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 07:37:38 UTC
[15/51] [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/query67.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query67.q.out b/ql/src/test/results/clientpositive/perf/spark/query67.q.out
index db91e67..8b2c2a1 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query67.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query67.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select *
from (select i_category
,i_class
@@ -41,7 +41,7 @@ order by i_category
,rk
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select *
from (select i_category
,i_class
@@ -84,6 +84,10 @@ order by i_category
,rk
limit 100
POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-1 depends on stages: Stage-2
@@ -100,18 +104,40 @@ STAGE PLANS:
alias: store
filterExpr: 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: SelectColumnIsNotNull(col 0:int)
predicate: 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), s_store_id (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
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 _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
@@ -131,63 +157,137 @@ STAGE PLANS:
alias: store_sales
filterExpr: (ss_sold_date_sk is not null and ss_store_sk is not null and ss_item_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 2:int))
predicate: (ss_item_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_item_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 7, 10, 13]
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: decimal(7,2))
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 7
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: (d_month_seq BETWEEN 1212 AND 1223 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: FilterLongColumnBetween(col 3:int, left 1212, right 1223), SelectColumnIsNotNull(col 0:int))
predicate: (d_date_sk is not null and d_month_seq BETWEEN 1212 AND 1223) (type: boolean)
Statistics: Num rows: 8116 Data size: 9081804 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int), d_year (type: int), d_moy (type: int), d_qoy (type: int)
outputColumnNames: _col0, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6, 8, 10]
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
value expressions: _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 9
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_brand (type: string), i_class (type: string), i_category (type: string), i_product_name (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 8, 10, 12, 21]
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: string), _col2 (type: string), _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
Reducer 2
Local Work:
Map Reduce Local Work
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -214,6 +314,11 @@ STAGE PLANS:
Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE
value expressions: _col3 (type: int), _col4 (type: decimal(7,2)), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col11 (type: string)
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:
@@ -241,9 +346,23 @@ STAGE PLANS:
value expressions: _col9 (type: decimal(28,2))
Reducer 4
Execution mode: vectorized
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumDecimal(col 9:decimal(28,2)) -> decimal(28,2)
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string, col 1:string, col 2:string, col 3:string, col 4:int, col 5:int, col 6:int, col 7:string, col 8:bigint
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY._col5 (type: int), KEY._col6 (type: int), KEY._col7 (type: string), KEY._col8 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col9
@@ -252,20 +371,39 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col9 (type: decimal(28,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8]
Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col8 (type: decimal(28,2))
sort order: +-
Map-reduce partition columns: _col0 (type: string)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkOperator
+ native: false
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ nativeConditionsNotMet: No PTF TopN IS false
Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string)
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: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), VALUE._col3 (type: int), VALUE._col4 (type: int), VALUE._col5 (type: int), VALUE._col6 (type: string), KEY.reducesinkkey1 (type: decimal(28,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 3, 4, 5, 6, 7, 8, 1]
Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE
PTF Operator
Function definitions:
@@ -287,31 +425,67 @@ STAGE PLANS:
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
+ PTF Vectorization:
+ className: VectorPTFOperator
+ evaluatorClasses: [VectorPTFEvaluatorRank]
+ functionInputExpressions: [col 1:decimal(28,2)]
+ functionNames: [rank]
+ native: true
+ orderExpressions: [col 1:decimal(28,2)]
+ partitionExpressions: [col 0:string]
Statistics: Num rows: 3449926075 Data size: 304353479997 Basic stats: COMPLETE Column stats: NONE
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterLongColLessEqualLongScalar(col 9:int, val 100)
predicate: (rank_window_0 <= 100) (type: boolean)
Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col8 (type: decimal(28,2)), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 3, 4, 5, 6, 7, 8, 1, 9]
Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: int), _col5 (type: int), _col6 (type: int), _col7 (type: string), _col8 (type: decimal(28,2)), _col9 (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: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
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: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: int), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: string), KEY.reducesinkkey8 (type: decimal(28,2)), KEY.reducesinkkey9 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
Statistics: Num rows: 1149975358 Data size: 101451159969 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query68.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query68.q.out b/ql/src/test/results/clientpositive/perf/spark/query68.q.out
index f2e6763..1f6902c 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query68.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query68.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select c_last_name
,c_first_name
,ca_city
@@ -39,7 +39,7 @@ select c_last_name
,ss_ticket_number
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select c_last_name
,c_first_name
,ca_city
@@ -80,6 +80,10 @@ select c_last_name
,ss_ticket_number
limit 100
POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-1 depends on stages: Stage-2
@@ -96,18 +100,40 @@ STAGE PLANS:
alias: store
filterExpr: ((s_city) IN ('Cedar Grove', 'Wildwood') 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 22, values Cedar Grove, Wildwood), SelectColumnIsNotNull(col 0:int))
predicate: ((s_city) IN ('Cedar Grove', 'Wildwood') 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 _col4 (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 12
@@ -116,18 +142,40 @@ STAGE PLANS:
alias: household_demographics
filterExpr: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) 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: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:int, val 2), FilterLongColEqualLongScalar(col 4:int, val 1)), SelectColumnIsNotNull(col 0:int))
predicate: (((hd_dep_count = 2) or (hd_vehicle_count = 1)) and hd_demo_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)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 7200 Data size: 770400 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
@@ -148,100 +196,220 @@ STAGE PLANS:
alias: customer
filterExpr: (c_customer_sk is not null and c_current_addr_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 0:int), SelectColumnIsNotNull(col 4:int))
predicate: (c_current_addr_sk is not null and 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_current_addr_sk (type: int), c_first_name (type: string), c_last_name (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 4, 8, 9]
Statistics: Num rows: 80000000 Data size: 68801615852 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: 80000000 Data size: 68801615852 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: string), _col3 (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 10
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_year) IN (1998, 1999, 2000) 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 [1998, 1999, 2000]), FilterLongColumnBetween(col 9:int, left 1, right 2), SelectColumnIsNotNull(col 0:int))
predicate: ((d_year) IN (1998, 1999, 2000) 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
Map 13
Map Operator Tree:
TableScan
alias: customer_address
filterExpr: 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: SelectColumnIsNotNull(col 0:int)
predicate: ca_address_sk is not null (type: boolean)
Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ca_address_sk (type: int), ca_city (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6]
Statistics: Num rows: 40000000 Data size: 40595195284 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: 40000000 Data size: 40595195284 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 5
Map Operator Tree:
TableScan
alias: current_addr
filterExpr: 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: SelectColumnIsNotNull(col 0:int)
predicate: ca_address_sk is not null (type: boolean)
Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ca_address_sk (type: int), ca_city (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 6]
Statistics: Num rows: 40000000 Data size: 40595195284 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: 40000000 Data size: 40595195284 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 6
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_addr_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 6:int), SelectColumnIsNotNull(col 3:int))
predicate: (ss_addr_sk is not null and 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_addr_sk (type: int), ss_store_sk (type: int), ss_ticket_number (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)), ss_ext_tax (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3, 5, 6, 7, 9, 15, 17, 18]
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), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2))
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
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:
@@ -258,6 +426,11 @@ STAGE PLANS:
Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: string), _col3 (type: string), _col5 (type: string)
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:
@@ -282,16 +455,32 @@ STAGE PLANS:
value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2)), _col7 (type: decimal(17,2))
Reducer 4
Execution mode: vectorized
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: int), VALUE._col3 (type: decimal(17,2)), VALUE._col4 (type: decimal(17,2)), VALUE._col5 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 3, 4, 1, 5, 6, 7]
Statistics: Num rows: 463823414 Data size: 40918636263 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 100 Data size: 8800 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -300,6 +489,11 @@ STAGE PLANS:
Reducer 7
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:
@@ -336,6 +530,11 @@ STAGE PLANS:
Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2))
Reducer 8
+ 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:
@@ -359,9 +558,23 @@ STAGE PLANS:
value expressions: _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2))
Reducer 9
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), sum(VALUE._col1), sum(VALUE._col2)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumDecimal(col 4:decimal(17,2)) -> decimal(17,2), VectorUDAFSumDecimal(col 5:decimal(17,2)) -> decimal(17,2), VectorUDAFSumDecimal(col 6:decimal(17,2)) -> decimal(17,2)
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:int, col 1:string, col 2:int, col 3:int
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0, 1, 2]
keys: KEY._col0 (type: int), KEY._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
@@ -369,11 +582,19 @@ STAGE PLANS:
Select Operator
expressions: _col3 (type: int), _col0 (type: int), _col1 (type: string), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2)), _col6 (type: decimal(17,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [3, 0, 1, 4, 5, 6]
Statistics: Num rows: 421657640 Data size: 37198759433 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: 421657640 Data size: 37198759433 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: string), _col3 (type: decimal(17,2)), _col4 (type: decimal(17,2)), _col5 (type: decimal(17,2))