blob: 6801978487b84772431cf382e8982e862e065838 [file] [log] [blame]
PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT VAR_POP(ctinyint),
(VAR_POP(ctinyint) / -26.28),
SUM(cfloat),
(-1.389 + SUM(cfloat)),
(SUM(cfloat) * (-1.389 + SUM(cfloat))),
MAX(ctinyint),
(-((SUM(cfloat) * (-1.389 + SUM(cfloat))))),
MAX(cint),
(MAX(cint) * 79.553),
VAR_SAMP(cdouble),
(10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))),
COUNT(cint),
(-563 % MAX(cint))
FROM alltypesorc
WHERE (((cdouble > ctinyint)
AND (cboolean2 > 0))
OR ((cbigint < ctinyint)
OR ((cint > cbigint)
OR (cboolean1 < 0))))
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT VAR_POP(ctinyint),
(VAR_POP(ctinyint) / -26.28),
SUM(cfloat),
(-1.389 + SUM(cfloat)),
(SUM(cfloat) * (-1.389 + SUM(cfloat))),
MAX(ctinyint),
(-((SUM(cfloat) * (-1.389 + SUM(cfloat))))),
MAX(cint),
(MAX(cint) * 79.553),
VAR_SAMP(cdouble),
(10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))),
COUNT(cint),
(-563 % MAX(cint))
FROM alltypesorc
WHERE (((cdouble > ctinyint)
AND (cboolean2 > 0))
OR ((cbigint < ctinyint)
OR ((cint > cbigint)
OR (cboolean1 < 0))))
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
enabled: true
enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
Map Reduce
Map Operator Tree:
TableScan
alias: alltypesorc
Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:ctinyint:tinyint, 1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float, 5:cdouble:double, 6:cstring1:string, 7:cstring2:string, 8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean, 11:cboolean2:boolean, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
predicateExpression: FilterExprOrExpr(children: FilterExprAndExpr(children: FilterDoubleColGreaterDoubleColumn(col 5:double, col 13:double)(children: CastLongToDouble(col 0:tinyint) -> 13:double), FilterLongColGreaterLongScalar(col 11:boolean, val 0)), FilterLongColLessLongColumn(col 3:bigint, col 0:bigint)(children: col 0:tinyint), FilterLongColGreaterLongColumn(col 2:bigint, col 3:bigint)(children: col 2:int), FilterLongColLessLongScalar(col 10:boolean, val 0))
predicate: (((cdouble > UDFToDouble(ctinyint)) and (cboolean2 > 0)) or (UDFToLong(cint) > cbigint) or (cbigint < UDFToLong(ctinyint)) or (cboolean1 < 0)) (type: boolean)
Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ctinyint (type: tinyint), cfloat (type: float), cint (type: int), cdouble (type: double), UDFToDouble(ctinyint) (type: double), (UDFToDouble(ctinyint) * UDFToDouble(ctinyint)) (type: double), (cdouble * cdouble) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Select Vectorization:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 4, 2, 5, 13, 16, 14]
selectExpressions: CastLongToDouble(col 0:tinyint) -> 13:double, DoubleColMultiplyDoubleColumn(col 14:double, col 15:double)(children: CastLongToDouble(col 0:tinyint) -> 14:double, CastLongToDouble(col 0:tinyint) -> 15:double) -> 16:double, DoubleColMultiplyDoubleColumn(col 5:double, col 5:double) -> 14:double
Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col5), sum(_col4), count(_col0), sum(_col1), max(_col0), max(_col2), sum(_col6), sum(_col3), count(_col3), count(_col2)
Group By Vectorization:
aggregators: VectorUDAFSumDouble(col 16:double) -> double, VectorUDAFSumDouble(col 13:double) -> double, VectorUDAFCount(col 0:tinyint) -> bigint, VectorUDAFSumDouble(col 4:float) -> double, VectorUDAFMaxLong(col 0:tinyint) -> tinyint, VectorUDAFMaxLong(col 2:int) -> int, VectorUDAFSumDouble(col 14:double) -> double, VectorUDAFSumDouble(col 5:double) -> double, VectorUDAFCount(col 5:double) -> bigint, VectorUDAFCount(col 2:int) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
native: false
vectorProcessingMode: HASH
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkOperator
native: false
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint), _col3 (type: double), _col4 (type: tinyint), _col5 (type: int), _col6 (type: double), _col7 (type: double), _col8 (type: bigint), _col9 (type: bigint)
Execution mode: vectorized
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
inputFormatFeatureSupport: [DECIMAL_64]
featureSupportInUse: [DECIMAL_64]
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
rowBatchContext:
dataColumnCount: 12
includeColumns: [0, 2, 3, 4, 5, 10, 11]
dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
partitionColumnCount: 0
scratchColumnTypeNames: [double, double, double, double]
Reduce Vectorization:
enabled: false
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0), sum(VALUE._col1), count(VALUE._col2), sum(VALUE._col3), max(VALUE._col4), max(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7), count(VALUE._col8), count(VALUE._col9)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: ((_col0 - ((_col1 * _col1) / _col2)) / _col2) (type: double), (((_col0 - ((_col1 * _col1) / _col2)) / _col2) / -26.28D) (type: double), _col3 (type: double), (-1.389D + _col3) (type: double), (_col3 * (-1.389D + _col3)) (type: double), _col4 (type: tinyint), (- (_col3 * (-1.389D + _col3))) (type: double), _col5 (type: int), (CAST( _col5 AS decimal(10,0)) * 79.553) (type: decimal(16,3)), ((_col6 - ((_col7 * _col7) / _col8)) / CASE WHEN ((_col8 = 1L)) THEN (null) ELSE ((_col8 - 1)) END) (type: double), (10.175D % (- (_col3 * (-1.389D + _col3)))) (type: double), _col9 (type: bigint), (-563 % _col5) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
Statistics: Num rows: 1 Data size: 72 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
limit: -1
Processor Tree:
ListSink
PREHOOK: query: SELECT VAR_POP(ctinyint),
(VAR_POP(ctinyint) / -26.28),
SUM(cfloat),
(-1.389 + SUM(cfloat)),
(SUM(cfloat) * (-1.389 + SUM(cfloat))),
MAX(ctinyint),
(-((SUM(cfloat) * (-1.389 + SUM(cfloat))))),
MAX(cint),
(MAX(cint) * 79.553),
VAR_SAMP(cdouble),
(10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))),
COUNT(cint),
(-563 % MAX(cint))
FROM alltypesorc
WHERE (((cdouble > ctinyint)
AND (cboolean2 > 0))
OR ((cbigint < ctinyint)
OR ((cint > cbigint)
OR (cboolean1 < 0))))
PREHOOK: type: QUERY
PREHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
POSTHOOK: query: SELECT VAR_POP(ctinyint),
(VAR_POP(ctinyint) / -26.28),
SUM(cfloat),
(-1.389 + SUM(cfloat)),
(SUM(cfloat) * (-1.389 + SUM(cfloat))),
MAX(ctinyint),
(-((SUM(cfloat) * (-1.389 + SUM(cfloat))))),
MAX(cint),
(MAX(cint) * 79.553),
VAR_SAMP(cdouble),
(10.175 % (-((SUM(cfloat) * (-1.389 + SUM(cfloat)))))),
COUNT(cint),
(-563 % MAX(cint))
FROM alltypesorc
WHERE (((cdouble > ctinyint)
AND (cboolean2 > 0))
OR ((cbigint < ctinyint)
OR ((cint > cbigint)
OR (cboolean1 < 0))))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
1074.8302575472321 -40.899172661614614 -21997.674998402596 -21999.063998402595 4.839282601059194E8 62 -4.839282601059194E8 1073680599 85414512692.247 7.569848642620917E10 10.175 3745 -563