http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query58.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query58.q.out b/ql/src/test/results/clientpositive/perf/spark/query58.q.out new file mode 100644 index 0000000..f06cbef --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query58.q.out @@ -0,0 +1,944 @@ +Warning: Map Join MAPJOIN[183][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[184][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +Warning: Map Join MAPJOIN[185][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +PREHOOK: query: explain +with ss_items as + (select i_item_id item_id + ,sum(ss_ext_sales_price) ss_item_rev + from store_sales + ,item + ,date_dim + where ss_item_sk = i_item_sk + and d_date in (select d_date + from date_dim + where d_week_seq = (select d_week_seq + from date_dim + where d_date = '1998-02-19')) + and ss_sold_date_sk = d_date_sk + group by i_item_id), + cs_items as + (select i_item_id item_id + ,sum(cs_ext_sales_price) cs_item_rev + from catalog_sales + ,item + ,date_dim + where cs_item_sk = i_item_sk + and d_date in (select d_date + from date_dim + where d_week_seq = (select d_week_seq + from date_dim + where d_date = '1998-02-19')) + and cs_sold_date_sk = d_date_sk + group by i_item_id), + ws_items as + (select i_item_id item_id + ,sum(ws_ext_sales_price) ws_item_rev + from web_sales + ,item + ,date_dim + where ws_item_sk = i_item_sk + and d_date in (select d_date + from date_dim + where d_week_seq =(select d_week_seq + from date_dim + where d_date = '1998-02-19')) + and ws_sold_date_sk = d_date_sk + group by i_item_id) + select ss_items.item_id + ,ss_item_rev + ,ss_item_rev/(ss_item_rev+cs_item_rev+ws_item_rev)/3 * 100 ss_dev + ,cs_item_rev + ,cs_item_rev/(ss_item_rev+cs_item_rev+ws_item_rev)/3 * 100 cs_dev + ,ws_item_rev + ,ws_item_rev/(ss_item_rev+cs_item_rev+ws_item_rev)/3 * 100 ws_dev + ,(ss_item_rev+cs_item_rev+ws_item_rev)/3 average + from ss_items,cs_items,ws_items + where ss_items.item_id=cs_items.item_id + and ss_items.item_id=ws_items.item_id + and ss_item_rev between 0.9 * cs_item_rev and 1.1 * cs_item_rev + and ss_item_rev between 0.9 * ws_item_rev and 1.1 * ws_item_rev + and cs_item_rev between 0.9 * ss_item_rev and 1.1 * ss_item_rev + and cs_item_rev between 0.9 * ws_item_rev and 1.1 * ws_item_rev + and ws_item_rev between 0.9 * ss_item_rev and 1.1 * ss_item_rev + and ws_item_rev between 0.9 * cs_item_rev and 1.1 * cs_item_rev + order by item_id + ,ss_item_rev + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with ss_items as + (select i_item_id item_id + ,sum(ss_ext_sales_price) ss_item_rev + from store_sales + ,item + ,date_dim + where ss_item_sk = i_item_sk + and d_date in (select d_date + from date_dim + where d_week_seq = (select d_week_seq + from date_dim + where d_date = '1998-02-19')) + and ss_sold_date_sk = d_date_sk + group by i_item_id), + cs_items as + (select i_item_id item_id + ,sum(cs_ext_sales_price) cs_item_rev + from catalog_sales + ,item + ,date_dim + where cs_item_sk = i_item_sk + and d_date in (select d_date + from date_dim + where d_week_seq = (select d_week_seq + from date_dim + where d_date = '1998-02-19')) + and cs_sold_date_sk = d_date_sk + group by i_item_id), + ws_items as + (select i_item_id item_id + ,sum(ws_ext_sales_price) ws_item_rev + from web_sales + ,item + ,date_dim + where ws_item_sk = i_item_sk + and d_date in (select d_date + from date_dim + where d_week_seq =(select d_week_seq + from date_dim + where d_date = '1998-02-19')) + and ws_sold_date_sk = d_date_sk + group by i_item_id) + select ss_items.item_id + ,ss_item_rev + ,ss_item_rev/(ss_item_rev+cs_item_rev+ws_item_rev)/3 * 100 ss_dev + ,cs_item_rev + ,cs_item_rev/(ss_item_rev+cs_item_rev+ws_item_rev)/3 * 100 cs_dev + ,ws_item_rev + ,ws_item_rev/(ss_item_rev+cs_item_rev+ws_item_rev)/3 * 100 ws_dev + ,(ss_item_rev+cs_item_rev+ws_item_rev)/3 average + from ss_items,cs_items,ws_items + where ss_items.item_id=cs_items.item_id + and ss_items.item_id=ws_items.item_id + and ss_item_rev between 0.9 * cs_item_rev and 1.1 * cs_item_rev + and ss_item_rev between 0.9 * ws_item_rev and 1.1 * ws_item_rev + and cs_item_rev between 0.9 * ss_item_rev and 1.1 * ss_item_rev + and cs_item_rev between 0.9 * ws_item_rev and 1.1 * ws_item_rev + and ws_item_rev between 0.9 * ss_item_rev and 1.1 * ss_item_rev + and ws_item_rev between 0.9 * cs_item_rev and 1.1 * cs_item_rev + order by item_id + ,ss_item_rev + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark + Edges: + Reducer 11 <- Map 10 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 10 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 11 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-3 + Spark + Edges: + Reducer 24 <- Map 23 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 23 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 24 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-4 + Spark + Edges: + Reducer 37 <- Map 36 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 36 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date = '1998-02-19') (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Reducer 37 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 2), Map 15 (PARTITION-LEVEL SORT, 2) + Reducer 14 <- Reducer 13 (GROUP, 2) + Reducer 17 <- Map 16 (PARTITION-LEVEL SORT, 403), Map 20 (PARTITION-LEVEL SORT, 403) + Reducer 18 <- Reducer 17 (PARTITION-LEVEL SORT, 438), Reducer 22 (PARTITION-LEVEL SORT, 438) + Reducer 19 <- Reducer 18 (GROUP, 481) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 310), Map 7 (PARTITION-LEVEL SORT, 310) + Reducer 22 <- Map 21 (PARTITION-LEVEL SORT, 2), Reducer 27 (PARTITION-LEVEL SORT, 2) + Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 2), Map 28 (PARTITION-LEVEL SORT, 2) + Reducer 27 <- Reducer 26 (GROUP, 2) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 336), Reducer 9 (PARTITION-LEVEL SORT, 336) + Reducer 30 <- Map 29 (PARTITION-LEVEL SORT, 159), Map 33 (PARTITION-LEVEL SORT, 159) + Reducer 31 <- Reducer 30 (PARTITION-LEVEL SORT, 169), Reducer 35 (PARTITION-LEVEL SORT, 169) + Reducer 32 <- Reducer 31 (GROUP, 186) + Reducer 35 <- Map 34 (PARTITION-LEVEL SORT, 2), Reducer 40 (PARTITION-LEVEL SORT, 2) + Reducer 39 <- Map 38 (PARTITION-LEVEL SORT, 2), Map 41 (PARTITION-LEVEL SORT, 2) + Reducer 4 <- Reducer 3 (GROUP, 369) + Reducer 40 <- Reducer 39 (GROUP, 2) + Reducer 5 <- Reducer 19 (PARTITION-LEVEL SORT, 518), Reducer 32 (PARTITION-LEVEL SORT, 518), Reducer 4 (PARTITION-LEVEL SORT, 518) + Reducer 6 <- Reducer 5 (SORT, 1) + Reducer 9 <- Map 8 (PARTITION-LEVEL SORT, 2), Reducer 14 (PARTITION-LEVEL SORT, 2) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_item_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_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 287989836 Data size: 38999608952 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) + Map 12 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + input vertices: + 0 Reducer 11 + Statistics: Num rows: 36524 Data size: 41199072 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: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Map 15 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Map 16 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_item_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_item_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)) + Map 20 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_id is not null and 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_item_id (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 21 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date is not null and 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: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 25 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + input vertices: + 0 Reducer 24 + Statistics: Num rows: 36524 Data size: 41199072 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: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Map 28 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Map 29 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ws_item_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: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: decimal(7,2)) + Map 33 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_id is not null and 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_item_id (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 34 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date is not null and 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: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 38 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_date = '1998-02-19') and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1 + input vertices: + 0 Reducer 37 + Statistics: Num rows: 36524 Data size: 41199072 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: 36524 Data size: 41199072 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Map 41 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date is not null and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date (type: string), d_week_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + Map 7 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_id is not null and 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_item_id (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 8 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date is not null and 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: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Reducer 13 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2 + Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Reducer 14 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 40176 Data size: 44957448 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: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE + Reducer 17 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: string) + Reducer 18 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 696954748 Data size: 61485550191 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: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 19 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + 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: decimal(17,2)) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 316788826 Data size: 42899570777 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: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: string) + Reducer 22 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Reducer 26 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2 + Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Reducer 27 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 40176 Data size: 44957448 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: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 348467716 Data size: 47189528877 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: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 30 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col4 + Statistics: Num rows: 158402938 Data size: 21538218500 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col4 (type: string) + Reducer 31 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col4 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 174243235 Data size: 23692040863 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: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 32 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + 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(17,2)) + Reducer 35 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Reducer 39 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2 + Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col2 (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + 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(17,2)) + Reducer 40 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 40176 Data size: 44957448 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: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE + Reducer 5 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 + Statistics: Num rows: 766650239 Data size: 67634106674 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 BETWEEN (0.9 * _col3) AND (1.1 * _col3) and _col1 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col3 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col3 BETWEEN (0.9 * _col5) AND (1.1 * _col5) and _col5 BETWEEN (0.9 * _col1) AND (1.1 * _col1) and _col5 BETWEEN (0.9 * _col3) AND (1.1 * _col3)) (type: boolean) + Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col3 (type: decimal(17,2)), (((_col3 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), _col1 (type: decimal(17,2)), (((_col1 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), _col5 (type: decimal(17,2)), (((_col5 / ((_col3 + _col1) + _col5)) / 3) * 100) (type: decimal(38,17)), (((_col3 + _col1) + _col5) / 3) (type: decimal(23,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: decimal(17,2)) + sort order: ++ + Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col2 (type: decimal(38,17)), _col3 (type: decimal(17,2)), _col4 (type: decimal(38,17)), _col5 (type: decimal(17,2)), _col6 (type: decimal(38,17)), _col7 (type: decimal(23,6)) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(17,2)), VALUE._col0 (type: decimal(38,17)), VALUE._col1 (type: decimal(17,2)), VALUE._col2 (type: decimal(38,17)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(38,17)), VALUE._col5 (type: decimal(23,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1442 Data size: 127213 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 8800 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 9 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-0 + Fetch Operator + limit: 100 + Processor Tree: + ListSink +
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query59.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query59.q.out b/ql/src/test/results/clientpositive/perf/spark/query59.q.out new file mode 100644 index 0000000..c2fe4f7 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query59.q.out @@ -0,0 +1,445 @@ +PREHOOK: query: explain +with wss as + (select d_week_seq, + ss_store_sk, + sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, + sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, + sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, + sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, + sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, + sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, + sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales + from store_sales,date_dim + where d_date_sk = ss_sold_date_sk + group by d_week_seq,ss_store_sk + ) + select s_store_name1,s_store_id1,d_week_seq1 + ,sun_sales1/sun_sales2,mon_sales1/mon_sales2 + ,tue_sales1/tue_sales1,wed_sales1/wed_sales2,thu_sales1/thu_sales2 + ,fri_sales1/fri_sales2,sat_sales1/sat_sales2 + from + (select s_store_name s_store_name1,wss.d_week_seq d_week_seq1 + ,s_store_id s_store_id1,sun_sales sun_sales1 + ,mon_sales mon_sales1,tue_sales tue_sales1 + ,wed_sales wed_sales1,thu_sales thu_sales1 + ,fri_sales fri_sales1,sat_sales sat_sales1 + from wss,store,date_dim d + where d.d_week_seq = wss.d_week_seq and + ss_store_sk = s_store_sk and + d_month_seq between 1185 and 1185 + 11) y, + (select s_store_name s_store_name2,wss.d_week_seq d_week_seq2 + ,s_store_id s_store_id2,sun_sales sun_sales2 + ,mon_sales mon_sales2,tue_sales tue_sales2 + ,wed_sales wed_sales2,thu_sales thu_sales2 + ,fri_sales fri_sales2,sat_sales sat_sales2 + from wss,store,date_dim d + where d.d_week_seq = wss.d_week_seq and + ss_store_sk = s_store_sk and + d_month_seq between 1185+ 12 and 1185 + 23) x + where s_store_id1=s_store_id2 + and d_week_seq1=d_week_seq2-52 + order by s_store_name1,s_store_id1,d_week_seq1 +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with wss as + (select d_week_seq, + ss_store_sk, + sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, + sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, + sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, + sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, + sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, + sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, + sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales + from store_sales,date_dim + where d_date_sk = ss_sold_date_sk + group by d_week_seq,ss_store_sk + ) + select s_store_name1,s_store_id1,d_week_seq1 + ,sun_sales1/sun_sales2,mon_sales1/mon_sales2 + ,tue_sales1/tue_sales1,wed_sales1/wed_sales2,thu_sales1/thu_sales2 + ,fri_sales1/fri_sales2,sat_sales1/sat_sales2 + from + (select s_store_name s_store_name1,wss.d_week_seq d_week_seq1 + ,s_store_id s_store_id1,sun_sales sun_sales1 + ,mon_sales mon_sales1,tue_sales tue_sales1 + ,wed_sales wed_sales1,thu_sales thu_sales1 + ,fri_sales fri_sales1,sat_sales sat_sales1 + from wss,store,date_dim d + where d.d_week_seq = wss.d_week_seq and + ss_store_sk = s_store_sk and + d_month_seq between 1185 and 1185 + 11) y, + (select s_store_name s_store_name2,wss.d_week_seq d_week_seq2 + ,s_store_id s_store_id2,sun_sales sun_sales2 + ,mon_sales mon_sales2,tue_sales tue_sales2 + ,wed_sales wed_sales2,thu_sales thu_sales2 + ,fri_sales fri_sales2,sat_sales sat_sales2 + from wss,store,date_dim d + where d.d_week_seq = wss.d_week_seq and + ss_store_sk = s_store_sk and + d_month_seq between 1185+ 12 and 1185 + 23) x + where s_store_id1=s_store_id2 + and d_week_seq1=d_week_seq2-52 + order by s_store_name1,s_store_id1,d_week_seq1 +limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s_store_id is not null and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int), s_store_id (type: string), s_store_name (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s_store_id is not null and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int), s_store_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 398), Map 14 (PARTITION-LEVEL SORT, 398) + Reducer 12 <- Reducer 11 (GROUP, 437) + Reducer 13 <- Map 15 (PARTITION-LEVEL SORT, 219), Reducer 12 (PARTITION-LEVEL SORT, 219) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) + Reducer 3 <- Reducer 2 (GROUP, 437) + Reducer 4 <- Map 8 (PARTITION-LEVEL SORT, 219), Reducer 3 (PARTITION-LEVEL SORT, 219) + Reducer 5 <- Reducer 13 (PARTITION-LEVEL SORT, 529), Reducer 4 (PARTITION-LEVEL SORT, 529) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_sold_date_sk is not null and ss_store_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_store_sk (type: int), ss_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)) + 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_sold_date_sk is not null and ss_store_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_store_sk (type: int), ss_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)) + Map 14 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date_sk is not null and d_week_seq 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_week_seq (type: int), d_day_name (type: string) + outputColumnNames: _col0, _col1, _col2 + 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), _col2 (type: string) + Map 15 + Map Operator Tree: + TableScan + alias: d + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_month_seq BETWEEN 1197 AND 1208 and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 8116 Data size: 9081804 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: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date_sk is not null and d_week_seq 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_week_seq (type: int), d_day_name (type: string) + outputColumnNames: _col0, _col1, _col2 + 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), _col2 (type: string) + Map 8 + Map Operator Tree: + TableScan + alias: d + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_month_seq BETWEEN 1185 AND 1196 and d_week_seq is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_week_seq (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 8116 Data size: 9081804 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: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + 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, _col4, _col5 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col4 (type: int), _col1 (type: int), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col5, _col6, _col7, _col8 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col5), sum(_col6), sum(_col7), sum(_col8) + keys: _col0 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + Reducer 12 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 316797606 Data size: 27947976754 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: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + Reducer 13 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 348477374 Data size: 30742775095 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: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col11 + input vertices: + 1 Map 16 + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col11 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string), (_col0 - 52) (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: string), (_col0 - 52) (type: int) + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + 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, _col2, _col4, _col5 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col4 (type: int), _col1 (type: int), CASE WHEN ((_col5 = 'Sunday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Monday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Tuesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Wednesday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Thursday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Friday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)), CASE WHEN ((_col5 = 'Saturday')) THEN (_col2) ELSE (null) END (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7), sum(_col8) + keys: _col0 (type: int), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 316797606 Data size: 27947976754 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: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) + Reducer 4 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 348477374 Data size: 30742775095 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: _col0, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13 + input vertices: + 1 Map 9 + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col13 (type: string), _col0 (type: int), _col12 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col1 (type: int) + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)), _col9 (type: decimal(17,2)) + Reducer 5 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string), _col1 (type: int) + 1 _col1 (type: string), (_col0 - 52) (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col12, _col13, _col14, _col15, _col16, _col17 + Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string), _col1 (type: int), (_col3 / _col12) (type: decimal(37,20)), (_col4 / _col13) (type: decimal(37,20)), (_col5 / _col5) (type: decimal(37,20)), (_col6 / _col14) (type: decimal(37,20)), (_col7 / _col15) (type: decimal(37,20)), (_col8 / _col16) (type: decimal(37,20)), (_col9 / _col17) (type: decimal(37,20)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: decimal(37,20)), _col4 (type: decimal(37,20)), _col5 (type: decimal(37,20)), _col6 (type: decimal(37,20)), _col7 (type: decimal(37,20)), _col8 (type: decimal(37,20)), _col9 (type: decimal(37,20)) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: decimal(37,20)), VALUE._col1 (type: decimal(37,20)), VALUE._col2 (type: decimal(37,20)), VALUE._col3 (type: decimal(37,20)), VALUE._col4 (type: decimal(37,20)), VALUE._col5 (type: decimal(37,20)), VALUE._col6 (type: decimal(37,20)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 421657640 Data size: 37198759476 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 8800 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 + limit: 100 + Processor Tree: + ListSink +
