http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query36.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query36.q.out b/ql/src/test/results/clientpositive/perf/spark/query36.q.out new file mode 100644 index 0000000..c072728 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query36.q.out @@ -0,0 +1,282 @@ +PREHOOK: query: explain +select + sum(ss_net_profit)/sum(ss_ext_sales_price) as gross_margin + ,i_category + ,i_class + ,grouping(i_category)+grouping(i_class) as lochierarchy + ,rank() over ( + partition by grouping(i_category)+grouping(i_class), + case when grouping(i_class) = 0 then i_category end + order by sum(ss_net_profit)/sum(ss_ext_sales_price) asc) as rank_within_parent + from + store_sales + ,date_dim d1 + ,item + ,store + where + d1.d_year = 1999 + and d1.d_date_sk = ss_sold_date_sk + and i_item_sk = ss_item_sk + and s_store_sk = ss_store_sk + and s_state in ('SD','FL','MI','LA', + 'MO','SC','AL','GA') + group by rollup(i_category,i_class) + order by + lochierarchy desc + ,case when lochierarchy = 0 then i_category end + ,rank_within_parent + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select + sum(ss_net_profit)/sum(ss_ext_sales_price) as gross_margin + ,i_category + ,i_class + ,grouping(i_category)+grouping(i_class) as lochierarchy + ,rank() over ( + partition by grouping(i_category)+grouping(i_class), + case when grouping(i_class) = 0 then i_category end + order by sum(ss_net_profit)/sum(ss_ext_sales_price) asc) as rank_within_parent + from + store_sales + ,date_dim d1 + ,item + ,store + where + d1.d_year = 1999 + and d1.d_date_sk = ss_sold_date_sk + and i_item_sk = ss_item_sk + and s_store_sk = ss_store_sk + and s_state in ('SD','FL','MI','LA', + 'MO','SC','AL','GA') + group by rollup(i_category,i_class) + order by + lochierarchy desc + ,case when lochierarchy = 0 then i_category end + ,rank_within_parent + limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 8 + Map Operator Tree: + TableScan + alias: store + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC', 'AL', 'GA') 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 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398) + Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 486), Reducer 2 (PARTITION-LEVEL SORT, 486) + Reducer 4 <- Reducer 3 (GROUP, 1009) + Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 793) + 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_ext_sales_price (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + 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)), _col4 (type: decimal(7,2)) + Map 7 + Map Operator Tree: + TableScan + alias: d1 + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_year = 1999) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 36524 Data size: 40870356 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: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Map 9 + Map Operator Tree: + TableScan + alias: item + 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_class (type: string), 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: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) + Reducer 2 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4 + 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 _col2 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col1, _col3, _col4 + input vertices: + 1 Map 8 + Statistics: Num rows: 696954748 Data size: 61485550191 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: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: decimal(7,2)), _col4 (type: decimal(7,2)) + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col4, _col10, _col11 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col11 (type: string), _col10 (type: string), _col4 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: sum(_col2), sum(_col3) + keys: _col0 (type: string), _col1 (type: string), 0 (type: int) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int) + Statistics: Num rows: 2299950717 Data size: 202902320028 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: sum(VALUE._col0), sum(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col2 (type: int) + outputColumnNames: _col0, _col1, _col4, _col5, _col6 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: (grouping(_col6, 1) + grouping(_col6, 0)) (type: int), CASE WHEN ((grouping(_col6, 0) = 0)) THEN (_col0) ELSE (null) END (type: string), (_col4 / _col5) (type: decimal(37,20)) + sort order: +++ + Map-reduce partition columns: (grouping(_col6, 1) + grouping(_col6, 0)) (type: int), CASE WHEN ((grouping(_col6, 0) = 0)) THEN (_col0) ELSE (null) END (type: string) + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: int) + Reducer 5 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: decimal(17,2)), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: int) + outputColumnNames: _col0, _col1, _col4, _col5, _col6 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + PTF Operator + Function definitions: + Input definition + input alias: ptf_0 + output shape: _col0: string, _col1: string, _col4: decimal(17,2), _col5: decimal(17,2), _col6: int + type: WINDOWING + Windowing table definition + input alias: ptf_1 + name: windowingtablefunction + order by: (_col4 / _col5) ASC NULLS FIRST + partition by: (grouping(_col6, 1) + grouping(_col6, 0)), CASE WHEN ((grouping(_col6, 0) = 0)) THEN (_col0) ELSE (null) END + raw input shape: + window functions: + window function definition + alias: rank_window_0 + arguments: (_col4 / _col5) + name: rank + window function: GenericUDAFRankEvaluator + window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) + isPivotResult: true + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (_col4 / _col5) (type: decimal(37,20)), _col0 (type: string), _col1 (type: string), (grouping(_col6, 1) + grouping(_col6, 0)) (type: int), rank_window_0 (type: int), CASE WHEN (((grouping(_col6, 1) + grouping(_col6, 0)) = 0)) THEN (_col0) ELSE (null) END (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col3 (type: int), _col5 (type: string), _col4 (type: int) + sort order: -++ + Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: decimal(37,20)), _col1 (type: string), _col2 (type: string) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: VALUE._col0 (type: decimal(37,20)), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1149975358 Data size: 101451159969 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 +
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query37.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query37.q.out b/ql/src/test/results/clientpositive/perf/spark/query37.q.out new file mode 100644 index 0000000..d8bff81 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query37.q.out @@ -0,0 +1,192 @@ +PREHOOK: query: explain +select i_item_id + ,i_item_desc + ,i_current_price + from item, inventory, date_dim, catalog_sales + where i_current_price between 22 and 22 + 30 + and inv_item_sk = i_item_sk + and d_date_sk=inv_date_sk + and d_date between cast('2001-06-02' as date) and (cast('2001-06-02' as date) + 60 days) + and i_manufact_id in (678,964,918,849) + and inv_quantity_on_hand between 100 and 500 + and cs_item_sk = i_item_sk + group by i_item_id,i_item_desc,i_current_price + order by i_item_id + limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select i_item_id + ,i_item_desc + ,i_current_price + from item, inventory, date_dim, catalog_sales + where i_current_price between 22 and 22 + 30 + and inv_item_sk = i_item_sk + and d_date_sk=inv_date_sk + and d_date between cast('2001-06-02' as date) and (cast('2001-06-02' as date) + 60 days) + and i_manufact_id in (678,964,918,849) + and inv_quantity_on_hand between 100 and 500 + and cs_item_sk = i_item_sk + group by i_item_id,i_item_desc,i_current_price + order by i_item_id + 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 7 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 2001-06-02 00:00:00.0 AND 2001-08-01 00:00:00.0 and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 8116 Data size: 9081804 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 + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 306), Map 5 (PARTITION-LEVEL SORT, 306), Map 6 (PARTITION-LEVEL SORT, 306) + Reducer 3 <- Reducer 2 (GROUP, 671) + Reducer 4 <- Reducer 3 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: catalog_sales + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: cs_item_sk is not null (type: boolean) + Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: cs_item_sk (type: int) + outputColumnNames: _col0 + 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 + Map 5 + Map Operator Tree: + TableScan + alias: item + Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((i_manufact_id) IN (678, 964, 918, 849) and i_current_price BETWEEN 22 AND 52 and i_item_sk is not null) (type: boolean) + Statistics: Num rows: 25666 Data size: 36863512 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: i_item_sk (type: int), i_item_id (type: string), i_item_desc (type: string), i_current_price (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 25666 Data size: 36863512 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: 25666 Data size: 36863512 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: decimal(7,2)) + Map 6 + Map Operator Tree: + TableScan + alias: inventory + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_quantity_on_hand BETWEEN 100 AND 500) (type: boolean) + Statistics: Num rows: 4176000 Data size: 65980122 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: inv_date_sk (type: int), inv_item_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 4176000 Data size: 65980122 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 + input vertices: + 1 Map 7 + Statistics: Num rows: 4593600 Data size: 72578135 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: 4593600 Data size: 72578135 Basic stats: COMPLETE Column stats: NONE + Local Work: + Map Reduce Local Work + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col1 (type: int) + outputColumnNames: _col2, _col3, _col4 + Statistics: Num rows: 633577652 Data size: 85799141554 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 633577652 Data size: 85799141554 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: decimal(7,2)) + Statistics: Num rows: 633577652 Data size: 85799141554 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + Reducer 3 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: decimal(7,2)) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col1 (type: string), _col2 (type: decimal(7,2)) + Reducer 4 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: decimal(7,2)) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 100 Data size: 13500 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 + http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query38.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query38.q.out b/ql/src/test/results/clientpositive/perf/spark/query38.q.out new file mode 100644 index 0000000..b9af964 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query38.q.out @@ -0,0 +1,458 @@ +PREHOOK: query: explain +select count(*) from ( + select distinct c_last_name, c_first_name, d_date + from store_sales, date_dim, customer + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_customer_sk = customer.c_customer_sk + and d_month_seq between 1212 and 1212 + 11 + intersect + select distinct c_last_name, c_first_name, d_date + from catalog_sales, date_dim, customer + where catalog_sales.cs_sold_date_sk = date_dim.d_date_sk + and catalog_sales.cs_bill_customer_sk = customer.c_customer_sk + and d_month_seq between 1212 and 1212 + 11 + intersect + select distinct c_last_name, c_first_name, d_date + from web_sales, date_dim, customer + where web_sales.ws_sold_date_sk = date_dim.d_date_sk + and web_sales.ws_bill_customer_sk = customer.c_customer_sk + and d_month_seq between 1212 and 1212 + 11 +) hot_cust +limit 100 +PREHOOK: type: QUERY +POSTHOOK: query: explain +select count(*) from ( + select distinct c_last_name, c_first_name, d_date + from store_sales, date_dim, customer + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_customer_sk = customer.c_customer_sk + and d_month_seq between 1212 and 1212 + 11 + intersect + select distinct c_last_name, c_first_name, d_date + from catalog_sales, date_dim, customer + where catalog_sales.cs_sold_date_sk = date_dim.d_date_sk + and catalog_sales.cs_bill_customer_sk = customer.c_customer_sk + and d_month_seq between 1212 and 1212 + 11 + intersect + select distinct c_last_name, c_first_name, d_date + from web_sales, date_dim, customer + where web_sales.ws_sold_date_sk = date_dim.d_date_sk + and web_sales.ws_bill_customer_sk = customer.c_customer_sk + and d_month_seq between 1212 and 1212 + 11 +) hot_cust +limit 100 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-4 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-2 + Spark +#### A masked pattern was here #### + Vertices: + Map 6 + Map Operator Tree: + TableScan + alias: date_dim + 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 BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8116 Data size: 9081804 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 + + Stage: Stage-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 11 + Map Operator Tree: + TableScan + alias: date_dim + 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 BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8116 Data size: 9081804 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 + + Stage: Stage-4 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: date_dim + 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 BETWEEN 1212 AND 1223) (type: boolean) + Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: d_date_sk (type: int), d_date (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 8116 Data size: 9081804 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 + + Stage: Stage-1 + Spark + Edges: + Reducer 10 <- Reducer 9 (GROUP PARTITION-LEVEL SORT, 369) + Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 706), Map 17 (PARTITION-LEVEL SORT, 706) + Reducer 15 <- Reducer 14 (GROUP PARTITION-LEVEL SORT, 186) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 975), Map 12 (PARTITION-LEVEL SORT, 975) + Reducer 3 <- Reducer 2 (GROUP PARTITION-LEVEL SORT, 481) + Reducer 4 <- Reducer 10 (GROUP, 259), Reducer 15 (GROUP, 259), Reducer 3 (GROUP, 259) + Reducer 5 <- Reducer 4 (GROUP, 1) + Reducer 9 <- Map 12 (PARTITION-LEVEL SORT, 873), Map 8 (PARTITION-LEVEL SORT, 873) +#### 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_customer_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_customer_sk (type: int) + outputColumnNames: _col0, _col1 + 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, _col3 + input vertices: + 1 Map 6 + Statistics: Num rows: 633595212 Data size: 55895953508 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: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: string) + Local Work: + Map Reduce Local Work + Map 12 + Map Operator Tree: + TableScan + alias: customer + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) + Map 13 + 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_customer_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_bill_customer_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 144002668 Data size: 19580198212 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, _col3 + input vertices: + 1 Map 16 + Statistics: Num rows: 158402938 Data size: 21538218500 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: string) + Local Work: + Map Reduce Local Work + Map 17 + Map Operator Tree: + TableScan + alias: customer + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: c_customer_sk is not null (type: boolean) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string), _col2 (type: string) + Map 8 + 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_customer_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_customer_sk (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 287989836 Data size: 38999608952 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, _col3 + input vertices: + 1 Map 11 + 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: _col3 (type: string) + Local Work: + Map Reduce Local Work + Reducer 10 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 174233858 Data size: 23594764438 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 87116929 Data size: 11797382219 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col3) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Reducer 14 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col6, _col7 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE + Reducer 15 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 43560808 Data size: 5923010113 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col3) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col6, _col7 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 348477374 Data size: 30742775095 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col1 (type: string), _col0 (type: string), _col2 (type: string) + mode: complete + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 174238687 Data size: 15371387547 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count(_col3) + keys: _col0 (type: string), _col1 (type: string), _col2 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 304916424 Data size: 33091779879 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: bigint) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 152458212 Data size: 16545889939 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col3 (type: bigint) + outputColumnNames: _col3 + Statistics: Num rows: 152458212 Data size: 16545889939 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (_col3 = 3) (type: boolean) + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1 Data size: 108 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + TopN Hash Memory Usage: 0.1 + value expressions: _col0 (type: bigint) + Reducer 5 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 100 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 16 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: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col3, _col6, _col7 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col7 (type: string), _col6 (type: string), _col3 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 348467716 Data size: 47189528877 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/query39.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query39.q.out b/ql/src/test/results/clientpositive/perf/spark/query39.q.out new file mode 100644 index 0000000..d63d8e2 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/spark/query39.q.out @@ -0,0 +1,473 @@ +PREHOOK: query: explain +with inv as +(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stdev,mean, case mean when 0 then null else stdev/mean end cov + from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean + from inventory + ,item + ,warehouse + ,date_dim + where inv_item_sk = i_item_sk + and inv_warehouse_sk = w_warehouse_sk + and inv_date_sk = d_date_sk + and d_year =1999 + group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo + where case mean when 0 then 0 else stdev/mean end > 1) +select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov + ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov +from inv inv1,inv inv2 +where inv1.i_item_sk = inv2.i_item_sk + and inv1.w_warehouse_sk = inv2.w_warehouse_sk + and inv1.d_moy=4 + and inv2.d_moy=4+1 +order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov + ,inv2.d_moy,inv2.mean, inv2.cov +PREHOOK: type: QUERY +POSTHOOK: query: explain +with inv as +(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stdev,mean, case mean when 0 then null else stdev/mean end cov + from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean + from inventory + ,item + ,warehouse + ,date_dim + where inv_item_sk = i_item_sk + and inv_warehouse_sk = w_warehouse_sk + and inv_date_sk = d_date_sk + and d_year =1999 + group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo + where case mean when 0 then 0 else stdev/mean end > 1) +select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov + ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov +from inv inv1,inv inv2 +where inv1.i_item_sk = inv2.i_item_sk + and inv1.w_warehouse_sk = inv2.w_warehouse_sk + and inv1.d_moy=4 + and inv2.d_moy=4+1 +order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov + ,inv2.d_moy,inv2.mean, inv2.cov +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-2 is a root stage + Stage-3 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-3 + 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: warehouse + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: w_warehouse_sk is not null (type: boolean) + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 27802 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-3 + Spark +#### A masked pattern was here #### + Vertices: + Map 16 + Map Operator Tree: + TableScan + alias: warehouse + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: w_warehouse_sk is not null (type: boolean) + Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 27 Data size: 27802 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 11 <- Map 10 (PARTITION-LEVEL SORT, 5), Map 14 (PARTITION-LEVEL SORT, 5) + Reducer 12 <- Map 15 (PARTITION-LEVEL SORT, 11), Reducer 11 (PARTITION-LEVEL SORT, 11) + Reducer 13 <- Reducer 12 (GROUP, 7) + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 5), Map 7 (PARTITION-LEVEL SORT, 5) + Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 11), Reducer 2 (PARTITION-LEVEL SORT, 11) + Reducer 4 <- Reducer 3 (GROUP, 7) + Reducer 5 <- Reducer 13 (PARTITION-LEVEL SORT, 4), Reducer 4 (PARTITION-LEVEL SORT, 4) + Reducer 6 <- Reducer 5 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: inventory + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 37584000 Data size: 593821104 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: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Map 10 + Map Operator Tree: + TableScan + alias: inventory + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean) + Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 37584000 Data size: 593821104 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: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int) + Map 14 + 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 = 5) 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 15 + Map Operator Tree: + TableScan + alias: item + 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) + outputColumnNames: _col0 + Statistics: Num rows: 462000 Data size: 663560457 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Map 7 + Map Operator Tree: + TableScan + alias: date_dim + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((d_moy = 4) 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 8 + Map Operator Tree: + TableScan + alias: item + 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) + outputColumnNames: _col0 + Statistics: Num rows: 462000 Data size: 663560457 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE + Reducer 11 + 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: 41342400 Data size: 653203228 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: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: int) + Reducer 12 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col7 + Statistics: Num rows: 45476640 Data size: 718523566 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, _col7, _col8, _col9 + input vertices: + 1 Map 16 + Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: stddev_samp(_col3), avg(_col3) + keys: _col8 (type: int), _col7 (type: int), _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:int>) + Reducer 13 + Reduce Operator Tree: + Group By Operator + aggregations: stddev_samp(VALUE._col0), avg(VALUE._col1) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col3 / _col4) > 1.0)) END (type: boolean) + Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col3 / _col4)) END (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: double), _col4 (type: double) + Reducer 2 + 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: 41342400 Data size: 653203228 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: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col3 (type: int) + Reducer 3 + Local Work: + Map Reduce Local Work + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col3, _col7 + Statistics: Num rows: 45476640 Data size: 718523566 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, _col7, _col8, _col9 + input vertices: + 1 Map 9 + Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: stddev_samp(_col3), avg(_col3) + keys: _col8 (type: int), _col7 (type: int), _col9 (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: string) + Statistics: Num rows: 50024305 Data size: 790375939 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:int>) + Reducer 4 + Reduce Operator Tree: + Group By Operator + aggregations: stddev_samp(VALUE._col0), avg(VALUE._col1) + keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col3 (type: double), _col4 (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 25012152 Data size: 395187961 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: CASE WHEN ((_col4 = 0.0)) THEN (false) ELSE (((_col3 / _col4) > 1.0)) END (type: boolean) + Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: int), _col4 (type: double), CASE WHEN ((_col4 = 0.0)) THEN (null) ELSE ((_col3 / _col4)) END (type: double) + outputColumnNames: _col1, _col2, _col3, _col4 + Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: int), _col2 (type: int) + sort order: ++ + Map-reduce partition columns: _col1 (type: int), _col2 (type: int) + Statistics: Num rows: 12506076 Data size: 197593980 Basic stats: COMPLETE Column stats: NONE + value expressions: _col3 (type: double), _col4 (type: double) + Reducer 5 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col1 (type: int), _col2 (type: int) + 1 _col1 (type: int), _col2 (type: int) + outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col9 + Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col2 (type: int), _col3 (type: double), _col4 (type: double), _col6 (type: int), _col7 (type: int), _col8 (type: double), _col9 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: double), _col3 (type: double), _col6 (type: double), _col7 (type: double) + sort order: ++++++ + Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE + value expressions: _col4 (type: int), _col5 (type: int) + Reducer 6 + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), 4 (type: int), KEY.reducesinkkey2 (type: double), KEY.reducesinkkey3 (type: double), VALUE._col0 (type: int), VALUE._col1 (type: int), 5 (type: int), KEY.reducesinkkey4 (type: double), KEY.reducesinkkey5 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 13756683 Data size: 217353382 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 13756683 Data size: 217353382 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 + +PREHOOK: query: with inv as +(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stdev,mean, case mean when 0 then null else stdev/mean end cov + from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean + from inventory + ,item + ,warehouse + ,date_dim + where inv_item_sk = i_item_sk + and inv_warehouse_sk = w_warehouse_sk + and inv_date_sk = d_date_sk + and d_year =1999 + group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo + where case mean when 0 then 0 else stdev/mean end > 1) +select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov + ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov +from inv inv1,inv inv2 +where inv1.i_item_sk = inv2.i_item_sk + and inv1.w_warehouse_sk = inv2.w_warehouse_sk + and inv1.d_moy=4 + and inv2.d_moy=4+1 + and inv1.cov > 1.5 +order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov + ,inv2.d_moy,inv2.mean, inv2.cov +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@inventory +PREHOOK: Input: default@item +PREHOOK: Input: default@warehouse +#### A masked pattern was here #### +POSTHOOK: query: with inv as +(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stdev,mean, case mean when 0 then null else stdev/mean end cov + from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy + ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean + from inventory + ,item + ,warehouse + ,date_dim + where inv_item_sk = i_item_sk + and inv_warehouse_sk = w_warehouse_sk + and inv_date_sk = d_date_sk + and d_year =1999 + group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo + where case mean when 0 then 0 else stdev/mean end > 1) +select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov + ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov +from inv inv1,inv inv2 +where inv1.i_item_sk = inv2.i_item_sk + and inv1.w_warehouse_sk = inv2.w_warehouse_sk + and inv1.d_moy=4 + and inv2.d_moy=4+1 + and inv1.cov > 1.5 +order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov + ,inv2.d_moy,inv2.mean, inv2.cov +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@inventory +POSTHOOK: Input: default@item +POSTHOOK: Input: default@warehouse +#### A masked pattern was here ####
