You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2015/01/24 01:16:37 UTC
svn commit: r1654439 [5/10] - in /hive/trunk: itests/src/test/resources/
itests/util/src/main/java/org/apache/hadoop/hive/ql/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/
ql/src/java/org/apache...
Modified: hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out?rev=1654439&r1=1654438&r2=1654439&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/ptf_streaming.q.out Sat Jan 24 00:16:36 2015
@@ -1,12 +1,7 @@
-PREHOOK: query: create temporary function noopstreaming as 'org.apache.hadoop.hive.ql.udf.ptf.NoopStreaming$NoopStreamingResolver'
-PREHOOK: type: CREATEFUNCTION
-PREHOOK: Output: noopstreaming
-POSTHOOK: query: create temporary function noopstreaming as 'org.apache.hadoop.hive.ql.udf.ptf.NoopStreaming$NoopStreamingResolver'
-POSTHOOK: type: CREATEFUNCTION
-POSTHOOK: Output: noopstreaming
PREHOOK: query: -- SORT_QUERY_RESULTS
--1. test1
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -16,11 +11,10 @@ from noopstreaming(on part
order by p_name
)
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- SORT_QUERY_RESULTS
--1. test1
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -30,6 +24,87 @@ from noopstreaming(on part
order by p_name
)
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_name (type: string)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int), p_retailprice (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int), _col7 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on part
+ partition by p_mfgr
+ order by p_name
+ )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on part
+ partition by p_mfgr
+ order by p_name
+ )
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15
@@ -59,21 +134,129 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18
Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66
PREHOOK: query: -- 2. testJoinWithNoop
+explain
select p_mfgr, p_name,
p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz
from noopstreaming (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j
distribute by j.p_mfgr
sort by j.p_name)
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 2. testJoinWithNoop
+explain
select p_mfgr, p_name,
p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz
from noopstreaming (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j
distribute by j.p_mfgr
sort by j.p_name)
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_partkey (type: int)
+ sort order: +
+ Map-reduce partition columns: p_partkey (type: int)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: p2
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_partkey (type: int)
+ sort order: +
+ Map-reduce partition columns: p_partkey (type: int)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 p_partkey (type: int)
+ 1 p_partkey (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), (_col5 - _wcol0) (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name,
+p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz
+from noopstreaming (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j
+distribute by j.p_mfgr
+sort by j.p_name)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name,
+p_size, p_size - lag(p_size,1,p_size) over (partition by p_mfgr order by p_name) as deltaSz
+from noopstreaming (on (select p1.* from part p1 join part p2 on p1.p_partkey = p2.p_partkey) j
+distribute by j.p_mfgr
+sort by j.p_name)
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 0
@@ -105,21 +288,114 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 44
Manufacturer#5 almond azure blanched chiffon midnight 23 -23
PREHOOK: query: -- 7. testJoin
+explain
select abc.*
from noopstreaming(on part
partition by p_mfgr
order by p_name
) abc join part p1 on abc.p_partkey = p1.p_partkey
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 7. testJoin
+explain
select abc.*
from noopstreaming(on part
partition by p_mfgr
order by p_name
) abc join part p1 on abc.p_partkey = p1.p_partkey
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_name (type: string)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_partkey (type: int)
+ sort order: +
+ Map-reduce partition columns: p_partkey (type: int)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 p_partkey (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select abc.*
+from noopstreaming(on part
+partition by p_mfgr
+order by p_name
+) abc join part p1 on abc.p_partkey = p1.p_partkey
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select abc.*
+from noopstreaming(on part
+partition by p_mfgr
+order by p_name
+) abc join part p1 on abc.p_partkey = p1.p_partkey
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
105685 almond antique violet chocolate turquoise Manufacturer#2 Brand#22 MEDIUM ANODIZED COPPER 14 MED CAN 1690.68 ly pending requ
@@ -151,21 +427,97 @@ POSTHOOK: Input: default@part
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
PREHOOK: query: -- 9. testNoopWithMap
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name, p_size desc) as r
from noopwithmapstreaming(on part
partition by p_mfgr
order by p_name, p_size desc)
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 9. testNoopWithMap
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name, p_size desc) as r
from noopwithmapstreaming(on part
partition by p_mfgr
order by p_name, p_size desc)
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_name (type: string), p_size (type: int)
+ sort order: ++-
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int)
+ sort order: ++-
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey2 (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name, p_size desc) as r
+from noopwithmapstreaming(on part
+partition by p_mfgr
+order by p_name, p_size desc)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name, p_size desc) as r
+from noopwithmapstreaming(on part
+partition by p_mfgr
+order by p_name, p_size desc)
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 1
@@ -195,6 +547,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 4
Manufacturer#5 almond azure blanched chiffon midnight 23 5
PREHOOK: query: -- 10. testNoopWithMapWithWindowing
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -203,9 +556,8 @@ from noopwithmapstreaming(on part
partition by p_mfgr
order by p_name)
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 10. testNoopWithMapWithWindowing
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -214,6 +566,87 @@ from noopwithmapstreaming(on part
partition by p_mfgr
order by p_name)
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_name (type: string)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int), p_retailprice (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int), _col7 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopwithmapstreaming(on part
+ partition by p_mfgr
+ order by p_name)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopwithmapstreaming(on part
+ partition by p_mfgr
+ order by p_name)
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15
@@ -243,6 +676,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18
Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66
PREHOOK: query: -- 12. testFunctionChain
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -252,9 +686,8 @@ partition by p_mfgr
order by p_mfgr, p_name
)))
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 12. testFunctionChain
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -264,6 +697,102 @@ partition by p_mfgr
order by p_mfgr, p_name
)))
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_mfgr (type: string), p_name (type: string)
+ sort order: +++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int), p_retailprice (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int), _col7 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int), _col7 (type: double)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on noopwithmapstreaming(on noopstreaming(on part
+partition by p_mfgr
+order by p_mfgr, p_name
+)))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on noopwithmapstreaming(on noopstreaming(on part
+partition by p_mfgr
+order by p_mfgr, p_name
+)))
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15
@@ -293,6 +822,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18
Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66
PREHOOK: query: -- 12.1 testFunctionChain
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -302,9 +832,8 @@ partition by p_mfgr
order by p_mfgr, p_name
)))
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 12.1 testFunctionChain
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -314,6 +843,102 @@ partition by p_mfgr
order by p_mfgr, p_name
)))
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_mfgr (type: string), p_name (type: string)
+ sort order: +++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int), p_retailprice (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int), _col7 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int), _col7 (type: double)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on noopwithmap(on noopstreaming(on part
+partition by p_mfgr
+order by p_mfgr, p_name
+)))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on noopwithmap(on noopstreaming(on part
+partition by p_mfgr
+order by p_mfgr, p_name
+)))
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15
@@ -343,6 +968,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18
Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66
PREHOOK: query: -- 12.2 testFunctionChain
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -352,9 +978,8 @@ partition by p_mfgr
order by p_mfgr, p_name
)))
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 12.2 testFunctionChain
+explain
select p_mfgr, p_name, p_size,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -364,6 +989,102 @@ partition by p_mfgr
order by p_mfgr, p_name
)))
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_mfgr (type: string), p_name (type: string)
+ sort order: +++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int), p_retailprice (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int), _col7 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int), _col7 (type: double)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noop(on noopwithmapstreaming(on noopstreaming(on part
+partition by p_mfgr
+order by p_mfgr, p_name
+)))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name, p_size,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+sum(p_retailprice) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noop(on noopwithmapstreaming(on noopstreaming(on part
+partition by p_mfgr
+order by p_mfgr, p_name
+)))
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 2 1 1 1173.15
@@ -393,6 +1114,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 46 4 4 6208.18
Manufacturer#5 almond azure blanched chiffon midnight 23 5 5 7672.66
PREHOOK: query: -- 14. testPTFJoinWithWindowingWithCount
+explain
select abc.p_mfgr, abc.p_name,
rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r,
dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr,
@@ -404,9 +1126,8 @@ partition by p_mfgr
order by p_name
) abc join part p1 on abc.p_partkey = p1.p_partkey
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 14. testPTFJoinWithWindowingWithCount
+explain
select abc.p_mfgr, abc.p_name,
rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r,
dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr,
@@ -418,6 +1139,124 @@ partition by p_mfgr
order by p_name
) abc join part p1 on abc.p_partkey = p1.p_partkey
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_name (type: string)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_size (type: int), p_retailprice (type: double)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: p1
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_partkey is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_partkey (type: int)
+ sort order: +
+ Map-reduce partition columns: p_partkey (type: int)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int), _col7 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 p_partkey (type: int)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int), _col7 (type: double)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int), VALUE._col5 (type: double)
+ outputColumnNames: _col1, _col2, _col5, _col7
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: bigint), _col7 (type: double), _wcol3 (type: double), _col5 (type: int), (_col5 - _wcol4) (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select abc.p_mfgr, abc.p_name,
+rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r,
+dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr,
+count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd,
+abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1,
+abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz
+from noopstreaming(on part
+partition by p_mfgr
+order by p_name
+) abc join part p1 on abc.p_partkey = p1.p_partkey
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select abc.p_mfgr, abc.p_name,
+rank() over (distribute by abc.p_mfgr sort by abc.p_name) as r,
+dense_rank() over (distribute by abc.p_mfgr sort by abc.p_name) as dr,
+count(abc.p_name) over (distribute by abc.p_mfgr sort by abc.p_name) as cd,
+abc.p_retailprice, sum(abc.p_retailprice) over (distribute by abc.p_mfgr sort by abc.p_name rows between unbounded preceding and current row) as s1,
+abc.p_size, abc.p_size - lag(abc.p_size,1,abc.p_size) over (distribute by abc.p_mfgr sort by abc.p_name) as deltaSz
+from noopstreaming(on part
+partition by p_mfgr
+order by p_name
+) abc join part p1 on abc.p_partkey = p1.p_partkey
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 1 1 4 1173.15 1173.15 2 0
@@ -449,6 +1288,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 4 4 4 1018.1 6208.18 46 44
Manufacturer#5 almond azure blanched chiffon midnight 5 5 5 1464.48 7672.66 23 -23
PREHOOK: query: -- 18. testMulti2OperatorsFunctionChainWithMap
+explain
select p_mfgr, p_name,
rank() over (partition by p_mfgr,p_name) as r,
dense_rank() over (partition by p_mfgr,p_name) as dr,
@@ -465,9 +1305,8 @@ from noopstreaming(on
partition by p_mfgr,p_name
order by p_mfgr,p_name)
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 18. testMulti2OperatorsFunctionChainWithMap
+explain
select p_mfgr, p_name,
rank() over (partition by p_mfgr,p_name) as r,
dense_rank() over (partition by p_mfgr,p_name) as dr,
@@ -484,6 +1323,116 @@ from noopstreaming(on
partition by p_mfgr,p_name
order by p_mfgr,p_name)
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_mfgr (type: string)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: ++++
+ Map-reduce partition columns: _col2 (type: string), _col1 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: ++++
+ Map-reduce partition columns: _col2 (type: string), _col1 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name,
+rank() over (partition by p_mfgr,p_name) as r,
+dense_rank() over (partition by p_mfgr,p_name) as dr,
+p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on
+ noopwithmap(on
+ noop(on
+ noopstreaming(on part
+ partition by p_mfgr
+ order by p_mfgr)
+ )
+ partition by p_mfgr,p_name
+ order by p_mfgr,p_name)
+ partition by p_mfgr,p_name
+ order by p_mfgr,p_name)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name,
+rank() over (partition by p_mfgr,p_name) as r,
+dense_rank() over (partition by p_mfgr,p_name) as dr,
+p_size, sum(p_size) over (partition by p_mfgr,p_name rows between unbounded preceding and current row) as s1
+from noopstreaming(on
+ noopwithmap(on
+ noop(on
+ noopstreaming(on part
+ partition by p_mfgr
+ order by p_mfgr)
+ )
+ partition by p_mfgr,p_name
+ order by p_mfgr,p_name)
+ partition by p_mfgr,p_name
+ order by p_mfgr,p_name)
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 1 1 2 2
@@ -513,6 +1462,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 1 1 46 46
Manufacturer#5 almond azure blanched chiffon midnight 1 1 23 23
PREHOOK: query: -- 19. testMulti3OperatorsFunctionChain
+explain
select p_mfgr, p_name,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -529,9 +1479,8 @@ from noop(on
partition by p_mfgr
order by p_mfgr )
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 19. testMulti3OperatorsFunctionChain
+explain
select p_mfgr, p_name,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -548,6 +1497,127 @@ from noop(on
partition by p_mfgr
order by p_mfgr )
POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+ Reducer 5 <- Reducer 4 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_mfgr (type: string)
+ sort order: ++
+ Map-reduce partition columns: p_mfgr (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: ++++
+ Map-reduce partition columns: _col2 (type: string), _col1 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col2 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int)
+ Reducer 4
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int)
+ Reducer 5
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noop(on
+ noopstreaming(on
+ noop(on
+ noopstreaming(on part
+ partition by p_mfgr
+ order by p_mfgr)
+ )
+ partition by p_mfgr,p_name
+ order by p_mfgr,p_name)
+ partition by p_mfgr
+ order by p_mfgr )
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+p_size, sum(p_size) over (partition by p_mfgr order by p_name rows between unbounded preceding and current row) as s1
+from noop(on
+ noopstreaming(on
+ noop(on
+ noopstreaming(on part
+ partition by p_mfgr
+ order by p_mfgr)
+ )
+ partition by p_mfgr,p_name
+ order by p_mfgr,p_name)
+ partition by p_mfgr
+ order by p_mfgr )
+POSTHOOK: type: QUERY
POSTHOOK: Input: default@part
#### A masked pattern was here ####
Manufacturer#1 almond antique burnished rose metallic 1 1 2 2
@@ -577,6 +1647,7 @@ Manufacturer#5 almond antique sky peru o
Manufacturer#5 almond aquamarine dodger light gainsboro 4 4 46 85
Manufacturer#5 almond azure blanched chiffon midnight 5 5 23 108
PREHOOK: query: -- 23. testMultiOperatorChainWithDiffPartitionForWindow2
+explain
select p_mfgr, p_name,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
@@ -590,13 +1661,116 @@ from noopwithmapstreaming(on
order by p_mfgr, p_name)
))
PREHOOK: type: QUERY
-PREHOOK: Input: default@part
-#### A masked pattern was here ####
POSTHOOK: query: -- 23. testMultiOperatorChainWithDiffPartitionForWindow2
+explain
select p_mfgr, p_name,
rank() over (partition by p_mfgr order by p_name) as r,
dense_rank() over (partition by p_mfgr order by p_name) as dr,
p_size,
+sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1,
+sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2
+from noopwithmapstreaming(on
+ noop(on
+ noopstreaming(on part
+ partition by p_mfgr, p_name
+ order by p_mfgr, p_name)
+ ))
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 2)
+ Reducer 4 <- Reducer 3 (PARTITION-LEVEL SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: p_mfgr (type: string), p_name (type: string), p_mfgr (type: string), p_name (type: string)
+ sort order: ++++
+ Map-reduce partition columns: p_mfgr (type: string), p_name (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int)
+ Reducer 2
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: ++++
+ Map-reduce partition columns: _col2 (type: string), _col1 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string), _col2 (type: string), _col5 (type: int)
+ Reducer 3
+ Reduce Operator Tree:
+ Extract
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col5 (type: int)
+ Reducer 4
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col3 (type: int)
+ outputColumnNames: _col1, _col2, _col5
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ PTF Operator
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint), _wcol2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select p_mfgr, p_name,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+p_size,
+sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1,
+sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2
+from noopwithmapstreaming(on
+ noop(on
+ noopstreaming(on part
+ partition by p_mfgr, p_name
+ order by p_mfgr, p_name)
+ ))
+PREHOOK: type: QUERY
+PREHOOK: Input: default@part
+#### A masked pattern was here ####
+POSTHOOK: query: select p_mfgr, p_name,
+rank() over (partition by p_mfgr order by p_name) as r,
+dense_rank() over (partition by p_mfgr order by p_name) as dr,
+p_size,
sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s1,
sum(p_size) over (partition by p_mfgr order by p_name range between unbounded preceding and current row) as s2
from noopwithmapstreaming(on