http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query71.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query71.q.out b/ql/src/test/results/clientpositive/perf/spark/query71.q.out
new file mode 100644
index 0000000..73af356
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query71.q.out
@@ -0,0 +1,343 @@
+PREHOOK: query: explain
+select i_brand_id brand_id, i_brand brand,t_hour,t_minute,
+ sum(ext_price) ext_price
+ from item, (select ws_ext_sales_price as ext_price,
+ ws_sold_date_sk as sold_date_sk,
+ ws_item_sk as sold_item_sk,
+ ws_sold_time_sk as time_sk
+ from web_sales,date_dim
+ where d_date_sk = ws_sold_date_sk
+ and d_moy=12
+ and d_year=2001
+ union all
+ select cs_ext_sales_price as ext_price,
+ cs_sold_date_sk as sold_date_sk,
+ cs_item_sk as sold_item_sk,
+ cs_sold_time_sk as time_sk
+ from catalog_sales,date_dim
+ where d_date_sk = cs_sold_date_sk
+ and d_moy=12
+ and d_year=2001
+ union all
+ select ss_ext_sales_price as ext_price,
+ ss_sold_date_sk as sold_date_sk,
+ ss_item_sk as sold_item_sk,
+ ss_sold_time_sk as time_sk
+ from store_sales,date_dim
+ where d_date_sk = ss_sold_date_sk
+ and d_moy=12
+ and d_year=2001
+ ) as tmp,time_dim
+ where
+ sold_item_sk = i_item_sk
+ and i_manager_id=1
+ and time_sk = t_time_sk
+ and (t_meal_time = 'breakfast' or t_meal_time = 'dinner')
+ group by i_brand, i_brand_id,t_hour,t_minute
+ order by ext_price desc, i_brand_id
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select i_brand_id brand_id, i_brand brand,t_hour,t_minute,
+ sum(ext_price) ext_price
+ from item, (select ws_ext_sales_price as ext_price,
+ ws_sold_date_sk as sold_date_sk,
+ ws_item_sk as sold_item_sk,
+ ws_sold_time_sk as time_sk
+ from web_sales,date_dim
+ where d_date_sk = ws_sold_date_sk
+ and d_moy=12
+ and d_year=2001
+ union all
+ select cs_ext_sales_price as ext_price,
+ cs_sold_date_sk as sold_date_sk,
+ cs_item_sk as sold_item_sk,
+ cs_sold_time_sk as time_sk
+ from catalog_sales,date_dim
+ where d_date_sk = cs_sold_date_sk
+ and d_moy=12
+ and d_year=2001
+ union all
+ select ss_ext_sales_price as ext_price,
+ ss_sold_date_sk as sold_date_sk,
+ ss_item_sk as sold_item_sk,
+ ss_sold_time_sk as time_sk
+ from store_sales,date_dim
+ where d_date_sk = ss_sold_date_sk
+ and d_moy=12
+ and d_year=2001
+ ) as tmp,time_dim
+ where
+ sold_item_sk = i_item_sk
+ and i_manager_id=1
+ and time_sk = t_time_sk
+ and (t_meal_time = 'breakfast' or t_meal_time = 'dinner')
+ group by i_brand, i_brand_id,t_hour,t_minute
+ order by ext_price desc, i_brand_id
+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 12 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 13 (PARTITION-LEVEL SORT, 398)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 154), Map 10 (PARTITION-LEVEL SORT, 154)
+ Reducer 3 <- Map 14 (PARTITION-LEVEL SORT, 943), Reducer 12 (PARTITION-LEVEL SORT, 943), Reducer 2 (PARTITION-LEVEL SORT, 943), Reducer 9 (PARTITION-LEVEL SORT, 943)
+ Reducer 4 <- Map 15 (PARTITION-LEVEL SORT, 1009), Reducer 3 (PARTITION-LEVEL SORT, 1009)
+ Reducer 5 <- Reducer 4 (GROUP, 1009)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+ Reducer 9 <- Map 10 (PARTITION-LEVEL SORT, 305), Map 8 (PARTITION-LEVEL SORT, 305)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_item_sk is not null and ws_sold_date_sk is not null and ws_sold_time_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_sold_time_sk (type: int), ws_item_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 10
+ 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 = 12) and (d_year = 2001) 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 11
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ss_item_sk is not null and ss_sold_date_sk is not null and ss_sold_time_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_sold_time_sk (type: int), ss_item_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))
+ Map 13
+ 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 = 12) and (d_year = 2001) 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 14
+ Map Operator Tree:
+ TableScan
+ alias: item
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((i_manager_id = 1) and i_item_sk is not null) (type: boolean)
+ Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: i_item_sk (type: int), i_brand_id (type: int), i_brand (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 231000 Data size: 331780228 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: string)
+ Map 15
+ Map Operator Tree:
+ TableScan
+ alias: time_dim
+ Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((t_meal_time = 'breakfast') or (t_meal_time = 'dinner')) and t_time_sk is not null) (type: boolean)
+ Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t_time_sk (type: int), t_hour (type: int), t_minute (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 86400 Data size: 40694400 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: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: int)
+ 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_item_sk is not null and cs_sold_date_sk is not null and cs_sold_time_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_sold_time_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))
+ Reducer 12
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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: 1108786976 Data size: 120333742785 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(7,2)), _col2 (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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: 1108786976 Data size: 120333742785 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(7,2)), _col2 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col4, _col5
+ Statistics: Num rows: 1219665700 Data size: 132367119932 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: 1219665700 Data size: 132367119932 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(7,2)), _col4 (type: int), _col5 (type: string)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col4, _col5, _col8, _col9
+ Statistics: Num rows: 1341632299 Data size: 145603835081 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ keys: _col4 (type: int), _col8 (type: int), _col9 (type: int), _col5 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1341632299 Data size: 145603835081 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string)
+ sort order: ++++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string)
+ Statistics: Num rows: 1341632299 Data size: 145603835081 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: decimal(17,2))
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int), KEY._col3 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col3 (type: string), _col1 (type: int), _col2 (type: int), _col4 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: decimal(17,2)), _col0 (type: int)
+ sort order: -+
+ Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: int)
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: int), KEY.reducesinkkey0 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 670816149 Data size: 72801917486 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 670816149 Data size: 72801917486 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
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: decimal(7,2)), _col2 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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: 1108786976 Data size: 120333742785 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(7,2)), _col2 (type: int)
+
+ 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/query72.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query72.q.out b/ql/src/test/results/clientpositive/perf/spark/query72.q.out
new file mode 100644
index 0000000..809d213
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query72.q.out
@@ -0,0 +1,489 @@
+PREHOOK: query: explain
+select i_item_desc
+ ,w_warehouse_name
+ ,d1.d_week_seq
+ ,count(case when p_promo_sk is null then 1 else 0 end) no_promo
+ ,count(case when p_promo_sk is not null then 1 else 0 end) promo
+ ,count(*) total_cnt
+from catalog_sales
+join inventory on (cs_item_sk = inv_item_sk)
+join warehouse on (w_warehouse_sk=inv_warehouse_sk)
+join item on (i_item_sk = cs_item_sk)
+join customer_demographics on (cs_bill_cdemo_sk = cd_demo_sk)
+join household_demographics on (cs_bill_hdemo_sk = hd_demo_sk)
+join date_dim d1 on (cs_sold_date_sk = d1.d_date_sk)
+join date_dim d2 on (inv_date_sk = d2.d_date_sk)
+join date_dim d3 on (cs_ship_date_sk = d3.d_date_sk)
+left outer join promotion on (cs_promo_sk=p_promo_sk)
+left outer join catalog_returns on (cr_item_sk = cs_item_sk and cr_order_number = cs_order_number)
+where d1.d_week_seq = d2.d_week_seq
+ and inv_quantity_on_hand < cs_quantity
+ and d3.d_date > d1.d_date + 5
+ and hd_buy_potential = '1001-5000'
+ and d1.d_year = 2001
+ and hd_buy_potential = '1001-5000'
+ and cd_marital_status = 'M'
+ and d1.d_year = 2001
+group by i_item_desc,w_warehouse_name,d1.d_week_seq
+order by total_cnt desc, i_item_desc, w_warehouse_name, d_week_seq
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select i_item_desc
+ ,w_warehouse_name
+ ,d1.d_week_seq
+ ,count(case when p_promo_sk is null then 1 else 0 end) no_promo
+ ,count(case when p_promo_sk is not null then 1 else 0 end) promo
+ ,count(*) total_cnt
+from catalog_sales
+join inventory on (cs_item_sk = inv_item_sk)
+join warehouse on (w_warehouse_sk=inv_warehouse_sk)
+join item on (i_item_sk = cs_item_sk)
+join customer_demographics on (cs_bill_cdemo_sk = cd_demo_sk)
+join household_demographics on (cs_bill_hdemo_sk = hd_demo_sk)
+join date_dim d1 on (cs_sold_date_sk = d1.d_date_sk)
+join date_dim d2 on (inv_date_sk = d2.d_date_sk)
+join date_dim d3 on (cs_ship_date_sk = d3.d_date_sk)
+left outer join promotion on (cs_promo_sk=p_promo_sk)
+left outer join catalog_returns on (cr_item_sk = cs_item_sk and cr_order_number = cs_order_number)
+where d1.d_week_seq = d2.d_week_seq
+ and inv_quantity_on_hand < cs_quantity
+ and d3.d_date > d1.d_date + 5
+ and hd_buy_potential = '1001-5000'
+ and d1.d_year = 2001
+ and hd_buy_potential = '1001-5000'
+ and cd_marital_status = 'M'
+ and d1.d_year = 2001
+group by i_item_desc,w_warehouse_name,d1.d_week_seq
+order by total_cnt desc, i_item_desc, w_warehouse_name, d_week_seq
+limit 100
+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 7
+ 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 15
+ Map Operator Tree:
+ TableScan
+ alias: household_demographics
+ Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hd_demo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: promotion
+ Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_promo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col5 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 10 <- Map 14 (PARTITION-LEVEL SORT, 338), Reducer 9 (PARTITION-LEVEL SORT, 338)
+ Reducer 11 <- Map 17 (PARTITION-LEVEL SORT, 452), Reducer 10 (PARTITION-LEVEL SORT, 452)
+ Reducer 12 <- Map 18 (PARTITION-LEVEL SORT, 492), Reducer 11 (PARTITION-LEVEL SORT, 492)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 186), Reducer 12 (PARTITION-LEVEL SORT, 186)
+ Reducer 3 <- Map 19 (PARTITION-LEVEL SORT, 67), Reducer 2 (PARTITION-LEVEL SORT, 67)
+ Reducer 4 <- Map 20 (PARTITION-LEVEL SORT, 97), Reducer 3 (PARTITION-LEVEL SORT, 97)
+ Reducer 5 <- Reducer 4 (GROUP, 80)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+ Reducer 9 <- Map 13 (PARTITION-LEVEL SORT, 306), Map 8 (PARTITION-LEVEL SORT, 306)
+#### 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col5
+ input vertices:
+ 1 Map 7
+ 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: _col0 (type: int), _col3 (type: int), _col5 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 13
+ Map Operator Tree:
+ TableScan
+ alias: d1
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_year = 2001) and d_date_sk is not null and d_week_seq 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), d_date (type: string), d_week_seq (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ value expressions: _col1 (type: string), _col2 (type: int)
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: customer_demographics
+ Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cd_demo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 930900 Data size: 358593079 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: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
+ Map 17
+ 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_item_desc (type: string)
+ outputColumnNames: _col0, _col1
+ 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)
+ Map 18
+ Map Operator Tree:
+ TableScan
+ alias: d3
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: d_date_sk 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_date (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 19
+ Map Operator Tree:
+ TableScan
+ alias: d2
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (d_date_sk is not null and d_week_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_week_seq (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Map 20
+ Map Operator Tree:
+ TableScan
+ alias: catalog_returns
+ Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: cr_item_sk is not null (type: boolean)
+ Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cr_item_sk (type: int), cr_order_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
+ Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ 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_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_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_ship_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_bill_hdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_quantity (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ 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: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int)
+ Reducer 10
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col9, _col10
+ Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col4, _col5, _col6, _col7, _col9, _col10
+ input vertices:
+ 1 Map 15
+ Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col5 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10
+ input vertices:
+ 1 Map 16
+ Statistics: Num rows: 421645953 Data size: 57099332415 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: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int)
+ Reducer 11
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col4 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col4, _col6, _col7, _col9, _col10, _col18
+ Statistics: Num rows: 463810558 Data size: 62809267017 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: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col18 (type: string)
+ Reducer 12
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col18, _col20
+ Statistics: Num rows: 510191624 Data size: 69090195216 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (UDFToDouble(_col20) > (UDFToDouble(_col9) + 5.0)) (type: boolean)
+ Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col18 (type: string), _col4 (type: int), _col6 (type: int), _col7 (type: int), _col10 (type: int)
+ outputColumnNames: _col3, _col8, _col10, _col11, _col14
+ Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col8 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col8 (type: int)
+ Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: string), _col10 (type: int), _col11 (type: int), _col14 (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col8 (type: int)
+ outputColumnNames: _col0, _col3, _col5, _col9, _col14, _col16, _col17, _col20
+ Statistics: Num rows: 187070265 Data size: 25333072028 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col3 < _col17) (type: boolean)
+ Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col20 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col20 (type: int)
+ Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: string), _col9 (type: string), _col14 (type: int), _col16 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col20 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col5, _col9, _col14, _col16, _col20
+ Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col14 (type: int), _col16 (type: int), _col5 (type: string), _col9 (type: string), _col20 (type: int)
+ outputColumnNames: _col4, _col6, _col13, _col15, _col22
+ Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: int), _col6 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col4 (type: int), _col6 (type: int)
+ Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col13 (type: string), _col15 (type: string), _col22 (type: int)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col4 (type: int), _col6 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col13, _col15, _col22
+ Statistics: Num rows: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col15 (type: string), _col13 (type: string), _col22 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 75451675 Data size: 10217672826 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: 75451675 Data size: 10217672826 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: bigint)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col5
+ Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col5 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ sort order: -+++
+ Statistics: Num rows: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey0 (type: bigint), KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 37725837 Data size: 5108836345 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
+ Reducer 9
+ 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, _col5, _col6, _col7, _col9, _col10
+ Statistics: Num rows: 316788826 Data size: 42899570777 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: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int)
+
+ 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/query73.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query73.q.out b/ql/src/test/results/clientpositive/perf/spark/query73.q.out
new file mode 100644
index 0000000..b25a16e
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query73.q.out
@@ -0,0 +1,261 @@
+PREHOOK: query: explain
+select c_last_name
+ ,c_first_name
+ ,c_salutation
+ ,c_preferred_cust_flag
+ ,ss_ticket_number
+ ,cnt from
+ (select ss_ticket_number
+ ,ss_customer_sk
+ ,count(*) cnt
+ from store_sales,date_dim,store,household_demographics
+ where store_sales.ss_sold_date_sk = date_dim.d_date_sk
+ and store_sales.ss_store_sk = store.s_store_sk
+ and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk
+ and date_dim.d_dom between 1 and 2
+ and (household_demographics.hd_buy_potential = '>10000' or
+ household_demographics.hd_buy_potential = 'unknown')
+ and household_demographics.hd_vehicle_count > 0
+ and case when household_demographics.hd_vehicle_count > 0 then
+ household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count else null end > 1
+ and date_dim.d_year in (2000,2000+1,2000+2)
+ and store.s_county in ('Mobile County','Maverick County','Huron County','Kittitas County')
+ group by ss_ticket_number,ss_customer_sk) dj,customer
+ where ss_customer_sk = c_customer_sk
+ and cnt between 1 and 5
+ order by cnt desc
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select c_last_name
+ ,c_first_name
+ ,c_salutation
+ ,c_preferred_cust_flag
+ ,ss_ticket_number
+ ,cnt from
+ (select ss_ticket_number
+ ,ss_customer_sk
+ ,count(*) cnt
+ from store_sales,date_dim,store,household_demographics
+ where store_sales.ss_sold_date_sk = date_dim.d_date_sk
+ and store_sales.ss_store_sk = store.s_store_sk
+ and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk
+ and date_dim.d_dom between 1 and 2
+ and (household_demographics.hd_buy_potential = '>10000' or
+ household_demographics.hd_buy_potential = 'unknown')
+ and household_demographics.hd_vehicle_count > 0
+ and case when household_demographics.hd_vehicle_count > 0 then
+ household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count else null end > 1
+ and date_dim.d_year in (2000,2000+1,2000+2)
+ and store.s_county in ('Mobile County','Maverick County','Huron County','Kittitas County')
+ group by ss_ticket_number,ss_customer_sk) dj,customer
+ where ss_customer_sk = c_customer_sk
+ and cnt between 1 and 5
+ order by cnt desc
+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 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_year) IN (2000, 2001, 2002) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean)
+ Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4058 Data size: 4540902 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: household_demographics
+ Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((hd_buy_potential = '>10000') or (hd_buy_potential = 'unknown')) and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0)) ELSE (null) END and hd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hd_demo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: store
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') 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 _col3 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 567), Reducer 5 (PARTITION-LEVEL SORT, 567)
+ Reducer 3 <- Reducer 2 (SORT, 1)
+ Reducer 5 <- Map 4 (GROUP, 529)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ 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_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ 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), _col3 (type: string), _col4 (type: string)
+ Map 4
+ 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_hdemo_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_customer_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3, _col4
+ input vertices:
+ 1 Map 6
+ 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 7
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col4
+ input vertices:
+ 1 Map 8
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: int), _col4 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col1 (type: int)
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col7
+ Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: string), _col2 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: int), _col7 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col5 (type: bigint)
+ sort order: -
+ Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 88000001 Data size: 75681779077 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 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col2 BETWEEN 1 AND 5 (type: boolean)
+ Statistics: Num rows: 42591679 Data size: 3757450287 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: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col2 (type: bigint)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
|