You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by st...@apache.org on 2017/09/28 18:12:18 UTC
[02/35] 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/query92.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query92.q.out b/ql/src/test/results/clientpositive/perf/spark/query92.q.out
new file mode 100644
index 0000000..677a85c
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query92.q.out
@@ -0,0 +1,303 @@
+PREHOOK: query: explain
+select
+ sum(ws_ext_discount_amt) as `Excess Discount Amount`
+from
+ web_sales
+ ,item
+ ,date_dim
+where
+i_manufact_id = 269
+and i_item_sk = ws_item_sk
+and d_date between '1998-03-18' and
+ (cast('1998-03-18' as date) + 90 days)
+and d_date_sk = ws_sold_date_sk
+and ws_ext_discount_amt
+ > (
+ SELECT
+ 1.3 * avg(ws_ext_discount_amt)
+ FROM
+ web_sales
+ ,date_dim
+ WHERE
+ ws_item_sk = i_item_sk
+ and d_date between '1998-03-18' and
+ (cast('1998-03-18' as date) + 90 days)
+ and d_date_sk = ws_sold_date_sk
+ )
+order by sum(ws_ext_discount_amt)
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+ sum(ws_ext_discount_amt) as `Excess Discount Amount`
+from
+ web_sales
+ ,item
+ ,date_dim
+where
+i_manufact_id = 269
+and i_item_sk = ws_item_sk
+and d_date between '1998-03-18' and
+ (cast('1998-03-18' as date) + 90 days)
+and d_date_sk = ws_sold_date_sk
+and ws_ext_discount_amt
+ > (
+ SELECT
+ 1.3 * avg(ws_ext_discount_amt)
+ FROM
+ web_sales
+ ,date_dim
+ WHERE
+ ws_item_sk = i_item_sk
+ and d_date between '1998-03-18' and
+ (cast('1998-03-18' as date) + 90 days)
+ and d_date_sk = ws_sold_date_sk
+ )
+order by sum(ws_ext_discount_amt)
+limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1998-03-18 00:00:00.0 AND 1998-06-16 01:00:00.0 and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1998-03-18 00:00:00.0 AND 1998-06-16 01:00:00.0 and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 261), Reducer 8 (PARTITION-LEVEL SORT, 261)
+ Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 4 <- Reducer 3 (SORT, 1)
+ Reducer 7 <- Map 6 (GROUP, 169)
+ Reducer 8 <- Map 10 (PARTITION-LEVEL SORT, 87), Reducer 7 (PARTITION-LEVEL SORT, 87)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (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_ext_discount_amt (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2
+ input vertices:
+ 1 Map 5
+ 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: decimal(7,2))
+ Local Work:
+ Map Reduce Local Work
+ 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_manufact_id = 269) 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)
+ outputColumnNames: _col0
+ 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
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_item_sk is not null and ws_sold_date_sk is not null) (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_ext_discount_amt (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2
+ input vertices:
+ 1 Map 9
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(_col2)
+ keys: _col1 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 158402938 Data size: 21538218500 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<count:bigint,sum:decimal(17,2),input: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 _col1 (type: int)
+ 1 _col2 (type: int)
+ outputColumnNames: _col2, _col5
+ Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col2 > _col5) (type: boolean)
+ Statistics: Num rows: 58081078 Data size: 7897346909 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: decimal(7,2))
+ outputColumnNames: _col2
+ Statistics: Num rows: 58081078 Data size: 7897346909 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col2)
+ 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
+ value expressions: _col0 (type: decimal(17,2))
+ Reducer 3
+ 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
+ Select Operator
+ expressions: _col0 (type: decimal(17,2))
+ outputColumnNames: _col1
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: decimal(17,2))
+ sort order: +
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: decimal(17,2))
+ 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 7
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (1.3 * _col1) (type: decimal(14,7)), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 79201469 Data size: 10769109250 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: 79201469 Data size: 10769109250 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(14,7))
+ Reducer 8
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 87121617 Data size: 11846020431 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: 87121617 Data size: 11846020431 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: decimal(14,7))
+
+ 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/query93.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query93.q.out b/ql/src/test/results/clientpositive/perf/spark/query93.q.out
new file mode 100644
index 0000000..71fbeb1
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query93.q.out
@@ -0,0 +1,181 @@
+PREHOOK: query: explain
+select ss_customer_sk
+ ,sum(act_sales) sumsales
+ from (select ss_item_sk
+ ,ss_ticket_number
+ ,ss_customer_sk
+ ,case when sr_return_quantity is not null then (ss_quantity-sr_return_quantity)*ss_sales_price
+ else (ss_quantity*ss_sales_price) end act_sales
+ from store_sales left outer join store_returns on (sr_item_sk = ss_item_sk
+ and sr_ticket_number = ss_ticket_number)
+ ,reason
+ where sr_reason_sk = r_reason_sk
+ and r_reason_desc = 'Did not like the warranty') t
+ group by ss_customer_sk
+ order by sumsales, ss_customer_sk
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select ss_customer_sk
+ ,sum(act_sales) sumsales
+ from (select ss_item_sk
+ ,ss_ticket_number
+ ,ss_customer_sk
+ ,case when sr_return_quantity is not null then (ss_quantity-sr_return_quantity)*ss_sales_price
+ else (ss_quantity*ss_sales_price) end act_sales
+ from store_sales left outer join store_returns on (sr_item_sk = ss_item_sk
+ and sr_ticket_number = ss_ticket_number)
+ ,reason
+ where sr_reason_sk = r_reason_sk
+ and r_reason_desc = 'Did not like the warranty') t
+ group by ss_customer_sk
+ order by sumsales, ss_customer_sk
+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 5
+ Map Operator Tree:
+ TableScan
+ alias: reason
+ Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((r_reason_desc = 'Did not like the warranty') and r_reason_sk is not null) (type: boolean)
+ Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: r_reason_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 436), Map 6 (PARTITION-LEVEL SORT, 436)
+ Reducer 3 <- Reducer 2 (GROUP, 437)
+ Reducer 4 <- Reducer 3 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ 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_reason_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_reason_sk (type: int), sr_ticket_number (type: int), sr_return_quantity (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ 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 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col2 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col2 (type: int)
+ Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 6
+ 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_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_ticket_number (type: int), ss_quantity (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), _col2 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col2 (type: int)
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col3 (type: int), _col4 (type: decimal(7,2))
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int), _col2 (type: int)
+ 1 _col0 (type: int), _col2 (type: int)
+ outputColumnNames: _col3, _col7, _col9, _col10
+ Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col7 (type: int), CASE WHEN (_col3 is not null) THEN ((CAST( (_col9 - _col3) AS decimal(10,0)) * _col10)) ELSE ((CAST( _col9 AS decimal(10,0)) * _col10)) END (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 3
+ 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
+ Reduce Output Operator
+ key expressions: _col1 (type: decimal(28,2)), _col0 (type: int)
+ sort order: ++
+ Statistics: Num rows: 316797606 Data size: 27947976754 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: int), KEY.reducesinkkey0 (type: decimal(28,2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 316797606 Data size: 27947976754 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
+
http://git-wip-us.apache.org/repos/asf/hive/blob/bd371246/ql/src/test/results/clientpositive/perf/spark/query94.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query94.q.out b/ql/src/test/results/clientpositive/perf/spark/query94.q.out
new file mode 100644
index 0000000..4ee2ed8
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query94.q.out
@@ -0,0 +1,359 @@
+PREHOOK: query: explain
+select
+ count(distinct ws_order_number) as `order count`
+ ,sum(ws_ext_ship_cost) as `total shipping cost`
+ ,sum(ws_net_profit) as `total net profit`
+from
+ web_sales ws1
+ ,date_dim
+ ,customer_address
+ ,web_site
+where
+ d_date between '1999-5-01' and
+ (cast('1999-5-01' as date) + 60 days)
+and ws1.ws_ship_date_sk = d_date_sk
+and ws1.ws_ship_addr_sk = ca_address_sk
+and ca_state = 'TX'
+and ws1.ws_web_site_sk = web_site_sk
+and web_company_name = 'pri'
+and exists (select *
+ from web_sales ws2
+ where ws1.ws_order_number = ws2.ws_order_number
+ and ws1.ws_warehouse_sk <> ws2.ws_warehouse_sk)
+and not exists(select *
+ from web_returns wr1
+ where ws1.ws_order_number = wr1.wr_order_number)
+order by count(distinct ws_order_number)
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+ count(distinct ws_order_number) as `order count`
+ ,sum(ws_ext_ship_cost) as `total shipping cost`
+ ,sum(ws_net_profit) as `total net profit`
+from
+ web_sales ws1
+ ,date_dim
+ ,customer_address
+ ,web_site
+where
+ d_date between '1999-5-01' and
+ (cast('1999-5-01' as date) + 60 days)
+and ws1.ws_ship_date_sk = d_date_sk
+and ws1.ws_ship_addr_sk = ca_address_sk
+and ca_state = 'TX'
+and ws1.ws_web_site_sk = web_site_sk
+and web_company_name = 'pri'
+and exists (select *
+ from web_sales ws2
+ where ws1.ws_order_number = ws2.ws_order_number
+ and ws1.ws_warehouse_sk <> ws2.ws_warehouse_sk)
+and not exists(select *
+ from web_returns wr1
+ where ws1.ws_order_number = wr1.wr_order_number)
+order by count(distinct ws_order_number)
+limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: web_site
+ Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((web_company_name = 'pri') and web_site_sk is not null) (type: boolean)
+ Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: web_site_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1999-05-01 00:00:00.0 AND 1999-06-30 00:00:00.0 and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 11 <- Map 10 (GROUP, 11)
+ Reducer 13 <- Map 12 (GROUP, 153)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 327), Map 8 (PARTITION-LEVEL SORT, 327)
+ Reducer 3 <- Reducer 11 (PARTITION-LEVEL SORT, 286), Reducer 13 (PARTITION-LEVEL SORT, 286), Reducer 2 (PARTITION-LEVEL SORT, 286)
+ Reducer 4 <- Reducer 3 (GROUP, 224)
+ Reducer 5 <- Reducer 4 (GROUP, 1)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: ws1
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_ship_date_sk (type: int), ws_ship_addr_sk (type: int), ws_web_site_sk (type: int), ws_warehouse_sk (type: int), ws_order_number (type: int), ws_ext_ship_cost (type: decimal(7,2)), ws_net_profit (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6
+ input vertices:
+ 1 Map 7
+ 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: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2))
+ Local Work:
+ Map Reduce Local Work
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: wr1
+ Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: wr_order_number is not null (type: boolean)
+ Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: wr_order_number (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 14398467 Data size: 1325194184 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: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ Map 12
+ Map Operator Tree:
+ TableScan
+ alias: ws2
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_order_number is not null and ws_warehouse_sk is not null) (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: ws_order_number (type: int), ws_warehouse_sk (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: customer_address
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((ca_state = 'TX') and ca_address_sk is not null) (type: boolean)
+ Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ca_address_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
+ Reducer 11
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 7199233 Data size: 662597045 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), true (type: boolean)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 7199233 Data size: 662597045 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: 7199233 Data size: 662597045 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: boolean)
+ Reducer 13
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 72001334 Data size: 9790099106 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: 72001334 Data size: 9790099106 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Reducer 2
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col4, _col5, _col6
+ input vertices:
+ 1 Map 9
+ Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col4 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: int)
+ Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2))
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0 _col4 (type: int)
+ 1 _col0 (type: int)
+ 2 _col1 (type: int)
+ outputColumnNames: _col3, _col4, _col5, _col6, _col14, _col15
+ residual filter predicates: {(_col3 <> _col15)}
+ Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col14 (type: boolean)
+ outputColumnNames: _col4, _col5, _col6, _col16
+ Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col16 is null (type: boolean)
+ Statistics: Num rows: 210834322 Data size: 28667370618 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2))
+ outputColumnNames: _col4, _col5, _col6
+ Statistics: Num rows: 210834322 Data size: 28667370618 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col5), sum(_col6)
+ keys: _col4 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 210834322 Data size: 28667370618 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: 210834322 Data size: 28667370618 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2))
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: int)
+ mode: partial2
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 210834322 Data size: 28667370618 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(_col0), sum(_col1), sum(_col2)
+ mode: partial2
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2))
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col0 (type: bigint)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2))
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 344 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/query95.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query95.q.out b/ql/src/test/results/clientpositive/perf/spark/query95.q.out
new file mode 100644
index 0000000..0d136b6
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query95.q.out
@@ -0,0 +1,468 @@
+PREHOOK: query: explain
+with ws_wh as
+(select ws1.ws_order_number,ws1.ws_warehouse_sk wh1,ws2.ws_warehouse_sk wh2
+ from web_sales ws1,web_sales ws2
+ where ws1.ws_order_number = ws2.ws_order_number
+ and ws1.ws_warehouse_sk <> ws2.ws_warehouse_sk)
+ select
+ count(distinct ws_order_number) as `order count`
+ ,sum(ws_ext_ship_cost) as `total shipping cost`
+ ,sum(ws_net_profit) as `total net profit`
+from
+ web_sales ws1
+ ,date_dim
+ ,customer_address
+ ,web_site
+where
+ d_date between '1999-5-01' and
+ (cast('1999-5-01' as date) + 60 days)
+and ws1.ws_ship_date_sk = d_date_sk
+and ws1.ws_ship_addr_sk = ca_address_sk
+and ca_state = 'TX'
+and ws1.ws_web_site_sk = web_site_sk
+and web_company_name = 'pri'
+and ws1.ws_order_number in (select ws_order_number
+ from ws_wh)
+and ws1.ws_order_number in (select wr_order_number
+ from web_returns,ws_wh
+ where wr_order_number = ws_wh.ws_order_number)
+order by count(distinct ws_order_number)
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+with ws_wh as
+(select ws1.ws_order_number,ws1.ws_warehouse_sk wh1,ws2.ws_warehouse_sk wh2
+ from web_sales ws1,web_sales ws2
+ where ws1.ws_order_number = ws2.ws_order_number
+ and ws1.ws_warehouse_sk <> ws2.ws_warehouse_sk)
+ select
+ count(distinct ws_order_number) as `order count`
+ ,sum(ws_ext_ship_cost) as `total shipping cost`
+ ,sum(ws_net_profit) as `total net profit`
+from
+ web_sales ws1
+ ,date_dim
+ ,customer_address
+ ,web_site
+where
+ d_date between '1999-5-01' and
+ (cast('1999-5-01' as date) + 60 days)
+and ws1.ws_ship_date_sk = d_date_sk
+and ws1.ws_ship_addr_sk = ca_address_sk
+and ca_state = 'TX'
+and ws1.ws_web_site_sk = web_site_sk
+and web_company_name = 'pri'
+and ws1.ws_order_number in (select ws_order_number
+ from ws_wh)
+and ws1.ws_order_number in (select wr_order_number
+ from web_returns,ws_wh
+ where wr_order_number = ws_wh.ws_order_number)
+order by count(distinct ws_order_number)
+limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: web_site
+ Statistics: Num rows: 84 Data size: 155408 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((web_company_name = 'pri') and web_site_sk is not null) (type: boolean)
+ Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: web_site_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 42 Data size: 77704 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (CAST( d_date AS TIMESTAMP) BETWEEN 1999-05-01 00:00:00.0 AND 1999-06-30 00:00:00.0 and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 11 <- Map 10 (PARTITION-LEVEL SORT, 306), Map 13 (PARTITION-LEVEL SORT, 306)
+ Reducer 12 <- Reducer 11 (GROUP, 169)
+ Reducer 15 <- Map 14 (PARTITION-LEVEL SORT, 306), Map 18 (PARTITION-LEVEL SORT, 306)
+ Reducer 16 <- Map 19 (PARTITION-LEVEL SORT, 179), Reducer 15 (PARTITION-LEVEL SORT, 179)
+ Reducer 17 <- Reducer 16 (GROUP, 186)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 327), Map 8 (PARTITION-LEVEL SORT, 327)
+ Reducer 3 <- Reducer 12 (PARTITION-LEVEL SORT, 381), Reducer 17 (PARTITION-LEVEL SORT, 381), Reducer 2 (PARTITION-LEVEL SORT, 381)
+ Reducer 4 <- Reducer 3 (GROUP, 448)
+ Reducer 5 <- Reducer 4 (GROUP, 1)
+ Reducer 6 <- Reducer 5 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: ws1
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_order_number is not null and ws_ship_addr_sk is not null and ws_ship_date_sk is not null and ws_web_site_sk is not null) (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_ship_date_sk (type: int), ws_ship_addr_sk (type: int), ws_web_site_sk (type: int), ws_order_number (type: int), ws_ext_ship_cost (type: decimal(7,2)), ws_net_profit (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5
+ input vertices:
+ 1 Map 7
+ 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)), _col5 (type: decimal(7,2))
+ Local Work:
+ Map Reduce Local Work
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: ws1
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ws_order_number is not null (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_warehouse_sk (type: int), ws_order_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Map 13
+ Map Operator Tree:
+ TableScan
+ alias: ws2
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ws_order_number is not null (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_warehouse_sk (type: int), ws_order_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: ws1
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ws_order_number is not null (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_warehouse_sk (type: int), ws_order_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Map 18
+ Map Operator Tree:
+ TableScan
+ alias: ws2
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ws_order_number is not null (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_warehouse_sk (type: int), ws_order_number (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 144002668 Data size: 19580198212 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: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Map 19
+ Map Operator Tree:
+ TableScan
+ alias: web_returns
+ Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: wr_order_number is not null (type: boolean)
+ Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: wr_order_number (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 14398467 Data size: 1325194184 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: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: customer_address
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((ca_state = 'TX') and ca_address_sk is not null) (type: boolean)
+ Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ca_address_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
+ Reducer 11
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 <> _col2) (type: boolean)
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int)
+ outputColumnNames: _col1
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 158402938 Data size: 21538218500 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Reducer 12
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 79201469 Data size: 10769109250 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: 79201469 Data size: 10769109250 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 _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (_col0 <> _col2) (type: boolean)
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 158402938 Data size: 21538218500 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: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Reducer 16
+ 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: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col1 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 174243235 Data size: 23692040863 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: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Reducer 17
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 87121617 Data size: 11846020363 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: 87121617 Data size: 11846020363 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2, _col3, _col4, _col5
+ Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col3, _col4, _col5
+ input vertices:
+ 1 Map 9
+ Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col3 (type: int)
+ Statistics: Num rows: 191667562 Data size: 26061245514 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col4 (type: decimal(7,2)), _col5 (type: decimal(7,2))
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ keys:
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ 2 _col0 (type: int)
+ outputColumnNames: _col3, _col4, _col5
+ Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col4), sum(_col5)
+ keys: _col3 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 421668645 Data size: 57334741373 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: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col2 (type: decimal(17,2)), _col3 (type: decimal(17,2))
+ Reducer 4
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1)
+ keys: KEY._col0 (type: int)
+ mode: partial2
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 421668645 Data size: 57334741373 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(_col0), sum(_col1), sum(_col2)
+ mode: partial2
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2))
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2)), _col0 (type: bigint)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ value expressions: _col1 (type: decimal(17,2)), _col2 (type: decimal(17,2))
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: decimal(17,2)), VALUE._col1 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 344 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/query96.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query96.q.out b/ql/src/test/results/clientpositive/perf/spark/query96.q.out
new file mode 100644
index 0000000..fed8084
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query96.q.out
@@ -0,0 +1,193 @@
+PREHOOK: query: explain
+select count(*)
+from store_sales
+ ,household_demographics
+ ,time_dim, store
+where ss_sold_time_sk = time_dim.t_time_sk
+ and ss_hdemo_sk = household_demographics.hd_demo_sk
+ and ss_store_sk = s_store_sk
+ and time_dim.t_hour = 8
+ and time_dim.t_minute >= 30
+ and household_demographics.hd_dep_count = 5
+ and store.s_store_name = 'ese'
+order by count(*)
+limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*)
+from store_sales
+ ,household_demographics
+ ,time_dim, store
+where ss_sold_time_sk = time_dim.t_time_sk
+ and ss_hdemo_sk = household_demographics.hd_demo_sk
+ and ss_store_sk = s_store_sk
+ and time_dim.t_hour = 8
+ and time_dim.t_minute >= 30
+ and household_demographics.hd_dep_count = 5
+ and store.s_store_name = 'ese'
+order by count(*)
+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 4
+ Map Operator Tree:
+ TableScan
+ alias: time_dim
+ Statistics: Num rows: 86400 Data size: 40694400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((t_hour = 8) and (t_minute >= 30) and t_time_sk is not null) (type: boolean)
+ Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t_time_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 14400 Data size: 6782400 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: household_demographics
+ Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((hd_dep_count = 5) and hd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hd_demo_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: store
+ Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((s_store_name = 'ese') and s_store_sk is not null) (type: boolean)
+ Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: s_store_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 852 Data size: 1628138 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+ Reducer 3 <- Reducer 2 (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_hdemo_sk is not null and ss_sold_time_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_time_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2
+ input vertices:
+ 1 Map 4
+ 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 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2
+ input vertices:
+ 1 Map 5
+ 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 _col2 (type: int)
+ 1 _col0 (type: int)
+ input vertices:
+ 1 Map 6
+ Statistics: Num rows: 766650239 Data size: 67634106676 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)
+ Local Work:
+ Map Reduce Local Work
+ Reducer 2
+ 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
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col1
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: bigint)
+ sort order: +
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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
+