You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by mm...@apache.org on 2017/10/29 20:39:51 UTC
[12/51] [partial] hive git commit: HIVE-17433: Vectorization: Support
Decimal64 in Hive Query Engine (Matt McCline, reviewed by Teddy Choi)
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
index 8d66875..7224d59 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id1.q.out
@@ -57,24 +57,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -85,17 +84,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkMultiKeyOperator
- keyColumns: [0, 1, 2]
+ keyColumnNums: [0, 1, 2]
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: []
+ valueColumnNums: []
Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -105,7 +105,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:string, val:string
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -113,7 +113,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: aaa
reduceColumnSortOrder: +++
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -121,16 +120,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:string, col 1:string, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -141,7 +140,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2]
+ projectedOutputColumnNums: [0, 1, 2]
Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -217,24 +216,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -245,17 +243,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkMultiKeyOperator
- keyColumns: [0, 1, 2]
+ keyColumnNums: [0, 1, 2]
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: []
+ valueColumnNums: []
Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -265,7 +264,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:string, val:string
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -273,7 +272,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: aaa
reduceColumnSortOrder: +++
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -281,16 +279,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:string, col 1:string, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -301,7 +299,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2]
+ projectedOutputColumnNums: [0, 1, 2]
Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -377,24 +375,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -405,17 +402,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkMultiKeyOperator
- keyColumns: [0, 1, 2]
+ keyColumnNums: [0, 1, 2]
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: []
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -425,7 +423,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:string, val:string
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -433,7 +431,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: aaa
reduceColumnSortOrder: +++
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -441,16 +438,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:string, col 1:string, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -461,7 +458,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2, 0, 1]
+ projectedOutputColumnNums: [2, 0, 1]
Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -531,24 +528,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -559,17 +555,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkMultiKeyOperator
- keyColumns: [0, 1, 2]
+ keyColumnNums: [0, 1, 2]
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: []
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 6624 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -579,7 +576,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:string, val:string
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -587,7 +584,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: aaa
reduceColumnSortOrder: +++
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -595,16 +591,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:string, col 1:string, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -615,7 +611,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2, 0, 1]
+ projectedOutputColumnNums: [2, 0, 1]
Statistics: Num rows: 9 Data size: 3312 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -685,24 +681,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -713,17 +708,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkMultiKeyOperator
- keyColumns: [0, 1, 2]
+ keyColumnNums: [0, 1, 2]
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: []
+ valueColumnNums: []
Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -733,7 +729,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:string, val:string
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -741,7 +737,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: aaa
reduceColumnSortOrder: +++
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -749,16 +744,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:string, col 1:string, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -769,8 +764,8 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 8]
- selectExpressions: IfExprStringScalarStringGroupColumn(col 3, val 0, col 7)(children: LongColEqualLongScalar(col 2, val 0) -> 3:long, IfExprStringScalarStringGroupColumn(col 4, val 1, col 8)(children: LongColEqualLongScalar(col 2, val 1) -> 4:long, IfExprStringScalarStringGroupColumn(col 5, val 2, col 7)(children: LongColEqualLongScalar(col 2, val 2) -> 5:long, IfExprStringScalarStringScalar(col 6, val 3, val nothing)(children: LongColEqualLongScalar(col 2, val 3) -> 6:long) -> 7:String) -> 8:String) -> 7:String) -> 8:String
+ projectedOutputColumnNums: [0, 1, 2, 8]
+ selectExpressions: IfExprStringScalarStringGroupColumn(col 3:boolean, val 0col 7:string)(children: LongColEqualLongScalar(col 2:int, val 0) -> 3:boolean, IfExprStringScalarStringGroupColumn(col 4:boolean, val 1col 8:string)(children: LongColEqualLongScalar(col 2:int, val 1) -> 4:boolean, IfExprStringScalarStringGroupColumn(col 5:boolean, val 2col 7:string)(children: LongColEqualLongScalar(col 2:int, val 2) -> 5:boolean, IfExprStringScalarStringScalar(col 6:boolean, val 3, val nothing)(children: LongColEqualLongScalar(col 2:int, val 3) -> 6:boolean) -> 7:string) -> 8:string) -> 7:string) -> 8:string
Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -846,24 +841,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: string), val (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 2208 Basic stats: COMPLETE Column stats: NONE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: string), _col1 (type: string), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -874,17 +868,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkMultiKeyOperator
- keyColumns: [0, 1, 2]
+ keyColumnNums: [0, 1, 2]
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: []
+ valueColumnNums: []
Statistics: Num rows: 24 Data size: 8832 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -894,7 +889,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:string, val:string
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -902,7 +897,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: aaa
reduceColumnSortOrder: +++
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -910,16 +904,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:string, col 1:string, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -930,8 +924,8 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 8]
- selectExpressions: IfExprStringScalarStringGroupColumn(col 3, val 0, col 7)(children: LongColEqualLongScalar(col 2, val 0) -> 3:long, IfExprStringScalarStringGroupColumn(col 4, val 1, col 8)(children: LongColEqualLongScalar(col 2, val 1) -> 4:long, IfExprStringScalarStringGroupColumn(col 5, val 2, col 7)(children: LongColEqualLongScalar(col 2, val 2) -> 5:long, IfExprStringScalarStringScalar(col 6, val 3, val nothing)(children: LongColEqualLongScalar(col 2, val 3) -> 6:long) -> 7:String) -> 8:String) -> 7:String) -> 8:String
+ projectedOutputColumnNums: [0, 1, 2, 8]
+ selectExpressions: IfExprStringScalarStringGroupColumn(col 3:boolean, val 0col 7:string)(children: LongColEqualLongScalar(col 2:int, val 0) -> 3:boolean, IfExprStringScalarStringGroupColumn(col 4:boolean, val 1col 8:string)(children: LongColEqualLongScalar(col 2:int, val 1) -> 4:boolean, IfExprStringScalarStringGroupColumn(col 5:boolean, val 2col 7:string)(children: LongColEqualLongScalar(col 2:int, val 2) -> 5:boolean, IfExprStringScalarStringScalar(col 6:boolean, val 3, val nothing)(children: LongColEqualLongScalar(col 2:int, val 3) -> 6:boolean) -> 7:string) -> 8:string) -> 7:string) -> 8:string
Statistics: Num rows: 12 Data size: 4416 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false