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 [8/43] - 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/src...
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out Tue Nov 25 13:03:18 2014
@@ -117,14 +117,35 @@ select a.key, a.value, b.value
from tab a join tab_part 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: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {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
@@ -135,47 +156,32 @@ 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 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 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col7
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2
- 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col7
+ input vertices:
+ 0 Map 2
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -198,32 +204,18 @@ from (select sum(substr(srcbucket_mapjoi
join tab b on a.k1 = 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 4 <- Map 3 (GROUP, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Map 2
Map Operator Tree:
TableScan
alias: srcbucket_mapjoin
@@ -247,28 +239,9 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 133 Data size: 1411 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
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -280,12 +253,52 @@ STAGE PLANS:
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: double)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Reducer 3
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 133 Data size: 1411 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
@@ -304,16 +317,14 @@ from (select sum(substr(tab.value,5)) as
join tab b on a.k1 = 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-4
+ Stage-4 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-1
+ Stage: Stage-3
Spark
- Edges:
- Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 1), Map 6 (PARTITION-LEVEL SORT, 1)
- Reducer 5 <- Reducer 4 (GROUP, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -324,13 +335,23 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ 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: tab_part
@@ -338,73 +359,40 @@ 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 6
- Map Operator Tree:
- TableScan
- alias: tab
- Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 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 {VALUE._col0} {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 150 Data size: 1600 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
- 1 {KEY.reducesinkkey0} {VALUE._col0}
- outputColumnNames: _col6, _col7
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col6, _col7
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(substr(_col7, 5))
- keys: _col6 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col6, _col7
+ input vertices:
+ 1 Map 4
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reducer 5
+ Select Operator
+ expressions: _col6 (type: int), _col7 (type: string)
+ outputColumnNames: _col6, _col7
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(_col7, 5))
+ keys: _col6 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Local Work:
+ Map Reduce Local Work
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -416,12 +404,52 @@ STAGE PLANS:
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: double)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-4
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: tab
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -440,107 +468,82 @@ from (select sum(substr(x.value,5)) as v
join tab_part b on a.k1 = b.key
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 6 (PARTITION-LEVEL SORT, 1)
- Reducer 5 <- Reducer 4 (GROUP, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Map 4
Map Operator Tree:
TableScan
- alias: x
+ alias: y
Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 6
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Spark
+ Edges:
+ Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
Map Operator Tree:
TableScan
- alias: y
+ alias: x
Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- 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
- Reducer 4
- 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: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: sum(substr(_col1, 5))
- keys: _col0 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 4
Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
- Reducer 5
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(_col1, 5))
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 133 Data size: 1411 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: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Local Work:
+ Map Reduce Local Work
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -552,12 +555,52 @@ STAGE PLANS:
expressions: _col1 (type: double), _col0 (type: int)
outputColumnNames: _col0, _col1
Statistics: Num rows: 66 Data size: 700 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 66 Data size: 700 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: double)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Reducer 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -576,14 +619,13 @@ select a.key, a.value, b.value
from tab_part a join tab b on a.key = b.key join tab c on a.key = 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-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
@@ -594,13 +636,18 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ 2 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+ Map 2
Map Operator Tree:
TableScan
alias: c
@@ -608,12 +655,23 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- Map 4
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ 2 key (type: int)
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
alias: a
@@ -621,35 +679,36 @@ 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- 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
- Inner Join 0 to 2
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {VALUE._col0}
- 2
- outputColumnNames: _col0, _col1, _col7
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 550 Data size: 5843 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 0 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ 2 key (type: int)
+ outputColumnNames: _col0, _col1, _col7
+ input vertices:
+ 1 Map 1
+ 2 Map 2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
@@ -666,15 +725,13 @@ select a.key, a.value, c.value
from (select x.key, x.value from tab_part x join tab y on x.key = y.key) a join tab c on a.key = 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-1
+ Stage: Stage-3
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
@@ -685,80 +742,88 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ Local Work:
+ Map Reduce Local Work
Map 3
Map Operator Tree:
TableScan
- alias: x
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ alias: y
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 5
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key} {value}
+ 1
+ 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: y
- Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ alias: x
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 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}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3213 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 {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: int), _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: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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
@@ -779,32 +844,18 @@ from (select key, sum(substr(srcbucket_m
join tab_part 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 4 <- Map 3 (GROUP, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Map 2
Map Operator Tree:
TableScan
alias: srcbucket_mapjoin
@@ -828,28 +879,9 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- 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
- Reducer 4
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -861,12 +893,52 @@ STAGE PLANS:
expressions: _col0 (type: int), _col1 (type: double)
outputColumnNames: _col0, _col1
Statistics: Num rows: 7 Data size: 728 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: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Reducer 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -885,32 +957,18 @@ from (select key, sum(substr(srcbucket_m
join tab_part 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 4 <- Map 3 (GROUP, 1)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 4 (PARTITION-LEVEL SORT, 1)
+ Reducer 3 <- Map 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: b
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
+ Map 2
Map Operator Tree:
TableScan
alias: srcbucket_mapjoin
@@ -928,28 +986,9 @@ STAGE PLANS:
Map-reduce partition columns: key (type: int)
Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
value expressions: substr(value, 5) (type: string)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {KEY.reducesinkkey0} {VALUE._col0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
- outputColumnNames: _col0, _col1, _col2
- 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
- Reducer 4
+ Reducer 3
+ Local Work:
+ Map Reduce Local Work
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -961,12 +1000,52 @@ STAGE PLANS:
expressions: _col0 (type: int), _col1 (type: double)
outputColumnNames: _col0, _col1
Statistics: Num rows: 7 Data size: 728 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: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: double)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+
+ Stage: Stage-1
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ input vertices:
+ 0 Reducer 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -985,14 +1064,35 @@ select a.key, a.value, b.value
from tab a join tab_part b on a.value = b.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-3
+ Spark
+#### A masked pattern was here ####
+ Vertices:
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {key}
+ 1 {value}
+ keys:
+ 0 value (type: string)
+ 1 value (type: string)
+ 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
@@ -1003,46 +1103,32 @@ STAGE PLANS:
Filter Operator
predicate: value is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: value (type: string)
- sort order: +
- Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: value (type: string)
- sort order: +
- Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: int)
- Reducer 2
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {VALUE._col0} {KEY.reducesinkkey0}
- 1 {KEY.reducesinkkey0}
- outputColumnNames: _col0, _col1, _col7
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col2
- 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 value (type: string)
+ 1 value (type: string)
+ outputColumnNames: _col0, _col1, _col7
+ input vertices:
+ 0 Map 2
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -1081,14 +1167,35 @@ select a.key, a.value, b.value
from tab1 a join tab_part 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: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1 {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
@@ -1099,47 +1206,32 @@ 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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string)
- Map 3
- Map Operator Tree:
- TableScan
- alias: a
- Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 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: 121 Data size: 1283 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 {VALUE._col0}
- outputColumnNames: _col0, _col1, _col6
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
- outputColumnNames: _col0, _col1, _col2
- 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
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col6
+ input vertices:
+ 0 Map 2
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ 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
+ Local Work:
+ Map Reduce Local Work
Stage: Stage-0
Fetch Operator
@@ -1152,15 +1244,13 @@ PREHOOK: type: QUERY
POSTHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.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 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
@@ -1171,76 +1261,84 @@ STAGE PLANS:
Filter Operator
predicate: value is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: value (type: string)
- sort order: +
- Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: int)
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {_col0}
+ 1 {key}
+ keys:
+ 0 _col1 (type: string)
+ 1 value (type: string)
+ Local Work:
+ Map Reduce Local Work
Map 3
Map Operator Tree:
TableScan
- alias: c
+ alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
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: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Map 5
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Spark HashTable Sink Operator
+ condition expressions:
+ 0 {value}
+ 1
+ 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
+ alias: c
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 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: 125 Data size: 1328 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 {VALUE._col0}
- 1 {VALUE._col0}
- outputColumnNames: _col0, _col12
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col12 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3213 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 {KEY.reducesinkkey0} {VALUE._col0}
- 1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: string)
- sort order: +
- Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1
+ input vertices:
+ 0 Map 3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {key}
+ keys:
+ 0 _col1 (type: string)
+ 1 value (type: string)
+ outputColumnNames: _col0, _col12
+ input vertices:
+ 1 Map 1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col12 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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