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 20:39:50 UTC
[11/51] [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_id2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
index 43e5958..24c7ce7 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_grouping_id2.q.out
@@ -58,14 +58,14 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -73,11 +73,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
@@ -88,11 +87,11 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [4]
- valueColumns: [3]
+ partitionColumnNums: [4]
+ valueColumnNums: [3]
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -100,7 +99,8 @@ STAGE PLANS:
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
@@ -110,7 +110,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -118,7 +118,6 @@ 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
@@ -126,18 +125,18 @@ STAGE PLANS:
dataColumnCount: 4
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3) -> bigint
+ aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
@@ -148,11 +147,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: [3]
+ partitionColumnNums: [0, 1]
+ valueColumnNums: [3]
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reducer 3
@@ -162,7 +161,6 @@ 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
@@ -170,18 +168,18 @@ STAGE PLANS:
dataColumnCount: 4
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3) -> bigint
+ aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3
@@ -192,7 +190,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 3]
+ projectedOutputColumnNums: [0, 1, 2, 3]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -262,14 +260,14 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -277,11 +275,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
@@ -292,11 +289,11 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [4]
- valueColumns: [3]
+ partitionColumnNums: [4]
+ valueColumnNums: [3]
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -304,7 +301,8 @@ STAGE PLANS:
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
@@ -314,7 +312,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -322,7 +320,6 @@ 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
@@ -330,18 +327,18 @@ STAGE PLANS:
dataColumnCount: 4
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3) -> bigint
+ aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2, _col3
@@ -352,11 +349,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: [3]
+ partitionColumnNums: [0, 1]
+ valueColumnNums: [3]
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Reducer 3
@@ -366,7 +363,6 @@ 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
@@ -374,18 +370,18 @@ STAGE PLANS:
dataColumnCount: 4
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3) -> bigint
+ aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2, _col3
@@ -396,7 +392,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 3]
+ projectedOutputColumnNums: [0, 1, 2, 3]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -478,24 +474,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 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:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -506,18 +501,19 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [3]
- valueColumns: []
+ partitionColumnNums: [3]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 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
@@ -527,7 +523,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -535,7 +531,6 @@ 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
@@ -543,16 +538,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2
@@ -563,11 +558,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: []
+ partitionColumnNums: [0, 1]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Execution mode: vectorized, llap
@@ -576,7 +571,6 @@ 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
@@ -584,16 +578,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2
@@ -604,7 +598,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -612,11 +606,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 2
+ keyExpressions: col 2:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col2 (type: int)
mode: hash
outputColumnNames: _col0, _col1
@@ -627,11 +620,11 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- keyColumns: [0]
+ keyColumnNums: [0]
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
- partitionColumns: [2]
- valueColumns: [1]
+ partitionColumnNums: [2]
+ valueColumnNums: [1]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 4
@@ -641,7 +634,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: a
reduceColumnSortOrder: +
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -649,18 +641,18 @@ STAGE PLANS:
dataColumnCount: 2
dataColumns: KEY._col0:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int)
mode: partials
outputColumnNames: _col0, _col1
@@ -671,10 +663,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [0]
+ keyColumnNums: [0]
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]
+ valueColumnNums: [1]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 5
@@ -684,7 +676,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: a
reduceColumnSortOrder: +
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -692,18 +683,18 @@ STAGE PLANS:
dataColumnCount: 2
dataColumns: KEY._col0:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int)
mode: final
outputColumnNames: _col0, _col1
@@ -790,24 +781,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 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:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -818,18 +808,19 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [3]
- valueColumns: []
+ partitionColumnNums: [3]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 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
@@ -839,7 +830,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -847,7 +838,6 @@ 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
@@ -855,16 +845,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2
@@ -875,11 +865,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: []
+ partitionColumnNums: [0, 1]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Execution mode: vectorized, llap
@@ -888,7 +878,6 @@ 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
@@ -896,16 +885,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2
@@ -916,7 +905,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -924,11 +913,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 2
+ keyExpressions: col 2:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col2 (type: int)
mode: hash
outputColumnNames: _col0, _col1
@@ -939,11 +927,11 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- keyColumns: [0]
+ keyColumnNums: [0]
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
- partitionColumns: [2]
- valueColumns: [1]
+ partitionColumnNums: [2]
+ valueColumnNums: [1]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 4
@@ -953,7 +941,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: a
reduceColumnSortOrder: +
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -961,18 +948,18 @@ STAGE PLANS:
dataColumnCount: 2
dataColumns: KEY._col0:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int)
mode: partials
outputColumnNames: _col0, _col1
@@ -983,10 +970,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [0]
+ keyColumnNums: [0]
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]
+ valueColumnNums: [1]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 5
@@ -996,7 +983,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: a
reduceColumnSortOrder: +
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1004,18 +990,18 @@ STAGE PLANS:
dataColumnCount: 2
dataColumns: KEY._col0:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int)
mode: final
outputColumnNames: _col0, _col1
@@ -1099,24 +1085,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 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:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -1127,11 +1112,11 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [3]
- valueColumns: []
+ partitionColumnNums: [3]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
@@ -1139,18 +1124,19 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [4]
- valueColumns: []
+ partitionColumnNums: [4]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 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
@@ -1160,7 +1146,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -1168,7 +1154,6 @@ 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
@@ -1176,16 +1161,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2
@@ -1196,11 +1181,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: []
+ partitionColumnNums: [0, 1]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Execution mode: vectorized, llap
@@ -1209,7 +1194,6 @@ 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
@@ -1217,16 +1201,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2
@@ -1237,7 +1221,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -1245,10 +1229,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [2]
+ keyColumnNums: [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: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reducer 4
Execution mode: llap
@@ -1275,7 +1259,6 @@ 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
@@ -1283,16 +1266,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2
@@ -1303,11 +1286,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: []
+ partitionColumnNums: [0, 1]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reducer 6
Execution mode: vectorized, llap
@@ -1316,7 +1299,6 @@ 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
@@ -1324,16 +1306,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2
@@ -1344,7 +1326,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -1352,10 +1334,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [2]
+ keyColumnNums: [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: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
@@ -1472,24 +1454,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 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:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -1500,11 +1481,11 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [3]
- valueColumns: []
+ partitionColumnNums: [3]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
@@ -1512,18 +1493,19 @@ STAGE PLANS:
Map-reduce partition columns: rand() (type: double)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [4]
- valueColumns: []
+ partitionColumnNums: [4]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 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
@@ -1533,7 +1515,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -1541,7 +1523,6 @@ 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
@@ -1549,16 +1530,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2
@@ -1569,11 +1550,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: []
+ partitionColumnNums: [0, 1]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reducer 3
Execution mode: vectorized, llap
@@ -1582,7 +1563,6 @@ 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
@@ -1590,16 +1570,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2
@@ -1610,7 +1590,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -1618,10 +1598,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [2]
+ keyColumnNums: [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: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reducer 4
Execution mode: llap
@@ -1648,7 +1628,6 @@ 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
@@ -1656,16 +1635,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: PARTIALS
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: partials
outputColumnNames: _col0, _col1, _col2
@@ -1676,11 +1655,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
- 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
- partitionColumns: [0, 1]
- valueColumns: []
+ partitionColumnNums: [0, 1]
+ valueColumnNums: []
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
Reducer 6
Execution mode: vectorized, llap
@@ -1689,7 +1668,6 @@ 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
@@ -1697,16 +1675,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
groupByMode: FINAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: STREAMING
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: final
outputColumnNames: _col0, _col1, _col2
@@ -1717,7 +1695,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -1725,10 +1703,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [2]
+ keyColumnNums: [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: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Stage: Stage-0
@@ -1835,14 +1813,14 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1850,11 +1828,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 0, col 1, ConstantVectorExpression(val 0) -> 2:long
+ keyExpressions: col 0:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
@@ -1865,10 +1842,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _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: [3]
+ valueColumnNums: [3]
Statistics: Num rows: 18 Data size: 144 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -1876,7 +1853,8 @@ STAGE PLANS:
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
@@ -1886,7 +1864,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -1894,7 +1872,6 @@ 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
@@ -1902,18 +1879,18 @@ STAGE PLANS:
dataColumnCount: 4
dataColumns: KEY._col0:int, KEY._col1:int, KEY._col2:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 3) -> bigint
+ aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0, col 1, col 2
+ keyExpressions: col 0:int, col 1:int, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
@@ -1924,7 +1901,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 3]
+ projectedOutputColumnNums: [0, 1, 2, 3]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -2004,24 +1981,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6 Data size: 48 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:int, col 1:int, ConstantVectorExpression(val 0) -> 3:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: _col0 (type: int), _col1 (type: int), 0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -2032,17 +2008,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int), _col1 (type: int), _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: 144 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
@@ -2052,7 +2029,7 @@ STAGE PLANS:
includeColumns: [0, 1]
dataColumns: key:int, value:int
partitionColumnCount: 0
- scratchColumnTypeNames: bigint
+ scratchColumnTypeNames: [bigint]
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
@@ -2060,7 +2037,6 @@ 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
@@ -2068,16 +2044,16 @@ STAGE PLANS:
dataColumnCount: 3
dataColumns: KEY._col0:int, KEY._col1:int, 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:int, col 1:int, col 2:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -2088,7 +2064,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -2096,11 +2072,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 2
+ keyExpressions: col 2:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col2 (type: int)
mode: hash
outputColumnNames: _col0, _col1
@@ -2111,10 +2086,10 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Reduce Sink Vectorization:
className: VectorReduceSinkLongOperator
- keyColumns: [0]
+ keyColumnNums: [0]
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]
+ valueColumnNums: [1]
Statistics: Num rows: 9 Data size: 72 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 3
@@ -2124,7 +2099,6 @@ STAGE PLANS:
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
reduceColumnNullOrder: a
reduceColumnSortOrder: +
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -2132,18 +2106,18 @@ STAGE PLANS:
dataColumnCount: 2
dataColumns: KEY._col0:int, VALUE._col0:bigint
partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -2225,24 +2199,23 @@ STAGE PLANS:
Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
+ vectorizationSchemaColumns: [0:key:int, 1:value:int, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: key (type: int), value (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputCol
<TRUNCATED>