You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by se...@apache.org on 2017/09/29 03:36:24 UTC
[33/48] hive git commit: HIVE-17543: Enable PerfCliDriver for HoS
(Sahil Takiar, reviewed by Peter Vary)
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query24.q.out b/ql/src/test/results/clientpositive/perf/spark/query24.q.out
new file mode 100644
index 0000000..54c607a
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query24.q.out
@@ -0,0 +1,610 @@
+Warning: Map Join MAPJOIN[104][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain
+with ssales as
+(select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size
+ ,sum(ss_sales_price) netpaid
+from store_sales
+ ,store_returns
+ ,store
+ ,item
+ ,customer
+ ,customer_address
+where ss_ticket_number = sr_ticket_number
+ and ss_item_sk = sr_item_sk
+ and ss_customer_sk = c_customer_sk
+ and ss_item_sk = i_item_sk
+ and ss_store_sk = s_store_sk
+ and c_birth_country = upper(ca_country)
+ and s_zip = ca_zip
+and s_market_id=7
+group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size)
+select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,sum(netpaid) paid
+from ssales
+where i_color = 'orchid'
+group by c_last_name
+ ,c_first_name
+ ,s_store_name
+having sum(netpaid) > (select 0.05*avg(netpaid)
+ from ssales)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+with ssales as
+(select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size
+ ,sum(ss_sales_price) netpaid
+from store_sales
+ ,store_returns
+ ,store
+ ,item
+ ,customer
+ ,customer_address
+where ss_ticket_number = sr_ticket_number
+ and ss_item_sk = sr_item_sk
+ and ss_customer_sk = c_customer_sk
+ and ss_item_sk = i_item_sk
+ and ss_store_sk = s_store_sk
+ and c_birth_country = upper(ca_country)
+ and s_zip = ca_zip
+and s_market_id=7
+group by c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,ca_state
+ ,s_state
+ ,i_color
+ ,i_current_price
+ ,i_manager_id
+ ,i_units
+ ,i_size)
+select c_last_name
+ ,c_first_name
+ ,s_store_name
+ ,sum(netpaid) paid
+from ssales
+where i_color = 'orchid'
+group by c_last_name
+ ,c_first_name
+ ,s_store_name
+having sum(netpaid) > (select 0.05*avg(netpaid)
+ from ssales)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-3 is a root stage
+ Stage-2 depends on stages: Stage-3
+ Stage-4 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 19
+ Map Operator Tree:
+ TableScan
+ alias: store
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((s_market_id = 7) and s_store_sk is not null and s_zip 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), s_store_name (type: string), s_state (type: string), s_zip (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Spark
+ Edges:
+ Reducer 13 <- Map 12 (PARTITION-LEVEL SORT, 975), Map 20 (PARTITION-LEVEL SORT, 975)
+ Reducer 14 <- Map 21 (PARTITION-LEVEL SORT, 486), Reducer 13 (PARTITION-LEVEL SORT, 486)
+ Reducer 15 <- Map 22 (PARTITION-LEVEL SORT, 564), Reducer 14 (PARTITION-LEVEL SORT, 564)
+ Reducer 16 <- Map 23 (PARTITION-LEVEL SORT, 899), Reducer 15 (PARTITION-LEVEL SORT, 899)
+ Reducer 17 <- Reducer 16 (GROUP, 640)
+ Reducer 18 <- Reducer 17 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 12
+ 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_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean)
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_sales_price (type: decimal(7,2))
+ 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 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col8, _col9
+ input vertices:
+ 1 Map 19
+ 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: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 20
+ Map Operator Tree:
+ TableScan
+ alias: customer
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean)
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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)
+ Map 21
+ 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_current_price (type: decimal(7,2)), i_size (type: string), i_color (type: string), i_units (type: string), i_manager_id (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ 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: decimal(7,2)), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int)
+ Map 22
+ Map Operator Tree:
+ TableScan
+ alias: store_returns
+ Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sr_item_sk is not null and sr_ticket_number is not null) (type: boolean)
+ Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: sr_item_sk (type: int), sr_ticket_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 57591150 Data size: 4462194832 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: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Map 23
+ Map Operator Tree:
+ TableScan
+ alias: customer_address
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ca_zip is not null and upper(ca_country) is not null) (type: boolean)
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ca_state (type: string), ca_zip (type: string), ca_country (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), upper(_col2) (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), upper(_col2) (type: string)
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Reducer 13
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3, _col4, _col6, _col8, _col9, _col11, _col12, _col13
+ 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: _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string)
+ Reducer 14
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3, _col4, _col6, _col8, _col9, _col11, _col12, _col13, _col15, _col16, _col17, _col18, _col19
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col3 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col3 (type: int)
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col9 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int)
+ Reducer 15
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col3 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col4, _col6, _col8, _col9, _col11, _col12, _col13, _col15, _col16, _col17, _col18, _col19
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col9 (type: string), _col13 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col9 (type: string), _col13 (type: string)
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: decimal(7,2)), _col6 (type: string), _col8 (type: string), _col11 (type: string), _col12 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int)
+ Reducer 16
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col9 (type: string), _col13 (type: string)
+ 1 _col1 (type: string), upper(_col2) (type: string)
+ outputColumnNames: _col4, _col6, _col8, _col11, _col12, _col15, _col16, _col17, _col18, _col19, _col22
+ Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4)
+ keys: _col11 (type: string), _col12 (type: string), _col6 (type: string), _col8 (type: string), _col15 (type: decimal(7,2)), _col16 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: int), _col22 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+ Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: string)
+ sort order: ++++++++++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: int), _col9 (type: string)
+ Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col10 (type: decimal(17,2))
+ Reducer 17
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: string), KEY._col8 (type: int), KEY._col9 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+ Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col10 (type: decimal(17,2))
+ outputColumnNames: _col10
+ Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(_col10)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(27,2),input:decimal(17,2)>)
+ Reducer 18
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (0.05 * _col0) (type: decimal(24,8))
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: store
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((s_market_id = 7) and s_store_sk is not null and s_zip 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), s_store_name (type: string), s_state (type: string), s_zip (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 400), Map 7 (PARTITION-LEVEL SORT, 400)
+ Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 1009), Reducer 2 (PARTITION-LEVEL SORT, 1009)
+ Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 564), Reducer 3 (PARTITION-LEVEL SORT, 564)
+ Reducer 5 <- Map 11 (PARTITION-LEVEL SORT, 899), Reducer 4 (PARTITION-LEVEL SORT, 899)
+ Reducer 6 <- Reducer 5 (GROUP PARTITION-LEVEL SORT, 640)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean)
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_sales_price (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: decimal(7,2))
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: store_returns
+ Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sr_item_sk is not null and sr_ticket_number is not null) (type: boolean)
+ Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: sr_item_sk (type: int), sr_ticket_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 57591150 Data size: 4462194832 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: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: customer_address
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ca_zip is not null and upper(ca_country) is not null) (type: boolean)
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ca_state (type: string), ca_zip (type: string), ca_country (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), upper(_col2) (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), upper(_col2) (type: string)
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: item
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((i_color = 'orchid') 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_current_price (type: decimal(7,2)), i_size (type: string), i_units (type: string), i_manager_id (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5
+ 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: decimal(7,2)), _col2 (type: string), _col4 (type: string), _col5 (type: int)
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: customer
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (c_birth_country is not null and c_customer_sk is not null) (type: boolean)
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: c_customer_sk (type: int), c_first_name (type: string), c_last_name (type: string), c_birth_country (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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)
+ Reducer 2
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col6, _col7, _col9, _col10
+ 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: _col0, _col1, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15
+ input vertices:
+ 1 Map 8
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col3 (type: int), _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string)
+ 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, _col3, _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15, _col17, _col18, _col19
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col3 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col3 (type: int)
+ Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col15 (type: string), _col17 (type: string), _col18 (type: string), _col19 (type: string)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col3 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col15, _col17, _col18, _col19
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col15 (type: string), _col19 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col15 (type: string), _col19 (type: string)
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col12 (type: string), _col14 (type: string), _col17 (type: string), _col18 (type: string)
+ Reducer 5
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col15 (type: string), _col19 (type: string)
+ 1 _col1 (type: string), upper(_col2) (type: string)
+ outputColumnNames: _col4, _col6, _col7, _col9, _col10, _col12, _col14, _col17, _col18, _col22
+ Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4)
+ keys: _col17 (type: string), _col18 (type: string), _col12 (type: string), _col22 (type: string), _col6 (type: decimal(7,2)), _col7 (type: string), _col9 (type: string), _col10 (type: int), _col14 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: decimal(7,2)), _col5 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string)
+ sort order: +++++++++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ Statistics: Num rows: 927646829 Data size: 81837272625 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col9 (type: decimal(17,2))
+ Reducer 6
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: decimal(7,2)), KEY._col5 (type: string), KEY._col6 (type: string), KEY._col7 (type: int), KEY._col8 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col9 (type: decimal(17,2))
+ outputColumnNames: _col1, _col2, _col7, _col9
+ Statistics: Num rows: 463823414 Data size: 40918636268 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col9)
+ keys: _col1 (type: string), _col2 (type: string), _col7 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 231911707 Data size: 20459318134 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string), _col3 (type: decimal(27,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 231911707 Data size: 20459318134 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ input vertices:
+ 1 Reducer 18
+ Statistics: Num rows: 231911707 Data size: 113455912641 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col3 > _col4) (type: boolean)
+ Statistics: Num rows: 77303902 Data size: 37818637383 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: decimal(27,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 77303902 Data size: 37818637383 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 77303902 Data size: 37818637383 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query25.q.out b/ql/src/test/results/clientpositive/perf/spark/query25.q.out
new file mode 100644
index 0000000..3ecb2e5
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query25.q.out
@@ -0,0 +1,415 @@
+PREHOOK: query: explain
+select
+ i_item_id
+ ,i_item_desc
+ ,s_store_id
+ ,s_store_name
+ ,sum(ss_net_profit) as store_sales_profit
+ ,sum(sr_net_loss) as store_returns_loss
+ ,sum(cs_net_profit) as catalog_sales_profit
+ from
+ store_sales
+ ,store_returns
+ ,catalog_sales
+ ,date_dim d1
+ ,date_dim d2
+ ,date_dim d3
+ ,store
+ ,item
+ where
+ d1.d_moy = 4
+ and d1.d_year = 2000
+ and d1.d_date_sk = ss_sold_date_sk
+ and i_item_sk = ss_item_sk
+ and s_store_sk = ss_store_sk
+ and ss_customer_sk = sr_customer_sk
+ and ss_item_sk = sr_item_sk
+ and ss_ticket_number = sr_ticket_number
+ and sr_returned_date_sk = d2.d_date_sk
+ and d2.d_moy between 4 and 10
+ and d2.d_year = 2000
+ and sr_customer_sk = cs_bill_customer_sk
+ and sr_item_sk = cs_item_sk
+ and cs_sold_date_sk = d3.d_date_sk
+ and d3.d_moy between 4 and 10
+ and d3.d_year = 2000
+ group by
+ i_item_id
+ ,i_item_desc
+ ,s_store_id
+ ,s_store_name
+ order by
+ i_item_id
+ ,i_item_desc
+ ,s_store_id
+ ,s_store_name
+ limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+ i_item_id
+ ,i_item_desc
+ ,s_store_id
+ ,s_store_name
+ ,sum(ss_net_profit) as store_sales_profit
+ ,sum(sr_net_loss) as store_returns_loss
+ ,sum(cs_net_profit) as catalog_sales_profit
+ from
+ store_sales
+ ,store_returns
+ ,catalog_sales
+ ,date_dim d1
+ ,date_dim d2
+ ,date_dim d3
+ ,store
+ ,item
+ where
+ d1.d_moy = 4
+ and d1.d_year = 2000
+ and d1.d_date_sk = ss_sold_date_sk
+ and i_item_sk = ss_item_sk
+ and s_store_sk = ss_store_sk
+ and ss_customer_sk = sr_customer_sk
+ and ss_item_sk = sr_item_sk
+ and ss_ticket_number = sr_ticket_number
+ and sr_returned_date_sk = d2.d_date_sk
+ and d2.d_moy between 4 and 10
+ and d2.d_year = 2000
+ and sr_customer_sk = cs_bill_customer_sk
+ and sr_item_sk = cs_item_sk
+ and cs_sold_date_sk = d3.d_date_sk
+ and d3.d_moy between 4 and 10
+ and d3.d_year = 2000
+ group by
+ i_item_id
+ ,i_item_desc
+ ,s_store_id
+ ,s_store_name
+ order by
+ i_item_id
+ ,i_item_desc
+ ,s_store_id
+ ,s_store_name
+ limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-4 depends on stages: Stage-3
+ Stage-1 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: store
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: s_store_sk is not null (type: boolean)
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: s_store_sk (type: int), s_store_id (type: string), s_store_name (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: d3
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) (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
+
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 12
+ Map Operator Tree:
+ TableScan
+ alias: d2
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_year = 2000) and d_date_sk is not null and d_moy BETWEEN 4 AND 10) (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
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 398), Map 7 (PARTITION-LEVEL SORT, 398)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 806), Reducer 9 (PARTITION-LEVEL SORT, 806)
+ Reducer 4 <- Map 13 (PARTITION-LEVEL SORT, 486), Reducer 3 (PARTITION-LEVEL SORT, 486)
+ Reducer 5 <- Reducer 4 (GROUP, 582)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+ Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 374), Map 8 (PARTITION-LEVEL SORT, 374)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ss_customer_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null and ss_ticket_number is not null) (type: boolean)
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_customer_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_net_profit (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ 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: int), _col4 (type: int), _col5 (type: decimal(7,2))
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: store_returns
+ Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sr_customer_sk is not null and sr_item_sk is not null and sr_returned_date_sk is not null and sr_ticket_number is not null) (type: boolean)
+ Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_customer_sk (type: int), sr_ticket_number (type: int), sr_net_loss (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 57591150 Data size: 4462194832 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 12
+ Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int), _col2 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: int), _col2 (type: int)
+ Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int), _col4 (type: decimal(7,2))
+ Local Work:
+ Map Reduce Local Work
+ Map 13
+ 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_id (type: string), i_item_desc (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: d1
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_moy = 4) and (d_year = 2000) and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: 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_net_profit (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3
+ input vertices:
+ 1 Map 10
+ Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: int), _col1 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: int), _col1 (type: int)
+ Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: decimal(7,2))
+ 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 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int)
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int), _col5 (type: decimal(7,2))
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int), _col2 (type: int), _col4 (type: int)
+ 1 _col8 (type: int), _col9 (type: int), _col10 (type: int)
+ outputColumnNames: _col1, _col3, _col5, _col12, _col20
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int), _col5 (type: decimal(7,2)), _col12 (type: decimal(7,2)), _col20 (type: decimal(7,2))
+ Reducer 4
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col5, _col12, _col20, _col25, _col26
+ Statistics: Num rows: 766650239 Data size: 67634106676 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: _col5, _col12, _col20, _col25, _col26, _col28, _col29
+ input vertices:
+ 1 Map 14
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col5), sum(_col20), sum(_col12)
+ keys: _col25 (type: string), _col26 (type: string), _col28 (type: string), _col29 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: ++++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2))
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ sort order: ++++
+ Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2))
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2)), VALUE._col2 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 9
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int), _col1 (type: int)
+ 1 _col1 (type: int), _col2 (type: int)
+ outputColumnNames: _col3, _col8, _col9, _col10, _col11
+ Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col8 (type: int), _col9 (type: int), _col10 (type: int)
+ sort order: +++
+ Map-reduce partition columns: _col8 (type: int), _col9 (type: int), _col10 (type: int)
+ Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: decimal(7,2)), _col11 (type: decimal(7,2))
+
+ 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/query26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query26.q.out b/ql/src/test/results/clientpositive/perf/spark/query26.q.out
new file mode 100644
index 0000000..b0f64e1
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query26.q.out
@@ -0,0 +1,253 @@
+PREHOOK: query: explain
+select i_item_id,
+ avg(cs_quantity) agg1,
+ avg(cs_list_price) agg2,
+ avg(cs_coupon_amt) agg3,
+ avg(cs_sales_price) agg4
+ from catalog_sales, customer_demographics, date_dim, item, promotion
+ where cs_sold_date_sk = d_date_sk and
+ cs_item_sk = i_item_sk and
+ cs_bill_cdemo_sk = cd_demo_sk and
+ cs_promo_sk = p_promo_sk and
+ cd_gender = 'F' and
+ cd_marital_status = 'W' and
+ cd_education_status = 'Primary' and
+ (p_channel_email = 'N' or p_channel_event = 'N') and
+ d_year = 1998
+ group by i_item_id
+ order by i_item_id
+ limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select i_item_id,
+ avg(cs_quantity) agg1,
+ avg(cs_list_price) agg2,
+ avg(cs_coupon_amt) agg3,
+ avg(cs_sales_price) agg4
+ from catalog_sales, customer_demographics, date_dim, item, promotion
+ where cs_sold_date_sk = d_date_sk and
+ cs_item_sk = i_item_sk and
+ cs_bill_cdemo_sk = cd_demo_sk and
+ cs_promo_sk = p_promo_sk and
+ cd_gender = 'F' and
+ cd_marital_status = 'W' and
+ cd_education_status = 'Primary' and
+ (p_channel_email = 'N' or p_channel_event = 'N') and
+ d_year = 1998
+ group by i_item_id
+ order by i_item_id
+ limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-1 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: promotion
+ Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean)
+ 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 _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, 306), Map 7 (PARTITION-LEVEL SORT, 306)
+ Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 336), Reducer 2 (PARTITION-LEVEL SORT, 336)
+ Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 411), Reducer 3 (PARTITION-LEVEL SORT, 411)
+ Reducer 5 <- Reducer 4 (GROUP, 447)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: catalog_sales
+ Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_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_cdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_quantity (type: int), cs_list_price (type: decimal(7,2)), cs_sales_price (type: decimal(7,2)), cs_coupon_amt (type: decimal(7,2))
+ 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: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
+ Map 10
+ 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_id (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 7
+ Map Operator Tree:
+ TableScan
+ alias: customer_demographics
+ Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cd_demo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 232725 Data size: 89648269 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: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 316788826 Data size: 42899570777 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: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7
+ 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: _col2, _col4, _col5, _col6, _col7
+ input vertices:
+ 1 Map 9
+ Statistics: Num rows: 383314495 Data size: 51908482889 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: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col4, _col5, _col6, _col7, _col18
+ Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(_col4), avg(_col5), avg(_col7), avg(_col6)
+ keys: _col18 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>), _col3 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>), _col4 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), avg(VALUE._col3)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: double), _col2 (type: decimal(11,6)), _col3 (type: decimal(11,6)), _col4 (type: decimal(11,6))
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double), VALUE._col1 (type: decimal(11,6)), VALUE._col2 (type: decimal(11,6)), VALUE._col3 (type: decimal(11,6))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query27.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query27.q.out b/ql/src/test/results/clientpositive/perf/spark/query27.q.out
new file mode 100644
index 0000000..627821f
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query27.q.out
@@ -0,0 +1,265 @@
+PREHOOK: query: explain
+select i_item_id,
+ s_state, grouping(s_state) g_state,
+ avg(ss_quantity) agg1,
+ avg(ss_list_price) agg2,
+ avg(ss_coupon_amt) agg3,
+ avg(ss_sales_price) agg4
+ from store_sales, customer_demographics, date_dim, store, item
+ where ss_sold_date_sk = d_date_sk and
+ ss_item_sk = i_item_sk and
+ ss_store_sk = s_store_sk and
+ ss_cdemo_sk = cd_demo_sk and
+ cd_gender = 'M' and
+ cd_marital_status = 'U' and
+ cd_education_status = '2 yr Degree' and
+ d_year = 2001 and
+ s_state in ('SD','FL', 'MI', 'LA', 'MO', 'SC')
+ group by rollup (i_item_id, s_state)
+ order by i_item_id
+ ,s_state
+ limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select i_item_id,
+ s_state, grouping(s_state) g_state,
+ avg(ss_quantity) agg1,
+ avg(ss_list_price) agg2,
+ avg(ss_coupon_amt) agg3,
+ avg(ss_sales_price) agg4
+ from store_sales, customer_demographics, date_dim, store, item
+ where ss_sold_date_sk = d_date_sk and
+ ss_item_sk = i_item_sk and
+ ss_store_sk = s_store_sk and
+ ss_cdemo_sk = cd_demo_sk and
+ cd_gender = 'M' and
+ cd_marital_status = 'U' and
+ cd_education_status = '2 yr Degree' and
+ d_year = 2001 and
+ s_state in ('SD','FL', 'MI', 'LA', 'MO', 'SC')
+ group by rollup (i_item_id, s_state)
+ order by i_item_id
+ ,s_state
+ limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-1 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: store
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') 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), s_state (type: string)
+ outputColumnNames: _col0, _col1
+ 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, 398), Map 7 (PARTITION-LEVEL SORT, 398)
+ Reducer 3 <- Map 8 (PARTITION-LEVEL SORT, 438), Reducer 2 (PARTITION-LEVEL SORT, 438)
+ Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 534), Reducer 3 (PARTITION-LEVEL SORT, 534)
+ Reducer 5 <- Reducer 4 (GROUP, 1009)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ss_cdemo_sk is not null and ss_item_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean)
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_sold_date_sk (type: int), ss_item_sk (type: int), ss_cdemo_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_list_price (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)), ss_coupon_amt (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 575995635 Data size: 50814502088 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
+ Map 10
+ 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_id (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 7
+ Map Operator Tree:
+ TableScan
+ alias: customer_demographics
+ Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cd_demo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 232725 Data size: 89648269 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: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7
+ 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, _col5, _col6, _col7, _col15
+ input vertices:
+ 1 Map 9
+ Statistics: Num rows: 766650239 Data size: 67634106676 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: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col15 (type: string)
+ Reducer 4
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col4, _col5, _col6, _col7, _col15, _col17
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col17 (type: string), _col15 (type: string), _col4 (type: int), _col5 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col6 (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(_col2), avg(_col3), avg(_col4), avg(_col5)
+ keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 2529945843 Data size: 223192556868 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: 2529945843 Data size: 223192556868 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col3 (type: struct<count:bigint,sum:double,input:int>), _col4 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>), _col5 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>), _col6 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2), avg(VALUE._col3)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), grouping(_col2, 0) (type: int), _col3 (type: double), _col4 (type: decimal(11,6)), _col5 (type: decimal(11,6)), _col6 (type: decimal(11,6))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col2 (type: int), _col3 (type: double), _col4 (type: decimal(11,6)), _col5 (type: decimal(11,6)), _col6 (type: decimal(11,6))
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: int), VALUE._col1 (type: double), VALUE._col2 (type: decimal(11,6)), VALUE._col3 (type: decimal(11,6)), VALUE._col4 (type: decimal(11,6))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+