http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query6.q.out b/ql/src/test/results/clientpositive/perf/spark/query6.q.out new file mode 100644 index 0000000..126cf9e --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query6.q.out @@ -0,0 +1,459 @@ +Warning: Map Join MAPJOIN[85][bigTable=?] in task 'Stage-1:MAPRED' is a cross product +PREHOOK: query: explain +select a.ca_state state, count(*) cnt + from customer_address a + ,customer c + ,store_sales s + ,date_dim d + ,item i + where a.ca_address_sk = c.c_current_addr_sk + and c.c_customer_sk = s.ss_customer_sk + and s.ss_sold_date_sk = d.d_date_sk + and s.ss_item_sk = i.i_item_sk + and d.d_month_seq = + (select distinct (d_month_seq) + from date_dim + where d_year = 2000 + and d_moy = 2 ) + and i.i_current_price > 1.2 * + (select avg(j.i_current_price) + from item j + where j.i_category = i.i_category) + group by a.ca_state + having count(*) >= 10 + order by cnt + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.ca_state state, count(*) cnt + from customer_address a + ,customer c + ,store_sales s + ,date_dim d + ,item i + where a.ca_address_sk = c.c_current_addr_sk + and c.c_customer_sk = s.ss_customer_sk + and s.ss_sold_date_sk = d.d_date_sk + and s.ss_item_sk = i.i_item_sk + and d.d_month_seq = + (select distinct (d_month_seq) + from date_dim + where d_year = 2000 + and d_moy = 2 ) + and i.i_current_price > 1.2 * + (select avg(j.i_current_price) + from item j + where j.i_category = i.i_category) + group by a.ca_state + having count(*) >= 10 + order by cnt + 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 + Edges: + Reducer 18 <- Map 17 (GROUP, 2) + Reducer 19 <- Reducer 18 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 17 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_moy = 2) and (d_year = 2000)) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_month_seq (type: int) + outputColumnNames: d_month_seq + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: d_month_seq (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Reducer 18 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 9131 Data size: 10217589 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) + Reducer 19 + 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 + Filter Operator + predicate: (sq_count_check(_col0) <= 1) (type: boolean) + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-1 + Spark + Edges: + Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 855), Map 13 (PARTITION-LEVEL SORT, 855) + Reducer 15 <- Map 14 (GROUP, 6) + Reducer 16 <- Map 20 (PARTITION-LEVEL SORT, 8), Reducer 15 (PARTITION-LEVEL SORT, 8) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 9 (PARTITION-LEVEL SORT, 2) + Reducer 3 <- Map 10 (PARTITION-LEVEL SORT, 398), Reducer 2 (PARTITION-LEVEL SORT, 398) + Reducer 4 <- Reducer 12 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009) + Reducer 5 <- Reducer 16 (PARTITION-LEVEL SORT, 483), Reducer 4 (PARTITION-LEVEL SORT, 483) + Reducer 6 <- Reducer 5 (GROUP, 529) + Reducer 7 <- Reducer 6 (SORT, 1) + Reducer 9 <- Map 8 (GROUP, 2) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: d + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (d_date_sk is not null and d_month_seq is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_month_seq (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 10 + Map Operator Tree: + TableScan + alias: s + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int) + Map 11 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (c_current_addr_sk is not null and c_customer_sk is not null) (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_current_addr_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int) + sort order: + + Map-reduce partition columns: _col1 (type: int) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 13 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ca_address_sk is not null (type: boolean) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int), ca_state (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Map 14 + Map Operator Tree: + TableScan + alias: j + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: i_category is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: avg(i_current_price) + keys: i_category (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>) + Map 20 + Map Operator Tree: + TableScan + alias: i + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: i_item_sk is not null (type: boolean) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_current_price (type: decimal(7,2)), i_category (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: decimal(7,2)) + 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_moy = 2) and (d_year = 2000) and d_month_seq is not null) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_month_seq (type: int) + outputColumnNames: d_month_seq + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: d_month_seq (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Reducer 12 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col3 + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: string) + Reducer 15 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Group By Operator + aggregations: avg(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: decimal(11,6)), true (type: boolean), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + input vertices: + 1 Reducer 19 + Statistics: Num rows: 231000 Data size: 333859228 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 231000 Data size: 333859228 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: decimal(11,6)), _col1 (type: boolean) + Reducer 16 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col2 (type: string) + outputColumnNames: _col0, _col1, _col4, _col5 + Statistics: Num rows: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col5 > (1.2 * CASE WHEN (_col1 is null) THEN (null) ELSE (_col0) END)) (type: boolean) + Statistics: Num rows: 169400 Data size: 243305506 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col4 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 169400 Data size: 243305506 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: 169400 Data size: 243305506 Basic stats: COMPLETE Column stats: NONE + 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 + Statistics: Num rows: 80353 Data size: 89916016 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: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col5 (type: int) + sort order: + + Map-reduce partition columns: _col5 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: int) + Reducer 4 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col5 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col4, _col9 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col4 (type: int) + sort order: + + Map-reduce partition columns: _col4 (type: int) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col9 (type: string) + Reducer 5 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col4 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col9 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) + Reducer 6 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col1 >= 10) (type: boolean) + Statistics: Num rows: 127775039 Data size: 11272351038 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: bigint) + sort order: + + Statistics: Num rows: 127775039 Data size: 11272351038 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: string) + Reducer 7 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: bigint) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 127775039 Data size: 11272351038 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 9 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 9131 Data size: 10217589 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: 9131 Data size: 10217589 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-0 + Fetch Operator + limit: 100 + Processor Tree: + ListSink +
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query60.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query60.q.out b/ql/src/test/results/clientpositive/perf/spark/query60.q.out new file mode 100644 index 0000000..6f0c9cd --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query60.q.out @@ -0,0 +1,691 @@ +PREHOOK: query: explain +with ss as ( + select + i_item_id,sum(ss_ext_sales_price) total_sales + from + store_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from + item +where i_category in ('Children')) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 9 + and ss_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_item_id), + cs as ( + select + i_item_id,sum(cs_ext_sales_price) total_sales + from + catalog_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from + item +where i_category in ('Children')) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 9 + and cs_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_item_id), + ws as ( + select + i_item_id,sum(ws_ext_sales_price) total_sales + from + web_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from + item +where i_category in ('Children')) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 9 + and ws_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_item_id) + select + i_item_id +,sum(total_sales) total_sales + from (select * from ss + union all + select * from cs + union all + select * from ws) tmp1 + group by i_item_id + order by i_item_id + ,total_sales + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +with ss as ( + select + i_item_id,sum(ss_ext_sales_price) total_sales + from + store_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from + item +where i_category in ('Children')) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 9 + and ss_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_item_id), + cs as ( + select + i_item_id,sum(cs_ext_sales_price) total_sales + from + catalog_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from + item +where i_category in ('Children')) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 9 + and cs_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_item_id), + ws as ( + select + i_item_id,sum(ws_ext_sales_price) total_sales + from + web_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from + item +where i_category in ('Children')) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 1999 + and d_moy = 9 + and ws_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -6 + group by i_item_id) + select + i_item_id +,sum(total_sales) total_sales + from (select * from ss + union all + select * from cs + union all + select * from ws) tmp1 + group by i_item_id + order by i_item_id + ,total_sales + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 398), Map 9 (PARTITION-LEVEL SORT, 398) + Reducer 11 <- Map 13 (PARTITION-LEVEL SORT, 596), Reducer 10 (PARTITION-LEVEL SORT, 596) + Reducer 15 <- Map 1 (PARTITION-LEVEL SORT, 7), Reducer 19 (PARTITION-LEVEL SORT, 7) + Reducer 16 <- Reducer 15 (PARTITION-LEVEL SORT, 375), Reducer 22 (PARTITION-LEVEL SORT, 375) + Reducer 17 <- Reducer 16 (GROUP, 406) + Reducer 19 <- Map 18 (GROUP, 3) + Reducer 21 <- Map 12 (PARTITION-LEVEL SORT, 305), Map 20 (PARTITION-LEVEL SORT, 305) + Reducer 22 <- Map 13 (PARTITION-LEVEL SORT, 494), Reducer 21 (PARTITION-LEVEL SORT, 494) + Reducer 26 <- Map 25 (PARTITION-LEVEL SORT, 7), Reducer 30 (PARTITION-LEVEL SORT, 7) + Reducer 27 <- Reducer 26 (PARTITION-LEVEL SORT, 191), Reducer 33 (PARTITION-LEVEL SORT, 191) + Reducer 28 <- Reducer 27 (GROUP, 204) + Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 487), Reducer 15 (PARTITION-LEVEL SORT, 487) + Reducer 30 <- Map 18 (GROUP, 3) + Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 34 (PARTITION-LEVEL SORT, 154) + Reducer 33 <- Map 35 (PARTITION-LEVEL SORT, 327), Reducer 32 (PARTITION-LEVEL SORT, 327) + Reducer 4 <- Reducer 3 (GROUP, 529) + Reducer 5 <- Reducer 17 (GROUP, 569), Reducer 28 (GROUP, 569), Reducer 4 (GROUP, 569) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_item_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 12 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Map 13 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Map 18 + 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 ('Children') and i_item_id is not null) (type: boolean) + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_id (type: string) + outputColumnNames: i_item_id + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: i_item_id (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE + Map 20 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (cs_bill_addr_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cs_sold_date_sk (type: int), cs_bill_addr_sk (type: int), cs_item_sk (type: int), cs_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 287989836 Data size: 38999608952 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Map 25 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (i_item_id is not null and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_item_id (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) + Map 31 + Map Operator Tree: + TableScan + alias: web_sales + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ws_bill_addr_sk is not null and ws_item_sk is not null and ws_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ws_sold_date_sk (type: int), ws_item_sk (type: int), ws_bill_addr_sk (type: int), ws_ext_sales_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Map 34 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_moy = 9) and (d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE + Map 35 + Map Operator Tree: + TableScan + alias: customer_address + Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((ca_gmt_offset = -6) and ca_address_sk is not null) (type: boolean) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ca_address_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE + Map 9 + Map Operator Tree: + TableScan + alias: store_sales + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ss_addr_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null) (type: boolean) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_addr_sk (type: int), ss_ext_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: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 10 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Reducer 11 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)) + Reducer 15 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 508200 Data size: 729916518 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: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 16 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col4 (type: int) + outputColumnNames: _col1, _col8 + Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 17 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: decimal(27,2)) + Reducer 19 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Reducer 21 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 316788826 Data size: 42899570777 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: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + Reducer 22 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col4, _col5 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col4 (type: int) + sort order: + + Map-reduce partition columns: _col4 (type: int) + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)) + Reducer 26 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 508200 Data size: 729916518 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: 508200 Data size: 729916518 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Reducer 27 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 28 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 95833781 Data size: 13030622757 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: decimal(27,2)) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col3 (type: int) + outputColumnNames: _col1, _col8 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col8) + keys: _col1 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: decimal(17,2)) + Reducer 30 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 115500 Data size: 165890114 Basic stats: COMPLETE Column stats: NONE + Reducer 32 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3 + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col2 (type: int) + sort order: + + Map-reduce partition columns: _col2 (type: int) + Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + Reducer 33 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col3 (type: decimal(7,2)) + outputColumnNames: _col3, _col5 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int) + sort order: + + Map-reduce partition columns: _col3 (type: int) + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + value expressions: _col5 (type: decimal(7,2)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col1) + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 670816147 Data size: 72801917426 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: decimal(27,2)) + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: decimal(27,2)) + sort order: ++ + Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: decimal(27,2)) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 335408073 Data size: 36400958658 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 10800 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: 100 + Processor Tree: + ListSink +
