http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query88.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query88.q.out b/ql/src/test/results/clientpositive/perf/spark/query88.q.out new file mode 100644 index 0000000..be44719 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query88.q.out @@ -0,0 +1,1294 @@ +Warning: Map Join MAPJOIN[251][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +PREHOOK: query: explain +select * +from + (select count(*) h8_30_to_9 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 8 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s1, + (select count(*) h9_to_9_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 9 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s2, + (select count(*) h9_30_to_10 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 9 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s3, + (select count(*) h10_to_10_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 10 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s4, + (select count(*) h10_30_to_11 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 10 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s5, + (select count(*) h11_to_11_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 11 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s6, + (select count(*) h11_30_to_12 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 11 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s7, + (select count(*) h12_to_12_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 12 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s8 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select * +from + (select count(*) h8_30_to_9 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 8 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s1, + (select count(*) h9_to_9_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 9 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s2, + (select count(*) h9_30_to_10 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 9 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s3, + (select count(*) h10_to_10_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 10 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s4, + (select count(*) h10_30_to_11 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 10 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s5, + (select count(*) h11_to_11_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 11 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s6, + (select count(*) h11_30_to_12 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 11 + and time_dim.t_minute >= 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s7, + (select count(*) h12_to_12_30 + from store_sales, household_demographics , time_dim, store + where ss_sold_time_sk = time_dim.t_time_sk + and ss_hdemo_sk = household_demographics.hd_demo_sk + and ss_store_sk = s_store_sk + and time_dim.t_hour = 12 + and time_dim.t_minute < 30 + and ((household_demographics.hd_dep_count = 3 and household_demographics.hd_vehicle_count<=3+2) or + (household_demographics.hd_dep_count = 0 and household_demographics.hd_vehicle_count<=0+2) or + (household_demographics.hd_dep_count = 1 and household_demographics.hd_vehicle_count<=1+2)) + and store.s_store_name = 'ese') s8 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-3 is a root stage + Stage-2 depends on stages: Stage-3, Stage-4, Stage-5, Stage-6, Stage-7, Stage-8, Stage-9 + Stage-10 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-10 + Stage-4 is a root stage + Stage-5 is a root stage + Stage-6 is a root stage + Stage-7 is a root stage + Stage-8 is a root stage + Stage-9 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 10 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 8 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 12) and (t_minute < 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 9 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-2 + Spark + Edges: + Reducer 12 <- Map 11 (GROUP, 1) + Reducer 17 <- Map 16 (GROUP, 1) + Reducer 22 <- Map 21 (GROUP, 1) + Reducer 27 <- Map 26 (GROUP, 1) + Reducer 32 <- Map 31 (GROUP, 1) + Reducer 37 <- Map 36 (GROUP, 1) + Reducer 7 <- Map 6 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 13 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 14 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 15 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Map 16 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 18 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 19 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 20 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Map 21 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 23 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 24 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 25 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Map 26 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 28 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 29 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 30 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Map 31 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 33 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 34 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 35 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Map 36 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 38 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 39 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 40 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Map 6 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 8 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 9 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 10 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Reducer 12 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + Reducer 17 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + Reducer 22 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + Reducer 27 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + Reducer 32 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + Reducer 37 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + Reducer 7 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + + Stage: Stage-10 + Spark +#### A masked pattern was here #### + Vertices: + Map 3 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 4 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 5 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_hdemo_sk is not null and ss_sold_time_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2 + input vertices: + 1 Map 3 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2 + input vertices: + 1 Map 4 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + input vertices: + 1 Map 5 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work + Reducer 2 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + Inner Join 0 to 3 + Inner Join 0 to 4 + Inner Join 0 to 5 + Inner Join 0 to 6 + Inner Join 0 to 7 + keys: + 0 + 1 + 2 + 3 + 4 + 5 + 6 + 7 + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + input vertices: + 1 Reducer 7 + 2 Reducer 12 + 3 Reducer 17 + 4 Reducer 22 + 5 Reducer 27 + 6 Reducer 32 + 7 Reducer 37 + Statistics: Num rows: 1 Data size: 65 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col7 (type: bigint), _col6 (type: bigint), _col5 (type: bigint), _col4 (type: bigint), _col3 (type: bigint), _col2 (type: bigint), _col1 (type: bigint) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 1 Data size: 65 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 65 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 13 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 11) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 14 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 15 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-5 + Spark +#### A masked pattern was here #### + Vertices: + Map 18 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 11) and (t_minute < 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 19 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 20 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-6 + Spark +#### A masked pattern was here #### + Vertices: + Map 23 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 10) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 24 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 25 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-7 + Spark +#### A masked pattern was here #### + Vertices: + Map 28 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 10) and (t_minute < 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 29 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 30 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-8 + Spark +#### A masked pattern was here #### + Vertices: + Map 33 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 9) and (t_minute >= 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 34 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 35 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-9 + Spark +#### A masked pattern was here #### + Vertices: + Map 38 + Map Operator Tree: + TableScan + alias: time_dim + Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((t_hour = 9) and (t_minute < 30) and t_time_sk is not null) (type: boolean) + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t_time_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 39 + Map Operator Tree: + TableScan + alias: household_demographics + Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((hd_dep_count = 3) and (hd_vehicle_count <= 5)) or ((hd_dep_count = 0) and (hd_vehicle_count <= 2)) or ((hd_dep_count = 1) and (hd_vehicle_count <= 3))) and hd_demo_sk is not null) (type: boolean) + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: hd_demo_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + Map 40 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean) + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query89.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query89.q.out b/ql/src/test/results/clientpositive/perf/spark/query89.q.out new file mode 100644 index 0000000..ca3a408 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query89.q.out @@ -0,0 +1,281 @@ +PREHOOK: query: explain +select * +from( +select i_category, i_class, i_brand, + s_store_name, s_company_name, + d_moy, + sum(ss_sales_price) sum_sales, + avg(sum(ss_sales_price)) over + (partition by i_category, i_brand, s_store_name, s_company_name) + avg_monthly_sales +from item, store_sales, date_dim, store +where ss_item_sk = i_item_sk and + ss_sold_date_sk = d_date_sk and + ss_store_sk = s_store_sk and + d_year in (2000) and + ((i_category in ('Home','Books','Electronics') and + i_class in ('wallpaper','parenting','musical') + ) + or (i_category in ('Shoes','Jewelry','Men') and + i_class in ('womens','birdal','pants') + )) +group by i_category, i_class, i_brand, + s_store_name, s_company_name, d_moy) tmp1 +where case when (avg_monthly_sales <> 0) then (abs(sum_sales - avg_monthly_sales) / avg_monthly_sales) else null end > 0.1 +order by sum_sales - avg_monthly_sales, s_store_name +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select * +from( +select i_category, i_class, i_brand, + s_store_name, s_company_name, + d_moy, + sum(ss_sales_price) sum_sales, + avg(sum(ss_sales_price)) over + (partition by i_category, i_brand, s_store_name, s_company_name) + avg_monthly_sales +from item, store_sales, date_dim, store +where ss_item_sk = i_item_sk and + ss_sold_date_sk = d_date_sk and + ss_store_sk = s_store_sk and + d_year in (2000) and + ((i_category in ('Home','Books','Electronics') and + i_class in ('wallpaper','parenting','musical') + ) + or (i_category in ('Shoes','Jewelry','Men') and + i_class in ('womens','birdal','pants') + )) +group by i_category, i_class, i_brand, + s_store_name, s_company_name, d_moy) tmp1 +where case when (avg_monthly_sales <> 0) then (abs(sum_sales - avg_monthly_sales) / avg_monthly_sales) else null end > 0.1 +order by sum_sales - avg_monthly_sales, s_store_name +limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 9 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int), s_store_name (type: string), s_company_name (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 400), Map 7 (PARTITION-LEVEL SORT, 400) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438) + Reducer 4 <- Reducer 3 (GROUP, 529) + Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 265) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_store_sk (type: int), ss_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Map 7 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((((i_category) IN ('Home', 'Books', 'Electronics') and (i_class) IN ('wallpaper', 'parenting', 'musical')) or ((i_category) IN ('Shoes', 'Jewelry', 'Men') and (i_class) IN ('womens', 'birdal', 'pants'))) and ((i_category) IN ('Home', 'Books', 'Electronics') or (i_category) IN ('Shoes', 'Jewelry', 'Men')) and ((i_class) IN ('wallpaper', 'parenting', 'musical') or (i_class) IN ('womens', 'birdal', 'pants')) and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_brand (type: string), i_class (type: string), i_category (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) + Map 8 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year) IN (2000) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 36525 Data size: 40871475 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_moy (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 36525 Data size: 40871475 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 36525 Data size: 40871475 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2, _col3, _col5, _col6, _col7 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string) + Reducer 3 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col5, _col6, _col7, _col10 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col5, _col6, _col7, _col10, _col12, _col13 + input vertices: + 1 Map 9 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col3) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col10 (type: int), _col12 (type: string), _col13 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) + sort order: ++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: int), _col4 (type: string), _col5 (type: string) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col6 (type: decimal(17,2)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: int), KEY._col4 (type: string), KEY._col5 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: string), _col1 (type: string), _col0 (type: string), _col4 (type: string), _col5 (type: string), _col3 (type: int), _col6 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) + sort order: ++++ + Map-reduce partition columns: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string) + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col5 (type: int), _col6 (type: decimal(17,2)) + Reducer 5 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: decimal(17,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string, _col2: string, _col3: string, _col4: string, _col5: int, _col6: decimal(17,2) + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: _col0 ASC NULLS FIRST, _col2 ASC NULLS FIRST, _col3 ASC NULLS FIRST, _col4 ASC NULLS FIRST + partition by: _col0, _col2, _col3, _col4 + raw input shape: + window functions: + window function definition + alias: avg_window_0 + arguments: _col6 + name: avg + window function: GenericUDAFAverageEvaluatorDecimal + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: decimal(17,2)) + outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5, _col6 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: CASE WHEN ((avg_window_0 <> 0)) THEN (((abs((_col6 - avg_window_0)) / avg_window_0) > 0.1)) ELSE (null) END (type: boolean) + Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: decimal(17,2)), avg_window_0 (type: decimal(21,6)), (_col6 - avg_window_0) (type: decimal(22,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 + Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col8 (type: decimal(22,6)), _col3 (type: string) + sort order: ++ + Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: decimal(17,2)), _col7 (type: decimal(21,6)) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), VALUE._col5 (type: decimal(17,2)), VALUE._col6 (type: decimal(21,6)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 191662559 Data size: 16908526602 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +