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 07:37:26 UTC
[03/51] [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/query83.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query83.q.out b/ql/src/test/results/clientpositive/perf/spark/query83.q.out
index 1199d29..6a38c0d 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query83.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query83.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
with sr_items as
(select i_item_id item_id,
sum(sr_return_quantity) sr_item_qty
@@ -64,7 +64,7 @@ with sr_items as
,sr_item_qty
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
with sr_items as
(select i_item_id item_id,
sum(sr_return_quantity) sr_item_qty
@@ -130,6 +130,10 @@ with sr_items as
,sr_item_qty
limit 100
POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
@@ -166,54 +170,117 @@ STAGE PLANS:
alias: catalog_returns
filterExpr: (cr_item_sk is not null and cr_returned_date_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: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int))
predicate: (cr_item_sk is not null and cr_returned_date_sk is not null) (type: boolean)
Statistics: Num rows: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cr_returned_date_sk (type: int), cr_item_sk (type: int), cr_return_quantity (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 17]
Statistics: Num rows: 28798881 Data size: 3057234680 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: 28798881 Data size: 3057234680 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (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 10
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_week_seq is not null and d_date 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 4:int), SelectColumnIsNotNull(col 2:string))
predicate: (d_date 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 (type: string), d_week_seq (type: int)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [2, 4]
Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (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 13
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') 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: FilterStringColumnInList(col 2, values 1998-01-02, 1998-10-15, 1998-11-10), SelectColumnIsNotNull(col 4:int))
predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') 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_week_seq (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [4]
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ keyExpressions: col 4:int
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumnNums: []
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
@@ -222,102 +289,224 @@ STAGE PLANS:
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
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 14
Map Operator Tree:
TableScan
alias: store_returns
filterExpr: (sr_item_sk is not null and sr_returned_date_sk is not null) (type: boolean)
Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int))
predicate: (sr_item_sk is not null and sr_returned_date_sk is not null) (type: boolean)
Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sr_returned_date_sk (type: int), sr_item_sk (type: int), sr_return_quantity (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 10]
Statistics: Num rows: 57591150 Data size: 4462194832 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: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (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 18
Map Operator Tree:
TableScan
alias: item
filterExpr: (i_item_sk is not null and i_item_id 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 1:string))
predicate: (i_item_id 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_item_id (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
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 19
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_date is not null 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: SelectColumnIsNotNull(col 2:string), SelectColumnIsNotNull(col 0:int))
predicate: (d_date is not null and 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: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: _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
Map 21
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_week_seq is not null and d_date 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 4:int), SelectColumnIsNotNull(col 2:string))
predicate: (d_date 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 (type: string), d_week_seq (type: int)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [2, 4]
Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (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 24
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') 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: FilterStringColumnInList(col 2, values 1998-01-02, 1998-10-15, 1998-11-10), SelectColumnIsNotNull(col 4:int))
predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') 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_week_seq (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [4]
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ keyExpressions: col 4:int
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumnNums: []
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
@@ -326,102 +515,224 @@ STAGE PLANS:
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
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 25
Map Operator Tree:
TableScan
alias: web_returns
filterExpr: (wr_item_sk is not null and wr_returned_date_sk is not null) (type: boolean)
Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 0:int))
predicate: (wr_item_sk is not null and wr_returned_date_sk is not null) (type: boolean)
Statistics: Num rows: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: wr_returned_date_sk (type: int), wr_item_sk (type: int), wr_return_quantity (type: int)
outputColumnNames: _col0, _col1, _col2
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 14]
Statistics: Num rows: 14398467 Data size: 1325194184 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: 14398467 Data size: 1325194184 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (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 29
Map Operator Tree:
TableScan
alias: item
filterExpr: (i_item_sk is not null and i_item_id 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 1:string))
predicate: (i_item_id 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_item_id (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
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 30
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_date is not null 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: SelectColumnIsNotNull(col 2:string), SelectColumnIsNotNull(col 0:int))
predicate: (d_date is not null and 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: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: _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
Map 32
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_week_seq is not null and d_date 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 4:int), SelectColumnIsNotNull(col 2:string))
predicate: (d_date 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 (type: string), d_week_seq (type: int)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [2, 4]
Statistics: Num rows: 73049 Data size: 81741831 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: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (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 35
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') 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: FilterStringColumnInList(col 2, values 1998-01-02, 1998-10-15, 1998-11-10), SelectColumnIsNotNull(col 4:int))
predicate: ((d_date) IN ('1998-01-02', '1998-10-15', '1998-11-10') 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_week_seq (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [4]
Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE
Group By Operator
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ keyExpressions: col 4:int
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumnNums: []
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0
@@ -430,49 +741,113 @@ STAGE PLANS:
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
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: item
filterExpr: (i_item_sk is not null and i_item_id 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 1:string))
predicate: (i_item_id 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_item_id (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
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 8
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_date is not null 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: SelectColumnIsNotNull(col 2:string), SelectColumnIsNotNull(col 0:int))
predicate: (d_date is not null and 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: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: _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
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:
@@ -494,8 +869,21 @@ STAGE PLANS:
Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE
Reducer 12
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
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
@@ -504,8 +892,17 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE
Reducer 15
+ 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:
@@ -522,6 +919,11 @@ STAGE PLANS:
Statistics: Num rows: 63350266 Data size: 4908414421 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: int), _col4 (type: string)
Reducer 16
+ 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:
@@ -545,9 +947,23 @@ STAGE PLANS:
value expressions: _col1 (type: bigint)
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)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -556,9 +972,18 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: 34842647 Data size: 2699627990 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
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:
@@ -575,6 +1000,11 @@ STAGE PLANS:
Statistics: Num rows: 31678769 Data size: 3362958220 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: int), _col4 (type: string)
Reducer 20
+ 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:
@@ -590,6 +1020,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE
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:
@@ -611,8 +1046,21 @@ STAGE PLANS:
Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE
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
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
@@ -621,8 +1069,17 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE
Reducer 26
+ 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:
@@ -639,6 +1096,11 @@ STAGE PLANS:
Statistics: Num rows: 15838314 Data size: 1457713633 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: int), _col4 (type: string)
Reducer 27
+ 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:
@@ -662,9 +1124,23 @@ STAGE PLANS:
value expressions: _col1 (type: bigint)
Reducer 28
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: VectorUDAFSumLong(col 1:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -673,9 +1149,18 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: 8711072 Data size: 801742469 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
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:
@@ -698,6 +1183,11 @@ STAGE PLANS:
Statistics: Num rows: 34846646 Data size: 3699254122 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 31
+ 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:
@@ -713,6 +1203,11 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE
Reducer 33
+ 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:
@@ -734,8 +1229,21 @@ STAGE PLANS:
Statistics: Num rows: 80353 Data size: 89916016 Basic stats: COMPLETE Column stats: NONE
Reducer 34
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
+ Group By Vectorization:
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: []
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
@@ -744,12 +1252,30 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: 40176 Data size: 44957448 Basic stats: COMPLETE Column stats: NONE
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: VectorUDAFSumLong(col 1:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -758,9 +1284,18 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkStringOperator
+ 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: 17423323 Data size: 1849627061 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Reducer 5
+ 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:
@@ -784,22 +1319,43 @@ STAGE PLANS:
value expressions: _col2 (type: double), _col3 (type: bigint), _col4 (type: double), _col5 (type: bigint), _col6 (type: double), _col7 (type: decimal(25,6))
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.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint), VALUE._col0 (type: double), VALUE._col1 (type: bigint), VALUE._col2 (type: double), VALUE._col3 (type: bigint), VALUE._col4 (type: double), VALUE._col5 (type: decimal(25,6))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7]
Statistics: Num rows: 76653825 Data size: 5939181706 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 100 Data size: 7700 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 100 Data size: 7700 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/query84.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query84.q.out b/ql/src/test/results/clientpositive/perf/spark/query84.q.out
index 0e62a3e..9bff3ee 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query84.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query84.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select c_customer_id as customer_id
,c_last_name || ', ' || c_first_name as customername
from customer
@@ -18,7 +18,7 @@ select c_customer_id as customer_id
order by c_customer_id
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select c_customer_id as customer_id
,c_last_name || ', ' || c_first_name as customername
from customer
@@ -38,6 +38,10 @@ select c_customer_id as customer_id
order by c_customer_id
limit 100
POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
STAGE DEPENDENCIES:
Stage-3 is a root stage
Stage-2 depends on stages: Stage-3
@@ -55,18 +59,40 @@ STAGE PLANS:
alias: income_band
filterExpr: ((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) (type: boolean)
Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 1:int, val 32287), FilterLongColLessEqualLongScalar(col 2:int, val 82287), SelectColumnIsNotNull(col 0:int))
predicate: ((ib_lower_bound >= 32287) and (ib_upper_bound <= 82287) and ib_income_band_sk is not null) (type: boolean)
Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ib_income_band_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 2 Data size: 24 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
@@ -80,12 +106,22 @@ STAGE PLANS:
alias: household_demographics
filterExpr: (hd_demo_sk is not null and hd_income_band_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: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:int))
predicate: (hd_demo_sk is not null and hd_income_band_sk is not null) (type: boolean)
Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: hd_demo_sk (type: int), hd_income_band_sk (type: int)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -93,15 +129,31 @@ STAGE PLANS:
keys:
0 _col1 (type: int)
1 _col0 (type: int)
+ Map Join Vectorization:
+ className: VectorMapJoinInnerBigOnlyLongOperator
+ 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
input vertices:
1 Map 9
Statistics: Num rows: 7920 Data size: 847440 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
@@ -119,78 +171,175 @@ STAGE PLANS:
alias: store_returns
filterExpr: sr_cdemo_sk is not null (type: boolean)
Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: SelectColumnIsNotNull(col 4:int)
predicate: sr_cdemo_sk is not null (type: boolean)
Statistics: Num rows: 57591150 Data size: 4462194832 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: sr_cdemo_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [4]
Statistics: Num rows: 57591150 Data size: 4462194832 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: 57591150 Data size: 4462194832 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 4
Map Operator Tree:
TableScan
alias: customer_demographics
filterExpr: 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: SelectColumnIsNotNull(col 0:int)
predicate: cd_demo_sk is not null (type: boolean)
Statistics: Num rows: 1861800 Data size: 717186159 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: 1861800 Data size: 717186159 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: 1861800 Data size: 717186159 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 5
Map Operator Tree:
TableScan
alias: customer
filterExpr: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_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: FilterExprAndExpr(children: SelectColumnIsNotNull(col 4:int), SelectColumnIsNotNull(col 2:int), SelectColumnIsNotNull(col 3:int))
predicate: (c_current_addr_sk is not null and c_current_cdemo_sk is not null and c_current_hdemo_sk is not null) (type: boolean)
Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: c_customer_id (type: string), c_current_cdemo_sk (type: int), c_current_hdemo_sk (type: int), c_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [1, 2, 3, 4, 8, 9]
Statistics: Num rows: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col3 (type: int)
sort order: +
Map-reduce partition columns: _col3 (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: _col0 (type: string), _col1 (type: int), _col2 (type: int), _col4 (type: string), _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
Map 7
Map Operator Tree:
TableScan
alias: customer_address
filterExpr: ((ca_city = 'Hopewell') and ca_address_sk is not null) (type: boolean)
Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 6:string, val Hopewell), SelectColumnIsNotNull(col 0:int))
predicate: ((ca_city = 'Hopewell') and ca_address_sk is not null) (type: boolean)
Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ca_address_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 20000000 Data size: 20297597642 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: 20000000 Data size: 20297597642 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:
@@ -214,16 +363,32 @@ STAGE PLANS:
value expressions: _col1 (type: string)
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: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 212960011 Data size: 183149913305 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 100 Data size: 86000 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -232,6 +397,11 @@ STAGE PLANS:
Reducer 6
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: