http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query68.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query68.q.out b/ql/src/test/results/clientpositive/perf/spark/query68.q.out new file mode 100644 index 0000000..585aa40 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query68.q.out @@ -0,0 +1,363 @@ +PREHOOK: query: explain +select c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + ,extended_price + ,extended_tax + ,list_price + from (select ss_ticket_number + ,ss_customer_sk + ,ca_city bought_city + ,sum(ss_ext_sales_price) extended_price + ,sum(ss_ext_list_price) list_price + ,sum(ss_ext_tax) extended_tax + from store_sales + ,date_dim + ,store + ,household_demographics + ,customer_address + 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 store_sales.ss_addr_sk = customer_address.ca_address_sk + and date_dim.d_dom between 1 and 2 + and (household_demographics.hd_dep_count = 2 or + household_demographics.hd_vehicle_count= 1) + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_city in ('Cedar Grove','Wildwood') + group by ss_ticket_number + ,ss_customer_sk + ,ss_addr_sk,ca_city) dn + ,customer + ,customer_address current_addr + where ss_customer_sk = c_customer_sk + and customer.c_current_addr_sk = current_addr.ca_address_sk + and current_addr.ca_city <> bought_city + order by c_last_name + ,ss_ticket_number + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + ,extended_price + ,extended_tax + ,list_price + from (select ss_ticket_number + ,ss_customer_sk + ,ca_city bought_city + ,sum(ss_ext_sales_price) extended_price + ,sum(ss_ext_list_price) list_price + ,sum(ss_ext_tax) extended_tax + from store_sales + ,date_dim + ,store + ,household_demographics + ,customer_address + 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 store_sales.ss_addr_sk = customer_address.ca_address_sk + and date_dim.d_dom between 1 and 2 + and (household_demographics.hd_dep_count = 2 or + household_demographics.hd_vehicle_count= 1) + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_city in ('Cedar Grove','Wildwood') + group by ss_ticket_number + ,ss_customer_sk + ,ss_addr_sk,ca_city) dn + ,customer + ,customer_address current_addr + where ss_customer_sk = c_customer_sk + and customer.c_current_addr_sk = current_addr.ca_address_sk + and current_addr.ca_city <> bought_city + order by c_last_name + ,ss_ticket_number + limit 100 +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 10 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_city) IN ('Cedar Grove', 'Wildwood') 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 _col4 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 11 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 7200 Data size: 770400 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: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year) IN (1998, 1999, 2000) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean) + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 855), Map 5 (PARTITION-LEVEL SORT, 855) + Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 882), Reducer 8 (PARTITION-LEVEL SORT, 882) + Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 7 <- Map 12 (PARTITION-LEVEL SORT, 846), Map 6 (PARTITION-LEVEL SORT, 846) + Reducer 8 <- Reducer 7 (GROUP, 582) +#### 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_current_addr_sk is not null and 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_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: string) + Map 12 + Map Operator Tree: + TableScan + alias: customer_address + 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_city (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 5 + Map Operator Tree: + TableScan + alias: current_addr + 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_city (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 6 + 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_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_addr_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)), ss_ext_tax (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 9 + 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 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 10 + 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 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col8 + input vertices: + 1 Map 11 + Statistics: Num rows: 766650239 Data size: 67634106676 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: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) + Local Work: + Map Reduce Local Work + 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, _col3, _col5 + Statistics: Num rows: 88000001 Data size: 75681779077 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: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string), _col3 (type: string), _col5 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col1 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col8, _col9, _col10, _col11 + Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col5 <> _col8) (type: boolean) + Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: string), _col2 (type: string), _col5 (type: string), _col8 (type: string), _col6 (type: int), _col9 (type: decimal(17,2)), _col11 (type: decimal(17,2)), _col10 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col4 (type: int) + sort order: ++ + Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)) + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: int), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 463823414 Data size: 40918636263 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 7 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col8, _col18 + Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col6), sum(_col7), sum(_col8) + keys: _col1 (type: int), _col18 (type: string), _col3 (type: int), _col5 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: int) + Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) + Reducer 8 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2) + keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: int), _col0 (type: int), _col1 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 421657640 Data size: 37198759433 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: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) + + 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/query69.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query69.q.out b/ql/src/test/results/clientpositive/perf/spark/query69.q.out new file mode 100644 index 0000000..e4430be --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query69.q.out @@ -0,0 +1,516 @@ +PREHOOK: query: explain +select + cd_gender, + cd_marital_status, + cd_education_status, + count(*) cnt1, + cd_purchase_estimate, + count(*) cnt2, + cd_credit_rating, + count(*) cnt3 + from + customer c,customer_address ca,customer_demographics + where + c.c_current_addr_sk = ca.ca_address_sk and + ca_state in ('CO','IL','MN') 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_moy between 1 and 1+2) and + (not 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_moy between 1 and 1+2) and + not 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_moy between 1 and 1+2)) + group by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating + order by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + cd_gender, + cd_marital_status, + cd_education_status, + count(*) cnt1, + cd_purchase_estimate, + count(*) cnt2, + cd_credit_rating, + count(*) cnt3 + from + customer c,customer_address ca,customer_demographics + where + c.c_current_addr_sk = ca.ca_address_sk and + ca_state in ('CO','IL','MN') 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_moy between 1 and 1+2) and + (not 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_moy between 1 and 1+2) and + not 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_moy between 1 and 1+2)) + group by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating + order by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating + 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 +#### A masked pattern was here #### + Vertices: + 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_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + 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_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 18 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year = 1999) and d_date_sk is not null and d_moy BETWEEN 1 AND 3) (type: boolean) + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 11 <- Map 10 (GROUP, 169) + Reducer 14 <- Map 13 (GROUP, 437) + Reducer 17 <- Map 16 (GROUP, 336) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 697), Map 8 (PARTITION-LEVEL SORT, 697) + Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 597), Reducer 2 (PARTITION-LEVEL SORT, 597) + Reducer 4 <- Reducer 11 (PARTITION-LEVEL SORT, 953), Reducer 14 (PARTITION-LEVEL SORT, 953), Reducer 3 (PARTITION-LEVEL SORT, 953) + Reducer 5 <- Reducer 17 (PARTITION-LEVEL SORT, 408), Reducer 4 (PARTITION-LEVEL SORT, 408) + Reducer 6 <- Reducer 5 (GROUP, 133) + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 12 + 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 + Local Work: + Map Reduce Local Work + Map 13 + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 15 + 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 + Local Work: + Map Reduce Local Work + Map 16 + 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 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1 + input vertices: + 1 Map 18 + 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 + Local Work: + Map Reduce Local Work + 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_state) IN ('CO', 'IL', 'MN') 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: 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_education_status (type: string), cd_purchase_estimate (type: int), cd_credit_rating (type: string) + 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: string), _col4 (type: int), _col5 (type: string) + Reducer 11 + 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 14 + 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 17 + 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 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 + 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) + 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, _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: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + 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, _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), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string), _col12 (type: boolean) + outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10, _col13 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col13 is null (type: boolean) + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + outputColumnNames: _col0, _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 348477374 Data size: 30742775095 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: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + value expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + 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: _col6, _col7, _col8, _col9, _col10, _col15 + Statistics: Num rows: 383325119 Data size: 33817053337 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: _col15 is null (type: boolean) + Statistics: Num rows: 191662559 Data size: 16908526624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + outputColumnNames: _col6, _col7, _col8, _col9, _col10 + Statistics: Num rows: 191662559 Data size: 16908526624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: int), _col10 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 191662559 Data size: 16908526624 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: string) + sort order: +++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string) + Statistics: Num rows: 191662559 Data size: 16908526624 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col5 (type: bigint) + Reducer 6 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 95831279 Data size: 8454263267 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col5 (type: bigint), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6 + Statistics: Num rows: 95831279 Data size: 8454263267 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: int), _col6 (type: string) + sort order: +++++ + Statistics: Num rows: 95831279 Data size: 8454263267 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (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), KEY.reducesinkkey3 (type: int), VALUE._col0 (type: bigint), KEY.reducesinkkey4 (type: string), VALUE._col0 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 95831279 Data size: 8454263267 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 + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query7.q.out b/ql/src/test/results/clientpositive/perf/spark/query7.q.out new file mode 100644 index 0000000..b0979c0 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query7.q.out @@ -0,0 +1,253 @@ +PREHOOK: query: explain +select i_item_id, + avg(ss_quantity) agg1, + avg(ss_list_price) agg2, + avg(ss_coupon_amt) agg3, + avg(ss_sales_price) agg4 + from store_sales, customer_demographics, date_dim, item, promotion + where ss_sold_date_sk = d_date_sk and + ss_item_sk = i_item_sk and + ss_cdemo_sk = cd_demo_sk and + ss_promo_sk = p_promo_sk and + cd_gender = 'F' and + cd_marital_status = 'W' and + cd_education_status = 'Primary' and + (p_channel_email = 'N' or p_channel_event = 'N') and + d_year = 1998 + group by i_item_id + order by i_item_id + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select i_item_id, + avg(ss_quantity) agg1, + avg(ss_list_price) agg2, + avg(ss_coupon_amt) agg3, + avg(ss_sales_price) agg4 + from store_sales, customer_demographics, date_dim, item, promotion + where ss_sold_date_sk = d_date_sk and + ss_item_sk = i_item_sk and + ss_cdemo_sk = cd_demo_sk and + ss_promo_sk = p_promo_sk and + cd_gender = 'F' and + cd_marital_status = 'W' and + cd_education_status = 'Primary' and + (p_channel_email = 'N' or p_channel_event = 'N') and + d_year = 1998 + group by i_item_id + order by i_item_id + limit 100 +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 9 + Map Operator Tree: + TableScan + alias: promotion + Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean) + Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: p_promo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2300 Data size: 2713420 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, 398), Map 7 (PARTITION-LEVEL SORT, 398) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) + Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 534), Reducer 3 (PARTITION-LEVEL SORT, 534) + Reducer 5 <- Reducer 4 (GROUP, 582) + 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_cdemo_sk is not null and ss_item_sk is not null and ss_promo_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_cdemo_sk (type: int), ss_promo_sk (type: int), ss_quantity (type: int), ss_list_price (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)), ss_coupon_amt (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 575995635 Data size: 50814502088 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Map 10 + 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 (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 7 + Map Operator Tree: + TableScan + alias: customer_demographics + Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 232725 Data size: 89648269 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: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE + 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_year = 1998) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + 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, _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) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Reducer 3 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7 + 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, _col5, _col6, _col7 + input vertices: + 1 Map 9 + Statistics: Num rows: 766650239 Data size: 67634106676 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: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5, _col6, _col7, _col18 + Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(_col4), avg(_col5), avg(_col7), avg(_col6) + keys: _col18 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 843315281 Data size: 74397518956 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: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>), _col3 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>), _col4 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>) + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), avg(VALUE._col3) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: double), _col2 (type: decimal(11,6)), _col3 (type: decimal(11,6)), _col4 (type: decimal(11,6)) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: decimal(11,6)), VALUE._col2 (type: decimal(11,6)), VALUE._col3 (type: decimal(11,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 421657640 Data size: 37198759433 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 + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query70.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query70.q.out b/ql/src/test/results/clientpositive/perf/spark/query70.q.out new file mode 100644 index 0000000..716665b --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query70.q.out @@ -0,0 +1,429 @@ +PREHOOK: query: explain +select + sum(ss_net_profit) as total_sum + ,s_state + ,s_county + ,grouping(s_state)+grouping(s_county) as lochierarchy + ,rank() over ( + partition by grouping(s_state)+grouping(s_county), + case when grouping(s_county) = 0 then s_state end + order by sum(ss_net_profit) desc) as rank_within_parent + from + store_sales + ,date_dim d1 + ,store + where + d1.d_month_seq between 1212 and 1212+11 + and d1.d_date_sk = ss_sold_date_sk + and s_store_sk = ss_store_sk + and s_state in + ( select s_state + from (select s_state as s_state, + rank() over ( partition by s_state order by sum(ss_net_profit) desc) as ranking + from store_sales, store, date_dim + where d_month_seq between 1212 and 1212+11 + and d_date_sk = ss_sold_date_sk + and s_store_sk = ss_store_sk + group by s_state + ) tmp1 + where ranking <= 5 + ) + group by rollup(s_state,s_county) + order by + lochierarchy desc + ,case when lochierarchy = 0 then s_state end + ,rank_within_parent + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + sum(ss_net_profit) as total_sum + ,s_state + ,s_county + ,grouping(s_state)+grouping(s_county) as lochierarchy + ,rank() over ( + partition by grouping(s_state)+grouping(s_county), + case when grouping(s_county) = 0 then s_state end + order by sum(ss_net_profit) desc) as rank_within_parent + from + store_sales + ,date_dim d1 + ,store + where + d1.d_month_seq between 1212 and 1212+11 + and d1.d_date_sk = ss_sold_date_sk + and s_store_sk = ss_store_sk + and s_state in + ( select s_state + from (select s_state as s_state, + rank() over ( partition by s_state order by sum(ss_net_profit) desc) as ranking + from store_sales, store, date_dim + where d_month_seq between 1212 and 1212+11 + and d_date_sk = ss_sold_date_sk + and s_store_sk = ss_store_sk + group by s_state + ) tmp1 + where ranking <= 5 + ) + group by rollup(s_state,s_county) + order by + lochierarchy desc + ,case when lochierarchy = 0 then s_state end + ,rank_within_parent + 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 8 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s_state 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_county (type: string), s_state (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 14 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s_state 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_state (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 10 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) + Reducer 11 <- Reducer 10 (GROUP, 481) + Reducer 12 <- Reducer 11 (PARTITION-LEVEL SORT, 241) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) + Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 561), Reducer 2 (PARTITION-LEVEL SORT, 561) + Reducer 4 <- Reducer 3 (GROUP, 1009) + Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 793) + 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_net_profit (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 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_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (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 + Map 7 + Map Operator Tree: + TableScan + alias: d1 + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (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 + 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_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_net_profit (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)) + Reducer 10 + 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 + 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 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col6 + input vertices: + 1 Map 14 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col6 (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 11 + 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), _col1 (type: decimal(17,2)) + sort order: +- + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + Reducer 12 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(17,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: decimal(17,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col1 DESC NULLS LAST + partition by: _col0 + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col1 + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (rank_window_0 <= 5) (type: boolean) + Statistics: Num rows: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 116159124 Data size: 10247591639 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: 116159124 Data size: 10247591639 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + 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 + 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 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col6, _col7 + input vertices: + 1 Map 8 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col7 (type: string) + sort order: + + Map-reduce partition columns: _col7 (type: string) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: decimal(7,2)), _col6 (type: string) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col7 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col2, _col6, _col7 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col7 (type: string), _col6 (type: string), _col2 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2) + keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: decimal(17,2)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col2 (type: int) + outputColumnNames: _col0, _col1, _col4, _col5 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (grouping(_col5, 1) + grouping(_col5, 0)) (type: int), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END (type: string), _col4 (type: decimal(17,2)) + sort order: ++- + Map-reduce partition columns: (grouping(_col5, 1) + grouping(_col5, 0)) (type: int), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END (type: string) + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col5 (type: int) + Reducer 5 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: decimal(17,2)), VALUE._col2 (type: int) + outputColumnNames: _col0, _col1, _col4, _col5 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string, _col4: decimal(17,2), _col5: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col4 DESC NULLS LAST + partition by: (grouping(_col5, 1) + grouping(_col5, 0)), CASE WHEN ((grouping(_col5, 0) = 0)) THEN (_col0) ELSE (null) END + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: _col4 + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col4 (type: decimal(17,2)), _col0 (type: string), _col1 (type: string), (grouping(_col5, 1) + grouping(_col5, 0)) (type: int), rank_window_0 (type: int), CASE WHEN (((grouping(_col5, 1) + grouping(_col5, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int), _col5 (type: string), _col4 (type: int) + sort order: -++ + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: decimal(17,2)), _col1 (type: string), _col2 (type: string) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1149975358 Data size: 101451159969 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 +
