http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query33.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query33.q.out b/ql/src/test/results/clientpositive/perf/spark/query33.q.out new file mode 100644 index 0000000..dcf2fef --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query33.q.out @@ -0,0 +1,683 @@ +PREHOOK: query: explain +with ss as ( + select + i_manufact_id,sum(ss_ext_sales_price) total_sales + from + store_sales, + date_dim, + customer_address, + item + where + i_manufact_id in (select + i_manufact_id +from + item +where i_category in ('Books')) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 3 + and ss_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_manufact_id), + cs as ( + select + i_manufact_id,sum(cs_ext_sales_price) total_sales + from + catalog_sales, + date_dim, + customer_address, + item + where + i_manufact_id in (select + i_manufact_id +from + item +where i_category in ('Books')) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 3 + and cs_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_manufact_id), + ws as ( + select + i_manufact_id,sum(ws_ext_sales_price) total_sales + from + web_sales, + date_dim, + customer_address, + item + where + i_manufact_id in (select + i_manufact_id +from + item +where i_category in ('Books')) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 3 + and ws_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_manufact_id) + select i_manufact_id ,sum(total_sales) total_sales + from (select * from ss + union all + select * from cs + union all + select * from ws) tmp1 + group by i_manufact_id + order by total_sales +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with ss as ( + select + i_manufact_id,sum(ss_ext_sales_price) total_sales + from + store_sales, + date_dim, + customer_address, + item + where + i_manufact_id in (select + i_manufact_id +from + item +where i_category in ('Books')) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 3 + and ss_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_manufact_id), + cs as ( + select + i_manufact_id,sum(cs_ext_sales_price) total_sales + from + catalog_sales, + date_dim, + customer_address, + item + where + i_manufact_id in (select + i_manufact_id +from + item +where i_category in ('Books')) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 3 + and cs_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_manufact_id), + ws as ( + select + i_manufact_id,sum(ws_ext_sales_price) total_sales + from + web_sales, + date_dim, + customer_address, + item + where + i_manufact_id in (select + i_manufact_id +from + item +where i_category in ('Books')) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 3 + and ws_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_manufact_id) + select i_manufact_id ,sum(total_sales) total_sales + from (select * from ss + union all + select * from cs + union all + select * from ws) tmp1 + group by i_manufact_id + order by total_sales +limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) + Reducer 11 <- Map 13 (PARTITION-LEVEL SORT, 596), Reducer 10 (PARTITION-LEVEL SORT, 596) + Reducer 15 <- Map 1 (PARTITION-LEVEL SORT, 7), Reducer 19 (PARTITION-LEVEL SORT, 7) + Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 375), Reducer 22 (PARTITION-LEVEL SORT, 375) + Reducer 17 <- Reducer 16 (GROUP, 406) + Reducer 19 <- Map 18 (GROUP, 3) + Reducer 21 <- Map 12 (PARTITION-LEVEL SORT, 305), Map 20 (PARTITION-LEVEL SORT, 305) + Reducer 22 <- Map 13 (PARTITION-LEVEL SORT, 494), Reducer 21 (PARTITION-LEVEL SORT, 494) + Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 7), Reducer 30 (PARTITION-LEVEL SORT, 7) + Reducer 27 <- Reducer 26 (PARTITION-LEVEL SORT, 191), Reducer 33 (PARTITION-LEVEL SORT, 191) + Reducer 28 <- Reducer 27 (GROUP, 204) + Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 487), Reducer 15 (PARTITION-LEVEL SORT, 487) + Reducer 30 <- Map 18 (GROUP, 3) + Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 34 (PARTITION-LEVEL SORT, 154) + Reducer 33 <- Map 35 (PARTITION-LEVEL SORT, 327), Reducer 32 (PARTITION-LEVEL SORT, 327) + Reducer 4 <- Reducer 3 (GROUP, 529) + Reducer 5 <- Reducer 17 (GROUP, 569), Reducer 28 (GROUP, 569), Reducer 4 (GROUP, 569) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_sk is not null and i_manufact_id 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_manufact_id (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 663560457 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + 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_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Map 13 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20000000 Data size: 20297597642 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: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Map 18 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((i_category) IN ('Books') and i_manufact_id is not null) (type: boolean) + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_manufact_id (type: int) + outputColumnNames: i_manufact_id + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: i_manufact_id (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 231000 Data size: 331780228 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: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Map 20 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_bill_addr_sk is not null and 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_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + 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: decimal(7,2)) + Map 25 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_sk is not null and i_manufact_id 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_manufact_id (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 663560457 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 31 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ws_bill_addr_sk is not null and 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_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + 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_moy = 3) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Map 35 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20000000 Data size: 20297597642 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: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Map 9 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_addr_sk is not null and 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_addr_sk (type: int), ss_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + 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: int), _col3 (type: decimal(7,2)) + Reducer 10 + 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 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Reducer 11 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)) + Reducer 15 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 508200 Data size: 729916518 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: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) + Reducer 16 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + outputColumnNames: _col1, _col8 + Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 383314495 Data size: 51908482889 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: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 17 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 670816147 Data size: 72801917426 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: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(27,2)) + Reducer 19 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 115500 Data size: 165890114 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: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Reducer 21 + 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 + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 22 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col4 (type: int) + sort order: + + Map-reduce partition columns: _col4 (type: int) + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)) + Reducer 26 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 508200 Data size: 729916518 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: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) + Reducer 27 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 191667562 Data size: 26061245514 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: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 28 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 95833781 Data size: 13030622757 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 670816147 Data size: 72801917426 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: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(27,2)) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 766650239 Data size: 67634106676 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: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 30 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 115500 Data size: 165890114 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: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Reducer 32 + 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 + Statistics: Num rows: 158402938 Data size: 21538218500 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Reducer 33 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 670816147 Data size: 72801917426 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: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(27,2)) + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: decimal(27,2)) + sort order: + + Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: int) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: decimal(27,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 10800 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 +
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query34.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query34.q.out b/ql/src/test/results/clientpositive/perf/spark/query34.q.out new file mode 100644 index 0000000..17d4280 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query34.q.out @@ -0,0 +1,273 @@ +PREHOOK: query: explain +select c_last_name + ,c_first_name + ,c_salutation + ,c_preferred_cust_flag + ,ss_ticket_number + ,cnt from + (select ss_ticket_number + ,ss_customer_sk + ,count(*) cnt + from store_sales,date_dim,store,household_demographics + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_store_sk = store.s_store_sk + and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk + and (date_dim.d_dom between 1 and 3 or date_dim.d_dom between 25 and 28) + and (household_demographics.hd_buy_potential = '>10000' or + household_demographics.hd_buy_potential = 'unknown') + and household_demographics.hd_vehicle_count > 0 + and (case when household_demographics.hd_vehicle_count > 0 + then household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count + else null + end) > 1.2 + and date_dim.d_year in (2000,2000+1,2000+2) + and store.s_county in ('Mobile County','Maverick County','Huron County','Kittitas County', + 'Fairfield County','Jackson County','Barrow County','Pennington County') + group by ss_ticket_number,ss_customer_sk) dn,customer + where ss_customer_sk = c_customer_sk + and cnt between 15 and 20 + order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc +PREHOOK: type: QUERY +POSTHOOK: query: explain +select c_last_name + ,c_first_name + ,c_salutation + ,c_preferred_cust_flag + ,ss_ticket_number + ,cnt from + (select ss_ticket_number + ,ss_customer_sk + ,count(*) cnt + from store_sales,date_dim,store,household_demographics + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_store_sk = store.s_store_sk + and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk + and (date_dim.d_dom between 1 and 3 or date_dim.d_dom between 25 and 28) + and (household_demographics.hd_buy_potential = '>10000' or + household_demographics.hd_buy_potential = 'unknown') + and household_demographics.hd_vehicle_count > 0 + and (case when household_demographics.hd_vehicle_count > 0 + then household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count + else null + end) > 1.2 + and date_dim.d_year in (2000,2000+1,2000+2) + and store.s_county in ('Mobile County','Maverick County','Huron County','Kittitas County', + 'Fairfield County','Jackson County','Barrow County','Pennington County') + group by ss_ticket_number,ss_customer_sk) dn,customer + where ss_customer_sk = c_customer_sk + and cnt between 15 and 20 + order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((hd_buy_potential = '>10000') or (hd_buy_potential = 'unknown')) and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.2)) ELSE (null) END and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + 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_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County', 'Fairfield County', 'Jackson County', 'Barrow County', 'Pennington County') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 567), Reducer 6 (PARTITION-LEVEL SORT, 567) + Reducer 3 <- Reducer 2 (SORT, 1) + Reducer 5 <- Map 4 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) + Reducer 6 <- Reducer 5 (GROUP, 529) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: customer + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) + Map 4 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_customer_sk is not null and ss_hdemo_sk is not null and 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_customer_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 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: int), _col3 (type: int), _col4 (type: int) + 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_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28) and (d_year) IN (2000, 2001, 2002) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 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: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: string), _col2 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: int), _col7 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order: +++- + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: int), _col5 (type: bigint) + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 88000001 Data size: 75681779077 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 5 + Local Work: + Map Reduce Local Work + 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 + 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 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4 + input vertices: + 1 Map 8 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col4 + input vertices: + 1 Map 9 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col1 (type: int), _col4 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 766650239 Data size: 67634106676 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: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: bigint) + Reducer 6 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: int), KEY._col1 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col2 BETWEEN 15 AND 20 (type: boolean) + Statistics: Num rows: 42591679 Data size: 3757450287 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: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: bigint) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query35.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query35.q.out b/ql/src/test/results/clientpositive/perf/spark/query35.q.out new file mode 100644 index 0000000..8759b71 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query35.q.out @@ -0,0 +1,524 @@ +PREHOOK: query: explain +select + ca_state, + cd_gender, + cd_marital_status, + count(*) cnt1, + avg(cd_dep_count), + max(cd_dep_count), + sum(cd_dep_count), + cd_dep_employed_count, + count(*) cnt2, + avg(cd_dep_employed_count), + max(cd_dep_employed_count), + sum(cd_dep_employed_count), + cd_dep_college_count, + count(*) cnt3, + avg(cd_dep_college_count), + max(cd_dep_college_count), + sum(cd_dep_college_count) + from + customer c,customer_address ca,customer_demographics + where + c.c_current_addr_sk = ca.ca_address_sk and + cd_demo_sk = c.c_current_cdemo_sk and + exists (select * + from store_sales,date_dim + where c.c_customer_sk = ss_customer_sk and + ss_sold_date_sk = d_date_sk and + d_year = 1999 and + d_qoy < 4) and + (exists (select * + from web_sales,date_dim + where c.c_customer_sk = ws_bill_customer_sk and + ws_sold_date_sk = d_date_sk and + d_year = 1999 and + d_qoy < 4) or + exists (select * + from catalog_sales,date_dim + where c.c_customer_sk = cs_ship_customer_sk and + cs_sold_date_sk = d_date_sk and + d_year = 1999 and + d_qoy < 4)) + group by ca_state, + cd_gender, + cd_marital_status, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count + order by ca_state, + cd_gender, + cd_marital_status, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + ca_state, + cd_gender, + cd_marital_status, + count(*) cnt1, + avg(cd_dep_count), + max(cd_dep_count), + sum(cd_dep_count), + cd_dep_employed_count, + count(*) cnt2, + avg(cd_dep_employed_count), + max(cd_dep_employed_count), + sum(cd_dep_employed_count), + cd_dep_college_count, + count(*) cnt3, + avg(cd_dep_college_count), + max(cd_dep_college_count), + sum(cd_dep_college_count) + from + customer c,customer_address ca,customer_demographics + where + c.c_current_addr_sk = ca.ca_address_sk and + cd_demo_sk = c.c_current_cdemo_sk and + exists (select * + from store_sales,date_dim + where c.c_customer_sk = ss_customer_sk and + ss_sold_date_sk = d_date_sk and + d_year = 1999 and + d_qoy < 4) and + (exists (select * + from web_sales,date_dim + where c.c_customer_sk = ws_bill_customer_sk and + ws_sold_date_sk = d_date_sk and + d_year = 1999 and + d_qoy < 4) or + exists (select * + from catalog_sales,date_dim + where c.c_customer_sk = cs_ship_customer_sk and + cs_sold_date_sk = d_date_sk and + d_year = 1999 and + d_qoy < 4)) + group by ca_state, + cd_gender, + cd_marital_status, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count + order by ca_state, + cd_gender, + cd_marital_status, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 154), Map 13 (PARTITION-LEVEL SORT, 154) + Reducer 12 <- Reducer 11 (GROUP, 169) + Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 398), Map 17 (PARTITION-LEVEL SORT, 398) + Reducer 16 <- Reducer 15 (GROUP, 437) + Reducer 19 <- Map 18 (PARTITION-LEVEL SORT, 305), Map 21 (PARTITION-LEVEL SORT, 305) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 8 (PARTITION-LEVEL SORT, 855) + Reducer 20 <- Reducer 19 (GROUP, 336) + Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 597), Reducer 2 (PARTITION-LEVEL SORT, 597) + Reducer 4 <- Reducer 12 (PARTITION-LEVEL SORT, 953), Reducer 16 (PARTITION-LEVEL SORT, 953), Reducer 3 (PARTITION-LEVEL SORT, 953) + Reducer 5 <- Reducer 20 (PARTITION-LEVEL SORT, 648), Reducer 4 (PARTITION-LEVEL SORT, 648) + Reducer 6 <- Reducer 5 (GROUP, 529) + Reducer 7 <- Reducer 6 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_current_cdemo_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int) + Map 10 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int) + Map 13 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12174 Data size: 13622706 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: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Map 14 + Map Operator Tree: + TableScan + alias: store_sales + 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) + outputColumnNames: _col0, _col1 + 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) + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12174 Data size: 13622706 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: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Map 18 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_ship_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_ship_customer_sk (type: int) + outputColumnNames: _col0, _col1 + 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) + 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_qoy < 4) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 12174 Data size: 13622706 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: 12174 Data size: 13622706 Basic stats: COMPLETE Column stats: NONE + Map 8 + Map Operator Tree: + TableScan + alias: ca + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ca_address_sk is not null (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int), ca_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 40595195284 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: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 9 + Map Operator Tree: + TableScan + alias: customer_demographics + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: cd_demo_sk is not null (type: boolean) + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cd_demo_sk (type: int), cd_gender (type: string), cd_marital_status (type: string), cd_dep_count (type: int), cd_dep_employed_count (type: int), cd_dep_college_count (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1861800 Data size: 717186159 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: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) + 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 + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0 + 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 + Reducer 12 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 79201469 Data size: 10769109250 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: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: boolean) + Reducer 15 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0 + 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 + Reducer 16 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + 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 + Reducer 19 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col1 (type: int) + mode: hash + outputColumnNames: _col0 + 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 + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col4 + Statistics: Num rows: 88000001 Data size: 75681779077 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: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col4 (type: string) + Reducer 20 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 158394413 Data size: 21449785388 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: 158394413 Data size: 21449785388 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: boolean) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col4, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 96800003 Data size: 83249958789 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: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + Inner Join 0 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col4, _col6, _col7, _col8, _col9, _col10, _col12 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col12 (type: boolean) + outputColumnNames: _col0, _col4, _col6, _col7, _col8, _col9, _col10, _col13 + Statistics: Num rows: 696954748 Data size: 61485550191 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: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col13 (type: boolean) + Reducer 5 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col6, _col7, _col8, _col9, _col10, _col13, _col15 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col13 is not null or _col15 is not null) (type: boolean) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) + outputColumnNames: _col4, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(), avg(_col8), max(_col8), sum(_col8), avg(_col9), max(_col9), sum(_col9), avg(_col10), max(_col10), sum(_col10) + keys: _col4 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: int), _col5 (type: int) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col6 (type: bigint), _col7 (type: struct<count:bigint,sum:double,input:int>), _col8 (type: int), _col9 (type: bigint), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: int), _col12 (type: bigint), _col13 (type: struct<count:bigint,sum:double,input:int>), _col14 (type: int), _col15 (type: bigint) + Reducer 6 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0), avg(VALUE._col1), max(VALUE._col2), sum(VALUE._col3), avg(VALUE._col4), max(VALUE._col5), sum(VALUE._col6), avg(VALUE._col7), max(VALUE._col8), sum(VALUE._col9) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: int), KEY._col5 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col6 (type: bigint), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col4 (type: int), _col10 (type: double), _col11 (type: int), _col12 (type: bigint), _col5 (type: int), _col13 (type: double), _col14 (type: int), _col15 (type: bigint), _col3 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9, _col10, _col11, _col12, _col14, _col15, _col16, _col17 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col17 (type: int), _col7 (type: int), _col12 (type: int) + sort order: ++++++ + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: bigint), _col4 (type: double), _col5 (type: int), _col6 (type: bigint), _col9 (type: double), _col10 (type: int), _col11 (type: bigint), _col14 (type: double), _col15 (type: int), _col16 (type: bigint) + Reducer 7 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: int), VALUE._col3 (type: bigint), KEY.reducesinkkey4 (type: int), VALUE._col0 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: int), VALUE._col6 (type: bigint), KEY.reducesinkkey5 (type: int), VALUE._col0 (type: bigint), VALUE._col7 (type: double), VALUE._col8 (type: int), VALUE._col9 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 + Statistics: Num rows: 383325119 Data size: 33817053293 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: -1 + Processor Tree: + ListSink +