 Data size: 7803535707759758 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col4 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6363893803988 Data size: 7803535707759758 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: - Statistics: Num rows: 6363893803988 Data size: 7803535707732365 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6363893803988 Data size: 7803535707759758 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: decimal(7,2)), _col2 (type: int), _col3 (type: int) - Reducer 5 + Reducer 6 Reduce Operator Tree: Join Operator condition map: @@ -734,7 +734,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 6456523813801603 Data size: 1024819115206086144 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: decimal(17,2)) - Reducer 6 + Reducer 7 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -759,7 +759,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 3228261906900801 Data size: 512409557603043008 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Reducer 7 + Reducer 8 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -778,7 +778,7 @@ STAGE PLANS: Statistics: Num rows: 1614130953450400 Data size: 256204778801521408 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col2 (type: int) - Reducer 8 + Reducer 9 Execution mode: vectorized Reduce Operator Tree: Select Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/0f7163fa/ql/src/test/results/clientpositive/perf/spark/query72.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query72.q.out b/ql/src/test/results/clientpositive/perf/spark/query72.q.out index 37cf704..3292856 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query72.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query72.q.out @@ -69,7 +69,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 7 + Map 9 Map Operator Tree: TableScan alias: warehouse @@ -94,7 +94,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 15 + Map 16 Map Operator Tree: TableScan alias: household_demographics @@ -114,7 +114,7 @@ STAGE PLANS: Execution mode: vectorized Local Work: Map Reduce Local Work - Map 16 + Map 17 Map Operator Tree: TableScan alias: promotion @@ -134,50 +134,57 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 10 <- Map 14 (PARTITION-LEVEL SORT, 338), Reducer 9 (PARTITION-LEVEL SORT, 338) - Reducer 11 <- Map 17 (PARTITION-LEVEL SORT, 452), Reducer 10 (PARTITION-LEVEL SORT, 452) - Reducer 12 <- Map 18 (PARTITION-LEVEL SORT, 492), Reducer 11 (PARTITION-LEVEL SORT, 492) - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 186), Reducer 12 (PARTITION-LEVEL SORT, 186) - Reducer 3 <- Map 19 (PARTITION-LEVEL SORT, 67), Reducer 2 (PARTITION-LEVEL SORT, 67) - Reducer 4 <- Map 20 (PARTITION-LEVEL SORT, 97), Reducer 3 (PARTITION-LEVEL SORT, 97) - Reducer 5 <- Reducer 4 (GROUP, 80) - Reducer 6 <- Reducer 5 (SORT, 1) - Reducer 9 <- Map 13 (PARTITION-LEVEL SORT, 306), Map 8 (PARTITION-LEVEL SORT, 306) + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 306), Map 14 (PARTITION-LEVEL SORT, 306) + Reducer 12 <- Map 15 (PARTITION-LEVEL SORT, 338), Reducer 11 (PARTITION-LEVEL SORT, 338) + Reducer 13 <- Map 18 (PARTITION-LEVEL SORT, 452), Reducer 12 (PARTITION-LEVEL SORT, 452) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 97), Reducer 8 (PARTITION-LEVEL SORT, 97) + Reducer 3 <- Reducer 2 (GROUP, 80) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 496), Reducer 13 (PARTITION-LEVEL SORT, 496) + Reducer 7 <- Map 19 (PARTITION-LEVEL SORT, 181), Reducer 6 (PARTITION-LEVEL SORT, 181) + Reducer 8 <- Map 20 (PARTITION-LEVEL SORT, 199), Reducer 7 (PARTITION-LEVEL SORT, 199) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: inventory - filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + alias: catalog_returns + filterExpr: cr_item_sk is not null (type: boolean) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + predicate: cr_item_sk is not null (type: boolean) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col5 - input vertices: - 1 Map 7 - Statistics: Num rows: 41342400 Data size: 653203228 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: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int), _col3 (type: int), _col5 (type: string) + expressions: cr_item_sk (type: int), cr_order_number (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Local Work: - Map Reduce Local Work - Map 13 + Map 10 + Map Operator Tree: + TableScan + alias: catalog_sales + filterExpr: (cs_item_sk is not null and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_sold_date_sk is not null and cs_ship_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_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: cs_sold_date_sk (type: int), cs_ship_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_bill_hdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_quantity (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int) + Execution mode: vectorized + Map 14 Map Operator Tree: TableScan alias: d1 @@ -197,7 +204,7 @@ STAGE PLANS: Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: int) Execution mode: vectorized - Map 14 + Map 15 Map Operator Tree: TableScan alias: customer_demographics @@ -216,7 +223,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 17 + Map 18 Map Operator Tree: TableScan alias: item @@ -236,26 +243,6 @@ STAGE PLANS: Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string) Execution mode: vectorized - Map 18 - Map Operator Tree: - TableScan - alias: d3 - filterExpr: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: d_date_sk is not null (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int), d_date (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized Map 19 Map Operator Tree: TableScan @@ -278,43 +265,72 @@ STAGE PLANS: Map 20 Map Operator Tree: TableScan - alias: catalog_returns - filterExpr: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + alias: d3 + filterExpr: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: cr_item_sk is not null (type: boolean) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + predicate: d_date_sk is not null (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cr_item_sk (type: int), cr_order_number (type: int) + expressions: d_date_sk (type: int), d_date (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) Execution mode: vectorized - Map 8 + Map 5 Map Operator Tree: TableScan - alias: catalog_sales - filterExpr: (cs_item_sk is not null and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_sold_date_sk is not null and cs_ship_date_sk is not null) (type: boolean) - Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + alias: inventory + filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean) + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_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: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cs_sold_date_sk (type: int), cs_ship_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_bill_hdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_quantity (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 - 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int) + expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3, _col5 + input vertices: + 1 Map 9 + Statistics: Num rows: 41342400 Data size: 653203228 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: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col3 (type: int), _col5 (type: string) Execution mode: vectorized - Reducer 10 + Local Work: + Map Reduce Local Work + Reducer 11 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10 + 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: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int) + Reducer 12 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -334,7 +350,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col9, _col10 input vertices: - 1 Map 15 + 1 Map 16 Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -344,7 +360,7 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col16 input vertices: - 1 Map 16 + 1 Map 17 Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col4 (type: int) @@ -352,7 +368,7 @@ STAGE PLANS: Map-reduce partition columns: _col4 (type: int) Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int) - Reducer 11 + Reducer 13 Reduce Operator Tree: Join Operator condition map: @@ -362,101 +378,43 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col16, _col18 Statistics: Num rows: 463810558 Data size: 62809267017 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: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE - value expressions: _col4 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int), _col18 (type: string) - Reducer 12 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col16, _col18, _col20 - Statistics: Num rows: 510191624 Data size: 69090195216 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0D)) (type: boolean) - Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col18 (type: string), _col4 (type: int), _col6 (type: int), _col7 (type: int), _col10 (type: int), _col16 (type: int) - outputColumnNames: _col3, _col8, _col10, _col11, _col14, _col20 - Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col8 (type: int) - sort order: + - Map-reduce partition columns: _col8 (type: int) - Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string), _col10 (type: int), _col11 (type: int), _col14 (type: int), _col20 (type: int) - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: int) - 1 _col8 (type: int) - outputColumnNames: _col0, _col3, _col5, _col9, _col14, _col16, _col17, _col20, _col26 - Statistics: Num rows: 187070265 Data size: 25333072028 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col3 < _col17) (type: boolean) - Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int), _col20 (type: int) - sort order: ++ - Map-reduce partition columns: _col0 (type: int), _col20 (type: int) - Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE - value expressions: _col5 (type: string), _col9 (type: string), _col14 (type: int), _col16 (type: int), _col26 (type: int) - Reducer 3 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int), _col20 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col5, _col9, _col14, _col16, _col20, _col26 - Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col14 (type: int), _col16 (type: int), _col5 (type: string), _col9 (type: string), _col20 (type: int), _col26 (type: int) - outputColumnNames: _col4, _col6, _col13, _col15, _col22, _col28 - Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE + expressions: _col18 (type: string), _col1 (type: int), _col4 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int) + outputColumnNames: _col1, _col3, _col6, _col8, _col9, _col11, _col12, _col18 + Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col4 (type: int), _col6 (type: int) - sort order: ++ - Map-reduce partition columns: _col4 (type: int), _col6 (type: int) - Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE - value expressions: _col13 (type: string), _col15 (type: string), _col22 (type: int), _col28 (type: int) - Reducer 4 + key expressions: _col6 (type: int) + sort order: + + Map-reduce partition columns: _col6 (type: int) + Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col3 (type: int), _col8 (type: int), _col9 (type: int), _col11 (type: string), _col12 (type: int), _col18 (type: int) + Reducer 2 Reduce Operator Tree: Join Operator condition map: - Left Outer Join 0 to 1 + Right Outer Join 0 to 1 keys: - 0 _col4 (type: int), _col6 (type: int) - 1 _col0 (type: int), _col1 (type: int) - outputColumnNames: _col13, _col15, _col22, _col28 - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: int), _col1 (type: int) + 1 _col4 (type: int), _col6 (type: int) + outputColumnNames: _col15, _col17, _col24, _col30 + Statistics: Num rows: 75451675 Data size: 10217672727 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col15 (type: string), _col13 (type: string), _col22 (type: int), CASE WHEN (_col28 is null) THEN (1) ELSE (0) END (type: int), CASE WHEN (_col28 is not null) THEN (1) ELSE (0) END (type: int) + expressions: _col17 (type: string), _col15 (type: string), _col24 (type: int), CASE WHEN (_col30 is null) THEN (1) ELSE (0) END (type: int), CASE WHEN (_col30 is not null) THEN (1) ELSE (0) END (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75451675 Data size: 10217672727 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(_col3), count(_col4), count() keys: _col0 (type: string), _col1 (type: string), _col2 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75451675 Data size: 10217672727 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: +++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 75451675 Data size: 10217672727 Basic stats: COMPLETE Column stats: NONE value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint) - Reducer 5 + Reducer 3 Execution mode: vectorized Reduce Operator Tree: Group By Operator @@ -464,20 +422,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37725837 Data size: 5108836295 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col5 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int) sort order: -+++ - Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37725837 Data size: 5108836295 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 value expressions: _col3 (type: bigint), _col4 (type: bigint) - Reducer 6 + Reducer 4 Execution mode: vectorized Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 37725837 Data size: 5108836295 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE @@ -488,22 +446,64 @@ STAGE PLANS: 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 9 + 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, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10 - Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + 0 _col1 (type: int) + 1 _col6 (type: int) + outputColumnNames: _col0, _col3, _col5, _col7, _col9, _col12, _col14, _col15, _col17, _col18, _col24 + Statistics: Num rows: 510191624 Data size: 69090195216 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col3 < _col15) (type: boolean) + Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col18 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col18 (type: int) + Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: string), _col7 (type: string), _col9 (type: int), _col12 (type: int), _col14 (type: int), _col17 (type: string), _col24 (type: int) + Reducer 7 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col18 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col5, _col7, _col9, _col12, _col14, _col17, _col18, _col24 + Statistics: Num rows: 187070265 Data size: 25333072028 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: int) + key expressions: _col9 (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: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int) + Map-reduce partition columns: _col9 (type: int) + Statistics: Num rows: 187070265 Data size: 25333072028 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: string), _col7 (type: string), _col12 (type: int), _col14 (type: int), _col17 (type: string), _col18 (type: int), _col24 (type: int) + Reducer 8 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col9 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col5, _col7, _col12, _col14, _col17, _col18, _col24, _col28 + Statistics: Num rows: 205777295 Data size: 27866379834 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(_col28) > (UDFToDouble(_col17) + 5.0D)) (type: boolean) + Statistics: Num rows: 68592431 Data size: 9288793187 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col12 (type: int), _col14 (type: int), _col5 (type: string), _col7 (type: string), _col18 (type: int), _col24 (type: int) + outputColumnNames: _col4, _col6, _col13, _col15, _col22, _col28 + Statistics: Num rows: 68592431 Data size: 9288793187 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col4 (type: int), _col6 (type: int) + sort order: ++ + Map-reduce partition columns: _col4 (type: int), _col6 (type: int) + Statistics: Num rows: 68592431 Data size: 9288793187 Basic stats: COMPLETE Column stats: NONE + value expressions: _col13 (type: string), _col15 (type: string), _col22 (type: int), _col28 (type: int) Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/0f7163fa/ql/src/test/results/clientpositive/perf/spark/query85.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query85.q.out b/ql/src/test/results/clientpositive/perf/spark/query85.q.out index af4a835..f5df424 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query85.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query85.q.out @@ -174,7 +174,7 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: - Map 14 + Map 11 Map Operator Tree: TableScan alias: web_page @@ -189,12 +189,12 @@ STAGE PLANS: Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col2 (type: int) + 0 _col10 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work - Map 15 + Map 12 Map Operator Tree: TableScan alias: reason @@ -209,7 +209,7 @@ STAGE PLANS: Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col13 (type: int) + 0 _col4 (type: int) 1 _col0 (type: int) Execution mode: vectorized Local Work: @@ -218,38 +218,18 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 52), Map 9 (PARTITION-LEVEL SORT, 52) - Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 67), Reducer 2 (PARTITION-LEVEL SORT, 67) - Reducer 4 <- Map 11 (PARTITION-LEVEL SORT, 68), Reducer 3 (PARTITION-LEVEL SORT, 68) - Reducer 5 <- Map 12 (PARTITION-LEVEL SORT, 12), Reducer 4 (PARTITION-LEVEL SORT, 12) - Reducer 6 <- Map 13 (PARTITION-LEVEL SORT, 165), Reducer 5 (PARTITION-LEVEL SORT, 165) - Reducer 7 <- Reducer 6 (GROUP, 71) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 62), Map 9 (PARTITION-LEVEL SORT, 62) + Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 57), Reducer 2 (PARTITION-LEVEL SORT, 57) + Reducer 4 <- Map 13 (PARTITION-LEVEL SORT, 81), Reducer 3 (PARTITION-LEVEL SORT, 81) + Reducer 5 <- Map 14 (PARTITION-LEVEL SORT, 13), Reducer 4 (PARTITION-LEVEL SORT, 13) + Reducer 6 <- Map 15 (PARTITION-LEVEL SORT, 167), Reducer 5 (PARTITION-LEVEL SORT, 167) + Reducer 7 <- Reducer 6 (GROUP, 59) Reducer 8 <- Reducer 7 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: web_sales - filterExpr: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_web_page_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 - Filter Operator - predicate: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) - Statistics: Num rows: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_page_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 48000888 Data size: 6526732556 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: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) - Execution mode: vectorized - Map 10 - Map Operator Tree: - TableScan alias: web_returns filterExpr: (wr_item_sk is not null and wr_order_number is not null and wr_refunded_cdemo_sk is not null and wr_returning_cdemo_sk is not null and wr_refunded_addr_sk is not null and wr_reason_sk is not null) (type: boolean) Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE @@ -267,7 +247,26 @@ STAGE PLANS: Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) Execution mode: vectorized - Map 11 + Map 10 + Map Operator Tree: + TableScan + alias: date_dim + filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year = 1998) 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) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 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: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Execution mode: vectorized + Map 13 Map Operator Tree: TableScan alias: cd1 @@ -287,7 +286,7 @@ STAGE PLANS: Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized - Map 12 + Map 14 Map Operator Tree: TableScan alias: cd2 @@ -306,7 +305,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: string) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Map 13 + Map 15 Map Operator Tree: TableScan alias: customer_address @@ -329,21 +328,22 @@ STAGE PLANS: Map 9 Map Operator Tree: TableScan - alias: date_dim - filterExpr: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + alias: web_sales + filterExpr: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_web_page_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 Filter Operator - predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + predicate: ((ws_sales_price BETWEEN 100 AND 150 or ws_sales_price BETWEEN 50 AND 100 or ws_sales_price BETWEEN 150 AND 200) and ws_item_sk is not null and ws_order_number is not null and ws_sold_date_sk is not null and ws_web_page_sk is not null) (type: boolean) + Statistics: Num rows: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_web_page_sk (type: int), ws_order_number (type: int), ws_quantity (type: int), ws_sales_price (type: decimal(7,2)), ws_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 48000888 Data size: 6526732556 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: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + key expressions: _col1 (type: int), _col3 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col3 (type: int) + Statistics: Num rows: 48000888 Data size: 6526732556 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -351,114 +351,118 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6 + 0 _col0 (type: int), _col5 (type: int) + 1 _col1 (type: int), _col3 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col10, _col12, _col13, _col14 Statistics: Num rows: 52800977 Data size: 7179405967 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: int), _col3 (type: int) - sort order: ++ - Map-reduce partition columns: _col1 (type: int), _col3 (type: int) + key expressions: _col8 (type: int) + sort order: + + Map-reduce partition columns: _col8 (type: int) Statistics: Num rows: 52800977 Data size: 7179405967 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col10 (type: int), _col12 (type: int), _col13 (type: decimal(7,2)), _col14 (type: decimal(7,2)) Reducer 3 + Local Work: + Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int), _col3 (type: int) - 1 _col0 (type: int), _col5 (type: int) - outputColumnNames: _col2, _col4, _col5, _col6, _col10, _col11, _col12, _col13, _col15, _col16 + 0 _col8 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col10, _col12, _col13, _col14 Statistics: Num rows: 58081075 Data size: 7897346734 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col10 (type: int) - sort order: + - Map-reduce partition columns: _col10 (type: int) - Statistics: Num rows: 58081075 Data size: 7897346734 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col11 (type: int), _col12 (type: int), _col13 (type: int), _col15 (type: decimal(7,2)), _col16 (type: decimal(7,2)) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col10 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col12, _col13, _col14 + input vertices: + 1 Map 11 + Statistics: Num rows: 63889183 Data size: 8687081595 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col6, _col7, _col12, _col13, _col14, _col19 + input vertices: + 1 Map 12 + Statistics: Num rows: 70278102 Data size: 9555789961 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: 70278102 Data size: 9555789961 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col13 (type: decimal(7,2)), _col14 (type: decimal(7,2)), _col19 (type: string) Reducer 4 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col10 (type: int) + 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col5, _col6, _col11, _col12, _col13, _col15, _col16, _col18, _col19 - Statistics: Num rows: 63889183 Data size: 8687081595 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col3, _col6, _col7, _col12, _col13, _col14, _col19, _col21, _col22 + Statistics: Num rows: 77305913 Data size: 10511369184 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col18 = 'D') and (_col19 = 'Primary') and _col5 BETWEEN 50 AND 100) or ((_col18 = 'M') and (_col19 = '4 yr Degree') and _col5 BETWEEN 100 AND 150) or ((_col18 = 'U') and (_col19 = 'Advanced Degree') and _col5 BETWEEN 150 AND 200)) (type: boolean) - Statistics: Num rows: 5324097 Data size: 723923250 Basic stats: COMPLETE Column stats: NONE + predicate: (((_col21 = 'D') and (_col22 = 'Primary') and _col13 BETWEEN 50 AND 100) or ((_col21 = 'M') and (_col22 = '4 yr Degree') and _col13 BETWEEN 100 AND 150) or ((_col21 = 'U') and (_col22 = 'Advanced Degree') and _col13 BETWEEN 150 AND 200)) (type: boolean) + Statistics: Num rows: 6442158 Data size: 875947239 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col12 (type: int), _col18 (type: string), _col19 (type: string) + key expressions: _col3 (type: int), _col21 (type: string), _col22 (type: string) sort order: +++ - Map-reduce partition columns: _col12 (type: int), _col18 (type: string), _col19 (type: string) - Statistics: Num rows: 5324097 Data size: 723923250 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col11 (type: int), _col13 (type: int), _col15 (type: decimal(7,2)), _col16 (type: decimal(7,2)) + Map-reduce partition columns: _col3 (type: int), _col21 (type: string), _col22 (type: string) + Statistics: Num rows: 6442158 Data size: 875947239 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col14 (type: decimal(7,2)), _col19 (type: string) Reducer 5 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col12 (type: int), _col18 (type: string), _col19 (type: string) + 0 _col3 (type: int), _col21 (type: string), _col22 (type: string) 1 _col0 (type: int), _col1 (type: string), _col2 (type: string) - outputColumnNames: _col2, _col4, _col6, _col11, _col13, _col15, _col16 - Statistics: Num rows: 5856506 Data size: 796315592 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col6, _col7, _col12, _col14, _col19 + Statistics: Num rows: 7086373 Data size: 963541983 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col11 (type: int) + key expressions: _col2 (type: int) sort order: + - Map-reduce partition columns: _col11 (type: int) - Statistics: Num rows: 5856506 Data size: 796315592 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)), _col13 (type: int), _col15 (type: decimal(7,2)), _col16 (type: decimal(7,2)) + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 7086373 Data size: 963541983 Basic stats: COMPLETE Column stats: NONE + value expressions: _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col14 (type: decimal(7,2)), _col19 (type: string) Reducer 6 - Local Work: - Map Reduce Local Work Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col11 (type: int) + 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col6, _col13, _col15, _col16, _col24 + outputColumnNames: _col6, _col7, _col12, _col14, _col19, _col27 Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((_col24 = 'KY') or (_col24 = 'GA') or (_col24 = 'NM')) and _col6 BETWEEN 100 AND 200) or (((_col24 = 'MT') or (_col24 = 'OR') or (_col24 = 'IN')) and _col6 BETWEEN 150 AND 300) or (((_col24 = 'WI') or (_col24 = 'MO') or (_col24 = 'WV')) and _col6 BETWEEN 50 AND 250)) (type: boolean) + predicate: ((((_col27 = 'KY') or (_col27 = 'GA') or (_col27 = 'NM')) and _col14 BETWEEN 100 AND 200) or (((_col27 = 'MT') or (_col27 = 'OR') or (_col27 = 'IN')) and _col14 BETWEEN 150 AND 300) or (((_col27 = 'WI') or (_col27 = 'MO') or (_col27 = 'WV')) and _col14 BETWEEN 50 AND 250)) (type: boolean) Statistics: Num rows: 7333332 Data size: 7442451276 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col2 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col13, _col15, _col16 - input vertices: - 1 Map 14 - Statistics: Num rows: 8066665 Data size: 8186696581 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col13 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col4, _col15, _col16, _col28 - input vertices: - 1 Map 15 - Statistics: Num rows: 8873331 Data size: 9005366434 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col4), count(_col4), sum(_col16), count(_col16), sum(_col15), count(_col15) - keys: _col28 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 8873331 Data size: 9005366434 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: 8873331 Data size: 9005366434 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint) + Select Operator + expressions: _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col12 (type: int), _col19 (type: string) + outputColumnNames: _col6, _col7, _col12, _col19 + Statistics: Num rows: 7333332 Data size: 7442451276 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col12), count(_col12), sum(_col7), count(_col7), sum(_col6), count(_col6) + keys: _col19 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 7333332 Data size: 7442451276 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: 7333332 Data size: 7442451276 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint) Reducer 7 Execution mode: vectorized Reduce Operator Tree: @@ -467,15 +471,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3666666 Data size: 3721225638 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: (UDFToDouble(_col1) / _col2) (type: double), (_col3 / _col4) (type: decimal(37,22)), (_col5 / _col6) (type: decimal(37,22)), substr(_col0, 1, 20) (type: string) outputColumnNames: _col4, _col5, _col6, _col7 - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3666666 Data size: 3721225638 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col7 (type: string), _col4 (type: double), _col5 (type: decimal(37,22)), _col6 (type: decimal(37,22)) sort order: ++++ - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3666666 Data size: 3721225638 Basic stats: COMPLETE Column stats: NONE TopN Hash Memory Usage: 0.1 Reducer 8 Execution mode: vectorized @@ -483,7 +487,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: double), KEY.reducesinkkey2 (type: decimal(37,22)), KEY.reducesinkkey3 (type: decimal(37,22)) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 4436665 Data size: 4502682709 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3666666 Data size: 3721225638 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 100 Statistics: Num rows: 100 Data size: 101400 Basic stats: COMPLETE Column stats: NONE
