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 07:38:02 UTC
[39/51] [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/query26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query26.q.out b/ql/src/test/results/clientpositive/perf/spark/query26.q.out
index 17bbc6a..a3fe272 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query26.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query26.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select i_item_id,
avg(cs_quantity) agg1,
avg(cs_list_price) agg2,
@@ -18,7 +18,7 @@ select i_item_id,
order by i_item_id
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select i_item_id,
avg(cs_quantity) agg1,
avg(cs_list_price) agg2,
@@ -38,6 +38,10 @@ select i_item_id,
order by i_item_id
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
@@ -54,18 +58,40 @@ STAGE PLANS:
alias: promotion
filterExpr: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean)
Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterStringGroupColEqualStringScalar(col 9:string, val N), FilterStringGroupColEqualStringScalar(col 14:string, val N)), SelectColumnIsNotNull(col 0:int))
predicate: (((p_channel_email = 'N') or (p_channel_event = 'N')) and p_promo_sk is not null) (type: boolean)
Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_promo_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 2300 Data size: 2713420 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col3 (type: int)
1 _col0 (type: int)
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Local Work:
Map Reduce Local Work
@@ -85,79 +111,176 @@ STAGE PLANS:
alias: catalog_sales
filterExpr: (cs_bill_cdemo_sk is not null and cs_sold_date_sk is not null and cs_item_sk is not null and cs_promo_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 4:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 15:int), SelectColumnIsNotNull(col 16:int))
predicate: (cs_bill_cdemo_sk is not null and cs_item_sk is not null and cs_promo_sk is not null and cs_sold_date_sk is not null) (type: boolean)
Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cs_sold_date_sk (type: int), cs_bill_cdemo_sk (type: int), cs_item_sk (type: int), cs_promo_sk (type: int), cs_quantity (type: int), cs_list_price (type: decimal(7,2)), cs_sales_price (type: decimal(7,2)), cs_coupon_amt (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 4, 15, 16, 18, 20, 21, 27]
Statistics: Num rows: 287989836 Data size: 38999608952 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: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 10
Map Operator Tree:
TableScan
alias: item
filterExpr: i_item_sk is not null (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: i_item_sk is not null (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: i_item_sk (type: int), i_item_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 7
Map Operator Tree:
TableScan
alias: customer_demographics
filterExpr: ((cd_gender = 'F') and (cd_marital_status = 'W') and (cd_education_status = 'Primary') and cd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 1:string, val F), FilterStringGroupColEqualStringScalar(col 2:string, val W), FilterStringGroupColEqualStringScalar(col 3:string, val Primary), SelectColumnIsNotNull(col 0:int))
predicate: ((cd_education_status = 'Primary') and (cd_gender = 'F') and (cd_marital_status = 'W') and cd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 232725 Data size: 89648269 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: 232725 Data size: 89648269 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: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 8
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_year = 1998) 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: FilterLongColEqualLongScalar(col 6:int, val 1998), SelectColumnIsNotNull(col 0:int))
predicate: ((d_year = 1998) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
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:
@@ -176,6 +299,11 @@ STAGE PLANS:
Reducer 3
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:
@@ -202,6 +330,11 @@ STAGE PLANS:
Statistics: Num rows: 383314495 Data size: 51908482889 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
Reducer 4
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -226,9 +359,23 @@ STAGE PLANS:
value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: decimal(17,2)), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint)
Reducer 5
Execution mode: vectorized
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), sum(VALUE._col6), count(VALUE._col7)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint, VectorUDAFSumDecimal(col 3:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFSumDecimal(col 5:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 6:bigint) -> bigint, VectorUDAFSumDecimal(col 7:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 8:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7]
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
@@ -236,25 +383,50 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), (_col1 / _col2) (type: double), (_col3 / _col4) (type: decimal(37,22)), (_col5 / _col6) (type: decimal(37,22)), (_col7 / _col8) (type: decimal(37,22))
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 9, 11, 12, 13]
+ selectExpressions: LongColDivideLongColumn(col 1:bigint, col 2:bigint) -> 9:double, DecimalColDivideDecimalColumn(col 3:decimal(17,2), col 10:decimal(19,0))(children: CastLongToDecimal(col 4:bigint) -> 10:decimal(19,0)) -> 11:decimal(37,22), DecimalColDivideDecimalColumn(col 5:decimal(17,2), col 10:decimal(19,0))(children: CastLongToDecimal(col 6:bigint) -> 10:decimal(19,0)) -> 12:decimal(37,22), DecimalColDivideDecimalColumn(col 7:decimal(17,2), col 10:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 10:decimal(19,0)) -> 13:decimal(37,22)
Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
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: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: double), _col2 (type: decimal(37,22)), _col3 (type: decimal(37,22)), _col4 (type: decimal(37,22))
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), VALUE._col0 (type: double), VALUE._col1 (type: decimal(37,22)), VALUE._col2 (type: decimal(37,22)), VALUE._col3 (type: decimal(37,22))
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4]
Statistics: Num rows: 210822976 Data size: 28549666139 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 100
+ Limit Vectorization:
+ className: VectorLimitOperator
+ native: true
Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 100 Data size: 13500 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/470ba3e2/ql/src/test/results/clientpositive/perf/spark/query27.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/spark/query27.q.out b/ql/src/test/results/clientpositive/perf/spark/query27.q.out
index 294222e..82b4dbf 100644
--- a/ql/src/test/results/clientpositive/perf/spark/query27.q.out
+++ b/ql/src/test/results/clientpositive/perf/spark/query27.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select i_item_id,
s_state, grouping(s_state) g_state,
avg(ss_quantity) agg1,
@@ -20,7 +20,7 @@ select i_item_id,
,s_state
limit 100
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select i_item_id,
s_state, grouping(s_state) g_state,
avg(ss_quantity) agg1,
@@ -42,6 +42,10 @@ select i_item_id,
,s_state
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
@@ -58,18 +62,40 @@ STAGE PLANS:
alias: store
filterExpr: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') 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 24, values SD, FL, MI, LA, MO, SC), SelectColumnIsNotNull(col 0:int))
predicate: ((s_state) IN ('SD', 'FL', 'MI', 'LA', 'MO', 'SC') 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), s_state (type: string)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 24]
Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
+ Spark Hash Table Sink Vectorization:
+ className: VectorSparkHashTableSinkOperator
+ native: true
keys:
0 _col3 (type: int)
1 _col0 (type: int)
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Local Work:
Map Reduce Local Work
@@ -89,79 +115,176 @@ STAGE PLANS:
alias: store_sales
filterExpr: (ss_cdemo_sk is not null and 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 4:int), SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 7:int), SelectColumnIsNotNull(col 2:int))
predicate: (ss_cdemo_sk is not null and 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_cdemo_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_list_price (type: decimal(7,2)), ss_sales_price (type: decimal(7,2)), ss_coupon_amt (type: decimal(7,2))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 2, 4, 7, 10, 12, 13, 19]
Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (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: _col0 (type: int), _col1 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2))
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 10
Map Operator Tree:
TableScan
alias: item
filterExpr: i_item_sk is not null (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: SelectColumnIsNotNull(col 0:int)
predicate: i_item_sk is not null (type: boolean)
Statistics: Num rows: 462000 Data size: 663560457 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: i_item_sk (type: int), i_item_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 7
Map Operator Tree:
TableScan
alias: customer_demographics
filterExpr: ((cd_gender = 'M') and (cd_marital_status = 'U') and (cd_education_status = '2 yr Degree') and cd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterStringGroupColEqualStringScalar(col 1:string, val M), FilterStringGroupColEqualStringScalar(col 2:string, val U), FilterStringGroupColEqualStringScalar(col 3:string, val 2 yr Degree), SelectColumnIsNotNull(col 0:int))
predicate: ((cd_education_status = '2 yr Degree') and (cd_gender = 'M') and (cd_marital_status = 'U') and cd_demo_sk is not null) (type: boolean)
Statistics: Num rows: 232725 Data size: 89648269 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: 232725 Data size: 89648269 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: 232725 Data size: 89648269 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
Map 8
Map Operator Tree:
TableScan
alias: date_dim
filterExpr: ((d_year = 2001) 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: FilterLongColEqualLongScalar(col 6:int, val 2001), SelectColumnIsNotNull(col 0:int))
predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean)
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: d_date_sk (type: int)
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkLongOperator
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE
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:
@@ -180,6 +303,11 @@ STAGE PLANS:
Reducer 3
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:
@@ -206,6 +334,11 @@ STAGE PLANS:
Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE
value expressions: _col4 (type: int), _col5 (type: decimal(7,2)), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col15 (type: string)
Reducer 4
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ notVectorizedReason: Tagging not supported
+ vectorized: false
Reduce Operator Tree:
Join Operator
condition map:
@@ -234,9 +367,23 @@ STAGE PLANS:
value expressions: _col3 (type: bigint), _col4 (type: bigint), _col5 (type: decimal(17,2)), _col6 (type: bigint), _col7 (type: decimal(17,2)), _col8 (type: bigint), _col9 (type: decimal(17,2)), _col10 (type: bigint)
Reducer 5
Execution mode: vectorized
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true
+ allNative: false
+ usesVectorUDFAdaptor: true
+ vectorized: true
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1), sum(VALUE._col2), count(VALUE._col3), sum(VALUE._col4), count(VALUE._col5), sum(VALUE._col6), count(VALUE._col7)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumLong(col 3:bigint) -> bigint, VectorUDAFCountMerge(col 4:bigint) -> bigint, VectorUDAFSumDecimal(col 5:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 6:bigint) -> bigint, VectorUDAFSumDecimal(col 7:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 8:bigint) -> bigint, VectorUDAFSumDecimal(col 9:decimal(17,2)) -> decimal(17,2), VectorUDAFCountMerge(col 10:bigint) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: MERGEPARTIAL
+ keyExpressions: col 0:string, col 1:string, col 2:bigint
+ native: false
+ vectorProcessingMode: MERGE_PARTIAL
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7]
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -244,25 +391,50 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: string), _col1 (type: string), grouping(_col2, 0) (type: bigint), (_col3 / _col4) (type: double), (_col5 / _col6) (type: decimal(37,22)), (_col7 / _col8) (type: decimal(37,22)), (_col9 / _col10) (type: decimal(37,22))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 11, 12, 14, 15, 16]
+ selectExpressions: VectorUDFAdaptor(grouping(_col2, 0)) -> 11:bigint, LongColDivideLongColumn(col 3:bigint, col 4:bigint) -> 12:double, DecimalColDivideDecimalColumn(col 5:decimal(17,2), col 13:decimal(19,0))(children: CastLongToDecimal(col 6:bigint) -> 13:decimal(19,0)) -> 14:decimal(37,22), DecimalColDivideDecimalColumn(col 7:decimal(17,2), col 13:decimal(19,0))(children: CastLongToDecimal(col 8:bigint) -> 13:decimal(19,0)) -> 15:decimal(37,22), DecimalColDivideDecimalColumn(col 9:decimal(17,2), col 13:decimal(19,0))(children: CastLongToDecimal(col 10:bigint) -> 13:decimal(19,0)) -> 16:decimal(37,22)
Statistics: Num rows: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
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: 1264972921 Data size: 111596278389 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: bigint), _col3 (type: double), _col4 (type: decimal(37,22)), _col5 (type: decimal(37,22)), _col6 (type: decimal(37,22))
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), VALUE._col0 (type: bigint), VALUE._col1 (type: double), VALUE._col2 (type: decimal(37,22)), VALUE._col3 (type: decimal(37,22)), VALUE._col4 (type: decimal(37,22))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
Statistics: Num rows: 1264972921 Data size: 111596278389 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