You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2019/01/04 00:24:11 UTC
[12/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
index 4b736dd..c4e8ac7 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets4.q.out
@@ -70,7 +70,7 @@ STAGE PLANS:
TableScan
alias: t1_n161
filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -80,7 +80,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColLessDoubleScalar(col 4:double, val 3.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -94,7 +94,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -105,7 +105,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
@@ -117,7 +117,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -165,7 +165,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -173,7 +173,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -181,7 +181,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -192,7 +192,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Reducer 3
Execution mode: llap
@@ -204,10 +204,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -244,7 +244,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -252,7 +252,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -260,7 +260,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -271,7 +271,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Stage: Stage-0
@@ -322,7 +322,7 @@ STAGE PLANS:
TableScan
alias: t1_n161
filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -332,7 +332,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColLessDoubleScalar(col 4:double, val 3.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -346,7 +346,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -357,7 +357,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
@@ -369,7 +369,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -417,7 +417,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -425,7 +425,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -433,7 +433,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -444,7 +444,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Reducer 3
Execution mode: llap
@@ -456,10 +456,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 2848 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -496,7 +496,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -504,7 +504,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -512,7 +512,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -523,7 +523,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Stage: Stage-0
@@ -605,7 +605,7 @@ STAGE PLANS:
TableScan
alias: t1_n161
filterExpr: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -615,7 +615,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColLessDoubleScalar(col 4:double, val 3.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) < 3.0D) (type: boolean)
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 340 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -629,7 +629,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -640,7 +640,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -688,7 +688,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -699,7 +699,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
@@ -711,7 +711,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 8 Data size: 2944 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -742,7 +742,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -750,7 +750,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -758,7 +758,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -769,7 +769,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Reducer 4
Execution mode: llap
@@ -781,10 +781,10 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 5696 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 1619 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 5696 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -821,7 +821,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Filter Operator
Filter Vectorization:
@@ -829,7 +829,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -837,7 +837,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -848,7 +848,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:string, 2:bigint
- Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string), _col2 (type: bigint)
Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
index ff43724..eadcb6e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets5.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n33
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -95,7 +95,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -140,7 +140,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -154,7 +154,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -165,7 +165,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -196,7 +196,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -205,13 +205,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -257,7 +257,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n33
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -268,7 +268,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -280,7 +280,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -290,7 +290,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -335,7 +335,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -349,7 +349,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -360,7 +360,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -391,7 +391,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -400,13 +400,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -479,7 +479,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n33
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -490,7 +490,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -502,7 +502,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -512,7 +512,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -557,7 +557,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
Group By Vectorization:
@@ -571,7 +571,7 @@ STAGE PLANS:
keys: _col0 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
@@ -582,7 +582,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 2:bigint
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -613,7 +613,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -624,7 +624,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:bigint
- Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col3 (type: bigint)
Reducer 4
Execution mode: vectorized, llap
@@ -655,7 +655,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: final
outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint)
@@ -664,13 +664,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
index 946abaf..a516ae4 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets6.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n84
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -73,7 +73,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColEqualDoubleScalar(col 4:double, val 5.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) = 5.0D) (type: boolean)
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -95,7 +95,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -140,14 +140,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -209,7 +209,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n84
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -219,7 +219,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterDoubleColEqualDoubleScalar(col 4:double, val 5.0)(children: CastStringToDouble(col 0:string) -> 4:double)
predicate: (UDFToDouble(a) = 5.0D) (type: boolean)
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -231,7 +231,7 @@ STAGE PLANS:
keys: a (type: string), b (type: string), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
sort order: +++
@@ -241,7 +241,7 @@ STAGE PLANS:
keyColumns: 0:string, 1:string, 2:bigint
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -286,14 +286,14 @@ STAGE PLANS:
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 534 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat