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 2018/02/16 15:52:32 UTC
[18/32] hive git commit: HIVE-18622: Vectorization: IF Statements,
Comparisons, and more do not handle NULLs correctly (Matt McCline,
reviewed by Sergey Shelukhin, Deepak Jaiswal, Vihang Karajgaonkar)
http://git-wip-us.apache.org/repos/asf/hive/blob/a4689020/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_date_1.q.out b/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
index 1e3d2b3..bacd667 100644
--- a/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
@@ -22,6 +22,7 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@vector_date_1
POSTHOOK: Lineage: vector_date_1.dt1 EXPRESSION []
POSTHOOK: Lineage: vector_date_1.dt2 EXPRESSION []
+_col0 _col1
PREHOOK: query: insert into table vector_date_1
select date '1999-12-31', date '2000-01-01' from src limit 1
PREHOOK: type: QUERY
@@ -34,6 +35,7 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@vector_date_1
POSTHOOK: Lineage: vector_date_1.dt1 SIMPLE []
POSTHOOK: Lineage: vector_date_1.dt2 SIMPLE []
+_c0 _c1
PREHOOK: query: insert into table vector_date_1
select date '2001-01-01', date '2001-06-01' from src limit 1
PREHOOK: type: QUERY
@@ -46,7 +48,20 @@ POSTHOOK: Input: default@src
POSTHOOK: Output: default@vector_date_1
POSTHOOK: Lineage: vector_date_1.dt1 SIMPLE []
POSTHOOK: Lineage: vector_date_1.dt2 SIMPLE []
-PREHOOK: query: explain
+_c0 _c1
+PREHOOK: query: select * from vector_date_1 order by dt1, dt2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@vector_date_1
+#### A masked pattern was here ####
+POSTHOOK: query: select * from vector_date_1 order by dt1, dt2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@vector_date_1
+#### A masked pattern was here ####
+vector_date_1.dt1 vector_date_1.dt2
+NULL NULL
+1999-12-31 2000-01-01
+2001-01-01 2001-06-01
+PREHOOK: query: explain vectorization detail
select
dt1, dt2,
-- should be all true
@@ -60,7 +75,7 @@ select
dt2 > dt1
from vector_date_1 order by dt1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select
dt1, dt2,
-- should be all true
@@ -74,6 +89,11 @@ select
dt2 > dt1
from vector_date_1 order by dt1
POSTHOOK: type: QUERY
+Explain
+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
@@ -91,26 +111,75 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: dt1 (type: date), dt2 (type: date), (dt1 = dt1) (type: boolean), (dt1 <> dt2) (type: boolean), (dt1 <= dt1) (type: boolean), (dt1 <= dt2) (type: boolean), (dt1 < dt2) (type: boolean), (dt2 >= dt2) (type: boolean), (dt2 >= dt1) (type: boolean), (dt2 > dt1) (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 3, 4, 5, 6, 7, 8, 9, 10]
+ selectExpressions: LongColEqualLongColumn(col 0:date, col 0:date) -> 3:boolean, LongColNotEqualLongColumn(col 0:date, col 1:date) -> 4:boolean, LongColLessEqualLongColumn(col 0:date, col 0:date) -> 5:boolean, LongColLessEqualLongColumn(col 0:date, col 1:date) -> 6:boolean, LongColLessLongColumn(col 0:date, col 1:date) -> 7:boolean, LongColGreaterEqualLongColumn(col 1:date, col 1:date) -> 8:boolean, LongColGreaterEqualLongColumn(col 1:date, col 0:date) -> 9:boolean, LongColGreaterLongColumn(col 1:date, col 0:date) -> 10:boolean
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumnNums: [0]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
+ valueColumnNums: [1, 3, 4, 5, 6, 7, 8, 9, 10]
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
Reducer 2
Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 10
+ dataColumns: KEY.reducesinkkey0:date, VALUE._col0:date, VALUE._col1:boolean, VALUE._col2:boolean, VALUE._col3:boolean, VALUE._col4:boolean, VALUE._col5:boolean, VALUE._col6:boolean, VALUE._col7:boolean, VALUE._col8:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -153,10 +222,11 @@ from vector_date_1 order by dt1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1 dt2 _c2 _c3 _c4 _c5 _c6 _c7 _c8 _c9
NULL NULL NULL NULL NULL NULL NULL NULL NULL NULL
1999-12-31 2000-01-01 true true true true true true true true
2001-01-01 2001-06-01 true true true true true true true true
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select
dt1, dt2,
-- should be all false
@@ -170,7 +240,7 @@ select
dt2 < dt1
from vector_date_1 order by dt1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select
dt1, dt2,
-- should be all false
@@ -184,6 +254,11 @@ select
dt2 < dt1
from vector_date_1 order by dt1
POSTHOOK: type: QUERY
+Explain
+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
@@ -201,26 +276,75 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: dt1 (type: date), dt2 (type: date), (dt1 <> dt1) (type: boolean), (dt1 = dt2) (type: boolean), (dt1 < dt1) (type: boolean), (dt1 >= dt2) (type: boolean), (dt1 > dt2) (type: boolean), (dt2 > dt2) (type: boolean), (dt2 <= dt1) (type: boolean), (dt2 < dt1) (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 3, 4, 5, 6, 7, 8, 9, 10]
+ selectExpressions: LongColNotEqualLongColumn(col 0:date, col 0:date) -> 3:boolean, LongColEqualLongColumn(col 0:date, col 1:date) -> 4:boolean, LongColLessLongColumn(col 0:date, col 0:date) -> 5:boolean, LongColGreaterEqualLongColumn(col 0:date, col 1:date) -> 6:boolean, LongColGreaterLongColumn(col 0:date, col 1:date) -> 7:boolean, LongColGreaterLongColumn(col 1:date, col 1:date) -> 8:boolean, LongColLessEqualLongColumn(col 1:date, col 0:date) -> 9:boolean, LongColLessLongColumn(col 1:date, col 0:date) -> 10:boolean
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumnNums: [0]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
+ valueColumnNums: [1, 3, 4, 5, 6, 7, 8, 9, 10]
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
Reducer 2
Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 10
+ dataColumns: KEY.reducesinkkey0:date, VALUE._col0:date, VALUE._col1:boolean, VALUE._col2:boolean, VALUE._col3:boolean, VALUE._col4:boolean, VALUE._col5:boolean, VALUE._col6:boolean, VALUE._col7:boolean, VALUE._col8:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -263,10 +387,11 @@ from vector_date_1 order by dt1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1 dt2 _c2 _c3 _c4 _c5 _c6 _c7 _c8 _c9
NULL NULL NULL NULL NULL NULL NULL NULL NULL NULL
1999-12-31 2000-01-01 false false false false false false false false
2001-01-01 2001-06-01 false false false false false false false false
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select
dt1,
-- should be all true
@@ -280,7 +405,7 @@ select
date '1970-01-01' < dt1
from vector_date_1 order by dt1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select
dt1,
-- should be all true
@@ -294,6 +419,11 @@ select
date '1970-01-01' < dt1
from vector_date_1 order by dt1
POSTHOOK: type: QUERY
+Explain
+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
@@ -311,26 +441,75 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: dt1 (type: date), (dt1 <> 1970-01-01) (type: boolean), (dt1 >= 1970-01-01) (type: boolean), (dt1 > 1970-01-01) (type: boolean), (dt1 <= 2100-01-01) (type: boolean), (dt1 < 2100-01-01) (type: boolean), (1970-01-01 <> dt1) (type: boolean), (1970-01-01 <= dt1) (type: boolean), (1970-01-01 < dt1) (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8, 9, 10]
+ selectExpressions: DateColNotEqualDateScalar(col 0:date, date 1970-01-01) -> 3:boolean, DateColGreaterEqualDateScalar(col 0:date, date 1970-01-01) -> 4:boolean, DateColGreaterDateScalar(col 0:date, date 1970-01-01) -> 5:boolean, DateColLessEqualDateScalar(col 0:date, date 2100-01-01) -> 6:boolean, DateColLessDateScalar(col 0:date, date 2100-01-01) -> 7:boolean, DateScalarNotEqualDateColumn(date 1970-01-01, col 0:date) -> 8:boolean, DateScalarLessEqualDateColumn(date 1970-01-01, col 0:date) -> 9:boolean, DateScalarLessDateColumn(date 1970-01-01, col 0:date) -> 10:boolean
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumnNums: [0]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
+ valueColumnNums: [3, 4, 5, 6, 7, 8, 9, 10]
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
Reducer 2
Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 9
+ dataColumns: KEY.reducesinkkey0:date, VALUE._col0:boolean, VALUE._col1:boolean, VALUE._col2:boolean, VALUE._col3:boolean, VALUE._col4:boolean, VALUE._col5:boolean, VALUE._col6:boolean, VALUE._col7:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8]
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -373,10 +552,11 @@ from vector_date_1 order by dt1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1 _c1 _c2 _c3 _c4 _c5 _c6 _c7 _c8
NULL NULL NULL NULL NULL NULL NULL NULL NULL
1999-12-31 true true true true true true true true
2001-01-01 true true true true true true true true
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select
dt1,
-- should all be false
@@ -390,7 +570,7 @@ select
date '1970-01-01' > dt1
from vector_date_1 order by dt1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select
dt1,
-- should all be false
@@ -404,6 +584,11 @@ select
date '1970-01-01' > dt1
from vector_date_1 order by dt1
POSTHOOK: type: QUERY
+Explain
+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
@@ -421,26 +606,75 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: dt1 (type: date), (dt1 = 1970-01-01) (type: boolean), (dt1 <= 1970-01-01) (type: boolean), (dt1 < 1970-01-01) (type: boolean), (dt1 >= 2100-01-01) (type: boolean), (dt1 > 2100-01-01) (type: boolean), (1970-01-01 = dt1) (type: boolean), (1970-01-01 >= dt1) (type: boolean), (1970-01-01 > dt1) (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8, 9, 10]
+ selectExpressions: DateColEqualDateScalar(col 0:date, date 1970-01-01) -> 3:boolean, DateColLessEqualDateScalar(col 0:date, date 1970-01-01) -> 4:boolean, DateColLessDateScalar(col 0:date, date 1970-01-01) -> 5:boolean, DateColGreaterEqualDateScalar(col 0:date, date 2100-01-01) -> 6:boolean, DateColGreaterDateScalar(col 0:date, date 2100-01-01) -> 7:boolean, DateScalarEqualDateColumn(date 1970-01-01, col 0:date) -> 8:boolean, DateScalarGreaterEqualDateColumn(date 1970-01-01, col 0:date) -> 9:boolean, DateScalarGreaterDateColumn(date 1970-01-01, col 0:date) -> 10:boolean
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumnNums: [0]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
+ valueColumnNums: [3, 4, 5, 6, 7, 8, 9, 10]
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
Reducer 2
Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 9
+ dataColumns: KEY.reducesinkkey0:date, VALUE._col0:boolean, VALUE._col1:boolean, VALUE._col2:boolean, VALUE._col3:boolean, VALUE._col4:boolean, VALUE._col5:boolean, VALUE._col6:boolean, VALUE._col7:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: boolean), VALUE._col1 (type: boolean), VALUE._col2 (type: boolean), VALUE._col3 (type: boolean), VALUE._col4 (type: boolean), VALUE._col5 (type: boolean), VALUE._col6 (type: boolean), VALUE._col7 (type: boolean)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8]
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -483,10 +717,11 @@ from vector_date_1 order by dt1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1 _c1 _c2 _c3 _c4 _c5 _c6 _c7 _c8
NULL NULL NULL NULL NULL NULL NULL NULL NULL
1999-12-31 false false false false false false false false
2001-01-01 false false false false false false false false
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select
dt1, dt2
from vector_date_1
@@ -499,7 +734,7 @@ where
and dt2 >= dt1
order by dt1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select
dt1, dt2
from vector_date_1
@@ -512,6 +747,11 @@ where
and dt2 >= dt1
order by dt1
POSTHOOK: type: QUERY
+Explain
+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
@@ -529,29 +769,81 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongColumn(col 0:date, col 0:date), FilterLongColNotEqualLongColumn(col 0:date, col 1:date), FilterLongColLessLongColumn(col 0:date, col 1:date), FilterLongColLessEqualLongColumn(col 0:date, col 1:date), FilterLongColGreaterLongColumn(col 1:date, col 0:date), FilterLongColGreaterEqualLongColumn(col 1:date, col 0:date))
predicate: ((dt1 < dt2) and (dt1 <= dt2) and (dt1 <> dt2) and (dt1 = dt1) and (dt2 > dt1) and (dt2 >= dt1)) (type: boolean)
Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: dt1 (type: date), dt2 (type: date)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumnNums: [0]
+ native: true
+ nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
+ valueColumnNums: [1]
Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: date)
Execution mode: vectorized, llap
LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reducer 2
Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:date, VALUE._col0:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -592,9 +884,10 @@ order by dt1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1 dt2
1999-12-31 2000-01-01
2001-01-01 2001-06-01
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select
dt1, dt2
from vector_date_1
@@ -609,7 +902,7 @@ where
and date '1970-01-01' <= dt1
order by dt1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select
dt1, dt2
from vector_date_1
@@ -624,6 +917,11 @@ where
and date '1970-01-01' <= dt1
order by dt1
POSTHOOK: type: QUERY
+Explain
+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
@@ -638,15 +936,30 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Filter Operator
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterExprAndExpr(children: FilterDateScalarEqualDateColumn(val 11323, col 0:date), FilterDateColNotEqualDateScalar(col 0:date, val 0), FilterDateScalarNotEqualDateColumn(val 0, col 0:date))
predicate: ((1970-01-01 <> dt1) and (2001-01-01 = dt1) and (dt1 <> 1970-01-01)) (type: boolean)
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: 2001-01-01 (type: date), dt2 (type: date)
outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [3, 1]
+ selectExpressions: ConstantVectorExpression(val 11323) -> 3:date
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -654,6 +967,21 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Execution mode: vectorized, llap
LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint]
Stage: Stage-0
Fetch Operator
@@ -693,13 +1021,15 @@ order by dt1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1 dt2
2001-01-01 2001-06-01
-PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT dt1 FROM vector_date_1 WHERE dt1 IN (date '1970-01-01', date '2001-01-01')
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT dt1 FROM vector_date_1 WHERE dt1 IN (date '1970-01-01', date '2001-01-01')
POSTHOOK: type: QUERY
+Explain
PLAN VECTORIZATION:
enabled: true
enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
@@ -720,6 +1050,7 @@ STAGE PLANS:
Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
+ vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
@@ -756,6 +1087,12 @@ STAGE PLANS:
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
Stage: Stage-0
Fetch Operator
@@ -771,6 +1108,7 @@ POSTHOOK: query: SELECT dt1 FROM vector_date_1 WHERE dt1 IN (date '1970-01-01',
POSTHOOK: type: QUERY
POSTHOOK: Input: default@vector_date_1
#### A masked pattern was here ####
+dt1
2001-01-01
PREHOOK: query: drop table vector_date_1
PREHOOK: type: DROPTABLE
http://git-wip-us.apache.org/repos/asf/hive/blob/a4689020/ql/src/test/results/clientpositive/llap/vector_decimal_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_decimal_1.q.out b/ql/src/test/results/clientpositive/llap/vector_decimal_1.q.out
index 4f1b509..f4863b7 100644
--- a/ql/src/test/results/clientpositive/llap/vector_decimal_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_decimal_1.q.out
@@ -32,6 +32,17 @@ POSTHOOK: Output: default@decimal_1
POSTHOOK: Lineage: decimal_1.t EXPRESSION []
POSTHOOK: Lineage: decimal_1.u EXPRESSION []
POSTHOOK: Lineage: decimal_1.v EXPRESSION []
+PREHOOK: query: insert into decimal_1 values (NULL, NULL, NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@decimal_1
+POSTHOOK: query: insert into decimal_1 values (NULL, NULL, NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@decimal_1
+POSTHOOK: Lineage: decimal_1.t EXPRESSION []
+POSTHOOK: Lineage: decimal_1.u EXPRESSION []
+POSTHOOK: Lineage: decimal_1.v EXPRESSION []
PREHOOK: query: explain vectorization detail
select cast(t as boolean) from decimal_1 order by t
PREHOOK: type: QUERY
@@ -58,7 +69,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -70,7 +81,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToBoolean(col 0:decimal(4,2)) -> 4:boolean
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -80,7 +91,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -121,13 +132,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -147,6 +158,7 @@ POSTHOOK: query: select cast(t as boolean) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
true
PREHOOK: query: explain vectorization detail
select cast(t as tinyint) from decimal_1 order by t
@@ -174,7 +186,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -186,7 +198,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:tinyint
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
@@ -196,7 +208,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -237,13 +249,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -263,6 +275,7 @@ POSTHOOK: query: select cast(t as tinyint) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17
PREHOOK: query: explain vectorization detail
select cast(t as smallint) from decimal_1 order by t
@@ -290,7 +303,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -302,7 +315,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:smallint
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
@@ -312,7 +325,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -353,13 +366,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -379,6 +392,7 @@ POSTHOOK: query: select cast(t as smallint) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17
PREHOOK: query: explain vectorization detail
select cast(t as int) from decimal_1 order by t
@@ -406,7 +420,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -418,7 +432,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:int
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -428,7 +442,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -469,13 +483,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -495,6 +509,7 @@ POSTHOOK: query: select cast(t as int) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17
PREHOOK: query: explain vectorization detail
select cast(t as bigint) from decimal_1 order by t
@@ -522,7 +537,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -534,7 +549,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:bigint
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -544,7 +559,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -585,13 +600,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -611,6 +626,7 @@ POSTHOOK: query: select cast(t as bigint) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17
PREHOOK: query: explain vectorization detail
select cast(t as float) from decimal_1 order by t
@@ -638,7 +654,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -650,7 +666,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToDouble(col 0:decimal(4,2)) -> 4:float
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: float)
sort order: +
@@ -660,7 +676,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -701,13 +717,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -727,6 +743,7 @@ POSTHOOK: query: select cast(t as float) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17.29
PREHOOK: query: explain vectorization detail
select cast(t as double) from decimal_1 order by t
@@ -754,7 +771,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -766,7 +783,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToDouble(col 0:decimal(4,2)) -> 4:double
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -776,7 +793,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -817,13 +834,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -843,6 +860,7 @@ POSTHOOK: query: select cast(t as double) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17.29
PREHOOK: query: explain vectorization detail
select cast(t as string) from decimal_1 order by t
@@ -870,7 +888,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -882,7 +900,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToString(col 0:decimal(4,2)) -> 4:string
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -892,7 +910,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -933,13 +951,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -959,6 +977,7 @@ POSTHOOK: query: select cast(t as string) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
17.29
PREHOOK: query: explain vectorization detail
select cast(t as timestamp) from decimal_1 order by t
@@ -986,7 +1005,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:decimal(4,2), 1:u:decimal(5,0), 2:v:decimal(10,0), 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
@@ -998,7 +1017,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToTimestamp(col 0:decimal(4,2)) -> 4:timestamp
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1008,7 +1027,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez 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
valueColumnNums: []
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1049,13 +1068,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1075,6 +1094,7 @@ POSTHOOK: query: select cast(t as timestamp) from decimal_1 order by t
POSTHOOK: type: QUERY
POSTHOOK: Input: default@decimal_1
#### A masked pattern was here ####
+NULL
1969-12-31 16:00:17.29
PREHOOK: query: drop table decimal_1
PREHOOK: type: DROPTABLE