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 03:35:58 UTC
[07/48] 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/query9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query9.q.out b/ql/src/test/results/clientpositive/perf/spark/query9.q.out
new file mode 100644
index 0000000..4ec2007
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query9.q.out
@@ -0,0 +1,824 @@
+Warning: Map Join MAPJOIN[171][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[172][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[173][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[174][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[175][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[176][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[177][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[178][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[179][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[180][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[181][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[182][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[183][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[184][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+Warning: Map Join MAPJOIN[185][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain
+select case when (select count(*)
+ from store_sales
+ where ss_quantity between 1 and 20) > 409437
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 1 and 20)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 1 and 20) end bucket1 ,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 21 and 40) > 4595804
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 21 and 40)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 21 and 40) end bucket2,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 41 and 60) > 7887297
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 41 and 60)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 41 and 60) end bucket3,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 61 and 80) > 10872978
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 61 and 80)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 61 and 80) end bucket4,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 81 and 100) > 43571537
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 81 and 100)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 81 and 100) end bucket5
+from reason
+where r_reason_sk = 1
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select case when (select count(*)
+ from store_sales
+ where ss_quantity between 1 and 20) > 409437
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 1 and 20)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 1 and 20) end bucket1 ,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 21 and 40) > 4595804
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 21 and 40)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 21 and 40) end bucket2,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 41 and 60) > 7887297
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 41 and 60)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 41 and 60) end bucket3,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 61 and 80) > 10872978
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 61 and 80)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 61 and 80) end bucket4,
+ case when (select count(*)
+ from store_sales
+ where ss_quantity between 81 and 100) > 43571537
+ then (select avg(ss_ext_list_price)
+ from store_sales
+ where ss_quantity between 81 and 100)
+ else (select avg(ss_net_paid_inc_tax)
+ from store_sales
+ where ss_quantity between 81 and 100) end bucket5
+from reason
+where r_reason_sk = 1
+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
+ Edges:
+ Reducer 11 <- Map 10 (GROUP, 1)
+ Reducer 13 <- Map 12 (GROUP, 1)
+ Reducer 15 <- Map 14 (GROUP, 1)
+ Reducer 17 <- Map 16 (GROUP, 1)
+ Reducer 19 <- Map 18 (GROUP, 1)
+ Reducer 21 <- Map 20 (GROUP, 1)
+ Reducer 23 <- Map 22 (GROUP, 1)
+ Reducer 25 <- Map 24 (GROUP, 1)
+ Reducer 27 <- Map 26 (GROUP, 1)
+ Reducer 29 <- Map 28 (GROUP, 1)
+ Reducer 3 <- Map 2 (GROUP, 1)
+ Reducer 31 <- Map 30 (GROUP, 1)
+ Reducer 5 <- Map 4 (GROUP, 1)
+ Reducer 7 <- Map 6 (GROUP, 1)
+ Reducer 9 <- Map 8 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 21 AND 40 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_ext_list_price (type: decimal(7,2))
+ outputColumnNames: ss_ext_list_price
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_ext_list_price)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ 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_quantity BETWEEN 21 AND 40 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_net_paid_inc_tax (type: decimal(7,2))
+ outputColumnNames: ss_net_paid_inc_tax
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_net_paid_inc_tax)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 41 AND 60 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 63999515 Data size: 5646055787 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)
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 41 AND 60 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_ext_list_price (type: decimal(7,2))
+ outputColumnNames: ss_ext_list_price
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_ext_list_price)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 18
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 41 AND 60 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_net_paid_inc_tax (type: decimal(7,2))
+ outputColumnNames: ss_net_paid_inc_tax
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_net_paid_inc_tax)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 1 AND 20 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 63999515 Data size: 5646055787 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)
+ Map 20
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 61 AND 80 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 63999515 Data size: 5646055787 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)
+ Map 22
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 61 AND 80 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_ext_list_price (type: decimal(7,2))
+ outputColumnNames: ss_ext_list_price
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_ext_list_price)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 24
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 61 AND 80 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_net_paid_inc_tax (type: decimal(7,2))
+ outputColumnNames: ss_net_paid_inc_tax
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_net_paid_inc_tax)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 26
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 81 AND 100 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 63999515 Data size: 5646055787 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)
+ Map 28
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 81 AND 100 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_ext_list_price (type: decimal(7,2))
+ outputColumnNames: ss_ext_list_price
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_ext_list_price)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 30
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 81 AND 100 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_net_paid_inc_tax (type: decimal(7,2))
+ outputColumnNames: ss_net_paid_inc_tax
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_net_paid_inc_tax)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 1 AND 20 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_ext_list_price (type: decimal(7,2))
+ outputColumnNames: ss_ext_list_price
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_ext_list_price)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ 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_quantity BETWEEN 1 AND 20 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ss_net_paid_inc_tax (type: decimal(7,2))
+ outputColumnNames: ss_net_paid_inc_tax
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg(ss_net_paid_inc_tax)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<count:bigint,sum:decimal(17,2),input:decimal(7,2)>)
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: store_sales
+ Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ss_quantity BETWEEN 21 AND 40 (type: boolean)
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 63999515 Data size: 5646055787 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Reducer 11
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 13
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 15
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 17
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 19
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 21
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 23
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 25
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 27
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 29
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 31
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 5
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 7
+ 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: 288 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+ Reducer 9
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: reason
+ Statistics: Num rows: 72 Data size: 14400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (r_reason_sk = 1) (type: boolean)
+ Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 36 Data size: 7200 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1
+ input vertices:
+ 1 Reducer 3
+ Statistics: Num rows: 36 Data size: 7524 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2
+ input vertices:
+ 1 Reducer 5
+ Statistics: Num rows: 36 Data size: 17928 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3
+ input vertices:
+ 1 Reducer 7
+ Statistics: Num rows: 36 Data size: 28332 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4
+ input vertices:
+ 1 Reducer 9
+ Statistics: Num rows: 36 Data size: 28656 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5
+ input vertices:
+ 1 Reducer 11
+ Statistics: Num rows: 36 Data size: 39060 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6
+ input vertices:
+ 1 Reducer 13
+ Statistics: Num rows: 36 Data size: 49464 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ input vertices:
+ 1 Reducer 15
+ Statistics: Num rows: 36 Data size: 49788 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ input vertices:
+ 1 Reducer 17
+ Statistics: Num rows: 36 Data size: 60192 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ input vertices:
+ 1 Reducer 19
+ Statistics: Num rows: 36 Data size: 70596 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+ input vertices:
+ 1 Reducer 21
+ Statistics: Num rows: 36 Data size: 70920 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
+ input vertices:
+ 1 Reducer 23
+ Statistics: Num rows: 36 Data size: 81324 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
+ input vertices:
+ 1 Reducer 25
+ Statistics: Num rows: 36 Data size: 91728 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
+ input vertices:
+ 1 Reducer 27
+ Statistics: Num rows: 36 Data size: 92052 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
+ input vertices:
+ 1 Reducer 29
+ Statistics: Num rows: 36 Data size: 102456 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
+ input vertices:
+ 1 Reducer 31
+ Statistics: Num rows: 36 Data size: 112860 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: CASE WHEN ((_col1 > 409437)) THEN (_col2) ELSE (_col3) END (type: decimal(11,6)), CASE WHEN ((_col4 > 4595804)) THEN (_col5) ELSE (_col6) END (type: decimal(11,6)), CASE WHEN ((_col7 > 7887297)) THEN (_col8) ELSE (_col9) END (type: decimal(11,6)), CASE WHEN ((_col10 > 10872978)) THEN (_col11) ELSE (_col12) END (type: decimal(11,6)), CASE WHEN ((_col13 > 43571537)) THEN (_col14) ELSE (_col15) END (type: decimal(11,6))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 36 Data size: 112860 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 36 Data size: 112860 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
+ Local Work:
+ Map Reduce Local Work
+
+ 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/query90.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query90.q.out b/ql/src/test/results/clientpositive/perf/spark/query90.q.out
new file mode 100644
index 0000000..115a2cc
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query90.q.out
@@ -0,0 +1,351 @@
+Warning: Map Join MAPJOIN[68][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
+PREHOOK: query: explain
+select cast(amc as decimal(15,4))/cast(pmc as decimal(15,4)) am_pm_ratio
+ from ( select count(*) amc
+ from web_sales, household_demographics , time_dim, web_page
+ where ws_sold_time_sk = time_dim.t_time_sk
+ and ws_ship_hdemo_sk = household_demographics.hd_demo_sk
+ and ws_web_page_sk = web_page.wp_web_page_sk
+ and time_dim.t_hour between 6 and 6+1
+ and household_demographics.hd_dep_count = 8
+ and web_page.wp_char_count between 5000 and 5200) at,
+ ( select count(*) pmc
+ from web_sales, household_demographics , time_dim, web_page
+ where ws_sold_time_sk = time_dim.t_time_sk
+ and ws_ship_hdemo_sk = household_demographics.hd_demo_sk
+ and ws_web_page_sk = web_page.wp_web_page_sk
+ and time_dim.t_hour between 14 and 14+1
+ and household_demographics.hd_dep_count = 8
+ and web_page.wp_char_count between 5000 and 5200) pt
+ order by am_pm_ratio
+ limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select cast(amc as decimal(15,4))/cast(pmc as decimal(15,4)) am_pm_ratio
+ from ( select count(*) amc
+ from web_sales, household_demographics , time_dim, web_page
+ where ws_sold_time_sk = time_dim.t_time_sk
+ and ws_ship_hdemo_sk = household_demographics.hd_demo_sk
+ and ws_web_page_sk = web_page.wp_web_page_sk
+ and time_dim.t_hour between 6 and 6+1
+ and household_demographics.hd_dep_count = 8
+ and web_page.wp_char_count between 5000 and 5200) at,
+ ( select count(*) pmc
+ from web_sales, household_demographics , time_dim, web_page
+ where ws_sold_time_sk = time_dim.t_time_sk
+ and ws_ship_hdemo_sk = household_demographics.hd_demo_sk
+ and ws_web_page_sk = web_page.wp_web_page_sk
+ and time_dim.t_hour between 14 and 14+1
+ and household_demographics.hd_dep_count = 8
+ and web_page.wp_char_count between 5000 and 5200) pt
+ order by am_pm_ratio
+ limit 100
+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 10
+ 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 BETWEEN 14 AND 15 and t_time_sk is not null) (type: boolean)
+ Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t_time_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 9600 Data size: 4521600 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 11
+ 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 = 8) 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 9
+ Map Operator Tree:
+ TableScan
+ alias: web_page
+ Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean)
+ Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: wp_web_page_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 511 Data size: 299380 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 8 <- Map 7 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_sold_time_sk (type: int), ws_ship_hdemo_sk (type: int), ws_web_page_sk (type: int)
+ 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 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 9
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 10
+ 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 _col1 (type: int)
+ 1 _col0 (type: int)
+ input vertices:
+ 1 Map 11
+ Statistics: Num rows: 191667562 Data size: 26061245514 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 8
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0
+ 1
+
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: web_page
+ Statistics: Num rows: 4602 Data size: 2696178 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (wp_char_count BETWEEN 5000 AND 5200 and wp_web_page_sk is not null) (type: boolean)
+ Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: wp_web_page_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 511 Data size: 299380 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 5
+ 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 BETWEEN 6 AND 7 and t_time_sk is not null) (type: boolean)
+ Statistics: Num rows: 9600 Data size: 4521600 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: t_time_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 9600 Data size: 4521600 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 6
+ 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 = 8) 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
+
+ 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: web_sales
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (ws_ship_hdemo_sk is not null and ws_sold_time_sk is not null and ws_web_page_sk is not null) (type: boolean)
+ Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ws_sold_time_sk (type: int), ws_ship_hdemo_sk (type: int), ws_web_page_sk (type: int)
+ 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 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 5
+ 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 _col1 (type: int)
+ 1 _col0 (type: int)
+ input vertices:
+ 1 Map 6
+ Statistics: Num rows: 191667562 Data size: 26061245514 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
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Reducer 8
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: (CAST( _col0 AS decimal(15,4)) / CAST( _col1 AS decimal(15,4))) (type: decimal(35,20))
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: decimal(35,20))
+ sort order: +
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.1
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: decimal(35,20))
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 17 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/query91.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query91.q.out b/ql/src/test/results/clientpositive/perf/spark/query91.q.out
new file mode 100644
index 0000000..fce1a15
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/spark/query91.q.out
@@ -0,0 +1,347 @@
+PREHOOK: query: explain
+select
+ cc_call_center_id Call_Center,
+ cc_name Call_Center_Name,
+ cc_manager Manager,
+ sum(cr_net_loss) Returns_Loss
+from
+ call_center,
+ catalog_returns,
+ date_dim,
+ customer,
+ customer_address,
+ customer_demographics,
+ household_demographics
+where
+ cr_call_center_sk = cc_call_center_sk
+and cr_returned_date_sk = d_date_sk
+and cr_returning_customer_sk= c_customer_sk
+and cd_demo_sk = c_current_cdemo_sk
+and hd_demo_sk = c_current_hdemo_sk
+and ca_address_sk = c_current_addr_sk
+and d_year = 1999
+and d_moy = 11
+and ( (cd_marital_status = 'M' and cd_education_status = 'Unknown')
+ or(cd_marital_status = 'W' and cd_education_status = 'Advanced Degree'))
+and hd_buy_potential like '0-500%'
+and ca_gmt_offset = -7
+group by cc_call_center_id,cc_name,cc_manager,cd_marital_status,cd_education_status
+order by sum(cr_net_loss) desc
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select
+ cc_call_center_id Call_Center,
+ cc_name Call_Center_Name,
+ cc_manager Manager,
+ sum(cr_net_loss) Returns_Loss
+from
+ call_center,
+ catalog_returns,
+ date_dim,
+ customer,
+ customer_address,
+ customer_demographics,
+ household_demographics
+where
+ cr_call_center_sk = cc_call_center_sk
+and cr_returned_date_sk = d_date_sk
+and cr_returning_customer_sk= c_customer_sk
+and cd_demo_sk = c_current_cdemo_sk
+and hd_demo_sk = c_current_hdemo_sk
+and ca_address_sk = c_current_addr_sk
+and d_year = 1999
+and d_moy = 11
+and ( (cd_marital_status = 'M' and cd_education_status = 'Unknown')
+ or(cd_marital_status = 'W' and cd_education_status = 'Advanced Degree'))
+and hd_buy_potential like '0-500%'
+and ca_gmt_offset = -7
+group by cc_call_center_id,cc_name,cc_manager,cd_marital_status,cd_education_status
+order by sum(cr_net_loss) desc
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-2
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: call_center
+ Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: cc_call_center_sk is not null (type: boolean)
+ Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cc_call_center_sk (type: int), cc_call_center_id (type: string), cc_name (type: string), cc_manager (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 60 Data size: 122700 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 13
+ Map Operator Tree:
+ TableScan
+ alias: household_demographics
+ Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((hd_buy_potential like '0-500%') 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 _col2 (type: int)
+ 1 _col0 (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 10 <- Map 12 (PARTITION-LEVEL SORT, 750), Reducer 9 (PARTITION-LEVEL SORT, 750)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 25), Map 6 (PARTITION-LEVEL SORT, 25)
+ Reducer 3 <- Reducer 10 (PARTITION-LEVEL SORT, 745), Reducer 2 (PARTITION-LEVEL SORT, 745)
+ Reducer 4 <- Reducer 3 (GROUP, 787)
+ Reducer 5 <- Reducer 4 (SORT, 1)
+ Reducer 9 <- Map 11 (PARTITION-LEVEL SORT, 541), Map 8 (PARTITION-LEVEL SORT, 541)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: catalog_returns
+ Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (cr_call_center_sk is not null and cr_returned_date_sk is not null and cr_returning_customer_sk is not null) (type: boolean)
+ Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cr_returned_date_sk (type: int), cr_returning_customer_sk (type: int), cr_call_center_sk (type: int), cr_net_loss (type: decimal(7,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 28798881 Data size: 3057234680 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: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2))
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: customer_demographics
+ Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((((cd_marital_status = 'M') and (cd_education_status = 'Unknown')) or ((cd_marital_status = 'W') and (cd_education_status = 'Advanced Degree'))) and ((cd_education_status = 'Unknown') or (cd_education_status = 'Advanced Degree')) and ((cd_marital_status = 'M') or (cd_marital_status = 'W')) and cd_demo_sk is not null) (type: boolean)
+ Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string)
+ Map 12
+ Map Operator Tree:
+ TableScan
+ alias: customer_address
+ Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((ca_gmt_offset = -7) 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
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((d_moy = 11) and (d_year = 1999) and d_date_sk is not null) (type: boolean)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: d_date_sk (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 18262 Data size: 20435178 Basic stats: COMPLETE Column stats: NONE
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: customer
+ Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk 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_current_cdemo_sk (type: int), c_current_hdemo_sk (type: int), c_current_addr_sk (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int)
+ Reducer 10
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col5, _col6
+ Statistics: Num rows: 96800003 Data size: 83249958789 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, _col5, _col6
+ input vertices:
+ 1 Map 13
+ Statistics: Num rows: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col5 (type: string), _col6 (type: string)
+ outputColumnNames: _col2, _col7, _col8
+ Statistics: Num rows: 106480005 Data size: 91574956652 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: 106480005 Data size: 91574956652 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col7 (type: string), _col8 (type: string)
+ Reducer 2
+ Local Work:
+ Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col3, _col8, _col9, _col10
+ input vertices:
+ 1 Map 7
+ Statistics: Num rows: 34846646 Data size: 3699254122 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: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: decimal(7,2)), _col8 (type: string), _col9 (type: string), _col10 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col2 (type: int)
+ outputColumnNames: _col3, _col8, _col9, _col10, _col18, _col19
+ Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col3)
+ keys: _col8 (type: string), _col9 (type: string), _col10 (type: string), _col18 (type: string), _col19 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 117128008 Data size: 100732454500 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: string)
+ sort order: +++++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string)
+ Statistics: Num rows: 117128008 Data size: 100732454500 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: decimal(17,2))
+ Reducer 4
+ 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: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col5 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2, _col6
+ Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col6 (type: decimal(17,2))
+ sort order: -
+ Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ Reducer 5
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 58564004 Data size: 50366227250 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 9
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col2, _col3, _col5, _col6
+ Statistics: Num rows: 88000001 Data size: 75681779077 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: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col2 (type: int), _col5 (type: string), _col6 (type: string)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+