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 15:52:21 UTC
[07/32] 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/vector_coalesce_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_coalesce_3.q.out b/ql/src/test/results/clientpositive/vector_coalesce_3.q.out
index 0e602f0..111e0a5 100644
--- a/ql/src/test/results/clientpositive/vector_coalesce_3.q.out
+++ b/ql/src/test/results/clientpositive/vector_coalesce_3.q.out
@@ -33,14 +33,37 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: _dummy_database@_dummy_table
POSTHOOK: Output: default@test_2
POSTHOOK: Lineage: test_2.member SCRIPT []
-PREHOOK: query: EXPLAIN
+PREHOOK: query: insert into test_1 values (NULL, NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@test_1
+POSTHOOK: query: insert into test_1 values (NULL, NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@test_1
+POSTHOOK: Lineage: test_1.attr EXPRESSION []
+POSTHOOK: Lineage: test_1.member EXPRESSION []
+PREHOOK: query: insert into test_2 values (NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@test_2
+POSTHOOK: query: insert into test_2 values (NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@test_2
+POSTHOOK: Lineage: test_2.member EXPRESSION []
+PREHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT m.member, (CASE WHEN COALESCE(n.attr, 5)>1 THEN n.attr END) AS attr
FROM test_2 m LEFT JOIN test_1 n ON m.member = n.member
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN
+POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL
SELECT m.member, (CASE WHEN COALESCE(n.attr, 5)>1 THEN n.attr END) AS attr
FROM test_2 m LEFT JOIN test_1 n ON m.member = n.member
POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
STAGE DEPENDENCIES:
Stage-4 is a root stage
Stage-3 depends on stages: Stage-4
@@ -57,11 +80,11 @@ STAGE PLANS:
$hdt$_1:n
TableScan
alias: n
- Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: member (type: bigint), attr (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
0 _col0 (type: bigint)
@@ -72,31 +95,68 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: m
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:member:bigint, 1:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
Select Operator
expressions: member (type: bigint)
outputColumnNames: _col0
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0]
+ Statistics: Num rows: 5 Data size: 32 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Left Outer Join 0 to 1
keys:
0 _col0 (type: bigint)
1 _col0 (type: bigint)
+ Map Join Vectorization:
+ bigTableKeyExpressions: col 0:bigint
+ bigTableValueExpressions: col 0:bigint
+ className: VectorMapJoinOperator
+ native: false
+ nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+ nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
outputColumnNames: _col0, _col2
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: bigint), CASE WHEN ((COALESCE(_col2,5) > 1)) THEN (_col2) ELSE (null) END (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3]
+ selectExpressions: IfExprColumnNull(col 2:boolean, col 1:bigint, null)(children: LongColGreaterLongScalar(col 3:bigint, val 1)(children: VectorCoalesce(columns [1, 2])(children: col 1:bigint, ConstantVectorExpression(val 5) -> 2:bigint) -> 3:bigint) -> 2:boolean, col 1:bigint) -> 3:bigint
+ Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 5 Data size: 35 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
Execution mode: vectorized
+ 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: 1
+ includeColumns: [0]
+ dataColumns: member:bigint
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint]
Local Work:
Map Reduce Local Work
@@ -122,3 +182,4 @@ POSTHOOK: Input: default@test_2
2 2
3 NULL
4 NULL
+NULL NULL
http://git-wip-us.apache.org/repos/asf/hive/blob/a4689020/ql/src/test/results/clientpositive/vector_data_types.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_data_types.q.out b/ql/src/test/results/clientpositive/vector_data_types.q.out
index 2b6491f..06a1fc4 100644
--- a/ql/src/test/results/clientpositive/vector_data_types.q.out
+++ b/ql/src/test/results/clientpositive/vector_data_types.q.out
@@ -95,6 +95,25 @@ POSTHOOK: Lineage: over1korc.s SIMPLE [(over1k)over1k.FieldSchema(name:s, type:s
POSTHOOK: Lineage: over1korc.si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ]
POSTHOOK: Lineage: over1korc.t SIMPLE [(over1k)over1k.FieldSchema(name:t, type:tinyint, comment:null), ]
POSTHOOK: Lineage: over1korc.ts SIMPLE [(over1k)over1k.FieldSchema(name:ts, type:timestamp, comment:null), ]
+PREHOOK: query: insert into over1korc values (NULL, NULL,NULL, NULL,NULL, NULL,NULL, NULL,NULL, NULL,NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@over1korc
+POSTHOOK: query: insert into over1korc values (NULL, NULL,NULL, NULL,NULL, NULL,NULL, NULL,NULL, NULL,NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@over1korc
+POSTHOOK: Lineage: over1korc.b EXPRESSION []
+POSTHOOK: Lineage: over1korc.bin EXPRESSION []
+POSTHOOK: Lineage: over1korc.bo EXPRESSION []
+POSTHOOK: Lineage: over1korc.d EXPRESSION []
+POSTHOOK: Lineage: over1korc.dec EXPRESSION []
+POSTHOOK: Lineage: over1korc.f EXPRESSION []
+POSTHOOK: Lineage: over1korc.i EXPRESSION []
+POSTHOOK: Lineage: over1korc.s EXPRESSION []
+POSTHOOK: Lineage: over1korc.si EXPRESSION []
+POSTHOOK: Lineage: over1korc.t EXPRESSION []
+POSTHOOK: Lineage: over1korc.ts EXPRESSION []
PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc ORDER BY t, si, i LIMIT 20
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc ORDER BY t, si, i LIMIT 20
@@ -113,22 +132,22 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float), d (type: double), bo (type: boolean), s (type: string), ts (type: timestamp), dec (type: decimal(4,2)), bin (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int)
sort order: +++
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary)
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: boolean), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: decimal(4,2)), VALUE._col7 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE
@@ -154,6 +173,7 @@ POSTHOOK: query: SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@over1korc
#### A masked pattern was here ####
+NULL NULL NULL NULL NULL NULL NULL NULL NULL NULL NULL
NULL 374 65560 4294967516 65.43 22.48 true oscar quirinius 2013-03-01 09:11:58.703316 16.86 mathematics
NULL 409 65536 4294967490 46.97 25.92 false fred miller 2013-03-01 09:11:58.703116 33.45 history
NULL 473 65720 4294967324 80.74 40.6 false holly falkner 2013-03-01 09:11:58.703111 18.80 mathematics
@@ -173,7 +193,6 @@ NULL 473 65720 4294967324 80.74 40.6 false holly falkner 2013-03-01 09:11:58.703
-2 461 65648 4294967425 58.52 24.85 false rachel thompson 2013-03-01 09:11:58.703318 85.62 zync studies
-1 268 65778 4294967418 56.33 44.73 true calvin falkner 2013-03-01 09:11:58.70322 7.37 history
-1 281 65643 4294967323 15.1 45.0 false irene nixon 2013-03-01 09:11:58.703223 80.96 undecided
--1 300 65663 4294967343 71.26 34.62 true calvin ovid 2013-03-01 09:11:58.703262 78.56 study skills
PREHOOK: query: SELECT SUM(HASH(*))
FROM (SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc ORDER BY t, si, i) as q
PREHOOK: type: QUERY
@@ -203,7 +222,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: over1korc
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Select Operator
@@ -213,7 +232,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int)
sort order: +++
@@ -222,7 +241,7 @@ STAGE PLANS:
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: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: boolean), _col7 (type: string), _col8 (type: timestamp), _col9 (type: decimal(4,2)), _col10 (type: binary)
Execution mode: vectorized
@@ -243,7 +262,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: boolean), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: decimal(4,2)), VALUE._col7 (type: binary)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 1049 Data size: 311170 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 20
Statistics: Num rows: 20 Data size: 5920 Basic stats: COMPLETE Column stats: NONE
@@ -269,6 +288,7 @@ POSTHOOK: query: SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc
POSTHOOK: type: QUERY
POSTHOOK: Input: default@over1korc
#### A masked pattern was here ####
+NULL NULL NULL NULL NULL NULL NULL NULL NULL NULL NULL
NULL 374 65560 4294967516 65.43 22.48 true oscar quirinius 2013-03-01 09:11:58.703316 16.86 mathematics
NULL 409 65536 4294967490 46.97 25.92 false fred miller 2013-03-01 09:11:58.703116 33.45 history
NULL 473 65720 4294967324 80.74 40.6 false holly falkner 2013-03-01 09:11:58.703111 18.80 mathematics
@@ -288,7 +308,95 @@ NULL 473 65720 4294967324 80.74 40.6 false holly falkner 2013-03-01 09:11:58.703
-2 461 65648 4294967425 58.52 24.85 false rachel thompson 2013-03-01 09:11:58.703318 85.62 zync studies
-1 268 65778 4294967418 56.33 44.73 true calvin falkner 2013-03-01 09:11:58.70322 7.37 history
-1 281 65643 4294967323 15.1 45.0 false irene nixon 2013-03-01 09:11:58.703223 80.96 undecided
--1 300 65663 4294967343 71.26 34.62 true calvin ovid 2013-03-01 09:11:58.703262 78.56 study skills
+PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
+SELECT SUM(HASH(*))
+FROM (SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc ORDER BY t, si, i) as q
+PREHOOK: type: QUERY
+POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION
+SELECT SUM(HASH(*))
+FROM (SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc ORDER BY t, si, i) as q
+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: over1korc
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ Select Operator
+ expressions: hash(t,si,i,b,f,d,bo,s,ts,dec,bin) (type: int)
+ outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [12]
+ selectExpressions: VectorUDFAdaptor(hash(t,si,i,b,f,d,bo,s,ts,dec,bin)) -> 12:int
+ Statistics: Num rows: 1050 Data size: 311254 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumLong(col 12:int) -> bigint
+ className: VectorGroupByOperator
+ groupByMode: HASH
+ native: false
+ vectorProcessingMode: HASH
+ projectedOutputColumnNums: [0]
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 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: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Execution mode: vectorized
+ 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: true
+ vectorized: true
+ 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)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 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 SUM(HASH(*))
FROM (SELECT t, si, i, b, f, d, bo, s, ts, `dec`, bin FROM over1korc ORDER BY t, si, i) as q
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/a4689020/ql/src/test/results/clientpositive/vector_date_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_date_1.q.out b/ql/src/test/results/clientpositive/vector_date_1.q.out
index 3f2b212..93f9a71 100644
--- a/ql/src/test/results/clientpositive/vector_date_1.q.out
+++ b/ql/src/test/results/clientpositive/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
@@ -85,16 +105,48 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 224 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: 224 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
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: 3 Data size: 224 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
+ 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, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
+ 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:
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)
@@ -144,10 +196,11 @@ 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
@@ -161,7 +214,7 @@ 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
@@ -175,6 +228,11 @@ 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
@@ -186,16 +244,48 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 224 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: 224 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
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: 3 Data size: 224 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
+ 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, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
+ 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:
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)
@@ -245,10 +335,11 @@ 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
@@ -262,7 +353,7 @@ 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
@@ -276,6 +367,11 @@ 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
@@ -287,16 +383,48 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 224 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: 224 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
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: 3 Data size: 224 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
+ 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]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
+ 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:
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)
@@ -346,10 +474,11 @@ 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
@@ -363,7 +492,7 @@ 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
@@ -377,6 +506,11 @@ 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
@@ -388,16 +522,48 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 224 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: 224 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
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: 3 Data size: 224 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
+ 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]
+ dataColumns: dt1:date, dt2:date
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, bigint, bigint, bigint, bigint, bigint, bigint, bigint]
+ 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:
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)
@@ -447,10 +613,11 @@ 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
@@ -463,7 +630,7 @@ 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
@@ -476,6 +643,11 @@ 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
@@ -487,19 +659,54 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 224 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: 74 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: 74 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
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: 74 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: date)
Execution mode: vectorized
+ 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: []
+ 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:
Select Operator
expressions: KEY.reducesinkkey0 (type: date), VALUE._col0 (type: date)
@@ -547,9 +754,10 @@ 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
@@ -564,7 +772,7 @@ 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
@@ -579,6 +787,11 @@ 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
@@ -590,21 +803,51 @@ STAGE PLANS:
TableScan
alias: vector_date_1
Statistics: Num rows: 3 Data size: 224 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: 1 Data size: 74 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: 1 Data size: 74 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 1 Data size: 74 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
Execution mode: vectorized
+ 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
@@ -644,13 +887,15 @@ 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]
@@ -668,6 +913,7 @@ STAGE PLANS:
Statistics: Num rows: 3 Data size: 224 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
@@ -703,6 +949,12 @@ 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
@@ -718,6 +970,7 @@ 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/vector_decimal_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_decimal_1.q.out b/ql/src/test/results/clientpositive/vector_decimal_1.q.out
index d922bfb..ffd32f6 100644
--- a/ql/src/test/results/clientpositive/vector_decimal_1.q.out
+++ b/ql/src/test/results/clientpositive/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
@@ -52,7 +63,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -64,7 +75,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToBoolean(col 0:decimal(4,2)) -> 4:boolean
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -73,7 +84,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -98,10 +109,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: boolean)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -121,6 +132,7 @@ 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
@@ -142,7 +154,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -154,7 +166,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:tinyint
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: tinyint)
sort order: +
@@ -163,7 +175,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -188,10 +200,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -211,6 +223,7 @@ 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
@@ -232,7 +245,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -244,7 +257,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:smallint
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: smallint)
sort order: +
@@ -253,7 +266,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -278,10 +291,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: smallint)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -301,6 +314,7 @@ 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
@@ -322,7 +336,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -334,7 +348,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:int
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -343,7 +357,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -368,10 +382,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -391,6 +405,7 @@ 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
@@ -412,7 +427,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -424,7 +439,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToLong(col 0:decimal(4,2)) -> 4:bigint
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -433,7 +448,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -458,10 +473,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -481,6 +496,7 @@ 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
@@ -502,7 +518,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -514,7 +530,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToDouble(col 0:decimal(4,2)) -> 4:float
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: float)
sort order: +
@@ -523,7 +539,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -548,10 +564,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: float)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -571,6 +587,7 @@ 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
@@ -592,7 +609,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -604,7 +621,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToDouble(col 0:decimal(4,2)) -> 4:double
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: double)
sort order: +
@@ -613,7 +630,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -638,10 +655,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: double)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -661,6 +678,7 @@ 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
@@ -682,7 +700,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -694,7 +712,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToString(col 0:decimal(4,2)) -> 4:string
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -703,7 +721,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -728,10 +746,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -751,6 +769,7 @@ 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
@@ -772,7 +791,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: decimal_1
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
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>]
@@ -784,7 +803,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4]
selectExpressions: CastDecimalToTimestamp(col 0:decimal(4,2)) -> 4:timestamp
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -793,7 +812,7 @@ STAGE PLANS:
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: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized
Map Vectorization:
enabled: true
@@ -818,10 +837,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: timestamp)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 336 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -841,6 +860,7 @@ 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