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 2018/08/08 07:37:45 UTC
[22/51] [partial] hive git commit: 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/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query57.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query57.q.out b/ql/src/test/results/clientpositive/perf/spark/query57.q.out
index 51e644a..53b6778 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query57.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query57.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
with v1 as(
select i_category, i_brand,
cc_name,
@@ -45,7 +45,7 @@ with v1 as(
order by sum_sales - avg_monthly_sales, 3
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
with v1 as(
select i_category, i_brand,
cc_name,
@@ -92,6 +92,10 @@ with v1 as(
order by sum_sales - avg_monthly_sales, 3
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-3 depends on stages: Stage-2
@@ -110,18 +114,40 @@ STAGE PLANS:
alias: call_center
filterExpr: (cc_call_center_sk is not null and cc_name is not null) (type: boolean)
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 6:string))
predicate: (cc_call_center_sk is not null and cc_name is not null) (type: boolean)
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cc_call_center_sk (type: int), cc_name (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6]
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col1 (type: int)
1 _col0 (type: int)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Local Work:
Map Reduce Local Work
@@ -135,18 +161,40 @@ STAGE PLANS:
alias: call_center
filterExpr: (cc_call_center_sk is not null and cc_name is not null) (type: boolean)
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 6:string))
predicate: (cc_call_center_sk is not null and cc_name is not null) (type: boolean)
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cc_call_center_sk (type: int), cc_name (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6]
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col1 (type: int)
1 _col0 (type: int)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Local Work:
Map Reduce Local Work
@@ -160,18 +208,40 @@ STAGE PLANS:
alias: call_center
filterExpr: (cc_call_center_sk is not null and cc_name is not null) (type: boolean)
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 6:string))
predicate: (cc_call_center_sk is not null and cc_name is not null) (type: boolean)
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cc_call_center_sk (type: int), cc_name (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6]
Statistics: Num rows: 60 Data size: 122700 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col1 (type: int)
1 _col0 (type: int)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Local Work:
Map Reduce Local Work
@@ -201,183 +271,395 @@ STAGE PLANS:
alias: catalog_sales
filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_call_center_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 15:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 11:int))
predicate: (cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_item_sk (type: int), cs_sales_price (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 11, 15, 21]
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2))
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 10
Map Operator Tree:
TableScan
alias: item
filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 12:string), SelectColumnIsNotNull(col 8:string))
predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 8, 12]
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 11
Map Operator Tree:
TableScan
alias: catalog_sales
filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_call_center_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 15:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 11:int))
predicate: (cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_item_sk (type: int), cs_sales_price (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 11, 15, 21]
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2))
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 17
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1999), FilterLongColEqualLongScalar(col 8:int, val 12)), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2001), FilterLongColEqualLongScalar(col 8:int, val 1))), SelectColumnIsNotNull(col 0:int))
predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6, 8]
Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 19
Map Operator Tree:
TableScan
alias: item
filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 12:string), SelectColumnIsNotNull(col 8:string))
predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 8, 12]
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 20
Map Operator Tree:
TableScan
alias: catalog_sales
filterExpr: (cs_item_sk is not null and cs_sold_date_sk is not null and cs_call_center_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 15:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 11:int))
predicate: (cs_call_center_sk is not null and cs_item_sk is not null and cs_sold_date_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cs_sold_date_sk (type: int), cs_call_center_sk (type: int), cs_item_sk (type: int), cs_sales_price (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 11, 15, 21]
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: decimal(7,2))
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 25
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1999), FilterLongColEqualLongScalar(col 8:int, val 12)), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2001), FilterLongColEqualLongScalar(col 8:int, val 1))), SelectColumnIsNotNull(col 0:int))
predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6, 8]
Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 27
Map Operator Tree:
TableScan
alias: item
filterExpr: (i_item_sk is not null and i_category is not null and i_brand is not null) (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 12:string), SelectColumnIsNotNull(col 8:string))
predicate: (i_brand is not null and i_category is not null and i_item_sk is not null) (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: i_item_sk (type: int), i_brand (type: string), i_category (type: string)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 8, 12]
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 8
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2000), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 1999), FilterLongColEqualLongScalar(col 8:int, val 12)), FilterExprAndExpr(children: FilterLongColEqualLongScalar(col 6:int, val 2001), FilterLongColEqualLongScalar(col 8:int, val 1))), SelectColumnIsNotNull(col 0:int))
predicate: (((d_year = 2000) or ((d_year = 1999) and (d_moy = 12)) or ((d_year = 2001) and (d_moy = 1))) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6, 8]
Statistics: Num rows: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ 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: 73048 Data size: 81740712 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reducer 12
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
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -404,6 +686,11 @@ STAGE PLANS:
Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string)
Reducer 13
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -427,9 +714,23 @@ STAGE PLANS:
value expressions: _col5 (type: decimal(17,2))
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)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumDecimal(col 5:decimal(17,2)) -> decimal(17,2)
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:int, col 1:int, col 2:string, col 3:string, col 4:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -438,14 +739,28 @@ STAGE PLANS:
key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int)
sort order: ++++
Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int)
+ 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: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col5 (type: decimal(17,2))
Reducer 15
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey3 (type: int), VALUE._col0 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [3, 4, 2, 1, 0, 5]
Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
@@ -466,18 +781,38 @@ STAGE PLANS:
name: avg
window function: GenericUDAFAverageEvaluatorDecimal
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
+ PTF Vectorization:
+ className: VectorPTFOperator
+ evaluatorClasses: [VectorPTFEvaluatorDecimalAvg]
+ functionInputExpressions: [col 5:decimal(17,2)]
+ functionNames: [avg]
+ native: true
+ orderExpressions: [col 0:string, col 1:string, col 2:string, col 3:int]
Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: avg_window_0 (type: decimal(21,6)), _col0 (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: decimal(17,2))
outputColumnNames: avg_window_0, _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [6, 3, 4, 2, 1, 0, 5]
Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int), _col1 (type: int)
sort order: +++++
Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ 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: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
value expressions: avg_window_0 (type: decimal(21,6)), _col5 (type: decimal(17,2))
Reducer 16
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: PTF operator: More than 1 argument expression of aggregation function rank
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: VALUE._col0 (type: decimal(21,6)), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: decimal(17,2))
@@ -527,6 +862,11 @@ STAGE PLANS:
Reducer 2
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
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -555,6 +895,11 @@ STAGE PLANS:
Reducer 21
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
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -581,6 +926,11 @@ STAGE PLANS:
Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: decimal(7,2)), _col5 (type: int), _col6 (type: int), _col8 (type: string)
Reducer 22
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -604,9 +954,23 @@ STAGE PLANS:
value expressions: _col5 (type: decimal(17,2))
Reducer 23
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)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumDecimal(col 5:decimal(17,2)) -> decimal(17,2)
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:int, col 1:int, col 2:string, col 3:string, col 4:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -615,9 +979,18 @@ STAGE PLANS:
key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int), _col1 (type: int)
sort order: +++++
Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ 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: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: decimal(17,2))
Reducer 24
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: PTF operator: More than 1 argument expression of aggregation function rank
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2))
@@ -658,6 +1031,11 @@ STAGE PLANS:
Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: decimal(17,2))
Reducer 3
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -681,9 +1059,23 @@ STAGE PLANS:
value expressions: _col5 (type: decimal(17,2))
Reducer 4
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)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumDecimal(col 5:decimal(17,2)) -> decimal(17,2)
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:int, col 1:int, col 2:string, col 3:string, col 4:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -692,9 +1084,18 @@ STAGE PLANS:
key expressions: _col4 (type: string), _col3 (type: string), _col2 (type: string), _col0 (type: int), _col1 (type: int)
sort order: +++++
Map-reduce partition columns: _col4 (type: string), _col3 (type: string), _col2 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ 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: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: decimal(17,2))
Reducer 5
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: PTF operator: More than 1 argument expression of aggregation function rank
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey3 (type: int), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: string), VALUE._col0 (type: decimal(17,2))
@@ -735,6 +1136,11 @@ STAGE PLANS:
Statistics: Num rows: 191657247 Data size: 25954241376 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: decimal(17,2))
Reducer 6
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -758,16 +1164,32 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: int), _col4 (type: decimal(21,6)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2))
Reducer 7
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:
Select Operator
expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey1 (type: int), VALUE._col2 (type: int), VALUE._col3 (type: decimal(21,6)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2)), VALUE._col6 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [2, 3, 1, 4, 5, 6, 7, 8]
Statistics: Num rows: 421645952 Data size: 57099332264 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat