You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by li...@apache.org on 2017/08/17 07:04:52 UTC
[2/5] hive git commit: HIVE-17321: HoS: analyze ORC table doesn't
compute raw data size when noscan/partialscan is not specified (Rui reviewed
by Liyun and Xuefu)
http://git-wip-us.apache.org/repos/asf/hive/blob/002626d5/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
index bfb2e4c..18a54ff 100644
--- a/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
+++ b/ql/src/test/results/clientpositive/spark/vectorization_short_regress.q.out
@@ -91,7 +91,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -101,7 +101,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterLongScalarEqualLongColumn(val 762, col 3) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 1) -> 12:double) -> boolean, FilterDoubleColGreaterDoubleScalar(col 12, val -5.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterDoubleColNotEqualDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 2) -> 12:double) -> boolean) -> boolean, FilterStringGroupColEqualStringScalar(col 6, val a) -> boolean, FilterExprAndExpr(children: FilterDecimalColLessEqualDecimalScalar(col 13, val -1.389)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean, FilterStringGroupColNotEqualStringScalar(col 7, val a) -> boolean, FilterDecimalScalarNotEqualDecimalColumn(val 79.553, col 14)(children: CastLongToDecimal(col 2) -> 14:decimal(13,3)) -> boolean, FilterLongColNotEqualLongColumn(col 11, col 10) -> boolean)
-> boolean) -> boolean
predicate: ((762 = cbigint) or ((UDFToFloat(csmallint) < cfloat) and (UDFToDouble(ctimestamp2) > -5.0) and (cdouble <> UDFToDouble(cint))) or (cstring1 = 'a') or ((CAST( cbigint AS decimal(22,3)) <= -1.389) and (cstring2 <> 'a') and (79.553 <> CAST( cint AS decimal(13,3))) and (cboolean2 <> cboolean1))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float), cdouble (type: double)
outputColumnNames: ctinyint, csmallint, cint, cfloat, cdouble
@@ -109,7 +109,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 4, 5]
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(cint), sum(cdouble), stddev_pop(cint), stddev_samp(csmallint), var_samp(cint), avg(cfloat), stddev_samp(cint), min(ctinyint), count(csmallint)
Group By Vectorization:
@@ -353,7 +353,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -363,7 +363,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColLessEqualLongScalar(col 3, val 197) -> boolean, FilterLongColLessLongColumn(col 2, col 3)(children: col 2) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleScalar(col 5, val -26.28) -> boolean, FilterDoubleColGreaterDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 1) -> 12:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 12, col 4)(children: CastLongToFloatViaLongToDouble(col 0) -> 12:double) -> boolean, FilterStringColRegExpStringScalar(col 6, pattern .*ss.*) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 4, val 79.5530014038086) -> boolean, FilterStringColLikeStringScalar(col 7, pattern 10%) -> boolean) -> boolean) -> boolean
predicate: (((cbigint <= 197) and (UDFToLong(cint) < cbigint)) or ((cdouble >= -26.28) and (UDFToDouble(csmallint) > cdouble)) or ((UDFToFloat(ctinyint) > cfloat) and cstring1 regexp '.*ss.*') or ((cfloat > 79.553) and (cstring2 like '10%'))) (type: boolean)
- Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cdouble (type: double)
outputColumnNames: ctinyint, csmallint, cint, cbigint, cdouble
@@ -371,7 +371,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 5]
- Statistics: Num rows: 6826 Data size: 209555 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6826 Data size: 1467614 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(cint), var_pop(cbigint), stddev_pop(csmallint), max(cdouble), avg(ctinyint), min(cint), min(cdouble), stddev_samp(csmallint), var_samp(cint)
Group By Vectorization:
@@ -607,7 +607,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -617,7 +617,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterTimestampColEqualTimestampColumn(col 8, col 9) -> boolean, FilterDoubleScalarEqualDoubleColumn(val 762.0, col 4) -> boolean, FilterStringGroupColEqualStringScalar(col 6, val ss) -> boolean, FilterExprAndExpr(children: FilterLongColLessEqualLongColumn(col 1, col 3)(children: col 1) -> boolean, FilterLongScalarEqualLongColumn(val 1, col 11) -> boolean) -> boolean, FilterExprAndExpr(children: SelectColumnIsNotNull(col 10) -> boolean, SelectColumnIsNotNull(col 9) -> boolean, FilterStringGroupColGreaterStringScalar(col 7, val a) -> boolean) -> boolean) -> boolean
predicate: ((ctimestamp1 = ctimestamp2) or (762 = cfloat) or (cstring1 = 'ss') or ((UDFToLong(csmallint) <= cbigint) and (1 = cboolean2)) or (cboolean1 is not null and ctimestamp2 is not null and (cstring2 > 'a'))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cdouble (type: double)
outputColumnNames: ctinyint, csmallint, cint, cbigint, cdouble
@@ -625,7 +625,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 5]
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: var_pop(cbigint), count(), max(ctinyint), stddev_pop(csmallint), max(cint), stddev_samp(cdouble), count(ctinyint), avg(ctinyint)
Group By Vectorization:
@@ -840,7 +840,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -850,7 +850,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterTimestampColLessEqualTimestampColumn(col 9, col 8) -> boolean, FilterDoubleColNotEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 3) -> 12:double) -> boolean, FilterStringScalarLessEqualStringGroupColumn(val ss, col 6) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongColLessLongColumn(col 1, col 0)(children: col 0) -> boolean, FilterDoubleColGreaterEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean) -> boolean, FilterDoubleColEqualDoubleScalar(col 4, val 17.0) -> boolean) -> boolean
predicate: (((ctimestamp2 <= ctimestamp1) and (UDFToDouble(cbigint) <> cdouble) and ('ss' <= cstring1)) or ((csmallint < UDFToShort(ctinyint)) and (UDFToDouble(ctimestamp1) >= 0.0)) or (cfloat = 17)) (type: boolean)
- Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cint (type: int), cbigint (type: bigint), cfloat (type: float)
outputColumnNames: ctinyint, cint, cbigint, cfloat
@@ -858,7 +858,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 2, 3, 4]
- Statistics: Num rows: 8874 Data size: 272428 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8874 Data size: 1907941 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(ctinyint), max(cbigint), stddev_samp(cint), var_pop(cint), var_pop(cbigint), max(cfloat)
Group By Vectorization:
@@ -1081,7 +1081,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -1091,7 +1091,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterStringColRegExpStringScalar(col 6, pattern a.*) -> boolean, FilterStringColLikeStringScalar(col 7, pattern %ss%) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongScalarNotEqualLongColumn(val 1, col 11) -> boolean, FilterDecimalColLessDecimalScalar(col 12, val 79.553)(children: CastLongToDecimal(col 1) -> 12:decimal(8,3)) -> boolean, FilterLongScalarNotEqualLongColumn(val -257, col 0)(children: col 0) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5, col 13)(children: CastLongToDouble(col 0) -> 13:double) -> boolean, FilterDoubleColGreaterEqualDoubleColumn(col 4, col 13)(children: CastLongToFloatViaLongToDouble(col 2) -> 13:double) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongColLessLongColumn(col 2, col 3)(children: col 2) -> boolean, FilterLongColGreaterLongColumn(col 0, col 3)(children: col 0) -> boolean
) -> boolean) -> boolean
predicate: ((cstring1 regexp 'a.*' and (cstring2 like '%ss%')) or ((1 <> cboolean2) and (CAST( csmallint AS decimal(8,3)) < 79.553) and (-257 <> UDFToInteger(ctinyint))) or ((cdouble > UDFToDouble(ctinyint)) and (cfloat >= UDFToFloat(cint))) or ((UDFToLong(cint) < cbigint) and (UDFToLong(ctinyint) > cbigint))) (type: boolean)
- Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cdouble (type: double), ctimestamp2 (type: timestamp), cstring1 (type: string), cboolean2 (type: boolean), ctinyint (type: tinyint), cfloat (type: float), ctimestamp1 (type: timestamp), csmallint (type: smallint), cbigint (type: bigint), (-3728 * cbigint) (type: bigint), (- cint) (type: int), (-863.257 - CAST( cint AS decimal(10,0))) (type: decimal(14,3)), (- csmallint) (type: smallint), (csmallint - (- csmallint)) (type: smallint), ((csmallint - (- csmallint)) + (- csmallint)) (type: smallint), (UDFToDouble(cint) / UDFToDouble(cint)) (type: double), ((-863.257 - CAST( cint AS decimal(10,0))) - -26.28) (type: decimal(15,3)), (- cfloat) (type: float), (cdouble * -89010.0) (type: double), (UDFToDouble(ctinyint) / 988888.0) (type: double), (- ctinyint) (type: tinyint), (79.553 / CAST( ctinyint AS decimal(3,0))) (type: decimal(9,7))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22
@@ -1100,7 +1100,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [2, 5, 9, 6, 11, 0, 4, 8, 1, 3, 14, 15, 17, 18, 20, 22, 24, 26, 13, 23, 28, 19, 30]
selectExpressions: LongScalarMultiplyLongColumn(val -3728, col 3) -> 14:long, LongColUnaryMinus(col 2) -> 15:long, DecimalScalarSubtractDecimalColumn(val -863.257, col 16)(children: CastLongToDecimal(col 2) -> 16:decimal(10,0)) -> 17:decimal(14,3), LongColUnaryMinus(col 1) -> 18:long, LongColSubtractLongColumn(col 1, col 19)(children: LongColUnaryMinus(col 1) -> 19:long) -> 20:long, LongColAddLongColumn(col 21, col 19)(children: LongColSubtractLongColumn(col 1, col 19)(children: LongColUnaryMinus(col 1) -> 19:long) -> 21:long, LongColUnaryMinus(col 1) -> 19:long) -> 22:long, DoubleColDivideDoubleColumn(col 13, col 23)(children: CastLongToDouble(col 2) -> 13:double, CastLongToDouble(col 2) -> 23:double) -> 24:double, DecimalColSubtractDecimalScalar(col 25, val -26.28)(children: DecimalScalarSubtractDecimalColumn(val -863.257, col 16)(children: CastLongToDecimal(col 2) -> 16:decimal(10,0)) -> 25:decimal(14,3)) -> 26:decimal(15,3), DoubleColUnaryMinus(col 4) -
> 13:double, DoubleColMultiplyDoubleScalar(col 5, val -89010.0) -> 23:double, DoubleColDivideDoubleScalar(col 27, val 988888.0)(children: CastLongToDouble(col 0) -> 27:double) -> 28:double, LongColUnaryMinus(col 0) -> 19:long, DecimalScalarDivideDecimalColumn(val 79.553, col 29)(children: CastLongToDecimal(col 0) -> 29:decimal(3,0)) -> 30:decimal(9,7)
- Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: timestamp), _col3 (type: string), _col4 (type: boolean), _col5 (type: tinyint), _col6 (type: float), _col7 (type: timestamp), _col8 (type: smallint), _col9 (type: bigint), _col10 (type: bigint), _col11 (type: int), _col12 (type: decimal(14,3)), _col13 (type: smallint), _col14 (type: smallint), _col15 (type: smallint), _col16 (type: double), _col17 (type: decimal(15,3)), _col18 (type: float), _col19 (type: double), _col20 (type: double), _col21 (type: tinyint), _col22 (type: decimal(9,7))
sort order: +++++++++++++++++++++++
@@ -1108,7 +1108,7 @@ STAGE PLANS:
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: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -1136,19 +1136,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22]
- Statistics: Num rows: 9898 Data size: 303864 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 9898 Data size: 2128105 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 50
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1377,7 +1377,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -1387,7 +1387,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongScalarGreaterLongColumn(val 197, col 0)(children: col 0) -> boolean, FilterLongColEqualLongColumn(col 2, col 3)(children: col 2) -> boolean) -> boolean, FilterLongColEqualLongScalar(col 3, val 359) -> boolean, FilterLongColLessLongScalar(col 10, val 0) -> boolean, FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6, pattern %ss) -> boolean, FilterDoubleColLessEqualDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 0) -> 12:double) -> boolean) -> boolean) -> boolean
predicate: (((197 > UDFToInteger(ctinyint)) and (UDFToLong(cint) = cbigint)) or (cbigint = 359) or (cboolean1 < 0) or ((cstring1 like '%ss') and (cfloat <= UDFToFloat(ctinyint)))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cbigint (type: bigint), cstring1 (type: string), cboolean1 (type: boolean), cfloat (type: float), cdouble (type: double), ctimestamp2 (type: timestamp), csmallint (type: smallint), cstring2 (type: string), cboolean2 (type: boolean), (UDFToDouble(cint) / UDFToDouble(cbigint)) (type: double), (CAST( cbigint AS decimal(19,0)) % 79.553) (type: decimal(5,3)), (- (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (10.175 % cfloat) (type: float), (- cfloat) (type: float), (cfloat - (- cfloat)) (type: float), ((cfloat - (- cfloat)) % -6432.0) (type: float), (cdouble * UDFToDouble(csmallint)) (type: double), (- cdouble) (type: double), (- cbigint) (type: bigint), (UDFToDouble(cfloat) - (UDFToDouble(cint) / UDFToDouble(cbigint))) (type: double), (- csmallint) (type: smallint), (3569 % cbigint) (type: bigint), (359.0 - cdouble) (type: double), (- csmallint) (type: smallint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24
@@ -1396,7 +1396,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [2, 3, 6, 10, 4, 5, 9, 1, 7, 11, 14, 16, 12, 13, 17, 19, 18, 21, 20, 22, 23, 26, 27, 24, 28]
selectExpressions: DoubleColDivideDoubleColumn(col 12, col 13)(children: CastLongToDouble(col 2) -> 12:double, CastLongToDouble(col 3) -> 13:double) -> 14:double, DecimalColModuloDecimalScalar(col 15, val 79.553)(children: CastLongToDecimal(col 3) -> 15:decimal(19,0)) -> 16:decimal(5,3), DoubleColUnaryMinus(col 17)(children: DoubleColDivideDoubleColumn(col 12, col 13)(children: CastLongToDouble(col 2) -> 12:double, CastLongToDouble(col 3) -> 13:double) -> 17:double) -> 12:double, DoubleScalarModuloDoubleColumn(val 10.175000190734863, col 4) -> 13:double, DoubleColUnaryMinus(col 4) -> 17:double, DoubleColSubtractDoubleColumn(col 4, col 18)(children: DoubleColUnaryMinus(col 4) -> 18:double) -> 19:double, DoubleColModuloDoubleScalar(col 20, val -6432.0)(children: DoubleColSubtractDoubleColumn(col 4, col 18)(children: DoubleColUnaryMinus(col 4) -> 18:double) -> 20:double) -> 18:double, DoubleColMultiplyDoubleColumn(col 5, col 20)(children: CastLongToDouble(col
1) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 5) -> 20:double, LongColUnaryMinus(col 3) -> 22:long, DoubleColSubtractDoubleColumn(col 4, col 25)(children: col 4, DoubleColDivideDoubleColumn(col 23, col 24)(children: CastLongToDouble(col 2) -> 23:double, CastLongToDouble(col 3) -> 24:double) -> 25:double) -> 23:double, LongColUnaryMinus(col 1) -> 26:long, LongScalarModuloLongColumn(val 3569, col 3) -> 27:long, DoubleScalarSubtractDoubleColumn(val 359.0, col 5) -> 24:double, LongColUnaryMinus(col 1) -> 28:long
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: bigint), _col2 (type: string), _col3 (type: boolean), _col4 (type: float), _col5 (type: double), _col6 (type: timestamp), _col7 (type: smallint), _col8 (type: string), _col9 (type: boolean), _col10 (type: double), _col11 (type: decimal(5,3)), _col12 (type: double), _col13 (type: float), _col14 (type: float), _col15 (type: float), _col16 (type: float), _col17 (type: double), _col18 (type: double), _col19 (type: bigint), _col20 (type: double), _col21 (type: smallint), _col22 (type: bigint), _col23 (type: double), _col24 (type: smallint)
sort order: +++++++++++++++++++++++++
@@ -1404,7 +1404,7 @@ STAGE PLANS:
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: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized
Map Vectorization:
@@ -1432,19 +1432,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 21]
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 25 Data size: 750 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 25 Data size: 5375 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1622,7 +1622,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -1632,7 +1632,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDecimalColGreaterDecimalScalar(col 12, val -26.28)(children: CastLongToDecimal(col 1) -> 12:decimal(7,2)) -> boolean, FilterStringColLikeStringScalar(col 7, pattern ss) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5, col 13)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterStringGroupColGreaterEqualStringScalar(col 6, val ss) -> boolean, FilterDoubleColNotEqualDoubleColumn(col 13, col 5)(children: CastLongToDouble(col 2) -> 13:double) -> boolean) -> boolean, FilterLongColEqualLongScalar(col 0, val -89010)(children: col 0) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 13, col 4)(children: CastLongToFloatViaLongToDouble(col 3) -> 13:double) -> boolean, FilterDecimalScalarLessEqualDecimalColumn(val -26.28, col 12)(children: CastLongToDecimal(col 1) -> 12:decimal(7,2)) -> boolean) ->
boolean) -> boolean
predicate: (((CAST( csmallint AS decimal(7,2)) > -26.28) and (cstring2 like 'ss')) or ((cdouble <= UDFToDouble(cbigint)) and (cstring1 >= 'ss') and (UDFToDouble(cint) <> cdouble)) or (UDFToInteger(ctinyint) = -89010) or ((UDFToFloat(cbigint) <= cfloat) and (-26.28 <= CAST( csmallint AS decimal(7,2))))) (type: boolean)
- Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cint (type: int), cstring1 (type: string), cboolean2 (type: boolean), ctimestamp2 (type: timestamp), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), cboolean1 (type: boolean), (cint + UDFToInteger(csmallint)) (type: int), (cbigint - UDFToLong(ctinyint)) (type: bigint), (- cbigint) (type: bigint), (- cfloat) (type: float), ((cbigint - UDFToLong(ctinyint)) + cbigint) (type: bigint), (cdouble / cdouble) (type: double), (- cdouble) (type: double), (UDFToLong((cint + UDFToInteger(csmallint))) * (- cbigint)) (type: bigint), ((- cdouble) + UDFToDouble(cbigint)) (type: double), (-1.389 / CAST( ctinyint AS decimal(3,0))) (type: decimal(8,7)), (UDFToDouble(cbigint) % cdouble) (type: double), (- csmallint) (type: smallint), (UDFToInteger(csmallint) + (cint + UDFToInteger(csmallint))) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21
@@ -1641,7 +1641,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [2, 6, 11, 9, 5, 4, 3, 1, 10, 14, 15, 16, 13, 18, 19, 20, 22, 25, 27, 24, 17, 28]
selectExpressions: LongColAddLongColumn(col 2, col 1)(children: col 1) -> 14:long, LongColSubtractLongColumn(col 3, col 0)(children: col 0) -> 15:long, LongColUnaryMinus(col 3) -> 16:long, DoubleColUnaryMinus(col 4) -> 13:double, LongColAddLongColumn(col 17, col 3)(children: LongColSubtractLongColumn(col 3, col 0)(children: col 0) -> 17:long) -> 18:long, DoubleColDivideDoubleColumn(col 5, col 5) -> 19:double, DoubleColUnaryMinus(col 5) -> 20:double, LongColMultiplyLongColumn(col 17, col 21)(children: col 17, LongColUnaryMinus(col 3) -> 21:long) -> 22:long, DoubleColAddDoubleColumn(col 23, col 24)(children: DoubleColUnaryMinus(col 5) -> 23:double, CastLongToDouble(col 3) -> 24:double) -> 25:double, DecimalScalarDivideDecimalColumn(val -1.389, col 26)(children: CastLongToDecimal(col 0) -> 26:decimal(3,0)) -> 27:decimal(8,7), DoubleColModuloDoubleColumn(col 23, col 5)(children: CastLongToDouble(col 3) -> 23:double) -> 24:double, LongColUnaryMinus(col 1) -> 17:
long, LongColAddLongColumn(col 1, col 21)(children: col 1, LongColAddLongColumn(col 2, col 1)(children: col 1) -> 21:long) -> 28:long
- Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col8 (type: boolean), _col1 (type: string), _col3 (type: timestamp), _col5 (type: float), _col6 (type: bigint), _col1 (type: string), _col4 (type: double), _col0 (type: int), _col7 (type: smallint), _col4 (type: double), _col9 (type: int), _col10 (type: bigint), _col11 (type: bigint), _col12 (type: float), _col13 (type: bigint), _col14 (type: double), _col15 (type: double), _col16 (type: bigint), _col17 (type: double), _col18 (type: decimal(8,7)), _col19 (type: double), _col20 (type: smallint), _col21 (type: int)
sort order: +++++++++++++++++++++++
@@ -1649,7 +1649,7 @@ STAGE PLANS:
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: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: boolean)
Execution mode: vectorized
@@ -1678,19 +1678,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [7, 1, 23, 2, 6, 3, 4, 8, 0, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22]
- Statistics: Num rows: 10922 Data size: 335301 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10922 Data size: 2348269 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 75
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 75 Data size: 2250 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 75 Data size: 16125 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1925,7 +1925,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -1935,7 +1935,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDecimalScalarGreaterEqualDecimalColumn(val -1.389, col 12)(children: CastLongToDecimal(col 2) -> 12:decimal(13,3)) -> boolean, FilterLongColLessLongColumn(col 1, col 0)(children: col 0) -> boolean, FilterLongScalarGreaterLongColumn(val -6432, col 1)(children: col 1) -> boolean) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleColumn(col 5, col 4)(children: col 4) -> boolean, FilterStringGroupColLessEqualStringScalar(col 7, val a) -> boolean) -> boolean, FilterExprAndExpr(children: FilterStringColLikeStringScalar(col 6, pattern ss%) -> boolean, FilterDecimalScalarGreaterDecimalColumn(val 10.175, col 13)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean) -> boolean) -> boolean
predicate: (((-1.389 >= CAST( cint AS decimal(13,3))) and (csmallint < UDFToShort(ctinyint)) and (-6432 > UDFToInteger(csmallint))) or ((cdouble >= UDFToDouble(cfloat)) and (cstring2 <= 'a')) or ((cstring1 like 'ss%') and (10.175 > CAST( cbigint AS decimal(22,3))))) (type: boolean)
- Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctimestamp1 (type: timestamp), cstring2 (type: string), cdouble (type: double), cfloat (type: float), cbigint (type: bigint), csmallint (type: smallint), (UDFToDouble(cbigint) / 3569.0) (type: double), (-257 - UDFToInteger(csmallint)) (type: int), (-6432.0 * cfloat) (type: float), (- cdouble) (type: double), (cdouble * 10.175) (type: double), (UDFToDouble((-6432.0 * cfloat)) / UDFToDouble(cfloat)) (type: double), (- cfloat) (type: float), (cint % UDFToInteger(csmallint)) (type: int), (- cdouble) (type: double), (cdouble * (- cdouble)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15
@@ -1944,7 +1944,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [8, 7, 5, 4, 3, 1, 15, 16, 14, 17, 18, 20, 19, 21, 22, 24]
selectExpressions: DoubleColDivideDoubleScalar(col 14, val 3569.0)(children: CastLongToDouble(col 3) -> 14:double) -> 15:double, LongScalarSubtractLongColumn(val -257, col 1)(children: col 1) -> 16:long, DoubleScalarMultiplyDoubleColumn(val -6432.0, col 4) -> 14:double, DoubleColUnaryMinus(col 5) -> 17:double, DoubleColMultiplyDoubleScalar(col 5, val 10.175) -> 18:double, DoubleColDivideDoubleColumn(col 19, col 4)(children: col 19, col 4) -> 20:double, DoubleColUnaryMinus(col 4) -> 19:double, LongColModuloLongColumn(col 2, col 1)(children: col 1) -> 21:long, DoubleColUnaryMinus(col 5) -> 22:double, DoubleColMultiplyDoubleColumn(col 5, col 23)(children: DoubleColUnaryMinus(col 5) -> 23:double) -> 24:double
- Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col5 (type: smallint), _col1 (type: string), _col2 (type: double), _col3 (type: float), _col4 (type: bigint), _col6 (type: double), _col7 (type: int), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: float), _col13 (type: int), _col14 (type: double), _col15 (type: double)
sort order: +++++++++++++++
@@ -1952,7 +1952,7 @@ STAGE PLANS:
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: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: timestamp)
Execution mode: vectorized
@@ -1981,19 +1981,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [15, 1, 2, 3, 4, 0, 5, 6, 7, 8, 9, 10, 11, 12, 8, 14]
- Statistics: Num rows: 3868 Data size: 118746 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3868 Data size: 831633 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 45
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 45 Data size: 1350 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 45 Data size: 9675 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2170,7 +2170,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -2180,7 +2180,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 1, val -257)(children: col 1) -> boolean, FilterExprOrExpr(children: FilterLongScalarEqualLongColumn(val -6432, col 1)(children: col 1) -> boolean, FilterExprAndExpr(children: FilterDoubleColGreaterEqualDoubleColumn(col 12, col 5)(children: CastLongToDouble(col 2) -> 12:double) -> boolean, FilterLongColLessEqualLongColumn(col 0, col 2)(children: col 0) -> boolean) -> boolean) -> boolean) -> boolean
predicate: ((UDFToInteger(csmallint) >= -257) and ((-6432 = UDFToInteger(csmallint)) or ((UDFToDouble(cint) >= cdouble) and (UDFToInteger(ctinyint) <= cint)))) (type: boolean)
- Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cbigint (type: bigint)
outputColumnNames: ctinyint, csmallint, cbigint
@@ -2188,7 +2188,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 3]
- Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: stddev_samp(csmallint), sum(cbigint), var_pop(ctinyint), count()
Group By Vectorization:
@@ -2203,7 +2203,7 @@ STAGE PLANS:
keys: csmallint (type: smallint)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
@@ -2212,7 +2212,7 @@ STAGE PLANS:
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: 2503 Data size: 76841 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2503 Data size: 538153 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -2247,7 +2247,7 @@ STAGE PLANS:
keys: KEY._col0 (type: smallint)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), _col1 (type: double), (-1.389 / CAST( _col0 AS decimal(5,0))) (type: decimal(10,9)), _col2 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col2)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), _col3 (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col4 (type: bigint), (_col4 - -89010) (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
@@ -2256,7 +2256,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [0, 5, 1, 7, 2, 11, 12, 3, 8, 4, 13]
selectExpressions: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 5:long, DecimalScalarDivideDecimalColumn(val -1.389, col 6)(children: CastLongToDecimal(col 0) -> 6:decimal(5,0)) -> 7:decimal(10,9), DoubleColDivideDoubleColumn(col 9, col 10)(children: CastLongToDouble(col 8)(children: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 8:long) -> 9:double, CastLongToDouble(col 2) -> 10:double) -> 11:double, LongColUnaryMinus(col 8)(children: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 8:long) -> 12:long, LongColUnaryMinus(col 13)(children: LongColUnaryMinus(col 8)(children: LongColModuloLongScalar(col 0, val -75)(children: col 0) -> 8:long) -> 13:long) -> 8:long, LongColSubtractLongScalar(col 4, val -89010) -> 13:long
- Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(10,9)), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint)
sort order: +++++++++++
@@ -2264,7 +2264,7 @@ STAGE PLANS:
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: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized
@@ -2283,19 +2283,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 1251 Data size: 38405 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1251 Data size: 268968 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 20 Data size: 600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 20 Data size: 4300 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2448,7 +2448,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -2458,7 +2458,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleScalar(col 5, val 2563.58) -> boolean, FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 3, col 2)(children: col 2) -> boolean, FilterLongColLessLongColumn(col 1, col 2)(children: col 1) -> boolean, FilterDoubleColLessDoubleScalar(col 4, val -5638.14990234375) -> boolean) -> boolean, FilterDecimalScalarEqualDecimalColumn(val 2563.58, col 12)(children: CastLongToDecimal(col 0) -> 12:decimal(6,2)) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessEqualDoubleColumn(col 5, col 13)(children: CastLongToDouble(col 3) -> 13:double) -> boolean, FilterDecimalScalarGreaterDecimalColumn(val -5638.15, col 14)(children: CastLongToDecimal(col 3) -> 14:decimal(21,2)) -> boolean) -> boolean) -> boolean) -> boolean
predicate: ((cdouble > 2563.58) and (((cbigint >= UDFToLong(cint)) and (UDFToInteger(csmallint) < cint) and (cfloat < -5638.15)) or (2563.58 = CAST( ctinyint AS decimal(6,2))) or ((cdouble <= UDFToDouble(cbigint)) and (-5638.15 > CAST( cbigint AS decimal(21,2)))))) (type: boolean)
- Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: cfloat (type: float), cdouble (type: double)
outputColumnNames: cfloat, cdouble
@@ -2466,7 +2466,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [4, 5]
- Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: var_samp(cdouble), count(cfloat), sum(cfloat), var_pop(cdouble), stddev_pop(cdouble), sum(cdouble)
Group By Vectorization:
@@ -2481,7 +2481,7 @@ STAGE PLANS:
keys: cdouble (type: double)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -2490,7 +2490,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2654 Data size: 81476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2654 Data size: 570619 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: struct<count:bigint,sum:double,variance:double>), _col2 (type: bigint), _col3 (type: double), _col4 (type: struct<count:bigint,sum:double,variance:double>), _col5 (type: struct<count:bigint,sum:double,variance:double>), _col6 (type: double)
Execution mode: vectorized
Map Vectorization:
@@ -2525,7 +2525,7 @@ STAGE PLANS:
keys: KEY._col0 (type: double)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
- Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: double), _col1 (type: double), (2563.58 * _col1) (type: double), (- _col1) (type: double), _col2 (type: bigint), ((2563.58 * _col1) + -5638.15) (type: double), ((- _col1) * ((2563.58 * _col1) + -5638.15)) (type: double), _col3 (type: double), _col4 (type: double), (_col0 - (- _col1)) (type: double), _col5 (type: double), (_col0 + _col1) (type: double), (_col0 * 762.0) (type: double), _col6 (type: double), (-863.257 % (_col0 * 762.0)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
@@ -2534,7 +2534,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [0, 1, 7, 8, 2, 10, 11, 3, 4, 12, 5, 9, 13, 6, 15]
selectExpressions: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1) -> 7:double, DoubleColUnaryMinus(col 1) -> 8:double, DoubleColAddDoubleScalar(col 9, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1) -> 9:double) -> 10:double, DoubleColMultiplyDoubleColumn(col 9, col 12)(children: DoubleColUnaryMinus(col 1) -> 9:double, DoubleColAddDoubleScalar(col 11, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 1) -> 11:double) -> 12:double) -> 11:double, DoubleColSubtractDoubleColumn(col 0, col 9)(children: DoubleColUnaryMinus(col 1) -> 9:double) -> 12:double, DoubleColAddDoubleColumn(col 0, col 1) -> 9:double, DoubleColMultiplyDoubleScalar(col 0, val 762.0) -> 13:double, DoubleScalarModuloDoubleColumn(val -863.257, col 14)(children: DoubleColMultiplyDoubleScalar(col 0, val 762.0) -> 14:double) -> 15:double
- Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -2542,7 +2542,7 @@ STAGE PLANS:
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: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double)
Reducer 3
Execution mode: vectorized
@@ -2561,13 +2561,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13]
- Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1327 Data size: 40738 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1327 Data size: 285309 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2770,7 +2770,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -2780,7 +2780,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDoubleColNotEqualDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterExprOrExpr(children: FilterExprAndExpr(children: FilterLongScalarNotEqualLongColumn(val -257, col 0)(children: col 0) -> boolean, SelectColumnIsNotNull(col 11) -> boolean, FilterStringColRegExpStringScalar(col 6, pattern .*ss) -> boolean, FilterDoubleScalarLessDoubleColumn(val -3.0, col 12)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean) -> boolean, FilterDoubleColEqualDoubleScalar(col 12, val -5.0)(children: CastTimestampToDouble(col 9) -> 12:double) -> boolean, FilterExprAndExpr(children: FilterDoubleColLessDoubleScalar(col 12, val 0.0)(children: CastTimestampToDouble(col 8) -> 12:double) -> boolean, FilterStringColLikeStringScalar(col 7, pattern %b%) -> boolean) -> boolean, FilterDoubleColEqualDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 2) -> 12:double) -
> boolean, FilterExprAndExpr(children: SelectColumnIsNull(col 10) -> boolean, FilterDoubleColLessDoubleColumn(col 4, col 12)(children: CastLongToFloatViaLongToDouble(col 2) -> 12:double) -> boolean) -> boolean) -> boolean) -> boolean
predicate: ((UDFToDouble(ctimestamp1) <> 0.0) and (((-257 <> UDFToInteger(ctinyint)) and cboolean2 is not null and cstring1 regexp '.*ss' and (-3.0 < UDFToDouble(ctimestamp1))) or (UDFToDouble(ctimestamp2) = -5.0) or ((UDFToDouble(ctimestamp1) < 0.0) and (cstring2 like '%b%')) or (cdouble = UDFToDouble(cint)) or (cboolean1 is null and (cfloat < UDFToFloat(cint))))) (type: boolean)
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cfloat (type: float), cdouble (type: double), cstring1 (type: string), ctimestamp1 (type: timestamp)
outputColumnNames: ctinyint, csmallint, cint, cfloat, cdouble, cstring1, ctimestamp1
@@ -2788,7 +2788,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 4, 5, 6, 8]
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: stddev_pop(cint), avg(csmallint), count(), min(ctinyint), var_samp(csmallint), var_pop(cfloat), avg(cint), var_samp(cfloat), avg(cfloat), min(cdouble), var_pop(csmallint), stddev_pop(ctinyint), sum(cint)
Group By Vectorization:
@@ -2803,7 +2803,7 @@ STAGE PLANS:
keys: ctimestamp1 (type: timestamp), cstring1 (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col1 (type: string)
sort order: ++
@@ -2812,7 +2812,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine spark IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
value expressions: _col2 (type: struct<count:bigint,sum:double,variance:double>), _col3 (type: struct<count:bigint,sum:double,input:smallint>), _col4 (type: bigint), _col5 (type: tinyint), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: struct<count:bigint,sum:double,variance:double>), _col8 (type: struct<count:bigint,sum:double,input:int>), _col9 (type: struct<count:bigint,sum:double,variance:double>), _col10 (type: struct<count:bigint,sum:double,input:float>), _col11 (type: double), _col12 (type: struct<count:bigint,sum:double,variance:double>), _col13 (type: struct<count:bigint,sum:double,variance:double>), _col14 (type: bigint)
Execution mode: vectorized
Map Vectorization:
@@ -2847,7 +2847,7 @@ STAGE PLANS:
keys: KEY._col0 (type: timestamp), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), (_col2 * 10.175) (type: double), (- _col2) (type: double), _col3 (type: double), (- _col2) (type: double), (-26.28 - _col2) (type: double), _col4 (type: bigint), (- _col4) (type: bigint), ((-26.28 - _col2) * (- _col2)) (type: double), _col5 (type: tinyint), (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4))) (type: double), (- (_col2 * 10.175)) (type: double), _col6 (type: double), (_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- _col2)) (type: double), (UDFToDouble((- _col4)) / _col2) (type: double), _col7 (type: double), (10.175 / _col3) (type: double), _col8 (type: double), _col9 (type: double), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) (type: double), (- (- (_col2 * 10.175))) (type: double), _col10 (type: double), (((_col6 + (((-26.28 - _col2) * (-
_col2)) * UDFToDouble((- _col4)))) - (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) * 10.175) (type: double), (10.175 % (10.175 / _col3)) (type: double), (- _col5) (type: tinyint), _col11 (type: double), _col12 (type: double), (- ((-26.28 - _col2) * (- _col2))) (type: double), ((- _col2) % _col10) (type: double), (-26.28 / CAST( (- _col5) AS decimal(3,0))) (type: decimal(8,6)), _col13 (type: double), _col14 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) / _col7) (type: double), (- (- _col4)) (type: bigint), _col4 (type: bigint), ((_col6 + (((-26.28 - _col2) * (- _col2)) * UDFToDouble((- _col4)))) % -26.28) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38
@@ -2856,7 +2856,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [0, 1, 2, 15, 16, 3, 17, 18, 4, 19, 22, 5, 21, 23, 6, 20, 26, 27, 7, 25, 8, 9, 29, 28, 10, 30, 32, 24, 11, 12, 31, 34, 37, 13, 14, 38, 40, 4, 39]
selectExpressions: DoubleColMultiplyDoubleScalar(col 2, val 10.175) -> 15:double, DoubleColUnaryMinus(col 2) -> 16:double, DoubleColUnaryMinus(col 2) -> 17:double, DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 18:double, LongColUnaryMinus(col 4) -> 19:long, DoubleColMultiplyDoubleColumn(col 20, col 21)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 20:double, DoubleColUnaryMinus(col 2) -> 21:double) -> 22:double, DoubleColMultiplyDoubleColumn(col 23, col 20)(children: DoubleColMultiplyDoubleColumn(col 20, col 21)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 20:double, DoubleColUnaryMinus(col 2) -> 21:double) -> 23:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 20:double) -> 21:double, DoubleColUnaryMinus(col 20)(children: DoubleColMultiplyDoubleScalar(col 2, val 10.175) -> 20:double) -> 23:double, DoubleColAddDoubleColumn(col 6, col 25)(children: DoubleColMultiplyDoubleColumn(col
26, col 20)(children: DoubleColMultiplyDoubleColumn(col 20, col 25)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 20:double, DoubleColUnaryMinus(col 2) -> 25:double) -> 26:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 20:double) -> 25:double) -> 20:double, DoubleColUnaryMinus(col 25)(children: DoubleColUnaryMinus(col 2) -> 25:double) -> 26:double, DoubleColDivideDoubleColumn(col 25, col 2)(children: CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 25:double) -> 27:double, DoubleScalarDivideDoubleColumn(val 10.175, col 3) -> 25:double, DoubleColSubtractDoubleColumn(col 28, col 30)(children: DoubleColAddDoubleColumn(col 6, col 29)(children: DoubleColMultiplyDoubleColumn(col 30, col 28)(children: DoubleColMultiplyDoubleColumn(col 28, col 29)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 28:double, DoubleColUnaryMinus(col 2) -> 29:double) -> 30:double, CastLongToDouble(col 24)(children:
LongColUnaryMinus(col 4) -> 24:long) -> 28:double) -> 29:double) -> 28:double, DoubleColMultiplyDoubleColumn(col 31, col 29)(children: DoubleColMultiplyDoubleColumn(col 29, col 30)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 29:double, DoubleColUnaryMinus(col 2) -> 30:double) -> 31:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 29:double) -> 30:double) -> 29:double, DoubleColUnaryMinus(col 30)(children: DoubleColUnaryMinus(col 28)(children: DoubleColMultiplyDoubleScalar(col 2, val 10.175) -> 28:double) -> 30:double) -> 28:double, DoubleColMultiplyDoubleScalar(col 31, val 10.175)(children: DoubleColSubtractDoubleColumn(col 30, col 32)(children: DoubleColAddDoubleColumn(col 6, col 31)(children: DoubleColMultiplyDoubleColumn(col 32, col 30)(children: DoubleColMultiplyDoubleColumn(col 30, col 31)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 30:double, DoubleColUnaryMinus(col 2) -> 31:double) -> 32:double, Cast
LongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 30:double) -> 31:double) -> 30:double, DoubleColMultiplyDoubleColumn(col 33, col 31)(children: DoubleColMultiplyDoubleColumn(col 31, col 32)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 31:double, DoubleColUnaryMinus(col 2) -> 32:double) -> 33:double, CastLongToDouble(col 24)(children: LongColUnaryMinus(col 4) -> 24:long) -> 31:double) -> 32:double) -> 31:double) -> 30:double, DoubleScalarModuloDoubleColumn(val 10.175, col 31)(children: DoubleScalarDivideDoubleColumn(val 10.175, col 3) -> 31:double) -> 32:double, LongColUnaryMinus(col 5) -> 24:long, DoubleColUnaryMinus(col 34)(children: DoubleColMultiplyDoubleColumn(col 31, col 33)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 31:double, DoubleColUnaryMinus(col 2) -> 33:double) -> 34:double) -> 31:double, DoubleColModuloDoubleColumn(col 33, col 10)(children: DoubleColUnaryMinus(col 2) -> 33:double) -> 34:double, DecimalScala
rDivideDecimalColumn(val -26.28, col 36)(children: CastLongToDecimal(col 35)(children: LongColUnaryMinus(col 5) -> 35:long) -> 36:decimal(3,0)) -> 37:decimal(8,6), DoubleColDivideDoubleColumn(col 33, col 7)(children: DoubleColAddDoubleColumn(col 6, col 38)(children: DoubleColMultiplyDoubleColumn(col 39, col 33)(children: DoubleColMultiplyDoubleColumn(col 33, col 38)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 33:double, DoubleColUnaryMinus(col 2) -> 38:double) -> 39:double, CastLongToDouble(col 35)(children: LongColUnaryMinus(col 4) -> 35:long) -> 33:double) -> 38:double) -> 33:double) -> 38:double, LongColUnaryMinus(col 35)(children: LongColUnaryMinus(col 4) -> 35:long) -> 40:long, DoubleColModuloDoubleScalar(col 33, val -26.28)(children: DoubleColAddDoubleColumn(col 6, col 39)(children: DoubleColMultiplyDoubleColumn(col 41, col 33)(children: DoubleColMultiplyDoubleColumn(col 33, col 39)(children: DoubleScalarSubtractDoubleColumn(val -26.28, col 2) -> 33:double
, DoubleColUnaryMinus(col 2) -> 39:double) -> 41:double, CastLongToDouble(col 35)(children: LongColUnaryMinus(col 4) -> 35:long) -> 33:double) -> 39:double) -> 33:double) -> 39:double
- Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col1 (type: string), _col2 (type: double), _col3 (type: double), _col4 (type: double), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint), _col10 (type: double), _col11 (type: tinyint), _col12 (type: double), _col13 (type: double), _col14 (type: double), _col15 (type: double), _col16 (type: double), _col17 (type: double), _col18 (type: double), _col19 (type: double), _col20 (type: double), _col21 (type: double), _col22 (type: double), _col23 (type: double), _col24 (type: double), _col25 (type: double), _col26 (type: double), _col27 (type: tinyint), _col28 (type: double), _col29 (type: double), _col30 (type: double), _col31 (type: double), _col32 (type: decimal(8,6)), _col33 (type: double), _col34 (type: bigint), _col35 (type: double), _col36 (type: bigint), _col37 (type: bigint), _col38 (type: double)
sort order: +++++++++++++++++++++++++++++++++++++++
@@ -2864,7 +2864,7 @@ STAGE PLANS:
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: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized
@@ -2883,19 +2883,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 4, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 8, 38]
- Statistics: Num rows: 6144 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 50
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 10750 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -3173,7 +3173,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
@@ -3183,7 +3183,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColLessDoubleColumn(col 5, col 12)(children: CastLongToDouble(col 1) -> 12:double) -> boolean, FilterLongColEqualLongColumn(col 11, col 10) -> boolean, FilterDecimalColLessEqualDecimalScalar(col 13, val -863.257)(children: CastLongToDecimal(col 3) -> 13:decimal(22,3)) -> boolean) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongScalar(col 2, val -257) -> boolean, SelectColumnIsNotNull(col 6) -> boolean, FilterLongColGreaterEqualLongScalar(col 10, val 1) -> boolean) -> boolean, FilterStringColRegExpStringScalar(col 7, pattern b) -> boolean, FilterExprAndExpr(children: FilterLongColGreaterEqualLongColumn(col 1, col 0)(children: col 0) -> boolean, SelectColumnIsNull(col 9) -> boolean) -> boolean) -> boolean, SelectColumnIsNotNull(col 10) -> boolean) -> boolean
predicate: ((((cdouble < UDFToDouble(csmallint)) and (cboolean2 = cboolean1) and (CAST( cbigint AS decimal(22,3)) <= -863.257)) or ((cint >= -257) and cstring1 is not null and (cboolean1 >= 1)) or cstring2 regexp 'b' or ((csmallint >= UDFToShort(ctinyint)) and ctimestamp2 is null)) and cboolean1 is not null) (type: boolean)
- Statistics: Num rows: 10239 Data size: 314333 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cboolean1 (type: boolean)
outputColumnNames: ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cboolean1
@@ -3191,7 +3191,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 10]
- Statistics: Num rows: 10239 Data size: 314333 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: max(cfloat), sum(cbigint), var_samp(cint), avg(cdouble), min(cbigint), var_pop(cbigint), sum(cint), stddev_samp(ctinyint), stddev_pop(csmallint), avg(cint)
Group By Vectorization:
@@ -3206,7 +3206,7 @@ STAGE PLANS:
keys: cboolean1 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 10239 Data size: 314333 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -3215,7 +3215,7 @@ STAGE PLANS:
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: 10239 Data size: 314333 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10239 Data size: 2201421 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: struct<count:bigint,sum:double,variance:double>), _col4 (type: struct<count:bigint,sum:double,input:double>), _col5 (type: bigint), _col6 (type: struct<count:bigint,sum:double,variance:double>), _col7 (type: bigint), _col8 (type: struct<count:bigint,sum:double,variance:double>), _col9 (type: struct<count:bigint,sum:double,variance:double>), _col10 (type: struct<count:bigint,sum:double,input:int>)
Execution mode: vectorized
Map Vectorization:
@@ -3250,7 +3250,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 5119 Data size: 157151 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: boolean), _col1 (type: float), (- _col1) (type: float), (-26.28 / UDFToDouble(_col1)) (type: double), _col2 (type: bigint), (CAST( _col2 AS decimal(19,0)) - 10.175) (type: decimal(23,3)), _col3 (type: double), (_col3 % UDFToDouble(_col1)) (type: double), (10.175 + (- _col1)) (type: float), _col4 (type: double), (UDFToDouble((CAST( _col2 AS decimal(19,0)) - 10.175)) + _col3) (type: double), _col5 (type: bigint), _col6 (type: double), (- (10.175 + (- _col1))) (type: float), (79.553 / _col6) (type: double), (_col3 % (79.553 / _col6)) (type: double), _col7 (type: bigint), _col8 (type: double), (-1.389 * CAST( _col5 AS decimal(19,0))) (type: decimal(24,3)), (CAST( _col7 AS decimal(19,0)) - (-1.389 * CAST( _col5 AS decimal(19,0)))) (type: decimal(25,3)), _col9 (type: double), (- (CAST( _col7 AS decimal(19,0)) - (-1.389 * CAST( _col5 AS decimal(19,0))))) (type: decimal(25,3)), _col10 (type: double), (- _col10) (type: double), (_col10 * UDFToDoubl
e(_col7)) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25
@@ -3259,7 +3259,7 @@ STAGE PLANS:
native: true
projectedOutputColumns: [0, 1, 11, 12, 2, 14, 3, 15, 17, 4, 19, 5, 6, 16, 20, 22, 7, 8, 23, 26, 9, 28, 10, 21, 30]
selectExpressions: DoubleColUnaryMinus(col 1) -> 11:double, DoubleScalarDivideDoubleColumn(val -26.28, col 1)(children: col 1) -> 12:double, DecimalColSubtractDecimalScalar(col 13, val 10.175)(children: CastLongToDecimal(col 2) -> 13:decimal(19,0)) -> 14:decimal(23,3), DoubleColModuloDoubleColumn(col 3, col 1)(children: col 1) -> 15:double, DoubleScalarAddDoubleColumn(val 10.175000190734863, col 16)(children: DoubleColUnaryMinus(col 1) -> 16:double) -> 17:double, DoubleColAddDoubleColumn(col 16, col 3)(children: CastDecimalToDouble(col 18)(children: DecimalColSubtractDecimalScalar(col 13, val 10.175)(children: CastLongToDecimal(col 2) -> 13:decimal(19,0)) -> 18:decimal(23,3)) -> 16:double) -> 19:double, DoubleColUnaryMinus(col 20)(children: DoubleScalarAddDoubleColumn(val 10.175000190734863, col 16)(children: DoubleColUnaryMinus(col 1) -> 16:double) -> 20:double) -> 16:double, DoubleScalarDivideDoubleColumn(val 79.553, col 6) -> 20:double, DoubleColModuloDouble
Column(col 3, col 21)(children: DoubleScalarDivideDoubleColumn(val 79.553, col 6) -> 21:double) -> 22:double, DecimalScalarMultiplyDecimalColumn(val -1.389, col 13)(children: CastLongToDecimal(col 5) -> 13:decimal(19,0)) -> 23:decimal(24,3), DecimalColSubtractDecimalColumn(col 13, col 25)(children: CastLongToDecimal(col 7) -> 13:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 24)(children: CastLongToDecimal(col 5) -> 24:decimal(19,0)) -> 25:decimal(24,3)) -> 26:decimal(25,3), FuncNegateDecimalToDecimal(col 27)(children: DecimalColSubtractDecimalColumn(col 13, col 25)(children: CastLongToDecimal(col 7) -> 13:decimal(19,0), DecimalScalarMultiplyDecimalColumn(val -1.389, col 24)(children: CastLongToDecimal(col 5) -> 24:decimal(19,0)) -> 25:decimal(24,3)) -> 27:decimal(25,3)) -> 28:decimal(25,3), DoubleColUnaryMinus(col 10) -> 21:double, DoubleColMultiplyDoubleColumn(col 10, col 29)(children: CastLongToDouble(col 7) -> 29:double) -> 30:double
- Statistics: Num rows: 5119 Data size: 157151 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -3267,7 +3267,7 @@ STAGE PLANS:
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: 5119 Data size: 157151 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: float), _col2 (type: float), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(23,3)), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: bigint), _col12 (type: double), _col13 (type: float), _col14 (type: double), _col15 (type: double), _col17 (type: bigint), _col18 (type: double), _col19 (type: decimal(24,3)), _col20 (type: decimal(25,3)), _col21 (type: double), _col22 (type: decimal(25,3)), _col23 (type: double), _col24 (type: double), _col25 (type: double)
Reducer 3
Execution mode: vectorized
@@ -3286,13 +3286,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 13, 16, 17, 18, 19, 20, 21, 22, 23, 24]
- Statistics: Num rows: 5119 Data size: 157151 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5119 Data size: 157151 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5119 Data size: 1100602 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat