You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2016/04/09 23:33:37 UTC
[03/10] hive git commit: HIVE-12968 :
genNotNullFilterForJoinSourcePlan: needs to merge predicates into the
multi-AND (Gopal V, Ashutosh Chauhan via Jesus Camacho Rodriguez)
http://git-wip-us.apache.org/repos/asf/hive/blob/677e5d20/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
index 9cab06c..c8f6cd7 100644
--- a/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/spark/spark_vectorized_dynamic_partition_pruning.q.out
@@ -58,10 +58,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ds (type: string)
- outputColumnNames: _col0
+ outputColumnNames: ds
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- keys: _col0 (type: string)
+ keys: ds (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
@@ -71,6 +71,7 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reducer 2
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
@@ -89,7 +90,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.srcpart_date
- Execution mode: vectorized
Stage: Stage-0
Move Operator
@@ -210,16 +210,20 @@ STAGE PLANS:
expressions: ds (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: ds
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- target column name: ds
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: ds
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ target column name: ds
+ target work: Map 1
Execution mode: vectorized
Stage: Stage-1
@@ -235,11 +239,15 @@ STAGE PLANS:
alias: srcpart
filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
@@ -249,11 +257,15 @@ STAGE PLANS:
Filter Operator
predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
@@ -261,8 +273,8 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string)
- 1 ds (type: string)
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -274,6 +286,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -287,7 +300,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -336,11 +348,15 @@ STAGE PLANS:
alias: srcpart
filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
@@ -350,11 +366,15 @@ STAGE PLANS:
Filter Operator
predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
@@ -362,8 +382,8 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string)
- 1 ds (type: string)
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -375,6 +395,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -388,7 +409,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -459,40 +479,49 @@ STAGE PLANS:
expressions: ds (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: ds
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- target column name: ds
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: ds
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ target column name: ds
+ target work: Map 1
Execution mode: vectorized
Map 8
Map Operator Tree:
TableScan
alias: srcpart_hour
- filterExpr: (hr is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (hr is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: hr (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: hr
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
- target column name: hr
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: hr
+ Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ target column name: hr
+ target work: Map 1
+ Execution mode: vectorized
Stage: Stage-1
Spark
@@ -507,12 +536,16 @@ STAGE PLANS:
TableScan
alias: srcpart
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- value expressions: hr (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
TableScan
@@ -522,40 +555,49 @@ STAGE PLANS:
Filter Operator
predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map 6
Map Operator Tree:
TableScan
alias: srcpart_hour
- filterExpr: (hr is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (hr is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: hr (type: string)
- sort order: +
- Map-reduce partition columns: hr (type: string)
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 172 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: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string)
- 1 ds (type: string)
- outputColumnNames: _col3
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col3 (type: string)
+ key expressions: _col1 (type: string)
sort order: +
- Map-reduce partition columns: _col3 (type: string)
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Reduce Operator Tree:
@@ -563,8 +605,8 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col3 (type: string)
- 1 hr (type: string)
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -576,6 +618,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 4
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -589,7 +632,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -645,12 +687,16 @@ STAGE PLANS:
alias: srcpart
filterExpr: (ds is not null and hr is not null) (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- value expressions: hr (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Map 5
Map Operator Tree:
TableScan
@@ -660,40 +706,49 @@ STAGE PLANS:
Filter Operator
predicate: (ds is not null and (date = '2008-04-08')) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map 6
Map Operator Tree:
TableScan
alias: srcpart_hour
- filterExpr: (hr is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 344 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (hr is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: hr (type: string)
- sort order: +
- Map-reduce partition columns: hr (type: string)
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 172 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: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string)
- 1 ds (type: string)
- outputColumnNames: _col3
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: _col3 (type: string)
+ key expressions: _col1 (type: string)
sort order: +
- Map-reduce partition columns: _col3 (type: string)
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Reduce Operator Tree:
@@ -701,8 +756,8 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col3 (type: string)
- 1 hr (type: string)
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -714,6 +769,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 4
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -727,7 +783,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -789,48 +844,58 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart_date_hour
- filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: ds (type: string)
- outputColumnNames: _col0
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: ds
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- target column name: ds
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: ds
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
+ target column name: ds
+ target work: Map 1
+ Execution mode: vectorized
Map 6
Map Operator Tree:
TableScan
alias: srcpart_date_hour
- filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: hr (type: string)
- outputColumnNames: _col0
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: _col2 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: hr
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- target column name: hr
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: hr
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
+ target column name: hr
+ target work: Map 1
+ Execution mode: vectorized
Stage: Stage-1
Spark
@@ -844,33 +909,42 @@ STAGE PLANS:
TableScan
alias: srcpart
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string), hr (type: string)
- sort order: ++
- Map-reduce partition columns: ds (type: string), hr (type: string)
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_date_hour
- filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string), hr (type: string)
- sort order: ++
- Map-reduce partition columns: ds (type: string), hr (type: string)
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col2 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col2 (type: string)
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string), hr (type: string)
- 1 ds (type: string), hr (type: string)
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col2 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -882,6 +956,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -895,7 +970,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -944,33 +1018,42 @@ STAGE PLANS:
alias: srcpart
filterExpr: (ds is not null and hr is not null) (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string), hr (type: string)
- sort order: ++
- Map-reduce partition columns: ds (type: string), hr (type: string)
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_date_hour
- filterExpr: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ filterExpr: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (((ds is not null and hr is not null) and (date = '2008-04-08')) and (hour = 11)) (type: boolean)
+ predicate: (ds is not null and hr is not null and (date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string), hr (type: string)
- sort order: ++
- Map-reduce partition columns: ds (type: string), hr (type: string)
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col2 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col2 (type: string)
+ Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string), hr (type: string)
- 1 ds (type: string), hr (type: string)
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col2 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -982,6 +1065,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -995,7 +1079,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1062,16 +1145,20 @@ STAGE PLANS:
expressions: ds (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: _col0 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: ds
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- target column name: ds
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: ds
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ target column name: ds
+ target work: Map 1
Execution mode: vectorized
Stage: Stage-1
@@ -1087,11 +1174,15 @@ STAGE PLANS:
alias: srcpart
filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
@@ -1101,11 +1192,15 @@ STAGE PLANS:
Filter Operator
predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 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: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
@@ -1113,8 +1208,8 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string)
- 1 ds (type: string)
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1126,6 +1221,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1139,7 +1235,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1188,11 +1283,15 @@ STAGE PLANS:
alias: srcpart
filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 21248 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: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
@@ -1202,20 +1301,24 @@ STAGE PLANS:
Filter Operator
predicate: (ds is not null and (date = 'I DONT EXIST')) (type: boolean)
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: ds (type: string)
- sort order: +
- Map-reduce partition columns: ds (type: string)
+ Select Operator
+ expressions: ds (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
- Reducer 2
- Reduce Operator Tree:
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 ds (type: string)
- 1 ds (type: string)
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1227,6 +1330,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1240,7 +1344,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1296,25 +1399,30 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double)
+ expressions: hr (type: double)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: double)
- mode: hash
+ Select Operator
+ expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: UDFToDouble(hr)
+ Group By Operator
+ keys: _col0 (type: double)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- target column name: hr
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: UDFToDouble(hr)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ target column name: hr
+ target work: Map 1
+ Execution mode: vectorized
Stage: Stage-1
Spark
@@ -1327,39 +1435,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: UDFToDouble(hr) is not null (type: boolean)
+ filterExpr: hr is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: UDFToDouble(hr) is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: UDFToDouble(hr) (type: double)
+ key expressions: UDFToDouble(_col0) (type: double)
sort order: +
- Map-reduce partition columns: UDFToDouble(hr) (type: double)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: UDFToDouble(_col0) (type: double)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double)
+ Select Operator
+ expressions: hr (type: double)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 UDFToDouble(hr) (type: double)
- 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double)
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ 0 UDFToDouble(_col0) (type: double)
+ 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1370,6 +1484,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1383,7 +1498,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1428,25 +1542,30 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (hr is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (hr is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: hr (type: double)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: double)
- mode: hash
+ Select Operator
+ expressions: _col0 (type: double)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: (hr * 2)
+ Group By Operator
+ keys: _col0 (type: double)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- target column name: hr
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: (UDFToDouble(hr) * 2.0)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ target column name: hr
+ target work: Map 1
+ Execution mode: vectorized
Stage: Stage-1
Spark
@@ -1459,39 +1578,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: (hr * 2) is not null (type: boolean)
+ filterExpr: hr is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (hr * 2) is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: (hr * 2) (type: double)
+ key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
sort order: +
- Map-reduce partition columns: (hr * 2) (type: double)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (hr is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (hr is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: hr (type: double)
- sort order: +
- Map-reduce partition columns: hr (type: double)
+ Select Operator
+ expressions: hr (type: double)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 (hr * 2) (type: double)
- 1 hr (type: double)
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+ 1 _col0 (type: double)
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1502,6 +1627,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1515,7 +1641,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1562,39 +1687,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: UDFToDouble(hr) is not null (type: boolean)
+ filterExpr: hr is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: UDFToDouble(hr) is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: UDFToDouble(hr) (type: double)
+ key expressions: UDFToDouble(_col0) (type: double)
sort order: +
- Map-reduce partition columns: UDFToDouble(hr) (type: double)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: UDFToDouble(_col0) (type: double)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(UDFToInteger((hr / 2))) is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToDouble(UDFToInteger((hr / 2))) (type: double)
- sort order: +
- Map-reduce partition columns: UDFToDouble(UDFToInteger((hr / 2))) (type: double)
+ Select Operator
+ expressions: hr (type: double)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
+ sort order: +
+ Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 UDFToDouble(hr) (type: double)
- 1 UDFToDouble(UDFToInteger((hr / 2))) (type: double)
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ 0 UDFToDouble(_col0) (type: double)
+ 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double)
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1605,6 +1736,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1618,7 +1750,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1665,39 +1796,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: (hr * 2) is not null (type: boolean)
+ filterExpr: hr is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (hr * 2) is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: (hr * 2) (type: double)
+ key expressions: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
sort order: +
- Map-reduce partition columns: (hr * 2) (type: double)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (hr is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (hr is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: hr (type: double)
- sort order: +
- Map-reduce partition columns: hr (type: double)
+ Select Operator
+ expressions: hr (type: double)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 (hr * 2) (type: double)
- 1 hr (type: double)
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ 0 (UDFToDouble(_col0) * UDFToDouble(2)) (type: double)
+ 1 _col0 (type: double)
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1708,6 +1845,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1721,7 +1859,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1779,25 +1916,30 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (UDFToString(hr) is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToString(hr) is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: UDFToString(hr) (type: string)
+ expressions: hr (type: double)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
+ Select Operator
+ expressions: UDFToString(_col0) (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Spark Partition Pruning Sink Operator
- partition key expr: UDFToString((hr * 2))
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- target column name: hr
- target work: Map 1
+ Spark Partition Pruning Sink Operator
+ partition key expr: UDFToString((UDFToDouble(hr) * 2.0))
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ target column name: hr
+ target work: Map 1
+ Execution mode: vectorized
Stage: Stage-1
Spark
@@ -1810,39 +1952,45 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: UDFToString((hr * 2)) is not null (type: boolean)
+ filterExpr: hr is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: UDFToString((hr * 2)) is not null (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hr (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- key expressions: UDFToString((hr * 2)) (type: string)
+ key expressions: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string)
sort order: +
- Map-reduce partition columns: UDFToString((hr * 2)) (type: string)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
alias: srcpart_double_hour
- filterExpr: (UDFToString(hr) is not null and (hour = 11)) (type: boolean)
+ filterExpr: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToString(hr) is not null and (hour = 11)) (type: boolean)
+ predicate: (hr is not null and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: UDFToString(hr) (type: string)
- sort order: +
- Map-reduce partition columns: UDFToString(hr) (type: string)
+ Select Operator
+ expressions: hr (type: double)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: UDFToString(_col0) (type: string)
+ sort order: +
+ Map-reduce partition columns: UDFToString(_col0) (type: string)
+ Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: vectorized
Reducer 2
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 UDFToString((hr * 2)) (type: string)
- 1 UDFToString(hr) (type: string)
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ 0 UDFToString((UDFToDouble(_col0) * UDFToDouble(2))) (type: string)
+ 1 UDFToString(_col0) (type: string)
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1853,6 +2001,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1866,7 +2015,6 @@ STAGE PLANS:
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: vectorized
Stage: Stage-0
Fetch Operator
@@ -1906,7 +2054,6 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
#### A masked pattern was here ####
1000
-Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: -- parent is reduce tasks
EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
PREHOOK: type: QUERY
@@ -1914,15 +2061,65 @@ POSTHOOK: query: -- parent is reduce tasks
EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-2 is a root stage
+ Stage-1 depends on stages: Stage-2
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-2
+ Spark
+ Edges:
+ Reducer 7 <- Map 6 (GROUP, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: srcpart
+ filterExpr: (ds = '2008-04-08') (type: boolean)
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: '2008-04-08' (type: string)
+ outputColumnNames: ds
+ Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1000 Data size: 10624 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: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ Reducer 7
+ Execution mode: vectorized
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Spark Partition Pruning Sink Operator
+ partition key expr: ds
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ target column name: ds
+ target work: Map 1
+
Stage: Stage-1
Spark
Edges:
Reducer 5 <- Map 4 (GROUP, 2)
- Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Reducer 5 (PARTITION-LEVEL SORT, 2)
Reducer 3 <- Reducer 2 (GROUP, 1)
#### A masked pattern was here ####
Vertices:
@@ -1930,13 +2127,17 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: (ds = '2008-04-08') (type: boolean)
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ filterExpr: ds is not null (type: boolean)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Select Operator
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ expressions: ds (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
- sort order:
- Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
Map 4
Map Operator Tree:
TableScan
@@ -1945,10 +2146,10 @@ STAGE PLANS:
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: '2008-04-08' (type: string)
- outputColumnNames: _col0
+ outputColumnNames: ds
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- keys: _col0 (type: string)
+ keys: ds (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
@@ -1963,9 +2164,9 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
- Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
mode: hash
@@ -1976,6 +2177,7 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: bigint)
Reducer 3
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
@@ -1989,20 +2191,19 @@ STAGE PLANS:
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: vectorized
Reducer 5
+ Execution mode: vectorized
Reduce Operator Tree:
Group By Operator
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Select Operator
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Execution mode: vectorized
Stage: Stage-0
Fetch Operator
@@ -2010,18 +2211,21 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
PREHOOK: type: QUERY
PREHOOK: Input: default@srcpart
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
POSTHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
+POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
1000
PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08'
@@ -2037,7 +2241,7 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
#### A masked pattern was here ####
1000
-Warning: Shuffle Join JOIN[4][tables = [srcpart, srcpart_date_hour]] in Work 'Reducer 2' is a cross product
+Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
PREHOOK: query: -- non-equi join
EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
PREHOOK: type: QUERY
@@ -2061,23 +2265,32 @@ STAGE PLANS:
TableScan
alias: srcpart
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
+ Select Operator
+ expressions: ds (type: string), hr (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
- value expressions: ds (type: string), hr (type: string)
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string), _col1 (type: string)
Map 4
Map Operator Tree:
TableScan
alias: srcpart_date_hour
- filterExpr: ((date = '2008-04-08') and (hour = 11)) (type: boolean)
+ filterExpr: ((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) (type: boolean)
Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE
Filter Operator
-
<TRUNCATED>