http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query79.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query79.q.out b/ql/src/test/results/clientpositive/perf/spark/query79.q.out new file mode 100644 index 0000000..f010369 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query79.q.out @@ -0,0 +1,258 @@ +PREHOOK: query: explain +select + c_last_name,c_first_name,substr(s_city,1,30),ss_ticket_number,amt,profit + from + (select ss_ticket_number + ,ss_customer_sk + ,store.s_city + ,sum(ss_coupon_amt) amt + ,sum(ss_net_profit) profit + 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 (household_demographics.hd_dep_count = 8 or household_demographics.hd_vehicle_count > 0) + and date_dim.d_dow = 1 + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_number_employees between 200 and 295 + group by ss_ticket_number,ss_customer_sk,ss_addr_sk,store.s_city) ms,customer + where ss_customer_sk = c_customer_sk + order by c_last_name,c_first_name,substr(s_city,1,30), profit +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + c_last_name,c_first_name,substr(s_city,1,30),ss_ticket_number,amt,profit + from + (select ss_ticket_number + ,ss_customer_sk + ,store.s_city + ,sum(ss_coupon_amt) amt + ,sum(ss_net_profit) profit + 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 (household_demographics.hd_dep_count = 8 or household_demographics.hd_vehicle_count > 0) + and date_dim.d_dow = 1 + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_number_employees between 200 and 295 + group by ss_ticket_number,ss_customer_sk,ss_addr_sk,store.s_city) ms,customer + where ss_customer_sk = c_customer_sk + order by c_last_name,c_first_name,substr(s_city,1,30), profit +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 8 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (s_number_employees BETWEEN 200 AND 295 and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 189 Data size: 361171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int), s_city (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 189 Data size: 361171 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 9 + 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 = 8) or (hd_vehicle_count > 0)) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 6000 Data size: 642000 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 6000 Data size: 642000 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 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 802), Reducer 6 (PARTITION-LEVEL SORT, 802) + 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_first_name (type: string), c_last_name (type: string) + outputColumnNames: _col0, _col1, _col2 + 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) + 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_addr_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_coupon_amt (type: decimal(7,2)), ss_net_profit (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: _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), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + 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_dow = 1) and (d_year) IN (1998, 1999, 2000) 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 + 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, _col5, _col6, _col7 + Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: string), _col1 (type: string), _col3 (type: int), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), substr(_col5, 1, 30) (type: string) + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 + Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string), _col5 (type: decimal(17,2)) + sort order: ++++ + Statistics: Num rows: 421657640 Data size: 37198759428 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col3 (type: int), _col4 (type: decimal(17,2)) + Reducer 3 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: decimal(17,2)), KEY.reducesinkkey3 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 421657640 Data size: 37198759428 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 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, _col5, _col6, _col7 + 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, _col13 + 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 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col5, _col6, _col7, _col13 + input vertices: + 1 Map 9 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col6), sum(_col7) + keys: _col1 (type: int), _col3 (type: int), _col5 (type: int), _col13 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + sort order: ++++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) + Reducer 6 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: int), _col0 (type: int), _col3 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 383325119 Data size: 33817053293 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: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + + 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/query8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query8.q.out b/ql/src/test/results/clientpositive/perf/spark/query8.q.out new file mode 100644 index 0000000..13cd0f4 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query8.q.out @@ -0,0 +1,549 @@ +PREHOOK: query: explain +select s_store_name + ,sum(ss_net_profit) + from store_sales + ,date_dim + ,store, + (select ca_zip + from ( + (SELECT substr(ca_zip,1,5) ca_zip + FROM customer_address + WHERE substr(ca_zip,1,5) IN ( + '89436','30868','65085','22977','83927','77557', + '58429','40697','80614','10502','32779', + '91137','61265','98294','17921','18427', + '21203','59362','87291','84093','21505', + '17184','10866','67898','25797','28055', + '18377','80332','74535','21757','29742', + '90885','29898','17819','40811','25990', + '47513','89531','91068','10391','18846', + '99223','82637','41368','83658','86199', + '81625','26696','89338','88425','32200', + '81427','19053','77471','36610','99823', + '43276','41249','48584','83550','82276', + '18842','78890','14090','38123','40936', + '34425','19850','43286','80072','79188', + '54191','11395','50497','84861','90733', + '21068','57666','37119','25004','57835', + '70067','62878','95806','19303','18840', + '19124','29785','16737','16022','49613', + '89977','68310','60069','98360','48649', + '39050','41793','25002','27413','39736', + '47208','16515','94808','57648','15009', + '80015','42961','63982','21744','71853', + '81087','67468','34175','64008','20261', + '11201','51799','48043','45645','61163', + '48375','36447','57042','21218','41100', + '89951','22745','35851','83326','61125', + '78298','80752','49858','52940','96976', + '63792','11376','53582','18717','90226', + '50530','94203','99447','27670','96577', + '57856','56372','16165','23427','54561', + '28806','44439','22926','30123','61451', + '92397','56979','92309','70873','13355', + '21801','46346','37562','56458','28286', + '47306','99555','69399','26234','47546', + '49661','88601','35943','39936','25632', + '24611','44166','56648','30379','59785', + '11110','14329','93815','52226','71381', + '13842','25612','63294','14664','21077', + '82626','18799','60915','81020','56447', + '76619','11433','13414','42548','92713', + '70467','30884','47484','16072','38936', + '13036','88376','45539','35901','19506', + '65690','73957','71850','49231','14276', + '20005','18384','76615','11635','38177', + '55607','41369','95447','58581','58149', + '91946','33790','76232','75692','95464', + '22246','51061','56692','53121','77209', + '15482','10688','14868','45907','73520', + '72666','25734','17959','24677','66446', + '94627','53535','15560','41967','69297', + '11929','59403','33283','52232','57350', + '43933','40921','36635','10827','71286', + '19736','80619','25251','95042','15526', + '36496','55854','49124','81980','35375', + '49157','63512','28944','14946','36503', + '54010','18767','23969','43905','66979', + '33113','21286','58471','59080','13395', + '79144','70373','67031','38360','26705', + '50906','52406','26066','73146','15884', + '31897','30045','61068','45550','92454', + '13376','14354','19770','22928','97790', + '50723','46081','30202','14410','20223', + '88500','67298','13261','14172','81410', + '93578','83583','46047','94167','82564', + '21156','15799','86709','37931','74703', + '83103','23054','70470','72008','49247', + '91911','69998','20961','70070','63197', + '54853','88191','91830','49521','19454', + '81450','89091','62378','25683','61869', + '51744','36580','85778','36871','48121', + '28810','83712','45486','67393','26935', + '42393','20132','55349','86057','21309', + '80218','10094','11357','48819','39734', + '40758','30432','21204','29467','30214', + '61024','55307','74621','11622','68908', + '33032','52868','99194','99900','84936', + '69036','99149','45013','32895','59004', + '32322','14933','32936','33562','72550', + '27385','58049','58200','16808','21360', + '32961','18586','79307','15492')) + intersect + (select ca_zip + from (SELECT substr(ca_zip,1,5) ca_zip,count(*) cnt + FROM customer_address, customer + WHERE ca_address_sk = c_current_addr_sk and + c_preferred_cust_flag='Y' + group by ca_zip + having count(*) > 10)A1))A2) V1 + where ss_store_sk = s_store_sk + and ss_sold_date_sk = d_date_sk + and d_qoy = 1 and d_year = 2002 + and (substr(s_zip,1,2) = substr(V1.ca_zip,1,2)) + group by s_store_name + order by s_store_name + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select s_store_name + ,sum(ss_net_profit) + from store_sales + ,date_dim + ,store, + (select ca_zip + from ( + (SELECT substr(ca_zip,1,5) ca_zip + FROM customer_address + WHERE substr(ca_zip,1,5) IN ( + '89436','30868','65085','22977','83927','77557', + '58429','40697','80614','10502','32779', + '91137','61265','98294','17921','18427', + '21203','59362','87291','84093','21505', + '17184','10866','67898','25797','28055', + '18377','80332','74535','21757','29742', + '90885','29898','17819','40811','25990', + '47513','89531','91068','10391','18846', + '99223','82637','41368','83658','86199', + '81625','26696','89338','88425','32200', + '81427','19053','77471','36610','99823', + '43276','41249','48584','83550','82276', + '18842','78890','14090','38123','40936', + '34425','19850','43286','80072','79188', + '54191','11395','50497','84861','90733', + '21068','57666','37119','25004','57835', + '70067','62878','95806','19303','18840', + '19124','29785','16737','16022','49613', + '89977','68310','60069','98360','48649', + '39050','41793','25002','27413','39736', + '47208','16515','94808','57648','15009', + '80015','42961','63982','21744','71853', + '81087','67468','34175','64008','20261', + '11201','51799','48043','45645','61163', + '48375','36447','57042','21218','41100', + '89951','22745','35851','83326','61125', + '78298','80752','49858','52940','96976', + '63792','11376','53582','18717','90226', + '50530','94203','99447','27670','96577', + '57856','56372','16165','23427','54561', + '28806','44439','22926','30123','61451', + '92397','56979','92309','70873','13355', + '21801','46346','37562','56458','28286', + '47306','99555','69399','26234','47546', + '49661','88601','35943','39936','25632', + '24611','44166','56648','30379','59785', + '11110','14329','93815','52226','71381', + '13842','25612','63294','14664','21077', + '82626','18799','60915','81020','56447', + '76619','11433','13414','42548','92713', + '70467','30884','47484','16072','38936', + '13036','88376','45539','35901','19506', + '65690','73957','71850','49231','14276', + '20005','18384','76615','11635','38177', + '55607','41369','95447','58581','58149', + '91946','33790','76232','75692','95464', + '22246','51061','56692','53121','77209', + '15482','10688','14868','45907','73520', + '72666','25734','17959','24677','66446', + '94627','53535','15560','41967','69297', + '11929','59403','33283','52232','57350', + '43933','40921','36635','10827','71286', + '19736','80619','25251','95042','15526', + '36496','55854','49124','81980','35375', + '49157','63512','28944','14946','36503', + '54010','18767','23969','43905','66979', + '33113','21286','58471','59080','13395', + '79144','70373','67031','38360','26705', + '50906','52406','26066','73146','15884', + '31897','30045','61068','45550','92454', + '13376','14354','19770','22928','97790', + '50723','46081','30202','14410','20223', + '88500','67298','13261','14172','81410', + '93578','83583','46047','94167','82564', + '21156','15799','86709','37931','74703', + '83103','23054','70470','72008','49247', + '91911','69998','20961','70070','63197', + '54853','88191','91830','49521','19454', + '81450','89091','62378','25683','61869', + '51744','36580','85778','36871','48121', + '28810','83712','45486','67393','26935', + '42393','20132','55349','86057','21309', + '80218','10094','11357','48819','39734', + '40758','30432','21204','29467','30214', + '61024','55307','74621','11622','68908', + '33032','52868','99194','99900','84936', + '69036','99149','45013','32895','59004', + '32322','14933','32936','33562','72550', + '27385','58049','58200','16808','21360', + '32961','18586','79307','15492')) + intersect + (select ca_zip + from (SELECT substr(ca_zip,1,5) ca_zip,count(*) cnt + FROM customer_address, customer + WHERE ca_address_sk = c_current_addr_sk and + c_preferred_cust_flag='Y' + group by ca_zip + having count(*) > 10)A1))A2) V1 + where ss_store_sk = s_store_sk + and ss_sold_date_sk = d_date_sk + and d_qoy = 1 and d_year = 2002 + and (substr(s_zip,1,2) = substr(V1.ca_zip,1,2)) + group by s_store_name + order by s_store_name + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-3 + Spark + Edges: + Reducer 10 <- Map 13 (PARTITION-LEVEL SORT, 586), Map 9 (PARTITION-LEVEL SORT, 586) + Reducer 11 <- Reducer 10 (GROUP, 349) + Reducer 12 <- Reducer 11 (GROUP, 59) + Reducer 7 <- Map 6 (GROUP, 159) + Reducer 8 <- Reducer 12 (GROUP, 109), Reducer 7 (GROUP, 109) +#### A masked pattern was here #### + Vertices: + Map 13 + Map Operator Tree: + TableScan + alias: customer + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((c_preferred_cust_flag = 'Y') and c_current_addr_sk is not null) (type: boolean) + Statistics: Num rows: 40000000 Data size: 34400807926 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_current_addr_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 40000000 Data size: 34400807926 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: 34400807926 Basic stats: COMPLETE Column stats: NONE + Map 6 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((substr(ca_zip, 1, 5)) IN ('89436', '30868', '65085', '22977', '83927', '77557', '58429', '40697', '80614', '10502', '32779', '91137', '61265', '98294', '17921', '18427', '21203', '59362', '87291', '84093', '21505', '17184', '10866', '67898', '25797', '28055', '18377', '80332', '74535', '21757', '29742', '90885', '29898', '17819', '40811', '25990', '47513', '89531', '91068', '10391', '18846', '99223', '82637', '41368', '83658', '86199', '81625', '26696', '89338', '88425', '32200', '81427', '19053', '77471', '36610', '99823', '43276', '41249', '48584', '83550', '82276', '18842', '78890', '14090', '38123', '40936', '34425', '19850', '43286', '80072', '79188', '54191', '11395', '50497', '84861', '90733', '21068', '57666', '37119', '25004', '57835', '70067', '62878', '95806', '19303', '18840', '19124', '29785', '16737', '16022', '49613', '89977', '68310', '60069', '98360', '48649', '39050', '41793', '25002', '27413', '39736', '47208', '16515', '94808', '5 7648', '15009', '80015', '42961', '63982', '21744', '71853', '81087', '67468', '34175', '64008', '20261', '11201', '51799', '48043', '45645', '61163', '48375', '36447', '57042', '21218', '41100', '89951', '22745', '35851', '83326', '61125', '78298', '80752', '49858', '52940', '96976', '63792', '11376', '53582', '18717', '90226', '50530', '94203', '99447', '27670', '96577', '57856', '56372', '16165', '23427', '54561', '28806', '44439', '22926', '30123', '61451', '92397', '56979', '92309', '70873', '13355', '21801', '46346', '37562', '56458', '28286', '47306', '99555', '69399', '26234', '47546', '49661', '88601', '35943', '39936', '25632', '24611', '44166', '56648', '30379', '59785', '11110', '14329', '93815', '52226', '71381', '13842', '25612', '63294', '14664', '21077', '82626', '18799', '60915', '81020', '56447', '76619', '11433', '13414', '42548', '92713', '70467', '30884', '47484', '16072', '38936', '13036', '88376', '45539', '35901', '19506', '65690', '73957', '71850', '49231', '14276', '20005', '18384', '76615', '11635', '38177', '55607', '41369', '95447', '58581', '58149', '91946', '33790', '76232', '75692', '95464', '22246', '51061', '56692', '53121', '77209', '15482', '10688', '14868', '45907', '73520', '72666', '25734', '17959', '24677', '66446', '94627', '53535', '15560', '41967', '69297', '11929', '59403', '33283', '52232', '57350', '43933', '40921', '36635', '10827', '71286', '19736', '80619', '25251', '95042', '15526', '36496', '55854', '49124', '81980', '35375', '49157', '63512', '28944', '14946', '36503', '54010', '18767', '23969', '43905', '66979', '33113', '21286', '58471', '59080', '13395', '79144', '70373', '67031', '38360', '26705', '50906', '52406', '26066', '73146', '15884', '31897', '30045', '61068', '45550', '92454', '13376', '14354', '19770', '22928', '97790', '50723', '46081', '30202', '14410', '20223', '88500', '67298', '13261', '14172', '81410', '93578', '83583', '46047', '94167', '82564', '21156', '15799', '86709', '37931', '74703' , '83103', '23054', '70470', '72008', '49247', '91911', '69998', '20961', '70070', '63197', '54853', '88191', '91830', '49521', '19454', '81450', '89091', '62378', '25683', '61869', '51744', '36580', '85778', '36871', '48121', '28810', '83712', '45486', '67393', '26935', '42393', '20132', '55349', '86057', '21309', '80218', '10094', '11357', '48819', '39734', '40758', '30432', '21204', '29467', '30214', '61024', '55307', '74621', '11622', '68908', '33032', '52868', '99194', '99900', '84936', '69036', '99149', '45013', '32895', '59004', '32322', '14933', '32936', '33562', '72550', '27385', '58049', '58200', '16808', '21360', '32961', '18586', '79307', '15492') and substr(substr(ca_zip, 1, 5), 1, 2) is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: substr(ca_zip, 1, 5) (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 20000000 Data size: 20297597642 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: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Map 9 + 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 and substr(substr(ca_zip, 1, 5), 1, 2) 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_zip (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) + 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 + Statistics: Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 44000000 Data size: 44654715780 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: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 11 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 > 10) (type: boolean) + Statistics: Num rows: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: substr(_col0, 1, 5) (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 7333333 Data size: 7442452291 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: 7333333 Data size: 7442452291 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 12 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 3666666 Data size: 3721225638 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13666666 Data size: 13870024459 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: 13666666 Data size: 13870024459 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 7 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10000000 Data size: 10148798821 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 13666666 Data size: 13870024459 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: 13666666 Data size: 13870024459 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 8 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 6833333 Data size: 6935012229 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 = 2) (type: boolean) + Statistics: Num rows: 1 Data size: 1014 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 1014 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 substr(_col0, 1, 2) (type: string) + 1 substr(_col2, 1, 2) (type: string) + + Stage: Stage-2 + 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_store_sk is not null and substr(s_zip, 1, 2) is not null) (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int), s_store_name (type: string), s_zip (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 substr(_col0, 1, 2) (type: string) + 1 substr(_col2, 1, 2) (type: string) + outputColumnNames: _col1, _col2 + input vertices: + 0 Reducer 8 + Statistics: Num rows: 1874 Data size: 3581903 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col1 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 5 (PARTITION-LEVEL SORT, 398) + Reducer 3 <- Reducer 2 (GROUP, 481) + Reducer 4 <- Reducer 3 (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 5 + 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 = 1) and (d_year = 2002) 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 + 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 _col1 (type: int) + outputColumnNames: _col2, _col8 + 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: _col8 (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 + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: decimal(17,2)) + Reducer 3 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: decimal(17,2)) + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 348477374 Data size: 30742775095 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 +