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 00:24:10 UTC
[11/35] 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_sets_grouping.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
index ab33222..1799c00 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_sets_grouping.q.out
@@ -62,7 +62,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2: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: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -85,7 +85,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -95,7 +95,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 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: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1) (type: bigint), grouping(_col2, 0) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -149,13 +149,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -226,7 +226,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -237,7 +237,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -249,7 +249,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -259,7 +259,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -304,7 +304,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1) (type: bigint), grouping(_col2, 0) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -313,13 +313,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -397,7 +397,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -408,7 +408,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -420,7 +420,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -430,7 +430,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -475,14 +475,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint)
predicate: (grouping(_col2, 1) = 1) (type: boolean)
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int)
outputColumnNames: _col0, _col1
@@ -490,13 +490,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -569,7 +569,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -580,7 +580,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -592,7 +592,7 @@ STAGE PLANS:
keys: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -602,7 +602,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -647,14 +647,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint), FilterLongColEqualLongScalar(col 4:bigint, val 1)(children: GroupingColumn(col 2, mask 1) -> 4:bigint))
predicate: ((grouping(_col2, 0) = 1) or (grouping(_col2, 1) = 1)) (type: boolean)
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1) + grouping(_col2, 0)) (type: bigint), CASE WHEN (((grouping(_col2, 1) + grouping(_col2, 0)) = 1)) THEN (_col0) ELSE (null) END (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -663,7 +663,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 7, 12]
selectExpressions: LongColAddLongColumn(col 5:bigint, col 6:bigint)(children: GroupingColumn(col 2, mask 2) -> 5:bigint, GroupingColumn(col 2, mask 1) -> 6:bigint) -> 7:bigint, IfExprColumnNull(col 11:boolean, col 0:int, null)(children: LongColEqualLongScalar(col 10:bigint, val 1)(children: LongColAddLongColumn(col 8:bigint, col 9:bigint)(children: GroupingColumn(col 2, mask 2) -> 8:bigint, GroupingColumn(col 2, mask 1) -> 9:bigint) -> 10:bigint) -> 11:boolean, col 0:int) -> 12:int
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: bigint), _col3 (type: int)
sort order: -+
@@ -673,7 +673,7 @@ 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: 0:int, 1:int
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Reducer 3
Execution mode: vectorized, llap
@@ -698,13 +698,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 0]
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -778,7 +778,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -789,7 +789,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -801,7 +801,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -811,7 +811,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -856,7 +856,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -865,13 +865,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 280 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -942,7 +942,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -953,7 +953,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -965,7 +965,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -975,7 +975,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1020,7 +1020,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L) (type: bigint), grouping(_col2, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
@@ -1029,13 +1029,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
selectExpressions: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1113,7 +1113,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1124,7 +1124,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1136,14 +1136,14 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint)
predicate: (grouping(_col2, 1L) = 1) (type: boolean)
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1153,7 +1153,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1198,14 +1198,14 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
pruneGroupingSetId: true
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 92 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1278,7 +1278,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1289,7 +1289,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1301,14 +1301,14 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 1)(children: GroupingColumn(col 2, mask 2) -> 3:bigint), FilterLongColEqualLongScalar(col 4:bigint, val 1)(children: GroupingColumn(col 2, mask 1) -> 4:bigint))
predicate: ((grouping(_col2, 0L) = 1) or (grouping(_col2, 1L) = 1)) (type: boolean)
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1318,7 +1318,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1363,7 +1363,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), (grouping(_col2, 1L) + grouping(_col2, 0L)) (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -1372,7 +1372,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 5]
selectExpressions: LongColAddLongColumn(col 3:bigint, col 4:bigint)(children: GroupingColumn(col 2, mask 2) -> 3:bigint, GroupingColumn(col 2, mask 1) -> 4:bigint) -> 5:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: bigint), CASE WHEN ((_col2 = 1L)) THEN (_col0) END (type: int)
sort order: -+
@@ -1383,7 +1383,7 @@ 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: 0:int, 1:int
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int)
Reducer 3
Execution mode: vectorized, llap
@@ -1408,13 +1408,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 0]
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1488,7 +1488,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1499,7 +1499,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1511,7 +1511,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -1521,7 +1521,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int
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: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1566,7 +1566,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), 0L (type: bigint), 0L (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -1575,13 +1575,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: ConstantVectorExpression(val 0) -> 2:bigint, ConstantVectorExpression(val 0) -> 3:bigint
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 72 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1647,7 +1647,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1658,7 +1658,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1670,7 +1670,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -1680,7 +1680,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int
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: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1725,7 +1725,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), 0L (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -1734,13 +1734,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2]
selectExpressions: ConstantVectorExpression(val 0) -> 2:bigint
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1808,7 +1808,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1819,7 +1819,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1831,7 +1831,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
@@ -1841,7 +1841,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int
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: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1886,13 +1886,13 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1960,7 +1960,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1971,7 +1971,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -1983,7 +1983,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -1993,7 +1993,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2038,7 +2038,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2047,13 +2047,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [2, 1]) -> 3:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2129,7 +2129,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2140,7 +2140,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2152,7 +2152,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2162,7 +2162,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 24 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2207,7 +2207,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 0L, 1L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2216,13 +2216,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [1, 2]) -> 3:bigint
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 12 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2298,7 +2298,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2309,7 +2309,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2321,7 +2321,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2331,7 +2331,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2376,7 +2376,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 1L, 0L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2385,13 +2385,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [2, 1]) -> 3:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2462,7 +2462,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: t1_n47
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2473,7 +2473,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 44 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -2485,7 +2485,7 @@ STAGE PLANS:
keys: key (type: int), value (type: int), 0L (type: bigint)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint)
sort order: +++
@@ -2495,7 +2495,7 @@ STAGE PLANS:
keyColumns: 0:int, 1:int, 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: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -2540,7 +2540,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), grouping(_col2, 0L, 1L) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -2549,13 +2549,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
selectExpressions: GroupingColumns(col 2, masks [1, 2]) -> 3:bigint
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat