You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by om...@apache.org on 2015/11/23 18:23:51 UTC
[28/55] [partial] hive git commit: HIVE-12017: Do not disable CBO by
default when number of joins in a query is equal or less than 1 (Jesus
Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/855e43df/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out
index cec4219..bf59bfe 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning_2.q.out
@@ -166,67 +166,72 @@ STAGE PLANS:
alias: agg
filterExpr: dim_shops_id is not null (type: boolean)
Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 dim_shops_id (type: int)
- 1 id (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 4
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- Filter Operator
- predicate: (_col1 = _col5) (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: amount (type: decimal(10,0)), dim_shops_id (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
Select Operator
- expressions: _col6 (type: string), _col0 (type: decimal(10,0))
- outputColumnNames: _col6, _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ expressions: _col3 (type: string), _col0 (type: decimal(10,0))
+ outputColumnNames: _col3, _col0
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), sum(_col0)
- keys: _col6 (type: string)
+ keys: _col3 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 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: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
Execution mode: llap
Map 4
Map Operator Tree:
TableScan
alias: d1
- filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+ filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+ predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
- Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- value expressions: label (type: string)
Select Operator
- expressions: id (type: int)
- outputColumnNames: _col0
+ expressions: id (type: int), label (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Select Operator
+ expressions: _col0 (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Dynamic Partitioning Event Operator
- Target Input: agg
- Partition key expr: dim_shops_id
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Target column: dim_shops_id
- Target Vertex: Map 1
+ Dynamic Partitioning Event Operator
+ Target Input: agg
+ Partition key expr: dim_shops_id
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Target column: dim_shops_id
+ Target Vertex: Map 1
Execution mode: llap
Reducer 2
Execution mode: llap
@@ -236,11 +241,11 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
Reducer 3
Execution mode: uber
@@ -248,10 +253,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0))
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -332,52 +337,57 @@ STAGE PLANS:
alias: agg
filterExpr: dim_shops_id is not null (type: boolean)
Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 dim_shops_id (type: int)
- 1 id (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 4
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- Filter Operator
- predicate: (_col1 = _col5) (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: amount (type: decimal(10,0)), dim_shops_id (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
Select Operator
- expressions: _col6 (type: string), _col0 (type: decimal(10,0))
- outputColumnNames: _col6, _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ expressions: _col3 (type: string), _col0 (type: decimal(10,0))
+ outputColumnNames: _col3, _col0
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), sum(_col0)
- keys: _col6 (type: string)
+ keys: _col3 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 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: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
Execution mode: llap
Map 4
Map Operator Tree:
TableScan
alias: d1
- filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+ filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+ predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
+ Select Operator
+ expressions: id (type: int), label (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- value expressions: label (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Execution mode: llap
Reducer 2
Execution mode: llap
@@ -387,11 +397,11 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
Reducer 3
Execution mode: uber
@@ -399,10 +409,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0))
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -473,27 +483,28 @@ STAGE PLANS:
alias: agg
filterExpr: dim_shops_id is not null (type: boolean)
Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 dim_shops_id (type: int)
- 1 id (type: int)
- outputColumnNames: _col1, _col5, _col6
- input vertices:
- 1 Map 2
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- Filter Operator
- predicate: (_col1 = _col5) (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: dim_shops_id (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2
+ input vertices:
+ 1 Map 2
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
Select Operator
- expressions: _col6 (type: string)
+ expressions: _col2 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -508,12 +519,16 @@ STAGE PLANS:
Filter Operator
predicate: id is not null (type: boolean)
Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
+ Select Operator
+ expressions: id (type: int), label (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE
- value expressions: label (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Execution mode: llap
Stage: Stage-0
@@ -553,6 +568,7 @@ bar
baz
baz
baz
+Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product
PREHOOK: query: EXPLAIN SELECT agg.amount
FROM agg_01 agg,
dim_shops d1
@@ -582,39 +598,42 @@ STAGE PLANS:
alias: agg
filterExpr: (dim_shops_id = 1) (type: boolean)
Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 1 (type: int)
- 1 1 (type: int)
+ Select Operator
+ expressions: amount (type: decimal(10,0))
outputColumnNames: _col0
- input vertices:
- 1 Map 2
Statistics: Num rows: 3 Data size: 9 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- File Output Operator
- compressed: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 2
Statistics: Num rows: 3 Data size: 9 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
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3 Data size: 9 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
Execution mode: llap
Map 2
Map Operator Tree:
TableScan
alias: d1
- filterExpr: (id = 1) (type: boolean)
+ filterExpr: (1 = id) (type: boolean)
Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (id = 1) (type: boolean)
+ predicate: (1 = id) (type: boolean)
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: 1 (type: int)
- sort order: +
- Map-reduce partition columns: 1 (type: int)
+ Select Operator
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
Execution mode: llap
Stage: Stage-0
@@ -623,6 +642,7 @@ STAGE PLANS:
Processor Tree:
ListSink
+Warning: Map Join MAPJOIN[15][bigTable=?] in task 'Map 1' is a cross product
PREHOOK: query: SELECT agg.amount
FROM agg_01 agg,
dim_shops d1
@@ -683,67 +703,72 @@ STAGE PLANS:
alias: agg
filterExpr: dim_shops_id is not null (type: boolean)
Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 dim_shops_id (type: int)
- 1 id (type: int)
- outputColumnNames: _col0, _col1, _col5, _col6
- input vertices:
- 1 Map 4
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- Filter Operator
- predicate: (_col1 = _col5) (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: amount (type: decimal(10,0)), dim_shops_id (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
Select Operator
- expressions: _col6 (type: string), _col0 (type: decimal(10,0))
- outputColumnNames: _col6, _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ expressions: _col3 (type: string), _col0 (type: decimal(10,0))
+ outputColumnNames: _col3, _col0
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(), sum(_col0)
- keys: _col6 (type: string)
+ keys: _col3 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 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: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
Execution mode: llap
Map 4
Map Operator Tree:
TableScan
alias: d1
- filterExpr: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+ filterExpr: ((label) IN ('foo', 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (id is not null and (label) IN ('foo', 'bar')) (type: boolean)
+ predicate: ((label) IN ('foo', 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
- Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- value expressions: label (type: string)
Select Operator
- expressions: id (type: int)
- outputColumnNames: _col0
+ expressions: id (type: int), label (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Select Operator
+ expressions: _col0 (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Dynamic Partitioning Event Operator
- Target Input: agg
- Partition key expr: dim_shops_id
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Target column: dim_shops_id
- Target Vertex: Map 1
+ Dynamic Partitioning Event Operator
+ Target Input: agg
+ Partition key expr: dim_shops_id
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Target column: dim_shops_id
+ Target Vertex: Map 1
Execution mode: llap
Reducer 2
Execution mode: llap
@@ -753,11 +778,11 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint), _col2 (type: decimal(20,0))
Reducer 3
Execution mode: uber
@@ -765,10 +790,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), VALUE._col1 (type: decimal(20,0))
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -840,61 +865,62 @@ STAGE PLANS:
alias: agg_01
filterExpr: dim_shops_id is not null (type: boolean)
Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 dim_shops_id (type: int)
- 1 id (type: int)
- outputColumnNames: _col0, _col1, _col5
- input vertices:
- 1 Map 3
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- Filter Operator
- predicate: (_col1 = _col5) (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: decimal(10,0))
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 8 Data size: 24 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: amount (type: decimal(10,0)), dim_shops_id (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 18 Data size: 58 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
Execution mode: llap
Map 3
Map Operator Tree:
TableScan
alias: dim_shops
- filterExpr: (id is not null and (label = 'foo')) (type: boolean)
+ filterExpr: ((label = 'foo') and id is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (id is not null and (label = 'foo')) (type: boolean)
+ predicate: ((label = 'foo') and id is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
- Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Dynamic Partitioning Event Operator
- Target Input: agg_01
- Partition key expr: dim_shops_id
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Target column: dim_shops_id
- Target Vertex: Map 1
+ Dynamic Partitioning Event Operator
+ Target Input: agg_01
+ Partition key expr: dim_shops_id
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Target column: dim_shops_id
+ Target Vertex: Map 1
Execution mode: llap
Map 4
Map Operator Tree:
@@ -902,61 +928,62 @@ STAGE PLANS:
alias: agg_01
filterExpr: dim_shops_id is not null (type: boolean)
Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 dim_shops_id (type: int)
- 1 id (type: int)
- outputColumnNames: _col0, _col1, _col5
- input vertices:
- 1 Map 5
- Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
- HybridGraceHashJoin: true
- Filter Operator
- predicate: (_col1 = _col5) (type: boolean)
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: decimal(10,0))
- outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 12 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 8 Data size: 24 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: amount (type: decimal(10,0)), dim_shops_id (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 9 Data size: 27 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 9 Data size: 29 Basic stats: COMPLETE Column stats: NONE
+ HybridGraceHashJoin: true
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 18 Data size: 58 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
Execution mode: llap
Map 5
Map Operator Tree:
TableScan
alias: dim_shops
- filterExpr: (id is not null and (label = 'bar')) (type: boolean)
+ filterExpr: ((label = 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 3 Data size: 15 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (id is not null and (label = 'bar')) (type: boolean)
+ predicate: ((label = 'bar') and id is not null) (type: boolean)
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: id (type: int)
- sort order: +
- Map-reduce partition columns: id (type: int)
- Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int)
- mode: hash
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Dynamic Partitioning Event Operator
- Target Input: agg_01
- Partition key expr: dim_shops_id
+ Group By Operator
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
- Target column: dim_shops_id
- Target Vertex: Map 4
+ Dynamic Partitioning Event Operator
+ Target Input: agg_01
+ Partition key expr: dim_shops_id
+ Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE
+ Target column: dim_shops_id
+ Target Vertex: Map 4
Execution mode: llap
Union 2
Vertex: Union 2