http://git-wip-us.apache.org/repos/asf/hive/blob/09b6f9a3/ql/src/test/results/clientpositive/perf/query43.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query43.q.out b/ql/src/test/results/clientpositive/perf/query43.q.out new file mode 100644 index 0000000..4e738e6 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query43.q.out @@ -0,0 +1,118 @@ +PREHOOK: query: explain select s_store_name, s_store_id, sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales from date_dim, store_sales, store where date_dim.d_date_sk = store_sales.ss_sold_date_sk and store.s_store_sk = store_sales.ss_store_sk and s_gmt_offset = -6 and d_year = 1998 group by s_store_name, s_store_id order by s_store_name, s_store_id,sun_sales,mon_sales,tue_sales,wed_sales,thu_sales,fri_sales,sat_sales limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select s_store_name, s_store_id, sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales from date_dim, store_sales, store where date_dim.d_date_sk = store_sales.ss_sold_date_sk and store.s_store_sk = store_sales.ss_store_sk and s_gmt_offset = -6 and d_year = 1998 group by s_store_name, s_store_id order by s_store_name, s_store_id,sun_sales,mon_sales,tue_sales,wed_sales,thu_sales,fri_sales,sat_sales limit 100 +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) +Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 5 + File Output Operator [FS_28] + compressed:false + Statistics:Num rows: 100 Data size: 111900 Basic stats: COMPLETE Column stats: NONE + table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} + Limit [LIM_27] + Number of rows:100 + Statistics:Num rows: 100 Data size: 111900 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_26] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + | Statistics:Num rows: 22096 Data size: 24726006 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_25] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) + sort order:+++++++++ + Statistics:Num rows: 22096 Data size: 24726006 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_23] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)","sum(VALUE._col2)","sum(VALUE._col3)","sum(VALUE._col4)","sum(VALUE._col5)","sum(VALUE._col6)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + | Statistics:Num rows: 22096 Data size: 24726006 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_22] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: decimal(17,2)), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2)), _col8 (type: decimal(17,2)) + Group By Operator [GBY_21] + aggregations:["sum(_col2)","sum(_col3)","sum(_col4)","sum(_col5)","sum(_col6)","sum(_col7)","sum(_col8)"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_19] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"] + Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_38] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col4 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col2","_col5","_col7","_col8"] + | Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + | Reduce Output Operator [RS_17] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string), _col2 (type: string) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_36] + | predicate:((s_gmt_offset = -6) and s_store_sk is not null) (type: boolean) + | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:store + | Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col4 (type: int) + Map-reduce partition columns:_col4 (type: int) + sort order:+ + Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: string), _col5 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_37] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col2","_col4","_col5"] + | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_10] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col2 (type: string) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col2"] + | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_34] + | 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 + | TableScan [TS_0] + | alias:date_dim + | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + |<-Map 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_12] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: decimal(7,2)) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator [FIL_35] + predicate:(ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + TableScan [TS_3] + alias:store_sales + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE +
http://git-wip-us.apache.org/repos/asf/hive/blob/09b6f9a3/ql/src/test/results/clientpositive/perf/query45.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query45.q.out b/ql/src/test/results/clientpositive/perf/query45.q.out new file mode 100644 index 0000000..dd14ac4 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query45.q.out @@ -0,0 +1,210 @@ +PREHOOK: query: explain select ca_zip, ca_county, sum(ws_sales_price) from web_sales JOIN customer ON web_sales.ws_bill_customer_sk = customer.c_customer_sk JOIN customer_address ON customer.c_current_addr_sk = customer_address.ca_address_sk JOIN date_dim ON web_sales.ws_sold_date_sk = date_dim.d_date_sk JOIN item ON web_sales.ws_item_sk = item.i_item_sk where ( item.i_item_id in (select i_item_id from item i2 where i2.i_item_sk in (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) ) ) and d_qoy = 2 and d_year = 2000 group by ca_zip, ca_county order by ca_zip, ca_county limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select ca_zip, ca_county, sum(ws_sales_price) from web_sales JOIN customer ON web_sales.ws_bill_customer_sk = customer.c_customer_sk JOIN customer_address ON customer.c_current_addr_sk = customer_address.ca_address_sk JOIN date_dim ON web_sales.ws_sold_date_sk = date_dim.d_date_sk JOIN item ON web_sales.ws_item_sk = item.i_item_sk where ( item.i_item_id in (select i_item_id from item i2 where i2.i_item_sk in (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) ) ) and d_qoy = 2 and d_year = 2000 group by ca_zip, ca_county order by ca_zip, ca_county limit 100 +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Map 9 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Reducer 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 7 + File Output Operator [FS_54] + compressed:false + Statistics:Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} + Limit [LIM_53] + Number of rows:100 + Statistics:Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_52] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_51] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: decimal(17,2)) + Select Operator [SEL_50] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_49] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_48] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: decimal(17,2)) + Group By Operator [GBY_47] + aggregations:["sum(_col3)"] + keys:_col7 (type: string), _col8 (type: string) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_46] + outputColumnNames:["_col7","_col8","_col3"] + Statistics:Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_82] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col3","_col7","_col8"] + | Statistics:Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 12 [SIMPLE_EDGE] + | Reduce Output Operator [RS_44] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + | Merge Join Operator [MERGEJOIN_81] + | | condition map:[{"":"Left Semi Join 0 to 1"}] + | | keys:{"0":"_col1 (type: string)","1":"_col0 (type: string)"} + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + | |<-Map 11 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_21] + | | key expressions:_col1 (type: string) + | | Map-reduce partition columns:_col1 (type: string) + | | sort order:+ + | | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col0 (type: int) + | | Select Operator [SEL_14] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_76] + | | predicate:(i_item_sk is not null and i_item_id is not null) (type: boolean) + | | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_12] + | | alias:item + | | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | |<-Map 13 [SIMPLE_EDGE] + | Reduce Output Operator [RS_23] + | key expressions:_col0 (type: string) + | Map-reduce partition columns:_col0 (type: string) + | sort order:+ + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_19] + | keys:_col0 (type: string) + | outputColumnNames:["_col0"] + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_17] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_77] + | predicate:((i_item_sk) IN (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) and i_item_id is not null) (type: boolean) + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_15] + | alias:item + | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_42] + key expressions:_col1 (type: int) + Map-reduce partition columns:_col1 (type: int) + sort order:+ + Statistics:Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: decimal(7,2)), _col7 (type: string), _col8 (type: string) + Merge Join Operator [MERGEJOIN_80] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col3","_col7","_col8"] + | Statistics:Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_39] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_11] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_75] + | predicate:(((d_qoy = 2) and (d_year = 2000)) and d_date_sk is not null) (type: boolean) + | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_9] + | alias:date_dim + | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col3 (type: decimal(7,2)), _col7 (type: string), _col8 (type: string) + Merge Join Operator [MERGEJOIN_79] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col5 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col1","_col3","_col7","_col8"] + | Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_34] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string), _col2 (type: string) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_74] + | predicate:ca_address_sk is not null (type: boolean) + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:customer_address + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_32] + key expressions:_col5 (type: int) + Map-reduce partition columns:_col5 (type: int) + sort order:+ + Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col1 (type: int), _col3 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_78] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col1","_col3","_col5"] + | Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_27] + | key expressions:_col2 (type: int) + | Map-reduce partition columns:_col2 (type: int) + | sort order:+ + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | value expressions:_col0 (type: int), _col1 (type: int), _col3 (type: decimal(7,2)) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | Filter Operator [FIL_72] + | predicate:((ws_bill_customer_sk is not null and ws_sold_date_sk is not null) and ws_item_sk is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | TableScan [TS_0] + | alias:web_sales + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int) + Select Operator [SEL_5] + outputColumnNames:["_col0","_col1"] + Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_73] + predicate:(c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) + Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_3] + alias:customer + Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + http://git-wip-us.apache.org/repos/asf/hive/blob/09b6f9a3/ql/src/test/results/clientpositive/perf/query46.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query46.q.out b/ql/src/test/results/clientpositive/perf/query46.q.out new file mode 100644 index 0000000..5d11fd7 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query46.q.out @@ -0,0 +1,241 @@ +PREHOOK: query: explain select c_last_name ,c_first_name ,ca_city ,bought_city ,ss_ticket_number ,amt,profit from (select ss_ticket_number ,ss_customer_sk ,ca_city bought_city ,sum(ss_coupon_amt) amt ,sum(ss_net_profit) profit 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 (household_demographics.hd_dep_count = 4 or household_demographics.hd_vehicle_count= 2) and date_dim.d_dow in (6,0) and date_dim.d_year in (1998,1998+1,1998+2) and store.s_city in ('Rosedale','Bethlehem','Clinton','Clifton','Springfield') group by ss_ticket_number,ss_customer_sk,ss_addr_sk,ca_city) dn,customer,customer_address current_addr where dn.ss_customer_sk = customer.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 ,c_first_name ,ca_city ,bought_city ,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 ,amt,profit from (select ss_ticket_number ,ss_customer_sk ,ca_city bought_city ,sum(ss_coupon_amt) amt ,sum(ss_net_profit) profit 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 (household_demographics.hd_dep_count = 4 or household_demographics.hd_vehicle_count= 2) and date_dim.d_dow in (6,0) and date_dim.d_year in (1998,1998+1,1998+2) and store.s_city in ('Rosedale','Bethlehem','Clinton','Clifton','Springfield') group by ss_ticket_number,ss_customer_sk,ss_addr_sk,ca_city) dn,customer,customer_address current_addr where dn.ss_customer_sk = customer.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 ,c_first_name ,ca_city ,bought_city ,ss_ticket_number limit 100 +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 3 <- Map 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 12 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 13 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Map 14 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE) +Reducer 8 <- Map 15 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:100 + Stage-1 + Reducer 9 + File Output Operator [FS_62] + compressed:false + Statistics:Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} + Limit [LIM_61] + Number of rows:100 + Statistics:Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_60] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + | Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_59] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int) + sort order:+++++ + Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + value expressions:_col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)) + Select Operator [SEL_58] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"] + Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_90] + predicate:(_col10 <> _col2) (type: boolean) + Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_103] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col6 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col2","_col3","_col4","_col7","_col8","_col10"] + | Statistics:Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE + |<-Map 15 [SIMPLE_EDGE] + | Reduce Output Operator [RS_55] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_46] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_97] + | predicate:ca_address_sk is not null (type: boolean) + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_44] + | alias:customer_address + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_53] + key expressions:_col6 (type: int) + Map-reduce partition columns:_col6 (type: int) + sort order:+ + Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col7 (type: string), _col8 (type: string) + Merge Join Operator [MERGEJOIN_102] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col2","_col3","_col4","_col6","_col7","_col8"] + | Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + |<-Map 14 [SIMPLE_EDGE] + | Reduce Output Operator [RS_50] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: int), _col2 (type: string), _col3 (type: string) + | Select Operator [SEL_43] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_96] + | predicate:(c_customer_sk is not null and c_current_addr_sk is not null) (type: boolean) + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_41] + | alias:customer + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_48] + key expressions:_col1 (type: int) + Map-reduce partition columns:_col1 (type: int) + sort order:+ + Statistics:Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + Select Operator [SEL_39] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + Statistics:Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_38] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_37] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + Map-reduce partition columns:_col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string) + sort order:++++ + Statistics:Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)) + Group By Operator [GBY_36] + aggregations:["sum(_col6)","sum(_col7)"] + keys:_col1 (type: int), _col3 (type: int), _col5 (type: int), _col17 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_35] + outputColumnNames:["_col1","_col3","_col5","_col17","_col6","_col7"] + Statistics:Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_101] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col3 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col3","_col5","_col6","_col7","_col17"] + | Statistics:Num rows: 44000000 Data size: 44654715780 Basic stats: COMPLETE Column stats: NONE + |<-Map 13 [SIMPLE_EDGE] + | Reduce Output Operator [RS_33] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_14] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_95] + | predicate:ca_address_sk is not null (type: boolean) + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_12] + | alias:customer_address + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_31] + key expressions:_col3 (type: int) + Map-reduce partition columns:_col3 (type: int) + sort order:+ + Statistics:Num rows: 24305 Data size: 27199223 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_100] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col3","_col5","_col6","_col7"] + | Statistics:Num rows: 24305 Data size: 27199223 Basic stats: COMPLETE Column stats: NONE + |<-Map 12 [SIMPLE_EDGE] + | Reduce Output Operator [RS_28] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_11] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_94] + | predicate:(((hd_dep_count = 4) or (hd_vehicle_count = 2)) and hd_demo_sk is not null) (type: boolean) + | Statistics:Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_9] + | alias:household_demographics + | Statistics:Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_26] + key expressions:_col2 (type: int) + Map-reduce partition columns:_col2 (type: int) + sort order:+ + Statistics:Num rows: 22096 Data size: 24726566 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col3 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_99] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col4 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col2","_col3","_col5","_col6","_col7"] + | Statistics:Num rows: 22096 Data size: 24726566 Basic stats: COMPLETE Column stats: NONE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_23] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_8] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_93] + | predicate:((s_city) IN ('Rosedale', 'Bethlehem', 'Clinton', 'Clifton', 'Springfield') and s_store_sk is not null) (type: boolean) + | Statistics:Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:store + | Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + key expressions:_col4 (type: int) + Map-reduce partition columns:_col4 (type: int) + sort order:+ + Statistics:Num rows: 20088 Data size: 22478696 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: int), _col3 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_98] + | 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: 20088 Data size: 22478696 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_16] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL 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)) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | Filter Operator [FIL_91] + | predicate:((((ss_sold_date_sk is not null and ss_store_sk is not null) and ss_hdemo_sk is not null) and ss_addr_sk is not null) and ss_customer_sk is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | TableScan [TS_0] + | alias:store_sales + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_92] + predicate:(((d_year) IN (1998, 1999, 2000) and (d_dow) IN (6, 0)) and d_date_sk is not null) (type: boolean) + Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_3] + alias:date_dim + Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + http://git-wip-us.apache.org/repos/asf/hive/blob/09b6f9a3/ql/src/test/results/clientpositive/perf/query48.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query48.q.out b/ql/src/test/results/clientpositive/perf/query48.q.out new file mode 100644 index 0000000..d15d578 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query48.q.out @@ -0,0 +1,160 @@ +PREHOOK: query: explain select sum (ss_quantity) from store_sales, store, customer_demographics, customer_address, date_dim where store.s_store_sk = store_sales.ss_store_sk and store_sales.ss_sold_date_sk = date_dim.d_date_sk and d_year = 1998 and ( ( customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and cd_marital_status = 'M' and cd_education_status = '4 yr Degree' and ss_sales_price between 100.00 and 150.00 ) or ( customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and cd_marital_status = 'M' and cd_education_status = '4 yr Degree' and ss_sales_price between 50.00 and 100.00 ) or ( customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and cd_marital_status = 'M' and cd_education_status = '4 yr Degree' and ss_sales_price between 150.00 and 200.00 ) ) and ( ( store_sales.ss_addr_sk = customer_address.ca_address_sk and ca_country = 'United States' and ca_state in ('KY', 'GA', 'NM') and ss_net_profit between 0 and 2000 ) or (store_sales.ss_addr_sk = customer_add ress.ca_address_sk and ca_country = 'United States' and ca_state in ('MT', 'OR', 'IN') and ss_net_profit between 150 and 3000 ) or (store_sales.ss_addr_sk = customer_address.ca_address_sk and ca_country = 'United States' and ca_state in ('WI', 'MO', 'WV') and ss_net_profit between 50 and 25000 ) ) +PREHOOK: type: QUERY +POSTHOOK: query: explain select sum (ss_quantity) from store_sales, store, customer_demographics, customer_address, date_dim where store.s_store_sk = store_sales.ss_store_sk and store_sales.ss_sold_date_sk = date_dim.d_date_sk and d_year = 1998 and ( ( customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and cd_marital_status = 'M' and cd_education_status = '4 yr Degree' and ss_sales_price between 100.00 and 150.00 ) or ( customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and cd_marital_status = 'M' and cd_education_status = '4 yr Degree' and ss_sales_price between 50.00 and 100.00 ) or ( customer_demographics.cd_demo_sk = store_sales.ss_cdemo_sk and cd_marital_status = 'M' and cd_education_status = '4 yr Degree' and ss_sales_price between 150.00 and 200.00 ) ) and ( ( store_sales.ss_addr_sk = customer_address.ca_address_sk and ca_country = 'United States' and ca_state in ('KY', 'GA', 'NM') and ss_net_profit between 0 and 2000 ) or (store_sales.ss_addr_sk = customer_ad dress.ca_address_sk and ca_country = 'United States' and ca_state in ('MT', 'OR', 'IN') and ss_net_profit between 150 and 3000 ) or (store_sales.ss_addr_sk = customer_address.ca_address_sk and ca_country = 'United States' and ca_state in ('WI', 'MO', 'WV') and ss_net_profit between 50 and 25000 ) ) +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE) +Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) +Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) +Reducer 5 <- Map 10 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 5 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 6 + File Output Operator [FS_42] + compressed:false + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table:{"input format:":"org.apache.hadoop.mapred.TextInputFormat","output format:":"org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat","serde:":"org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe"} + Group By Operator [GBY_40] + | aggregations:["sum(VALUE._col0)"] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_39] + sort order: + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: bigint) + Group By Operator [GBY_38] + aggregations:["sum(_col4)"] + outputColumnNames:["_col0"] + Statistics:Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_66] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col4"] + | Statistics:Num rows: 18150000 Data size: 18420070657 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_35] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_31] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_62] + | 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 + | TableScan [TS_29] + | alias:date_dim + | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_33] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 16500000 Data size: 16745518417 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: int) + Select Operator [SEL_28] + outputColumnNames:["_col0","_col4"] + Statistics:Num rows: 16500000 Data size: 16745518417 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_57] + predicate:(((_col12) IN ('KY', 'GA', 'NM') and _col6 BETWEEN 0 AND 2000) or ((_col12) IN ('MT', 'OR', 'IN') and _col6 BETWEEN 150 AND 3000) or ((_col12) IN ('WI', 'MO', 'WV') and _col6 BETWEEN 50 AND 25000)) (type: boolean) + Statistics:Num rows: 16500000 Data size: 16745518417 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_65] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col4","_col6","_col12"] + | Statistics:Num rows: 22000000 Data size: 22327357890 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_11] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_61] + | predicate:((((ca_state) IN ('KY', 'GA', 'NM') or (ca_state) IN ('MT', 'OR', 'IN') or (ca_state) IN ('WI', 'MO', 'WV')) and (ca_country = 'United States')) and ca_address_sk is not null) (type: boolean) + | Statistics:Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_9] + | alias:customer_address + | Statistics:Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_23] + key expressions:_col2 (type: int) + Map-reduce partition columns:_col2 (type: int) + sort order:+ + Statistics:Num rows: 5445 Data size: 1972040 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_64] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col2","_col4","_col6"] + | Statistics:Num rows: 5445 Data size: 1972040 Basic stats: COMPLETE Column stats: NONE + |<-Map 8 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 4950 Data size: 1792764 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_8] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 4950 Data size: 1792764 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_60] + | predicate:(((cd_education_status = '4 yr Degree') and (cd_marital_status = 'M')) and cd_demo_sk is not null) (type: boolean) + | Statistics:Num rows: 4950 Data size: 1792764 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:customer_demographics + | Statistics:Num rows: 19800 Data size: 7171059 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col1 (type: int) + Map-reduce partition columns:_col1 (type: int) + sort order:+ + Statistics:Num rows: 1874 Data size: 3581903 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_63] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col3 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col1","_col2","_col4","_col6"] + | Statistics:Num rows: 1874 Data size: 3581903 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | key expressions:_col3 (type: int) + | Map-reduce partition columns:_col3 (type: int) + | sort order:+ + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | value expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: int), _col6 (type: decimal(7,2)) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col6"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | Filter Operator [FIL_58] + | predicate:((((((ss_net_profit BETWEEN 0 AND 2000 or ss_net_profit BETWEEN 150 AND 3000 or ss_net_profit BETWEEN 50 AND 25000) and ss_store_sk is not null) and (ss_sales_price BETWEEN 100.0 AND 150.0 or ss_sales_price BETWEEN 50.0 AND 100.0 or ss_sales_price BETWEEN 150.0 AND 200.0)) and ss_cdemo_sk is not null) and ss_addr_sk is not null) and ss_sold_date_sk is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | TableScan [TS_0] + | alias:store_sales + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 7 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_59] + predicate:s_store_sk is not null (type: boolean) + Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_3] + alias:store + Statistics:Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE +
