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 [14/43] - 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/join_alt_syntax.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_alt_syntax.q.out Tue Nov 25 13:03:18 2014
@@ -5,14 +5,13 @@ POSTHOOK: query: explain select p1.p_nam
from part p1 , part p2
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
@@ -20,40 +19,51 @@ STAGE PLANS:
TableScan
alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: p_name (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_name}
+ 1 {p_name}
+ keys:
+ 0
+ 1
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: p_name (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col1}
- 1 {VALUE._col1}
- outputColumnNames: _col1, _col13
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col13 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {p_name}
+ 1 {p_name}
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1, _col13
+ input vertices:
+ 1 Map 1
Statistics: Num rows: 28 Data size: 3461 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: _col1 (type: string), _col13 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 28 Data size: 3461 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
@@ -70,14 +80,13 @@ from part p1 ,part p2 ,part p3
where p1.p_name = p2.p_name and p2.p_name = p3.p_name
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)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -88,12 +97,18 @@ STAGE PLANS:
Filter Operator
predicate: p_name is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_name}
+ 1 {p_name}
+ 2
+ keys:
+ 0 p_name (type: string)
+ 1 p_name (type: string)
+ 2 p_name (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: p2
@@ -101,12 +116,23 @@ STAGE PLANS:
Filter Operator
predicate: p_name is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_name}
+ 1
+ 2 {p_name}
+ keys:
+ 0 p_name (type: string)
+ 1 p_name (type: string)
+ 2 p_name (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
alias: p1
@@ -114,37 +140,39 @@ STAGE PLANS:
Filter Operator
predicate: p_name is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- 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
- Inner Join 1 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- 2 {KEY.reducesinkkey0}
- outputColumnNames: _col1, _col13, _col25
- Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 = _col13) and (_col13 = _col25)) (type: boolean)
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 7 Data size: 865 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
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {p_name}
+ 1 {p_name}
+ 2 {p_name}
+ keys:
+ 0 p_name (type: string)
+ 1 p_name (type: string)
+ 2 p_name (type: string)
+ outputColumnNames: _col1, _col13, _col25
+ input vertices:
+ 1 Map 2
+ 2 Map 1
+ Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 = _col13) and (_col13 = _col25)) (type: boolean)
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 7 Data size: 865 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
@@ -161,14 +189,13 @@ from part p1 , (select p_name from part)
where p1.p_name = p2.p_name and p2.p_name = p3.p_name
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)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -183,12 +210,18 @@ STAGE PLANS:
expressions: p_name (type: string)
outputColumnNames: _col0
Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_name}
+ 1
+ 2 {p_name}
+ keys:
+ 0 p_name (type: string)
+ 1 _col0 (type: string)
+ 2 p_name (type: string)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: p3
@@ -196,12 +229,23 @@ STAGE PLANS:
Filter Operator
predicate: p_name is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_name}
+ 1 {_col0}
+ 2
+ keys:
+ 0 p_name (type: string)
+ 1 _col0 (type: string)
+ 2 p_name (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
alias: p1
@@ -209,37 +253,39 @@ STAGE PLANS:
Filter Operator
predicate: p_name is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- 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
- Inner Join 1 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- 2 {KEY.reducesinkkey0}
- outputColumnNames: _col1, _col12, _col14
- Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((_col1 = _col12) and (_col12 = _col14)) (type: boolean)
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col12 (type: string), _col14 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 7 Data size: 865 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
+ Inner Join 1 to 2
+ condition expressions:
+ 0 {p_name}
+ 1 {_col0}
+ 2 {p_name}
+ keys:
+ 0 p_name (type: string)
+ 1 _col0 (type: string)
+ 2 p_name (type: string)
+ outputColumnNames: _col1, _col12, _col14
+ input vertices:
+ 1 Map 1
+ 2 Map 2
+ Statistics: Num rows: 28 Data size: 3460 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: ((_col1 = _col12) and (_col12 = _col14)) (type: boolean)
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col12 (type: string), _col14 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 7 Data size: 865 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
@@ -256,94 +302,110 @@ from part p1 , part p2 , part p3
where p2.p_partkey + p1.p_partkey = p1.p_partkey and p3.p_name = p2.p_name
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 2
Map Operator Tree:
TableScan
- alias: p3
+ alias: p2
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: p_name is not null (type: boolean)
Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_partkey} {p_name}
+ 1 {p_partkey} {p_name}
+ keys:
+ 0
+ 1
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
Map 3
Map Operator Tree:
TableScan
- alias: p2
+ alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: p_name is not null (type: boolean)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- value expressions: p_partkey (type: int), p_name (type: string)
- Map 5
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {p_partkey} {p_name}
+ 1 {p_partkey} {p_name}
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col12, _col13
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col12 + _col0) = _col0) and _col13 is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col12}
+ 1 {p_name}
+ keys:
+ 0 _col13 (type: string)
+ 1 p_name (type: string)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
- alias: p1
+ alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
- value expressions: p_partkey (type: int), p_name (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1} {VALUE._col12} {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col12, _col13, _col25
- Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (((_col12 + _col0) = _col0) and (_col25 = _col13)) (type: boolean)
- Statistics: Num rows: 3 Data size: 370 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 370 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 3 Data size: 370 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
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1}
- 1 {VALUE._col0} {VALUE._col1}
- outputColumnNames: _col0, _col1, _col12, _col13
- Statistics: Num rows: 28 Data size: 3461 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (((_col12 + _col0) = _col0) and _col13 is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col13 (type: string)
- sort order: +
- Map-reduce partition columns: _col13 (type: string)
- Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col12 (type: int)
+ Filter Operator
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13}
+ 1 {p_name}
+ keys:
+ 0 _col13 (type: string)
+ 1 p_name (type: string)
+ outputColumnNames: _col0, _col1, _col12, _col13, _col25
+ input vertices:
+ 0 Map 3
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col12 + _col0) = _col0) and (_col25 = _col13)) (type: boolean)
+ Statistics: Num rows: 3 Data size: 370 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 3 Data size: 370 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 370 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
@@ -362,127 +424,140 @@ where p2.p_name = p3.p_name and p1.p_par
and p1.p_partkey = p2.p_partkey
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
- alias: p4
+ 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
- value expressions: p_name (type: string)
- Map 3
+ predicate: (p_name is not null and p_partkey is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_partkey} {p_name}
+ 1
+ keys:
+ 0 p_name (type: string), p_partkey (type: int)
+ 1 p_name (type: string), p_partkey (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
- alias: p3
+ alias: p4
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: p_name is not null (type: boolean)
+ 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_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13} {_col25}
+ 1 {p_name}
+ keys:
+ 0 _col0 (type: int)
+ 1 p_partkey (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
Map Operator Tree:
TableScan
- alias: p2
+ alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (p_name is not null and p_partkey is not null) (type: boolean)
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string), p_partkey (type: int)
- sort order: ++
- Map-reduce partition columns: p_name (type: string), p_partkey (type: int)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
- Map 7
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {p_partkey} {p_name}
+ 1 {p_partkey} {p_name}
+ keys:
+ 0 p_name (type: string), p_partkey (type: int)
+ 1 p_name (type: string), p_partkey (type: int)
+ outputColumnNames: _col0, _col1, _col12, _col13
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col12}
+ 1 {p_name}
+ keys:
+ 0 _col13 (type: string)
+ 1 p_name (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: p1
+ alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_name is not null and p_partkey is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string), p_partkey (type: int)
- sort order: ++
- Map-reduce partition columns: p_name (type: string), p_partkey (type: int)
- Statistics: Num rows: 7 Data size: 847 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} {VALUE._col0} {VALUE._col11} {VALUE._col12} {VALUE._col24}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col12, _col13, _col25, _col36, _col37
- Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (((_col13 = _col25) and (_col0 = _col36)) and (_col0 = _col12)) (type: boolean)
- Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string), _col37 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 126 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
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1} {VALUE._col12} {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col12, _col13, _col25
- Statistics: Num rows: 14 Data size: 1730 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: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string), _col12 (type: int), _col13 (type: string), _col25 (type: string)
- Reducer 6
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey1} {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col12, _col13
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col13 (type: string)
- sort order: +
- Map-reduce partition columns: _col13 (type: string)
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col12 (type: int)
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13}
+ 1 {p_name}
+ keys:
+ 0 _col13 (type: string)
+ 1 p_name (type: string)
+ outputColumnNames: _col0, _col1, _col12, _col13, _col25
+ input vertices:
+ 0 Map 4
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13} {_col25}
+ 1 {p_partkey} {p_name}
+ keys:
+ 0 _col0 (type: int)
+ 1 p_partkey (type: int)
+ outputColumnNames: _col0, _col1, _col12, _col13, _col25, _col36, _col37
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col13 = _col25) and (_col0 = _col36)) and (_col0 = _col12)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string), _col37 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 126 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
@@ -501,127 +576,140 @@ where p2.p_name = p3.p_name and p1.p_par
and p1.p_partkey = p2.p_partkey
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-3 depends on stages: Stage-4
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-4
Spark
- Edges:
- Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 3
Map Operator Tree:
TableScan
- alias: p4
+ 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
- value expressions: p_name (type: string)
- Map 3
+ predicate: (p_name is not null and p_partkey is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {p_partkey} {p_name}
+ 1
+ keys:
+ 0 p_name (type: string), p_partkey (type: int)
+ 1 p_name (type: string), p_partkey (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
- alias: p3
+ alias: p4
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: p_name is not null (type: boolean)
+ 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_name (type: string)
- sort order: +
- Map-reduce partition columns: p_name (type: string)
- Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13} {_col25}
+ 1 {p_name}
+ keys:
+ 0 _col0 (type: int)
+ 1 p_partkey (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 4
Map Operator Tree:
TableScan
- alias: p2
+ alias: p1
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: (p_name is not null and p_partkey is not null) (type: boolean)
Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string), p_partkey (type: int)
- sort order: ++
- Map-reduce partition columns: p_name (type: string), p_partkey (type: int)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
- Map 7
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {p_partkey} {p_name}
+ 1 {p_partkey} {p_name}
+ keys:
+ 0 p_name (type: string), p_partkey (type: int)
+ 1 p_name (type: string), p_partkey (type: int)
+ outputColumnNames: _col0, _col1, _col12, _col13
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1} {_col12}
+ 1 {p_name}
+ keys:
+ 0 _col13 (type: string)
+ 1 p_name (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: p1
+ alias: p3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (p_name is not null and p_partkey is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 847 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: p_name (type: string), p_partkey (type: int)
- sort order: ++
- Map-reduce partition columns: p_name (type: string), p_partkey (type: int)
- Statistics: Num rows: 7 Data size: 847 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} {VALUE._col0} {VALUE._col11} {VALUE._col12} {VALUE._col24}
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col0, _col1, _col12, _col13, _col25, _col36, _col37
- Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (((_col13 = _col25) and (_col0 = _col36)) and (_col0 = _col12)) (type: boolean)
- Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string), _col37 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 126 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
- Reducer 4
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {VALUE._col1} {VALUE._col12} {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col12, _col13, _col25
- Statistics: Num rows: 14 Data size: 1730 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: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string), _col12 (type: int), _col13 (type: string), _col25 (type: string)
- Reducer 6
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey1} {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey1} {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col12, _col13
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col13 (type: string)
- sort order: +
- Map-reduce partition columns: _col13 (type: string)
- Statistics: Num rows: 7 Data size: 931 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col12 (type: int)
+ predicate: p_name is not null (type: boolean)
+ Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13}
+ 1 {p_name}
+ keys:
+ 0 _col13 (type: string)
+ 1 p_name (type: string)
+ outputColumnNames: _col0, _col1, _col12, _col13, _col25
+ input vertices:
+ 0 Map 4
+ Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1} {_col12} {_col13} {_col25}
+ 1 {p_partkey} {p_name}
+ keys:
+ 0 _col0 (type: int)
+ 1 p_partkey (type: int)
+ outputColumnNames: _col0, _col1, _col12, _col13, _col25, _col36, _col37
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (((_col13 = _col25) and (_col0 = _col36)) and (_col0 = _col12)) (type: boolean)
+ Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col13 (type: string), _col25 (type: string), _col37 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 126 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 126 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