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 07:37:35 UTC
[12/51] [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/query72.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query72.q.out b/ql/src/test/results/clientpositive/perf/spark/query72.q.out
index 37cf704..ca142a7 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query72.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query72.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select i_item_desc
,w_warehouse_name
,d1.d_week_seq
@@ -28,7 +28,7 @@ group by i_item_desc,w_warehouse_name,d1.d_week_seq
order by total_cnt desc, i_item_desc, w_warehouse_name, d_week_seq
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select i_item_desc
,w_warehouse_name
,d1.d_week_seq
@@ -58,6 +58,10 @@ group by i_item_desc,w_warehouse_name,d1.d_week_seq
order by total_cnt desc, i_item_desc, w_warehouse_name, d_week_seq
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
@@ -75,18 +79,40 @@ STAGE PLANS:
alias: warehouse
filterExpr: w_warehouse_sk is not null (type: boolean)
Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: w_warehouse_sk is not null (type: boolean)
Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: w_warehouse_sk (type: int), w_warehouse_name (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2]
Statistics: Num rows: 27 Data size: 27802 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col2 (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
@@ -100,18 +126,40 @@ STAGE PLANS:
alias: household_demographics
filterExpr: ((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 2:string, val 1001-5000), SelectColumnIsNotNull(col 0:int))
predicate: ((hd_buy_potential = '1001-5000') and hd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: hd_demo_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 3600 Data size: 385200 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col3 (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
Map 16
@@ -119,15 +167,33 @@ STAGE PLANS:
TableScan
alias: promotion
Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Select Operator
expressions: p_promo_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col5 (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
@@ -151,12 +217,22 @@ STAGE PLANS:
alias: inventory
filterExpr: (inv_item_sk is not null and inv_warehouse_sk is not null and inv_date_sk is not null) (type: boolean)
Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int))
predicate: (inv_date_sk is not null and inv_item_sk is not null and inv_warehouse_sk is not null) (type: boolean)
Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: inv_date_sk (type: int), inv_item_sk (type: int), inv_warehouse_sk (type: int), inv_quantity_on_hand (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3]
Statistics: Num rows: 37584000 Data size: 593821104 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -164,6 +240,10 @@ STAGE PLANS:
keys:
0 _col2 (type: int)
1 _col0 (type: int)
+ Map Join Vectorization:
+ className: VectorMapJoinInnerLongOperator
+ native: true
+ nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
outputColumnNames: _col0, _col1, _col3, _col5
input vertices:
1 Map 7
@@ -172,9 +252,22 @@ STAGE PLANS:
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (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: 41342400 Data size: 653203228 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col3 (type: int), _col5 (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
Local Work:
Map Reduce Local Work
Map 13
@@ -183,140 +276,306 @@ STAGE PLANS:
alias: d1
filterExpr: ((d_year = 2001) and d_date_sk is not null and d_week_seq 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: FilterLongColEqualLongScalar(col 6:int, val 2001), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 4:int))
predicate: ((d_year = 2001) and d_date_sk is not null and d_week_seq is not null) (type: boolean)
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_date (type: string), d_week_seq (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 4]
Statistics: Num rows: 36524 Data size: 40870356 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: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _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 14
Map Operator Tree:
TableScan
alias: customer_demographics
filterExpr: ((cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 2:string, val M), SelectColumnIsNotNull(col 0:int))
predicate: ((cd_marital_status = 'M') and cd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cd_demo_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 930900 Data size: 358593079 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: 930900 Data size: 358593079 Basic stats: COMPLETE Column stats: NONE
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: item
filterExpr: i_item_sk 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: SelectColumnIsNotNull(col 0:int)
predicate: 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_item_desc (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 4]
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)
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 18
Map Operator Tree:
TableScan
alias: d3
filterExpr: 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: SelectColumnIsNotNull(col 0:int)
predicate: d_date_sk is not null (type: boolean)
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_date (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2]
Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (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 19
Map Operator Tree:
TableScan
alias: d2
filterExpr: (d_date_sk is not null and d_week_seq 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: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 4:int))
predicate: (d_date_sk is not null and d_week_seq is not null) (type: boolean)
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_week_seq (type: int)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 4]
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
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_returns
filterExpr: cr_item_sk is not null (type: boolean)
Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: cr_item_sk is not null (type: boolean)
Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cr_item_sk (type: int), cr_order_number (type: int)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [2, 16]
Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: int)
sort order: ++
Map-reduce partition columns: _col0 (type: int), _col1 (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: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
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: catalog_sales
filterExpr: (cs_item_sk is not null and cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_sold_date_sk is not null and cs_ship_date_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 4:int), SelectColumnIsNotNull(col 5:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 2:int))
predicate: (cs_bill_cdemo_sk is not null and cs_bill_hdemo_sk is not null and cs_item_sk is not null and cs_ship_date_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_ship_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_bill_hdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_order_number (type: int), cs_quantity (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 4, 5, 15, 16, 17, 18]
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: int), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (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 10
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:
@@ -353,6 +612,11 @@ STAGE PLANS:
Statistics: Num rows: 421645953 Data size: 57099332415 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int)
Reducer 11
+ 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:
@@ -369,6 +633,11 @@ STAGE PLANS:
Statistics: Num rows: 463810558 Data size: 62809267017 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: int), _col6 (type: int), _col7 (type: int), _col9 (type: string), _col10 (type: int), _col16 (type: int), _col18 (type: string)
Reducer 12
+ 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:
@@ -392,6 +661,11 @@ STAGE PLANS:
Statistics: Num rows: 170063874 Data size: 23030064981 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: string), _col10 (type: int), _col11 (type: int), _col14 (type: int), _col20 (type: int)
Reducer 2
+ 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:
@@ -411,6 +685,11 @@ STAGE PLANS:
Statistics: Num rows: 62356755 Data size: 8444357342 Basic stats: COMPLETE Column stats: NONE
value expressions: _col5 (type: string), _col9 (type: string), _col14 (type: int), _col16 (type: int), _col26 (type: int)
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:
@@ -431,6 +710,11 @@ STAGE PLANS:
Statistics: Num rows: 68592431 Data size: 9288793277 Basic stats: COMPLETE Column stats: NONE
value expressions: _col13 (type: string), _col15 (type: string), _col22 (type: int), _col28 (type: int)
Reducer 4
+ 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:
@@ -458,9 +742,23 @@ STAGE PLANS:
value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint)
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: count(VALUE._col0), count(VALUE._col1), count(VALUE._col2)
+ Group By Vectorization:
+ aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint, VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFCountMerge(col 5:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string, col 1:string, col 2:int
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0, 1, 2]
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
@@ -468,27 +766,52 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col5 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int)
sort order: -+++
+ 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: 37725837 Data size: 5108836345 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col3 (type: bigint), _col4 (type: bigint)
Reducer 6
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: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: bigint), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [1, 2, 3, 4, 5, 0]
Statistics: Num rows: 37725837 Data size: 5108836345 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
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 9
+ 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:
http://git-wip-us.apache.org/repos/asf/hive/blob/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query73.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query73.q.out b/ql/src/test/results/clientpositive/perf/spark/query73.q.out
index ddaca3d..b27e1d8 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query73.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query73.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select c_last_name
,c_first_name
,c_salutation
@@ -25,7 +25,7 @@ select c_last_name
and cnt between 1 and 5
order by cnt desc
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select c_last_name
,c_first_name
,c_salutation
@@ -52,6 +52,10 @@ select c_last_name
and cnt between 1 and 5
order by cnt desc
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
@@ -68,18 +72,40 @@ STAGE PLANS:
alias: household_demographics
filterExpr: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringColumnInList(col 2, values >10000, unknown), FilterLongColGreaterLongScalar(col 4:int, val 0), SelectColumnIsTrue(col 11:boolean)(children: IfExprCondExprNull(col 6:boolean, col 10:boolean, null)(children: LongColGreaterLongScalar(col 4:int, val 0) -> 6:boolean, DoubleColGreaterDoubleScalar(col 9:double, val 1.0)(children: DoubleColDivideDoubleColumn(col 7:double, col 8:double)(children: CastLongToDouble(col 3:int) -> 7:double, CastLongToDouble(col 4:int) -> 8:double) -> 9:double) -> 10:boolean) -> 11:boolean), SelectColumnIsNotNull(col 0:int))
predicate: ((hd_buy_potential) IN ('>10000', 'unknown') and (hd_vehicle_count > 0) and CASE WHEN ((hd_vehicle_count > 0)) THEN (((UDFToDouble(hd_dep_count) / UDFToDouble(hd_vehicle_count)) > 1.0D)) ELSE (null) END and hd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: hd_demo_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 1200 Data size: 128400 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col2 (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
Map 9
@@ -88,18 +114,40 @@ STAGE PLANS:
alias: store
filterExpr: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) (type: boolean)
Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringColumnInList(col 23, values Mobile County, Maverick County, Huron County, Kittitas County), SelectColumnIsNotNull(col 0:int))
predicate: ((s_county) IN ('Mobile County', 'Maverick County', 'Huron County', 'Kittitas County') and s_store_sk is not null) (type: boolean)
Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: s_store_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col3 (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
@@ -118,60 +166,134 @@ STAGE PLANS:
alias: customer
filterExpr: c_customer_sk is not null (type: boolean)
Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: c_customer_sk is not null (type: boolean)
Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: c_customer_sk (type: int), c_salutation (type: string), c_first_name (type: string), c_last_name (type: string), c_preferred_cust_flag (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 7, 8, 9, 10]
Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (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 4
Map Operator Tree:
TableScan
alias: store_sales
filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_hdemo_sk is not null and ss_customer_sk is not null) (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: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int), SelectColumnIsNotNull(col 5:int), SelectColumnIsNotNull(col 3:int))
predicate: (ss_customer_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean)
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_hdemo_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3, 5, 7, 9]
Statistics: Num rows: 575995635 Data size: 50814502088 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: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (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 7
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_year) IN (2000, 2001, 2002) and d_dom BETWEEN 1 AND 2 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: FilterLongColumnInList(col 6:int, values [2000, 2001, 2002]), FilterLongColumnBetween(col 9:int, left 1, right 2), SelectColumnIsNotNull(col 0:int))
predicate: ((d_year) IN (2000, 2001, 2002) and d_date_sk is not null and d_dom BETWEEN 1 AND 2) (type: boolean)
Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 8116 Data size: 9081804 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: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
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 2
+ 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:
@@ -192,13 +314,26 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int)
Reducer 3
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), VALUE._col2 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: int), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [1, 2, 3, 4, 5, 0]
Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -207,6 +342,11 @@ STAGE PLANS:
Reducer 5
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:
@@ -250,9 +390,23 @@ STAGE PLANS:
value expressions: _col2 (type: bigint)
Reducer 6
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: count(VALUE._col0)
+ Group By Vectorization:
+ aggregators: VectorUDAFCountMerge(col 2:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:int, col 1:int
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: int), KEY._col1 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -260,14 +414,26 @@ STAGE PLANS:
Select Operator
expressions: _col1 (type: int), _col0 (type: int), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [1, 0, 2]
Statistics: Num rows: 383325119 Data size: 33817053293 Basic stats: COMPLETE Column stats: NONE
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterLongColumnBetween(col 2:bigint, left 1, right 5)
predicate: _col2 BETWEEN 1 AND 5 (type: boolean)
Statistics: Num rows: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (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: 42591679 Data size: 3757450287 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: bigint)