http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query23.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query23.q.out
b/ql/src/test/results/clientpositive/perf/spark/query23.q.out
new file mode 100644
index 0000000..8b5a83a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query23.q.out
@@ -0,0 +1,1110 @@
+Warning: Map Join MAPJOIN[275][bigTable=?] in task 'Stage-1:MAPRED' is a cross
product
+Warning: Map Join MAPJOIN[276][bigTable=?] in task 'Stage-1:MAPRED' is a cross
product
+PREHOOK: query: explain
+with frequent_ss_items as
+ (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date
solddate,count(*) cnt
+ from store_sales
+ ,date_dim
+ ,item
+ where ss_sold_date_sk = d_date_sk
+ and ss_item_sk = i_item_sk
+ and d_year in (1999,1999+1,1999+2,1999+3)
+ group by substr(i_item_desc,1,30),i_item_sk,d_date
+ having count(*) >4),
+ max_store_sales as
+ (select max(csales) tpcds_cmax
+ from (select c_customer_sk,sum(ss_quantity*ss_sales_price) csales
+ from store_sales
+ ,customer
+ ,date_dim
+ where ss_customer_sk = c_customer_sk
+ and ss_sold_date_sk = d_date_sk
+ and d_year in (1999,1999+1,1999+2,1999+3)
+ group by c_customer_sk) x),
+ best_ss_customer as
+ (select c_customer_sk,sum(ss_quantity*ss_sales_price) ssales
+ from store_sales
+ ,customer
+ where ss_customer_sk = c_customer_sk
+ group by c_customer_sk
+ having sum(ss_quantity*ss_sales_price) > (95/100.0) * (select
+ *
+from
+ max_store_sales))
+ select sum(sales)
+ from ((select cs_quantity*cs_list_price sales
+ from catalog_sales
+ ,date_dim
+ where d_year = 1999
+ and d_moy = 1
+ and cs_sold_date_sk = d_date_sk
+ and cs_item_sk in (select item_sk from frequent_ss_items)
+ and cs_bill_customer_sk in (select c_customer_sk from
best_ss_customer))
+ union all
+ (select ws_quantity*ws_list_price sales
+ from web_sales
+ ,date_dim
+ where d_year = 1999
+ and d_moy = 1
+ and ws_sold_date_sk = d_date_sk
+ and ws_item_sk in (select item_sk from frequent_ss_items)
+ and ws_bill_customer_sk in (select c_customer_sk from
best_ss_customer))) y
+ limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+with frequent_ss_items as
+ (select substr(i_item_desc,1,30) itemdesc,i_item_sk item_sk,d_date
solddate,count(*) cnt
+ from store_sales
+ ,date_dim
+ ,item
+ where ss_sold_date_sk = d_date_sk
+ and ss_item_sk = i_item_sk
+ and d_year in (1999,1999+1,1999+2,1999+3)
+ group by substr(i_item_desc,1,30),i_item_sk,d_date
+ having count(*) >4),
+ max_store_sales as
+ (select max(csales) tpcds_cmax
+ from (select c_customer_sk,sum(ss_quantity*ss_sales_price) csales
+ from store_sales
+ ,customer
+ ,date_dim
+ where ss_customer_sk = c_customer_sk
+ and ss_sold_date_sk = d_date_sk
+ and d_year in (1999,1999+1,1999+2,1999+3)
+ group by c_customer_sk) x),
+ best_ss_customer as
+ (select c_customer_sk,sum(ss_quantity*ss_sales_price) ssales
+ from store_sales
+ ,customer
+ where ss_customer_sk = c_customer_sk
+ group by c_customer_sk
+ having sum(ss_quantity*ss_sales_price) > (95/100.0) * (select
+ *
+from
+ max_store_sales))
+ select sum(sales)
+ from ((select cs_quantity*cs_list_price sales
+ from catalog_sales
+ ,date_dim
+ where d_year = 1999
+ and d_moy = 1
+ and cs_sold_date_sk = d_date_sk
+ and cs_item_sk in (select item_sk from frequent_ss_items)
+ and cs_bill_customer_sk in (select c_customer_sk from
best_ss_customer))
+ union all
+ (select ws_quantity*ws_list_price sales
+ from web_sales
+ ,date_dim
+ where d_year = 1999
+ and d_moy = 1
+ and ws_sold_date_sk = d_date_sk
+ and ws_item_sk in (select item_sk from frequent_ss_items)
+ and ws_bill_customer_sk in (select c_customer_sk from
best_ss_customer))) y
+ 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
+ Edges:
+ Reducer 14 <- Map 13 (PARTITION-LEVEL SORT, 398), Map 18
(PARTITION-LEVEL SORT, 398)
+ Reducer 15 <- Map 19 (PARTITION-LEVEL SORT, 975), Reducer 14
(PARTITION-LEVEL SORT, 975)
+ Reducer 16 <- Reducer 15 (GROUP, 481)
+ Reducer 17 <- Reducer 16 (GROUP, 1)
+ Reducer 21 <- Map 20 (PARTITION-LEVEL SORT, 398), Map 25
(PARTITION-LEVEL SORT, 398)
+ Reducer 22 <- Map 26 (PARTITION-LEVEL SORT, 975), Reducer 21
(PARTITION-LEVEL SORT, 975)
+ Reducer 23 <- Reducer 22 (GROUP, 481)
+ Reducer 24 <- Reducer 23 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 13
+ 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
+ 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)
+ Map 18
+ 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 (1999, 2000, 2001, 2002) and
d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Map 19
+ 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)
+ outputColumnNames: _col0
+ 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
+ Map 20
+ 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), ss_quantity (type: int), ss_sales_price (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 575995635 Data size: 50814502088
Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _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 25
+ 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 (1999, 2000, 2001, 2002) and
d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Map 26
+ 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)
+ outputColumnNames: _col0
+ 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
+ Reducer 14
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1
+ 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
+ Reducer 15
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col6
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 696954748 Data size: 61485550191
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: 696954748 Data size: 61485550191
Basic stats: COMPLETE Column stats: NONE
+ Reducer 16
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 17
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col0) <= 1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ 2
+ Reducer 21
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 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: _col2 (type: int), _col3 (type:
decimal(7,2))
+ Reducer 22
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col6
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int), (CAST( _col2 AS
decimal(10,0)) * _col3) (type: decimal(18,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 696954748 Data size: 61485550191
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: 696954748 Data size: 61485550191
Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(28,2))
+ Reducer 23
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: decimal(28,2))
+ outputColumnNames: _col1
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: max(_col1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 224 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 224 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(28,2))
+ Reducer 24
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE
Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ 2
+
+ Stage: Stage-3
+ Spark
+ Edges:
+ Reducer 43 <- Map 42 (PARTITION-LEVEL SORT, 398), Map 47
(PARTITION-LEVEL SORT, 398)
+ Reducer 44 <- Map 48 (PARTITION-LEVEL SORT, 975), Reducer 43
(PARTITION-LEVEL SORT, 975)
+ Reducer 45 <- Reducer 44 (GROUP, 481)
+ Reducer 46 <- Reducer 45 (GROUP, 1)
+ Reducer 50 <- Map 49 (PARTITION-LEVEL SORT, 398), Map 54
(PARTITION-LEVEL SORT, 398)
+ Reducer 51 <- Map 55 (PARTITION-LEVEL SORT, 975), Reducer 50
(PARTITION-LEVEL SORT, 975)
+ Reducer 52 <- Reducer 51 (GROUP, 481)
+ Reducer 53 <- Reducer 52 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 42
+ 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
+ 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)
+ Map 47
+ 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 (1999, 2000, 2001, 2002) and
d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Map 48
+ 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)
+ outputColumnNames: _col0
+ 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
+ Map 49
+ 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), ss_quantity (type: int), ss_sales_price (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 575995635 Data size: 50814502088
Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _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 54
+ 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 (1999, 2000, 2001, 2002) and
d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Map 55
+ 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)
+ outputColumnNames: _col0
+ 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
+ Reducer 43
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1
+ 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
+ Reducer 44
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col6
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 696954748 Data size: 61485550191
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: 696954748 Data size: 61485550191
Basic stats: COMPLETE Column stats: NONE
+ Reducer 45
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 46
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col0) <= 1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE
Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ 2
+ Reducer 50
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _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: _col2 (type: int), _col3 (type:
decimal(7,2))
+ Reducer 51
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col6
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col6 (type: int), (CAST( _col2 AS
decimal(10,0)) * _col3) (type: decimal(18,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 696954748 Data size: 61485550191
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: 696954748 Data size: 61485550191
Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(28,2))
+ Reducer 52
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: decimal(28,2))
+ outputColumnNames: _col1
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: max(_col1)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 224 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 224 Basic stats:
COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(28,2))
+ Reducer 53
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 224 Basic stats: COMPLETE
Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ 2
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 10 <- Reducer 38 (GROUP PARTITION-LEVEL SORT, 481)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 305), Map 35
(PARTITION-LEVEL SORT, 305)
+ Reducer 28 <- Map 27 (PARTITION-LEVEL SORT, 935), Map 30
(PARTITION-LEVEL SORT, 935)
+ Reducer 29 <- Reducer 28 (GROUP, 437)
+ Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 376), Reducer 2
(PARTITION-LEVEL SORT, 376)
+ Reducer 32 <- Map 31 (PARTITION-LEVEL SORT, 154), Map 35
(PARTITION-LEVEL SORT, 154)
+ Reducer 33 <- Reducer 10 (PARTITION-LEVEL SORT, 209), Reducer 32
(PARTITION-LEVEL SORT, 209)
+ Reducer 34 <- Reducer 33 (PARTITION-LEVEL SORT, 451), Reducer 58
(PARTITION-LEVEL SORT, 451)
+ Reducer 37 <- Map 11 (PARTITION-LEVEL SORT, 398), Map 36
(PARTITION-LEVEL SORT, 398)
+ Reducer 38 <- Map 12 (PARTITION-LEVEL SORT, 442), Reducer 37
(PARTITION-LEVEL SORT, 442)
+ Reducer 4 <- Reducer 29 (PARTITION-LEVEL SORT, 634), Reducer 3
(PARTITION-LEVEL SORT, 634)
+ Reducer 5 <- Reducer 34 (GROUP, 1), Reducer 4 (GROUP, 1)
+ Reducer 58 <- Reducer 28 (GROUP, 437)
+#### 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_bill_customer_sk is not null and cs_item_sk
is not null and cs_sold_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 287989836 Data size: 38999608952
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cs_sold_date_sk (type: int),
cs_bill_customer_sk (type: int), cs_item_sk (type: int), cs_quantity (type:
int), cs_list_price (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ 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: decimal(7,2))
+ 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_year) IN (1999, 2000, 2001, 2002) and
d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int), d_date (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36525 Data size: 40871475 Basic
stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 12
+ 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 27
+ 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 (type: boolean)
+ Statistics: Num rows: 575995635 Data size: 50814502088
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_customer_sk (type: int), ss_quantity
(type: int), ss_sales_price (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 575995635 Data size: 50814502088
Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 575995635 Data size: 50814502088
Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type:
decimal(7,2))
+ Map 30
+ 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)
+ outputColumnNames: _col0
+ 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
+ Map 31
+ Map Operator Tree:
+ TableScan
+ alias: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic
stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_bill_customer_sk is not null and ws_item_sk
is not null and ws_sold_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_sold_date_sk (type: int), ws_item_sk
(type: int), ws_bill_customer_sk (type: int), ws_quantity (type: int),
ws_list_price (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ 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: int), _col4 (type: decimal(7,2))
+ Map 35
+ 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 = 1) 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 36
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic
stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ss_item_sk is not null and ss_sold_date_sk is
not null) (type: boolean)
+ Statistics: Num rows: 575995635 Data size: 50814502088
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_sold_date_sk (type: int), ss_item_sk
(type: int)
+ outputColumnNames: _col0, _col1
+ 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)
+ Reducer 10
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: int), KEY._col1 (type: string),
KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col3 (type: bigint)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 348477374 Data size: 30742775095 Basic
stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col3 > 4) (type: boolean)
+ Statistics: Num rows: 116159124 Data size: 10247591639
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
+ outputColumnNames: _col1
+ Statistics: Num rows: 116159124 Data size: 10247591639
Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: int)
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 58079562 Data size: 5123795819
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: 58079562 Data size: 5123795819
Basic stats: COMPLETE Column stats: NONE
+ 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, _col4
+ 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: decimal(7,2))
+ Reducer 28
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: int), (CAST( _col1 AS
decimal(10,0)) * _col2) (type: decimal(18,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col1)
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 633595212 Data size: 55895953508
Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 633595212 Data size: 55895953508
Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: decimal(28,2))
+ Reducer 29
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 316797606 Data size: 27947976754 Basic
stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0
+ 1
+ 2
+ outputColumnNames: _col1, _col2, _col3
+ input vertices:
+ 0 Reducer 17
+ 1 Reducer 24
+ Statistics: Num rows: 316797606 Data size: 101761818952
Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col3 > (0.95 * _col1)) (type: boolean)
+ Statistics: Num rows: 105599202 Data size: 33920606317
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 105599202 Data size: 33920606317
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: 105599202 Data size: 33920606317
Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ 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
+ Statistics: Num rows: 348467716 Data size: 47189528877 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: 348467716 Data size: 47189528877 Basic
stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int), _col4 (type:
decimal(7,2))
+ Reducer 32
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3, _col4
+ 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: _col2 (type: int), _col3 (type: int),
_col4 (type: decimal(7,2))
+ Reducer 33
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col4
+ Statistics: Num rows: 174243235 Data size: 23692040863 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: 174243235 Data size: 23692040863 Basic
stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int), _col4 (type:
decimal(7,2))
+ Reducer 34
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ outputColumnNames: _col3, _col4
+ Statistics: Num rows: 191667562 Data size: 26061245514 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (CAST( _col3 AS decimal(10,0)) * _col4) (type:
decimal(18,2))
+ outputColumnNames: _col0
+ Statistics: Num rows: 191667562 Data size: 26061245514 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 112 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 112 Basic stats:
COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: decimal(28,2))
+ Reducer 37
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col3
+ 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)
+ Reducer 38
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col5, _col6
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: substr(_col6, 1, 30) (type: string), _col5
(type: int), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: int), _col0 (type: string), _col2
(type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 696954748 Data size: 61485550191
Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type:
string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 696954748 Data size: 61485550191
Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: bigint)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ outputColumnNames: _col3, _col4
+ Statistics: Num rows: 383314495 Data size: 51908482889 Basic
stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (CAST( _col3 AS decimal(10,0)) * _col4) (type:
decimal(18,2))
+ outputColumnNames: _col0
+ Statistics: Num rows: 383314495 Data size: 51908482889 Basic
stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 112 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 112 Basic stats:
COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col0 (type: decimal(28,2))
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE
Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE
Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 112 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 58
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 316797606 Data size: 27947976754 Basic
stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0
+ 1
+ 2
+ outputColumnNames: _col1, _col2, _col3
+ input vertices:
+ 0 Reducer 46
+ 1 Reducer 53
+ Statistics: Num rows: 316797606 Data size: 101761818952
Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col3 > (0.95 * _col1)) (type: boolean)
+ Statistics: Num rows: 105599202 Data size: 33920606317
Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 105599202 Data size: 33920606317
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: 105599202 Data size: 33920606317
Basic stats: COMPLETE Column stats: NONE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+
