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 2018/08/16 00:21:12 UTC
[38/51] [partial] hive git commit: Revert "HIVE-20315: Vectorization:
Fix more NULL / Wrong Results issues and avoid unnecessary casts/conversions
(Matt McCline, reviewed by Teddy Choi)"
http://git-wip-us.apache.org/repos/asf/hive/blob/142367d9/ql/src/test/results/clientpositive/perf/spark/query28.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query28.q.out b/ql/src/test/results/clientpositive/perf/spark/query28.q.out
index caaca45..b437829 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query28.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query28.q.out
@@ -1,5 +1,5 @@
Warning: Map Join MAPJOIN[94][bigTable=?] in task 'Stage-1:MAPRED' is a cross product
-PREHOOK: query: explain vectorization expression
+PREHOOK: query: explain
select *
from (select avg(ss_list_price) B1_LP
,count(ss_list_price) B1_CNT
@@ -51,7 +51,7 @@ from (select avg(ss_list_price) B1_LP
or ss_wholesale_cost between 42 and 42+20)) B6
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain
select *
from (select avg(ss_list_price) B1_LP
,count(ss_list_price) B1_CNT
@@ -103,10 +103,6 @@ from (select avg(ss_list_price) B1_LP
or ss_wholesale_cost between 42 and 42+20)) B6
limit 100
POSTHOOK: type: QUERY
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-1 depends on stages: Stage-2
@@ -134,33 +130,15 @@ STAGE PLANS:
alias: store_sales
filterExpr: (ss_quantity BETWEEN 16 AND 20 and (ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100)) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterExprAndExpr(children: FilterLongColumnBetween(col 10:int, left 16, right 20), FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 12:decimal(7,2)/DECIMAL_64, decimal64LeftVal 14200, decimalLeftVal 14200, decimal64RightVal 15200, decimalRightVal 15200), FilterDecimal64ColumnBetween(col 19:decimal(7,2)/DECIMAL_64, decimal64LeftVal 305400, decimalLeftVal 305400, decimal64RightVal 405400, decimalRightVal 405400), FilterDecimal64ColumnBetween(col 11:decimal(7,2)/DECIMAL_64, decimal64LeftVal 8000, decimalLeftVal 8000, decimal64RightVal 10000, decimalRightVal 10000)))
predicate: ((ss_list_price BETWEEN 142 AND 152 or ss_coupon_amt BETWEEN 3054 AND 4054 or ss_wholesale_cost BETWEEN 80 AND 100) and ss_quantity BETWEEN 16 AND 20) (type: boolean)
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_list_price (type: decimal(7,2))
outputColumnNames: ss_list_price
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [12]
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ss_list_price), count(ss_list_price)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal64(col 12:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64, VectorUDAFCount(col 12:decimal(7,2)/DECIMAL_64) -> bigint
- className: VectorGroupByOperator
- groupByMode: HASH
- keyExpressions: col 12:decimal(7,2)/DECIMAL_64
- native: false
- vectorProcessingMode: HASH
- projectedOutputColumnNums: [0, 1]
keys: ss_list_price (type: decimal(7,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -169,55 +147,24 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(7,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(7,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Map 13
Map Operator Tree:
TableScan
alias: store_sales
filterExpr: (ss_quantity BETWEEN 11 AND 15 and (ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24)) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterExprAndExpr(children: FilterLongColumnBetween(col 10:int, left 11, right 15), FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 12:decimal(7,2)/DECIMAL_64, decimal64LeftVal 6600, decimalLeftVal 6600, decimal64RightVal 7600, decimalRightVal 7600), FilterDecimal64ColumnBetween(col 19:decimal(7,2)/DECIMAL_64, decimal64LeftVal 92000, decimalLeftVal 92000, decimal64RightVal 192000, decimalRightVal 192000), FilterDecimal64ColumnBetween(col 11:decimal(7,2)/DECIMAL_64, decimal64LeftVal 400, decimalLeftVal 400, decimal64RightVal 2400, decimalRightVal 2400)))
predicate: ((ss_list_price BETWEEN 66 AND 76 or ss_coupon_amt BETWEEN 920 AND 1920 or ss_wholesale_cost BETWEEN 4 AND 24) and ss_quantity BETWEEN 11 AND 15) (type: boolean)
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_list_price (type: decimal(7,2))
outputColumnNames: ss_list_price
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [12]
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ss_list_price), count(ss_list_price)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal64(col 12:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64, VectorUDAFCount(col 12:decimal(7,2)/DECIMAL_64) -> bigint
- className: VectorGroupByOperator
- groupByMode: HASH
- keyExpressions: col 12:decimal(7,2)/DECIMAL_64
- native: false
- vectorProcessingMode: HASH
- projectedOutputColumnNums: [0, 1]
keys: ss_list_price (type: decimal(7,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -226,55 +173,24 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(7,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(7,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Map 16
Map Operator Tree:
TableScan
alias: store_sales
filterExpr: (ss_quantity BETWEEN 6 AND 10 and (ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52)) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterExprAndExpr(children: FilterLongColumnBetween(col 10:int, left 6, right 10), FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 12:decimal(7,2)/DECIMAL_64, decimal64LeftVal 9100, decimalLeftVal 9100, decimal64RightVal 10100, decimalRightVal 10100), FilterDecimal64ColumnBetween(col 19:decimal(7,2)/DECIMAL_64, decimal64LeftVal 143000, decimalLeftVal 143000, decimal64RightVal 243000, decimalRightVal 243000), FilterDecimal64ColumnBetween(col 11:decimal(7,2)/DECIMAL_64, decimal64LeftVal 3200, decimalLeftVal 3200, decimal64RightVal 5200, decimalRightVal 5200)))
predicate: ((ss_list_price BETWEEN 91 AND 101 or ss_coupon_amt BETWEEN 1430 AND 2430 or ss_wholesale_cost BETWEEN 32 AND 52) and ss_quantity BETWEEN 6 AND 10) (type: boolean)
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_list_price (type: decimal(7,2))
outputColumnNames: ss_list_price
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [12]
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ss_list_price), count(ss_list_price)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal64(col 12:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64, VectorUDAFCount(col 12:decimal(7,2)/DECIMAL_64) -> bigint
- className: VectorGroupByOperator
- groupByMode: HASH
- keyExpressions: col 12:decimal(7,2)/DECIMAL_64
- native: false
- vectorProcessingMode: HASH
- projectedOutputColumnNums: [0, 1]
keys: ss_list_price (type: decimal(7,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -283,55 +199,24 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(7,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(7,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Map 4
Map Operator Tree:
TableScan
alias: store_sales
filterExpr: (ss_quantity BETWEEN 26 AND 30 and (ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62)) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterExprAndExpr(children: FilterLongColumnBetween(col 10:int, left 26, right 30), FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 12:decimal(7,2)/DECIMAL_64, decimal64LeftVal 2800, decimalLeftVal 2800, decimal64RightVal 3800, decimalRightVal 3800), FilterDecimal64ColumnBetween(col 19:decimal(7,2)/DECIMAL_64, decimal64LeftVal 251300, decimalLeftVal 251300, decimal64RightVal 351300, decimalRightVal 351300), FilterDecimal64ColumnBetween(col 11:decimal(7,2)/DECIMAL_64, decimal64LeftVal 4200, decimalLeftVal 4200, decimal64RightVal 6200, decimalRightVal 6200)))
predicate: ((ss_list_price BETWEEN 28 AND 38 or ss_coupon_amt BETWEEN 2513 AND 3513 or ss_wholesale_cost BETWEEN 42 AND 62) and ss_quantity BETWEEN 26 AND 30) (type: boolean)
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_list_price (type: decimal(7,2))
outputColumnNames: ss_list_price
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [12]
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ss_list_price), count(ss_list_price)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal64(col 12:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64, VectorUDAFCount(col 12:decimal(7,2)/DECIMAL_64) -> bigint
- className: VectorGroupByOperator
- groupByMode: HASH
- keyExpressions: col 12:decimal(7,2)/DECIMAL_64
- native: false
- vectorProcessingMode: HASH
- projectedOutputColumnNums: [0, 1]
keys: ss_list_price (type: decimal(7,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -340,55 +225,24 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(7,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(7,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Map 7
Map Operator Tree:
TableScan
alias: store_sales
filterExpr: (ss_quantity BETWEEN 21 AND 25 and (ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58)) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterExprAndExpr(children: FilterLongColumnBetween(col 10:int, left 21, right 25), FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 12:decimal(7,2)/DECIMAL_64, decimal64LeftVal 13500, decimalLeftVal 13500, decimal64RightVal 14500, decimalRightVal 14500), FilterDecimal64ColumnBetween(col 19:decimal(7,2)/DECIMAL_64, decimal64LeftVal 1418000, decimalLeftVal 1418000, decimal64RightVal 1518000, decimalRightVal 1518000), FilterDecimal64ColumnBetween(col 11:decimal(7,2)/DECIMAL_64, decimal64LeftVal 3800, decimalLeftVal 3800, decimal64RightVal 5800, decimalRightVal 5800)))
predicate: ((ss_list_price BETWEEN 135 AND 145 or ss_coupon_amt BETWEEN 14180 AND 15180 or ss_wholesale_cost BETWEEN 38 AND 58) and ss_quantity BETWEEN 21 AND 25) (type: boolean)
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_list_price (type: decimal(7,2))
outputColumnNames: ss_list_price
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [12]
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ss_list_price), count(ss_list_price)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal64(col 12:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64, VectorUDAFCount(col 12:decimal(7,2)/DECIMAL_64) -> bigint
- className: VectorGroupByOperator
- groupByMode: HASH
- keyExpressions: col 12:decimal(7,2)/DECIMAL_64
- native: false
- vectorProcessingMode: HASH
- projectedOutputColumnNums: [0, 1]
keys: ss_list_price (type: decimal(7,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -397,101 +251,42 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(7,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(7,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reducer 11
Execution mode: vectorized
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- keyExpressions: col 0:decimal(7,2)
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: decimal(7,2))
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col2), count(_col0)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFCount(col 0:decimal(7,2)) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1, 2]
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Reduce Sink Vectorization:
- className: VectorReduceSinkEmptyKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint)
Reducer 12
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 0:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [4, 1, 2]
- selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(17,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 3:decimal(19,0)) -> 4:decimal(37,22)
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
- Spark Hash Table Sink Vectorization:
- className: VectorSparkHashTableSinkOperator
- native: true
keys:
0
1
@@ -501,83 +296,37 @@ STAGE PLANS:
5
Reducer 14
Execution mode: vectorized
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- keyExpressions: col 0:decimal(7,2)
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: decimal(7,2))
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col2), count(_col0)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFCount(col 0:decimal(7,2)) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1, 2]
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Reduce Sink Vectorization:
- className: VectorReduceSinkEmptyKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint)
Reducer 15
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 0:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [4, 1, 2]
- selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(17,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 3:decimal(19,0)) -> 4:decimal(37,22)
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
- Spark Hash Table Sink Vectorization:
- className: VectorSparkHashTableSinkOperator
- native: true
keys:
0
1
@@ -587,83 +336,37 @@ STAGE PLANS:
5
Reducer 17
Execution mode: vectorized
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- keyExpressions: col 0:decimal(7,2)
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: decimal(7,2))
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col2), count(_col0)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFCount(col 0:decimal(7,2)) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1, 2]
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Reduce Sink Vectorization:
- className: VectorReduceSinkEmptyKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint)
Reducer 18
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 0:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [4, 1, 2]
- selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(17,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 3:decimal(19,0)) -> 4:decimal(37,22)
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
- Spark Hash Table Sink Vectorization:
- className: VectorSparkHashTableSinkOperator
- native: true
keys:
0
1
@@ -673,83 +376,37 @@ STAGE PLANS:
5
Reducer 5
Execution mode: vectorized
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- keyExpressions: col 0:decimal(7,2)
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: decimal(7,2))
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col2), count(_col0)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFCount(col 0:decimal(7,2)) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1, 2]
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Reduce Sink Vectorization:
- className: VectorReduceSinkEmptyKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint)
Reducer 6
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 0:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [4, 1, 2]
- selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(17,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 3:decimal(19,0)) -> 4:decimal(37,22)
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
- Spark Hash Table Sink Vectorization:
- className: VectorSparkHashTableSinkOperator
- native: true
keys:
0
1
@@ -759,83 +416,37 @@ STAGE PLANS:
5
Reducer 8
Execution mode: vectorized
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- keyExpressions: col 0:decimal(7,2)
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: decimal(7,2))
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col2), count(_col0)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFCount(col 0:decimal(7,2)) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1, 2]
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Reduce Sink Vectorization:
- className: VectorReduceSinkEmptyKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint)
Reducer 9
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 0:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [4, 1, 2]
- selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(17,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 3:decimal(19,0)) -> 4:decimal(37,22)
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
- Spark Hash Table Sink Vectorization:
- className: VectorSparkHashTableSinkOperator
- native: true
keys:
0
1
@@ -857,33 +468,15 @@ STAGE PLANS:
alias: store_sales
filterExpr: (ss_quantity BETWEEN 0 AND 5 and (ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34)) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterExprAndExpr(children: FilterLongColumnBetween(col 10:int, left 0, right 5), FilterExprOrExpr(children: FilterDecimal64ColumnBetween(col 12:decimal(7,2)/DECIMAL_64, decimal64LeftVal 1100, decimalLeftVal 1100, decimal64RightVal 2100, decimalRightVal 2100), FilterDecimal64ColumnBetween(col 19:decimal(7,2)/DECIMAL_64, decimal64LeftVal 46000, decimalLeftVal 46000, decimal64RightVal 146000, decimalRightVal 146000), FilterDecimal64ColumnBetween(col 11:decimal(7,2)/DECIMAL_64, decimal64LeftVal 1400, decimalLeftVal 1400, decimal64RightVal 3400, decimalRightVal 3400)))
predicate: ((ss_list_price BETWEEN 11 AND 21 or ss_coupon_amt BETWEEN 460 AND 1460 or ss_wholesale_cost BETWEEN 14 AND 34) and ss_quantity BETWEEN 0 AND 5) (type: boolean)
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_list_price (type: decimal(7,2))
outputColumnNames: ss_list_price
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [12]
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(ss_list_price), count(ss_list_price)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal64(col 12:decimal(7,2)/DECIMAL_64) -> decimal(17,2)/DECIMAL_64, VectorUDAFCount(col 12:decimal(7,2)/DECIMAL_64) -> bigint
- className: VectorGroupByOperator
- groupByMode: HASH
- keyExpressions: col 12:decimal(7,2)/DECIMAL_64
- native: false
- vectorProcessingMode: HASH
- projectedOutputColumnNums: [0, 1]
keys: ss_list_price (type: decimal(7,2))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -892,96 +485,40 @@ STAGE PLANS:
key expressions: _col0 (type: decimal(7,2))
sort order: +
Map-reduce partition columns: _col0 (type: decimal(7,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: decimal(17,2)), _col2 (type: bigint)
Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reducer 2
Execution mode: vectorized
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- keyExpressions: col 0:decimal(7,2)
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: decimal(7,2))
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 21333171 Data size: 1882018537 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count(_col2), count(_col0)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 1:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFCount(col 0:decimal(7,2)) -> bigint
- className: VectorGroupByOperator
- groupByMode: PARTIAL2
- native: false
- vectorProcessingMode: STREAMING
- projectedOutputColumnNums: [0, 1, 2]
mode: partial2
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Reduce Sink Vectorization:
- className: VectorReduceSinkEmptyKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark 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: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: decimal(17,2)), _col1 (type: bigint), _col2 (type: bigint)
Reducer 3
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
- Group By Vectorization:
- aggregators: VectorUDAFSumDecimal(col 0:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
- className: VectorGroupByOperator
- groupByMode: MERGEPARTIAL
- native: false
- vectorProcessingMode: GLOBAL
- projectedOutputColumnNums: [0, 1, 2]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: (_col0 / _col1) (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [4, 1, 2]
- selectExpressions: DecimalColDivideDecimalColumn(col 0:decimal(17,2), col 3:decimal(19,0))(children: CastLongToDecimal(col 1:bigint) -> 3:decimal(19,0)) -> 4:decimal(37,22)
Statistics: Num rows: 1 Data size: 232 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -997,12 +534,6 @@ STAGE PLANS:
3
4
5
- Map Join Vectorization:
- bigTableValueExpressions: col 4:decimal(37,22), col 1:bigint, col 2:bigint
- className: VectorMapJoinOperator
- native: false
- nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
- nativeConditionsNotMet: One MapJoin Condition IS false
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
input vertices:
1 Reducer 6
@@ -1014,22 +545,12 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: decimal(37,22)), _col1 (type: bigint), _col2 (type: bigint), _col15 (type: decimal(37,22)), _col16 (type: bigint), _col17 (type: bigint), _col12 (type: decimal(37,22)), _col13 (type: bigint), _col14 (type: bigint), _col9 (type: decimal(37,22)), _col10 (type: bigint), _col11 (type: bigint), _col6 (type: decimal(37,22)), _col7 (type: bigint), _col8 (type: bigint), _col3 (type: decimal(37,22)), _col4 (type: bigint), _col5 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1, 2, 15, 16, 17, 12, 13, 14, 9, 10, 11, 6, 7, 8, 3, 4, 5]
Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
- Limit Vectorization:
- className: VectorLimitOperator
- native: true
Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 1 Data size: 1393 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat