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 [36/43] - 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/smb_mapjoin_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out Tue Nov 25 13:03:18 2014
@@ -53,14 +53,35 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.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 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -71,47 +92,32 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 104 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 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 114 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 0 Map 2
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 114 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -136,14 +142,13 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.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)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -151,44 +156,51 @@ STAGE PLANS:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 1 Map 1
Statistics: Num rows: 2 Data size: 228 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
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 228 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -218,14 +230,32 @@ POSTHOOK: query: explain
select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.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 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -233,44 +263,32 @@ STAGE PLANS:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 0 Map 2
Statistics: Num rows: 2 Data size: 228 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
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 228 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -385,14 +403,35 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.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 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -403,47 +442,32 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 104 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 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 114 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 0 Map 2
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 114 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -468,14 +492,13 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.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)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -483,44 +506,51 @@ STAGE PLANS:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 1 Map 1
Statistics: Num rows: 2 Data size: 228 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
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 228 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -550,14 +580,32 @@ POSTHOOK: query: explain
select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.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 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
Stage: Stage-1
Spark
- Edges:
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -565,44 +613,32 @@ STAGE PLANS:
TableScan
alias: b
Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Right Outer Join0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Right Outer Join0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5, _col6
+ input vertices:
+ 0 Map 2
Statistics: Num rows: 2 Data size: 228 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
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 228 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out Tue Nov 25 13:03:18 2014
@@ -73,14 +73,13 @@ on (a.ds = '1' and b.ds = '2' and
a.type = b.type)
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)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -91,12 +90,21 @@ STAGE PLANS:
Filter Operator
predicate: (((userid is not null and pageid is not null) and postid is not null) and type is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: userid (type: int), pageid (type: int), postid (type: int), type (type: string)
- sort order: ++++
- Map-reduce partition columns: userid (type: int), pageid (type: int), postid (type: int), type (type: string)
- Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {userid} {pageid} {postid} {type}
+ 1
+ keys:
+ 0 userid (type: int), pageid (type: int), postid (type: int), type (type: string)
+ 1 userid (type: int), pageid (type: int), postid (type: int), type (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: a
@@ -104,32 +112,32 @@ STAGE PLANS:
Filter Operator
predicate: (((userid is not null and pageid is not null) and postid is not null) and type is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: userid (type: int), pageid (type: int), postid (type: int), type (type: string)
- sort order: ++++
- Map-reduce partition columns: userid (type: int), pageid (type: int), postid (type: int), type (type: string)
- Statistics: Num rows: 1 Data size: 138 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} {KEY.reducesinkkey1} {KEY.reducesinkkey2} {KEY.reducesinkkey3}
- 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} {KEY.reducesinkkey2} {KEY.reducesinkkey3}
- outputColumnNames: _col0, _col1, _col2, _col3, _col8, _col9, _col10, _col11
- Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string), '1' (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col11 (type: string), '2' (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 151 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {userid} {pageid} {postid} {type}
+ 1 {userid} {pageid} {postid} {type}
+ keys:
+ 0 userid (type: int), pageid (type: int), postid (type: int), type (type: string)
+ 1 userid (type: int), pageid (type: int), postid (type: int), type (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col8, _col9, _col10, _col11
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string), '1' (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col11 (type: string), '2' (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 151 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out Tue Nov 25 13:03:18 2014 differ