http://git-wip-us.apache.org/repos/asf/hive/blob/09b6f9a3/ql/src/test/results/clientpositive/perf/query34.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query34.q.out b/ql/src/test/results/clientpositive/perf/query34.q.out new file mode 100644 index 0000000..193cf4f --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query34.q.out @@ -0,0 +1,177 @@ +PREHOOK: query: explain select c_last_name ,c_first_name ,c_salutation ,c_preferred_cust_flag ,ss_ticket_number ,cnt from (select ss_ticket_number ,ss_customer_sk ,count(*) cnt from store_sales,date_dim,store,household_demographics where store_sales.ss_sold_date_sk = date_dim.d_date_sk and store_sales.ss_store_sk = store.s_store_sk and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk and (date_dim.d_dom between 1 and 3 or date_dim.d_dom between 25 and 28) and (household_demographics.hd_buy_potential = '1001-5000' or household_demographics.hd_buy_potential = '5001-10000') and household_demographics.hd_vehicle_count > 0 and (case when household_demographics.hd_vehicle_count > 0 then household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count else null end) > 1.2 and date_dim.d_year in (1998,1998+1,1998+2) and store.s_county in ('Kittitas County','Adams County','Richland County','Furnas County', 'Orange County','Appanoose County','Franklin Parish','Tehama Co unty') group by ss_ticket_number,ss_customer_sk) dn,customer where dn.ss_customer_sk = customer.c_customer_sk and cnt between 15 and 20 order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc +PREHOOK: type: QUERY +POSTHOOK: query: explain select c_last_name ,c_first_name ,c_salutation ,c_preferred_cust_flag ,ss_ticket_number ,cnt from (select ss_ticket_number ,ss_customer_sk ,count(*) cnt from store_sales,date_dim,store,household_demographics where store_sales.ss_sold_date_sk = date_dim.d_date_sk and store_sales.ss_store_sk = store.s_store_sk and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk and (date_dim.d_dom between 1 and 3 or date_dim.d_dom between 25 and 28) and (household_demographics.hd_buy_potential = '1001-5000' or household_demographics.hd_buy_potential = '5001-10000') and household_demographics.hd_vehicle_count > 0 and (case when household_demographics.hd_vehicle_count > 0 then household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count else null end) > 1.2 and date_dim.d_year in (1998,1998+1,1998+2) and store.s_county in ('Kittitas County','Adams County','Richland County','Furnas County', 'Orange County','Appanoose County','Franklin Parish','Tehama C ounty') group by ss_ticket_number,ss_customer_sk) dn,customer where dn.ss_customer_sk = customer.c_customer_sk and cnt between 15 and 20 order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +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 4 (SIMPLE_EDGE) +Reducer 6 <- Map 11 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 7 + File Output Operator [FS_45] + compressed:false + Statistics:Num rows: 88000001 Data size: 75681779077 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"} + Select Operator [SEL_44] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_43] + key expressions:_col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + sort order:+++- + Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: int), _col5 (type: bigint) + Select Operator [SEL_42] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_69] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col2","_col4","_col5","_col6","_col7"] + | Statistics:Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_40] + | 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: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) + | Select Operator [SEL_36] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_65] + | predicate:c_customer_sk is not null (type: boolean) + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_34] + | alias:customer + | Statistics:Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col1 (type: int) + Map-reduce partition columns:_col1 (type: int) + sort order:+ + Statistics:Num rows: 12153 Data size: 13599611 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: bigint) + Select Operator [SEL_31] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 12153 Data size: 13599611 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_60] + predicate:_col2 BETWEEN 15 AND 20 (type: boolean) + Statistics:Num rows: 12153 Data size: 13599611 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_30] + | aggregations:["count(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: int) + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 24306 Data size: 27199223 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: int), _col1 (type: int) + Map-reduce partition columns:_col0 (type: int), _col1 (type: int) + sort order:++ + Statistics:Num rows: 48612 Data size: 54398446 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: bigint) + Group By Operator [GBY_28] + aggregations:["count()"] + keys:_col1 (type: int), _col4 (type: int) + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 48612 Data size: 54398446 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_68] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col4"] + | Statistics:Num rows: 48612 Data size: 54398446 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 800 Data size: 85600 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_11] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 800 Data size: 85600 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_64] + | predicate:((((CASE WHEN ((hd_vehicle_count > 0)) THEN ((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count))) ELSE (null) END > 1.2) and ((hd_buy_potential = '1001-5000') or (hd_buy_potential = '5001-10000'))) and (hd_vehicle_count > 0)) and hd_demo_sk is not null) (type: boolean) + | Statistics:Num rows: 800 Data size: 85600 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_23] + key expressions:_col2 (type: int) + Map-reduce partition columns:_col2 (type: int) + sort order:+ + Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col4 (type: int) + Merge Join Operator [MERGEJOIN_67] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col3 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col2","_col4"] + | Statistics:Num rows: 44193 Data size: 49453132 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | 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_63] + | predicate:((s_county) IN ('Kittitas County', 'Adams County', 'Richland County', 'Furnas County', 'Orange County', 'Appanoose County', 'Franklin Parish', 'Tehama County') 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_18] + key expressions:_col3 (type: int) + Map-reduce partition columns:_col3 (type: int) + sort order:+ + Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE + value expressions:_col1 (type: int), _col2 (type: int), _col4 (type: int) + Merge Join Operator [MERGEJOIN_66] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 40176 Data size: 44957392 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | 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) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | Filter Operator [FIL_61] + | predicate:(((ss_sold_date_sk is not null and ss_store_sk is not null) and ss_hdemo_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 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + 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_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_62] + predicate:(((d_year) IN (1998, 1999, 2000) and (d_dom BETWEEN 1 AND 3 or d_dom BETWEEN 25 AND 28)) and d_date_sk is not null) (type: boolean) + Statistics:Num rows: 36524 Data size: 40870356 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/query39.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query39.q.out b/ql/src/test/results/clientpositive/perf/query39.q.out new file mode 100644 index 0000000..0ad62cc --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query39.q.out @@ -0,0 +1,313 @@ +PREHOOK: query: explain with inv as (select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stdev,mean, case mean when 0 then null else stdev/mean end cov from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean from inventory ,item ,warehouse ,date_dim where inv_item_sk = i_item_sk and inv_warehouse_sk = w_warehouse_sk and inv_date_sk = d_date_sk and d_year =1999 group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo where case mean when 0 then 0 else stdev/mean end > 1) select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov from inv inv1,inv inv2 where inv1.i_item_sk = inv2.i_item_sk and inv1.w_warehouse_sk = inv2.w_warehouse_sk and inv1.d_moy=3 and inv2.d_moy=3+1 order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov +PREHOOK: type: QUERY +POSTHOOK: query: explain with inv as (select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stdev,mean, case mean when 0 then null else stdev/mean end cov from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean from inventory ,item ,warehouse ,date_dim where inv_item_sk = i_item_sk and inv_warehouse_sk = w_warehouse_sk and inv_date_sk = d_date_sk and d_year =1999 group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo where case mean when 0 then 0 else stdev/mean end > 1) select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov from inv inv1,inv inv2 where inv1.i_item_sk = inv2.i_item_sk and inv1.w_warehouse_sk = inv2.w_warehouse_sk and inv1.d_moy=3 and inv2.d_moy=3+1 order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +Reducer 12 <- Map 11 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 13 <- Map 17 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE) +Reducer 14 <- Map 18 (SIMPLE_EDGE), Reducer 13 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (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 4 (SIMPLE_EDGE) +Reducer 6 <- Reducer 15 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (SIMPLE_EDGE) + +Stage-0 + Fetch Operator + limit:-1 + Stage-1 + Reducer 7 + File Output Operator [FS_76] + compressed:false + Statistics:Num rows: 112735 Data size: 161919824 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"} + Select Operator [SEL_75] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + | Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_74] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: double), _col7 (type: int), _col8 (type: double), _col9 (type: double) + sort order:++++++++ + Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE + value expressions:_col5 (type: int), _col6 (type: int) + Select Operator [SEL_73] + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9"] + Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_121] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int), _col1 (type: int)","1":"_col2 (type: int), _col1 (type: int)"} + | outputColumnNames:["_col1","_col2","_col3","_col4","_col5","_col7","_col8","_col9","_col10","_col11"] + | Statistics:Num rows: 112735 Data size: 161919824 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 15 [SIMPLE_EDGE] + | Reduce Output Operator [RS_71] + | key expressions:_col2 (type: int), _col1 (type: int) + | Map-reduce partition columns:_col2 (type: int), _col1 (type: int) + | sort order:++ + | Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: int), _col4 (type: double), _col5 (type: double) + | Select Operator [SEL_65] + | outputColumnNames:["_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_108] + | predicate:(CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1.0) (type: boolean) + | Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_113] + | outputColumnNames:["_col0","_col1","_col3","_col4","_col5"] + | Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE + | Group By Operator [GBY_64] + | | aggregations:["stddev_samp(VALUE._col0)","avg(VALUE._col1)"] + | | keys:KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: int) + | | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | | Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 14 [SIMPLE_EDGE] + | Reduce Output Operator [RS_63] + | key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) + | Map-reduce partition columns:_col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) + | sort order:++++ + | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,input:int>) + | Group By Operator [GBY_62] + | aggregations:["stddev_samp(_col3)","avg(_col3)"] + | keys:_col4 (type: int), _col5 (type: int), _col6 (type: string), _col9 (type: int) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_61] + | outputColumnNames:["_col4","_col5","_col6","_col9","_col3"] + | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + | Merge Join Operator [MERGEJOIN_120] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | | outputColumnNames:["_col3","_col4","_col5","_col6"] + | | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + | |<-Map 18 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_59] + | | 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_45] + | | outputColumnNames:["_col0"] + | | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_112] + | | predicate:(((d_moy = 4) and d_date_sk is not null) and (d_year = 1999)) (type: boolean) + | | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_43] + | | alias:date_dim + | | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 13 [SIMPLE_EDGE] + | Reduce Output Operator [RS_57] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: string) + | Merge Join Operator [MERGEJOIN_119] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | | outputColumnNames:["_col0","_col3","_col4","_col5","_col6"] + | | Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE + | |<-Map 17 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_54] + | | key expressions:_col0 (type: int) + | | Map-reduce partition columns:_col0 (type: int) + | | sort order:+ + | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | | value expressions:_col1 (type: string) + | | Select Operator [SEL_42] + | | outputColumnNames:["_col0","_col1"] + | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | | Filter Operator [FIL_111] + | | predicate:w_warehouse_sk is not null (type: boolean) + | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | | TableScan [TS_40] + | | alias:warehouse + | | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | |<-Reducer 12 [SIMPLE_EDGE] + | Reduce Output Operator [RS_52] + | key expressions:_col2 (type: int) + | Map-reduce partition columns:_col2 (type: int) + | sort order:+ + | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col0 (type: int), _col3 (type: int), _col4 (type: int) + | Merge Join Operator [MERGEJOIN_118] + | | condition map:[{"":"Inner Join 0 to 1"}] + | | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | | outputColumnNames:["_col0","_col2","_col3","_col4"] + | | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + | |<-Map 11 [SIMPLE_EDGE] + | | Reduce Output Operator [RS_47] + | | key expressions:_col1 (type: int) + | | Map-reduce partition columns:_col1 (type: int) + | | sort order:+ + | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | | value expressions:_col0 (type: int), _col2 (type: int), _col3 (type: int) + | | Select Operator [SEL_36] + | | outputColumnNames:["_col0","_col1","_col2","_col3"] + | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | | Filter Operator [FIL_109] + | | predicate:((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean) + | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | | TableScan [TS_34] + | | alias:inventory + | | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | |<-Map 16 [SIMPLE_EDGE] + | Reduce Output Operator [RS_49] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_39] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_110] + | predicate:i_item_sk is not null (type: boolean) + | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_37] + | alias:item + | Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_69] + key expressions:_col2 (type: int), _col1 (type: int) + Map-reduce partition columns:_col2 (type: int), _col1 (type: int) + sort order:++ + Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: int), _col4 (type: double), _col5 (type: double) + Select Operator [SEL_31] + outputColumnNames:["_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_103] + predicate:(CASE (_col5) WHEN (0) THEN (0) ELSE ((_col4 / _col5)) END > 1.0) (type: boolean) + Statistics:Num rows: 102487 Data size: 147199837 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_114] + outputColumnNames:["_col0","_col1","_col3","_col4","_col5"] + Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_30] + | aggregations:["stddev_samp(VALUE._col0)","avg(VALUE._col1)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: int) + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + | Statistics:Num rows: 307461 Data size: 441599512 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_29] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) + Map-reduce partition columns:_col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int) + sort order:++++ + Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,input:int>) + Group By Operator [GBY_28] + aggregations:["stddev_samp(_col3)","avg(_col3)"] + keys:_col4 (type: int), _col5 (type: int), _col6 (type: string), _col9 (type: int) + outputColumnNames:["_col0","_col1","_col2","_col3","_col4","_col5"] + Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_27] + outputColumnNames:["_col4","_col5","_col6","_col9","_col3"] + Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_117] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col3","_col4","_col5","_col6"] + | Statistics:Num rows: 614922 Data size: 883199024 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | 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_107] + | predicate:(((d_moy = 3) and d_date_sk is not null) and (d_year = 1999)) (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_23] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: string) + Merge Join Operator [MERGEJOIN_116] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col3","_col4","_col5","_col6"] + | Statistics:Num rows: 559020 Data size: 802908187 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_106] + | predicate:w_warehouse_sk is not null (type: boolean) + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:warehouse + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 2 [SIMPLE_EDGE] + Reduce Output Operator [RS_18] + key expressions:_col2 (type: int) + Map-reduce partition columns:_col2 (type: int) + sort order:+ + Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col3 (type: int), _col4 (type: int) + Merge Join Operator [MERGEJOIN_115] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col2","_col3","_col4"] + | Statistics:Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_13] + | key expressions:_col1 (type: int) + | Map-reduce partition columns:_col1 (type: int) + | sort order:+ + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | value expressions:_col0 (type: int), _col2 (type: int), _col3 (type: int) + | 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_104] + | predicate:((inv_item_sk is not null and inv_warehouse_sk is not null) and inv_date_sk is not null) (type: boolean) + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | TableScan [TS_0] + | alias:inventory + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_5] + outputColumnNames:["_col0"] + Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator [FIL_105] + predicate:i_item_sk is not null (type: boolean) + Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + TableScan [TS_3] + alias:item + Statistics:Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + +PREHOOK: query: with inv as (select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stdev,mean, case mean when 0 then null else stdev/mean end cov from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean from inventory ,item ,warehouse ,date_dim where inv_item_sk = i_item_sk and inv_warehouse_sk = w_warehouse_sk and inv_date_sk = d_date_sk and d_year =1999 group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo where case mean when 0 then 0 else stdev/mean end > 1) select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov from inv inv1,inv inv2 where inv1.i_item_sk = inv2.i_item_sk and inv1.w_warehouse_sk = inv2.w_warehouse_sk and inv1.d_moy=3 and inv2.d_moy=3+1 and inv1.cov > 1.5 order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@inventory +PREHOOK: Input: default@item +PREHOOK: Input: default@warehouse +#### A masked pattern was here #### +POSTHOOK: query: with inv as (select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stdev,mean, case mean when 0 then null else stdev/mean end cov from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean from inventory ,item ,warehouse ,date_dim where inv_item_sk = i_item_sk and inv_warehouse_sk = w_warehouse_sk and inv_date_sk = d_date_sk and d_year =1999 group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo where case mean when 0 then 0 else stdev/mean end > 1) select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov from inv inv1,inv inv2 where inv1.i_item_sk = inv2.i_item_sk and inv1.w_warehouse_sk = inv2.w_warehouse_sk and inv1.d_moy=3 and inv2.d_moy=3+1 and inv1.cov > 1.5 order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov ,inv2.d_moy,inv2.mean, inv2.cov +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@inventory +POSTHOOK: Input: default@item +POSTHOOK: Input: default@warehouse +#### A masked pattern was here #### http://git-wip-us.apache.org/repos/asf/hive/blob/09b6f9a3/ql/src/test/results/clientpositive/perf/query40.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query40.q.out b/ql/src/test/results/clientpositive/perf/query40.q.out new file mode 100644 index 0000000..08c3e49 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query40.q.out @@ -0,0 +1,177 @@ +PREHOOK: query: explain select w_state ,i_item_id ,sum(case when (cast(d_date as date) < cast ('1998-04-08' as date)) then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_before ,sum(case when (cast(d_date as date) >= cast ('1998-04-08' as date)) then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_after from catalog_sales left outer join catalog_returns on (catalog_sales.cs_order_number = catalog_returns.cr_order_number and catalog_sales.cs_item_sk = catalog_returns.cr_item_sk) ,warehouse ,item ,date_dim where i_current_price between 0.99 and 1.49 and item.i_item_sk = catalog_sales.cs_item_sk and catalog_sales.cs_warehouse_sk = warehouse.w_warehouse_sk and catalog_sales.cs_sold_date_sk = date_dim.d_date_sk and date_dim.d_date between '1998-03-09' and '1998-05-08' group by w_state,i_item_id order by w_state,i_item_id limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select w_state ,i_item_id ,sum(case when (cast(d_date as date) < cast ('1998-04-08' as date)) then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_before ,sum(case when (cast(d_date as date) >= cast ('1998-04-08' as date)) then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_after from catalog_sales left outer join catalog_returns on (catalog_sales.cs_order_number = catalog_returns.cr_order_number and catalog_sales.cs_item_sk = catalog_returns.cr_item_sk) ,warehouse ,item ,date_dim where i_current_price between 0.99 and 1.49 and item.i_item_sk = catalog_sales.cs_item_sk and catalog_sales.cs_warehouse_sk = warehouse.w_warehouse_sk and catalog_sales.cs_sold_date_sk = date_dim.d_date_sk and date_dim.d_date between '1998-03-09' and '1998-05-08' group by w_state,i_item_id order by w_state,i_item_id limit 100 +POSTHOOK: type: QUERY +Plan optimized by CBO. + +Vertex dependency in root stage +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 <- Map 11 (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_41] + compressed:false + Statistics:Num rows: 100 Data size: 143600 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_40] + Number of rows:100 + Statistics:Num rows: 100 Data size: 143600 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_39] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 139755 Data size: 200727046 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 6 [SIMPLE_EDGE] + Reduce Output Operator [RS_38] + key expressions:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 139755 Data size: 200727046 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: decimal(23,2)), _col3 (type: decimal(23,2)) + Group By Operator [GBY_36] + | aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] + | keys:KEY._col0 (type: string), KEY._col1 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 139755 Data size: 200727046 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 5 [SIMPLE_EDGE] + Reduce Output Operator [RS_35] + key expressions:_col0 (type: string), _col1 (type: string) + Map-reduce partition columns:_col0 (type: string), _col1 (type: string) + sort order:++ + Statistics:Num rows: 279510 Data size: 401454092 Basic stats: COMPLETE Column stats: NONE + value expressions:_col2 (type: decimal(23,2)), _col3 (type: decimal(23,2)) + Group By Operator [GBY_34] + aggregations:["sum(_col2)","sum(_col3)"] + keys:_col0 (type: string), _col1 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 279510 Data size: 401454092 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_32] + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 279510 Data size: 401454092 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_63] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col4","_col7","_col9","_col11","_col14"] + | Statistics:Num rows: 279510 Data size: 401454092 Basic stats: COMPLETE Column stats: NONE + |<-Map 11 [SIMPLE_EDGE] + | Reduce Output Operator [RS_30] + | 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:_col1 (type: string) + | Select Operator [SEL_13] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_59] + | predicate:(d_date BETWEEN '1998-03-09' AND '1998-05-08' and d_date_sk is not null) (type: boolean) + | Statistics:Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_11] + | alias:date_dim + | Statistics:Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_28] + key expressions:_col0 (type: int) + Map-reduce partition columns:_col0 (type: int) + sort order:+ + Statistics:Num rows: 254100 Data size: 364958258 Basic stats: COMPLETE Column stats: NONE + value expressions:_col4 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string), _col11 (type: string) + Merge Join Operator [MERGEJOIN_62] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col2 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col4","_col7","_col9","_col11"] + | Statistics:Num rows: 254100 Data size: 364958258 Basic stats: COMPLETE Column stats: NONE + |<-Map 10 [SIMPLE_EDGE] + | Reduce Output Operator [RS_25] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_10] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_58] + | predicate:(i_current_price BETWEEN 0.99 AND 1.49 and i_item_sk is not null) (type: boolean) + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_8] + | alias:item + | Statistics:Num rows: 462000 Data size: 663560457 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: 29 Data size: 30582 Basic stats: COMPLETE Column stats: NONE + value expressions:_col0 (type: int), _col4 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col9 (type: string) + Merge Join Operator [MERGEJOIN_61] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col1 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col0","_col2","_col4","_col7","_col9"] + | Statistics:Num rows: 29 Data size: 30582 Basic stats: COMPLETE Column stats: NONE + |<-Map 9 [SIMPLE_EDGE] + | Reduce Output Operator [RS_20] + | key expressions:_col0 (type: int) + | Map-reduce partition columns:_col0 (type: int) + | sort order:+ + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: string) + | Select Operator [SEL_7] + | outputColumnNames:["_col0","_col1"] + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_57] + | predicate:w_warehouse_sk is not null (type: boolean) + | Statistics:Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_5] + | alias:warehouse + | Statistics:Num rows: 27 Data size: 27802 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: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions:_col0 (type: int), _col2 (type: int), _col4 (type: decimal(7,2)), _col7 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_60] + | condition map:[{"":"Left Outer Join0 to 1"}] + | keys:{"0":"_col3 (type: int), _col2 (type: int)","1":"_col1 (type: int), _col0 (type: int)"} + | outputColumnNames:["_col0","_col1","_col2","_col4","_col7"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 1 [SIMPLE_EDGE] + | Reduce Output Operator [RS_14] + | key expressions:_col3 (type: int), _col2 (type: int) + | Map-reduce partition columns:_col3 (type: int), _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), _col4 (type: decimal(7,2)) + | Select Operator [SEL_2] + | outputColumnNames:["_col0","_col1","_col2","_col3","_col4"] + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + | Filter Operator [FIL_55] + | predicate:((cs_warehouse_sk is not null and cs_item_sk is not null) and cs_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:catalog_sales + | Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + |<-Map 8 [SIMPLE_EDGE] + Reduce Output Operator [RS_15] + key expressions:_col1 (type: int), _col0 (type: int) + Map-reduce partition columns:_col1 (type: int), _col0 (type: int) + sort order:++ + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + value expressions:_col2 (type: decimal(7,2)) + Select Operator [SEL_4] + outputColumnNames:["_col0","_col1","_col2"] + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + Filter Operator [FIL_56] + predicate:cr_item_sk is not null (type: boolean) + Statistics:Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE + TableScan [TS_3] + alias:catalog_returns + 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/query42.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/query42.q.out b/ql/src/test/results/clientpositive/perf/query42.q.out new file mode 100644 index 0000000..a3264c7 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/query42.q.out @@ -0,0 +1,117 @@ +PREHOOK: query: explain select dt.d_year ,item.i_category_id ,item.i_category ,sum(ss_ext_sales_price) as s from date_dim dt ,store_sales ,item where dt.d_date_sk = store_sales.ss_sold_date_sk and store_sales.ss_item_sk = item.i_item_sk and item.i_manager_id = 1 and dt.d_moy=12 and dt.d_year=1998 group by dt.d_year ,item.i_category_id ,item.i_category order by s desc,dt.d_year ,item.i_category_id ,item.i_category limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain select dt.d_year ,item.i_category_id ,item.i_category ,sum(ss_ext_sales_price) as s from date_dim dt ,store_sales ,item where dt.d_date_sk = store_sales.ss_sold_date_sk and store_sales.ss_item_sk = item.i_item_sk and item.i_manager_id = 1 and dt.d_moy=12 and dt.d_year=1998 group by dt.d_year ,item.i_category_id ,item.i_category order by s desc,dt.d_year ,item.i_category_id ,item.i_category 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_27] + compressed:false + Statistics:Num rows: 100 Data size: 143600 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_26] + Number of rows:100 + Statistics:Num rows: 100 Data size: 143600 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_25] + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 127050 Data size: 182479129 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 4 [SIMPLE_EDGE] + Reduce Output Operator [RS_24] + key expressions:_col3 (type: decimal(17,2)), _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order:-+++ + Statistics:Num rows: 127050 Data size: 182479129 Basic stats: COMPLETE Column stats: NONE + Group By Operator [GBY_22] + | aggregations:["sum(VALUE._col0)"] + | keys:KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) + | outputColumnNames:["_col0","_col1","_col2","_col3"] + | Statistics:Num rows: 127050 Data size: 182479129 Basic stats: COMPLETE Column stats: NONE + |<-Reducer 3 [SIMPLE_EDGE] + Reduce Output Operator [RS_21] + key expressions:_col0 (type: int), _col1 (type: int), _col2 (type: string) + Map-reduce partition columns:_col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order:+++ + Statistics:Num rows: 254100 Data size: 364958258 Basic stats: COMPLETE Column stats: NONE + value expressions:_col3 (type: decimal(17,2)) + Group By Operator [GBY_20] + aggregations:["sum(_col5)"] + keys:_col1 (type: int), _col7 (type: int), _col8 (type: string) + outputColumnNames:["_col0","_col1","_col2","_col3"] + Statistics:Num rows: 254100 Data size: 364958258 Basic stats: COMPLETE Column stats: NONE + Select Operator [SEL_19] + outputColumnNames:["_col1","_col7","_col8","_col5"] + Statistics:Num rows: 254100 Data size: 364958258 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator [MERGEJOIN_37] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col4 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col5","_col7","_col8"] + | Statistics:Num rows: 254100 Data size: 364958258 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: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | value expressions:_col1 (type: int), _col2 (type: string) + | Select Operator [SEL_8] + | outputColumnNames:["_col0","_col1","_col2"] + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_35] + | predicate:((i_manager_id = 1) and i_item_sk is not null) (type: boolean) + | Statistics:Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_6] + | alias:item + | Statistics:Num rows: 462000 Data size: 663560457 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: 20088 Data size: 22478696 Basic stats: COMPLETE Column stats: NONE + value expressions:_col5 (type: decimal(7,2)) + Merge Join Operator [MERGEJOIN_36] + | condition map:[{"":"Inner Join 0 to 1"}] + | keys:{"0":"_col0 (type: int)","1":"_col0 (type: int)"} + | outputColumnNames:["_col4","_col5"] + | Statistics:Num rows: 20088 Data size: 22478696 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: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | Select Operator [SEL_2] + | outputColumnNames:["_col0"] + | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | Filter Operator [FIL_33] + | predicate:(((d_year = 1998) and (d_moy = 12)) and d_date_sk is not null) (type: boolean) + | Statistics:Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + | TableScan [TS_0] + | alias:dt + | 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_34] + predicate:(ss_sold_date_sk is not null and ss_item_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 +