You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/11/25 14:03:23 UTC
svn commit: r1641614 [30/43] - in /hive/branches/spark:
itests/src/test/resources/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/
ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/
ql/src/java/org/apache/hadoop/hive/ql/parse/spark/ ql/sr...
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin.q.out Tue Nov 25 13:03:18 2014
@@ -79,16 +79,15 @@ FROM src src1 JOIN src src2 ON (src1.key
INSERT OVERWRITE TABLE dest_j1 SELECT src1.key, src2.value
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 depends on stages: Stage-2
Stage-3 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -99,13 +98,21 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: src1
@@ -113,33 +120,33 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col6
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 275 Data size: 2921 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
- name: default.dest_j1
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col6
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 275 Data size: 2921 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
+ name: default.dest_j1
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-2
Dependency Collection
@@ -191,14 +198,13 @@ FROM T1 a JOIN T2 b ON a.key = b.key
JOIN T4 d ON c.key = d.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -209,13 +215,20 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {key} {val}
+ 2 {key} {val}
+ 3 {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: b
@@ -223,13 +236,20 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {val}
+ 2 {key} {val}
+ 3 {key} {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
alias: c
@@ -237,13 +257,25 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {key} {val}
+ 2 {val}
+ 3 {key} {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 4
Map Operator Tree:
TableScan
alias: a
@@ -251,37 +283,40 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ Inner Join 2 to 3
+ condition expressions:
+ 0 {key} {val}
+ 1 {key} {val}
+ 2 {key} {val}
+ 3 {key} {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+ input vertices:
+ 1 Map 2
+ 2 Map 3
+ 3 Map 1
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 1 to 2
- Inner Join 2 to 3
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- 3 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -323,14 +358,13 @@ FROM T1 a JOIN T2 b ON a.key = b.key
JOIN T4 d ON c.key = d.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -341,13 +375,20 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {key} {val}
+ 2 {key} {val}
+ 3 {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: b
@@ -355,13 +396,20 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {val}
+ 2 {key} {val}
+ 3 {key} {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 3
Map Operator Tree:
TableScan
alias: c
@@ -369,13 +417,25 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {key} {val}
+ 2 {val}
+ 3 {key} {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 4
Map Operator Tree:
TableScan
alias: a
@@ -383,37 +443,40 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 1 to 2
+ Inner Join 2 to 3
+ condition expressions:
+ 0 {key} {val}
+ 1 {key} {val}
+ 2 {key} {val}
+ 3 {key} {val}
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ 2 key (type: string)
+ 3 key (type: string)
+ outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+ input vertices:
+ 1 Map 2
+ 2 Map 3
+ 3 Map 1
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: val (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 1 to 2
- Inner Join 2 to 3
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- 2 {KEY.reducesinkkey0} {VALUE._col0}
- 3 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -447,15 +510,37 @@ PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: UDFToDouble(key) is not null (type: boolean)
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {val}
+ 1 {key}
+ keys:
+ 0 UDFToDouble(key) (type: double)
+ 1 (key + 1) (type: double)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-1
Spark
Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
+ Reducer 2 <- Map 1 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -466,51 +551,36 @@ STAGE PLANS:
Filter Operator
predicate: (key + 1) is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: (key + 1) (type: double)
- sort order: +
- Map-reduce partition columns: (key + 1) (type: double)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string)
- Map 4
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: UDFToDouble(key) is not null (type: boolean)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(key) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(key) (type: double)
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: key (type: string), val (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {val}
+ 1 {key}
+ keys:
+ 0 UDFToDouble(key) (type: double)
+ 1 (key + 1) (type: double)
+ outputColumnNames: _col0, _col1, _col5
+ input vertices:
+ 0 Map 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col5))
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 2
Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string)
- outputColumnNames: _col0, _col1, _col5
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col0)), sum(hash(_col1)), sum(hash(_col5))
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint)
- Reducer 3
- Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2)
mode: mergepartial
@@ -560,18 +630,16 @@ ON (x.key = Y.key)
SELECT sum(hash(Y.key)), sum(hash(Y.value))
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
alias: src
@@ -580,15 +648,26 @@ STAGE PLANS:
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
alias: src
@@ -597,40 +676,39 @@ STAGE PLANS:
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2)), sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 2
Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col3 (type: string)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col2)), sum(hash(_col3))
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint), _col1 (type: bigint)
- Reducer 3
- Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), sum(VALUE._col1)
mode: mergepartial
@@ -688,77 +766,85 @@ ON (x.key = Y.key and substring(x.value,
SELECT sum(hash(Y.key)), sum(hash(Y.value))
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key is not null and UDFToDouble(substring(value, 5)) is not null) (type: boolean)
+ predicate: (key is not null and (substring(value, 5) + 1) is not null) (type: boolean)
Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {_col1}
+ keys:
+ 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
+ 1 _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key is not null and (substring(value, 5) + 1) is not null) (type: boolean)
+ predicate: (key is not null and UDFToDouble(substring(value, 5)) is not null) (type: boolean)
Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {_col0} {_col1}
+ keys:
+ 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double)
+ 1 _col0 (type: string), (substring(_col1, 5) + 1) (type: double)
+ outputColumnNames: _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string)
+ outputColumnNames: _col2, _col3
+ Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col2)), sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 2
Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col3 (type: string)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col2)), sum(hash(_col3))
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint), _col1 (type: bigint)
- Reducer 3
- Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), sum(VALUE._col1)
mode: mergepartial
@@ -824,15 +910,13 @@ JOIN
ON src1.c1 = src3.c5 AND src3.c5 < 80
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -847,71 +931,91 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Local Work:
+ Map Reduce Local Work
Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key < 80) and (key < 100)) (type: boolean)
+ predicate: ((key < 100) and (key < 80)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((key < 100) and (key < 80)) (type: boolean)
+ predicate: ((key < 80) and (key < 100)) (type: boolean)
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- 2
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col0)), sum(hash(_col3))
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {_col0}
+ 1 {_col1}
+ 2
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ 2 _col0 (type: string)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 1
+ 2 Map 4
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 121 Data size: 1284 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0)), sum(hash(_col3))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Group By Operator
@@ -969,15 +1073,13 @@ POSTHOOK: query: EXPLAIN
SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-3 is a root stage
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -985,46 +1087,55 @@ STAGE PLANS:
TableScan
alias: v
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(key) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(key) (type: double)
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- value expressions: val (type: string)
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1 {val}
+ keys:
+ 0 (key + 1) (type: double)
+ 1 UDFToDouble(key) (type: double)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: k
Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: (key + 1) (type: double)
- sort order: +
- Map-reduce partition columns: (key + 1) (type: double)
- Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
- value expressions: key (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {VALUE._col0}
- 1 {VALUE._col1}
- outputColumnNames: _col0, _col6
- Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col6
- Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
- Group By Operator
- aggregations: sum(hash(_col0)), sum(hash(_col6))
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {key}
+ 1 {val}
+ keys:
+ 0 (key + 1) (type: double)
+ 1 UDFToDouble(key) (type: double)
+ outputColumnNames: _col0, _col6
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col6
+ Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+ Group By Operator
+ aggregations: sum(hash(_col0)), sum(hash(_col6))
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Group By Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin_noskew.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin_noskew.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin_noskew.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoin_noskew.q.out Tue Nov 25 13:03:18 2014
@@ -5,18 +5,16 @@ POSTHOOK: query: explain
create table noskew as select a.* from src a join src b on a.key=b.key order by a.key limit 30
POSTHOOK: type: CREATETABLE_AS_SELECT
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
- Stage-3 depends on stages: Stage-4
+ Stage-5 depends on stages: Stage-2, Stage-0
+ Stage-3 depends on stages: Stage-5
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
- Reducer 3 <- Reducer 2 (SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -27,12 +25,23 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (SORT, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
@@ -40,31 +49,30 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: string)
+ 1 key (type: string)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Local Work:
+ Map Reduce Local Work
Reducer 3
Reduce Operator Tree:
Select Operator
@@ -86,7 +94,7 @@ STAGE PLANS:
Stage: Stage-2
Dependency Collection
- Stage: Stage-4
+ Stage: Stage-5
Create Table Operator:
Create Table
columns: key string, value string