This is an automated email from the ASF dual-hosted git repository.
dkuzmenko pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new a61af0a6690 HIVE-28327: Missing null-check in TruncDateFromTimestamp
(Seonggon Namgung, reviewed by Denys Kuzmenko, Shohei Okumiya)
a61af0a6690 is described below
commit a61af0a6690ac3880920ab3147165038cc895756
Author: seonggon <[email protected]>
AuthorDate: Fri Jul 19 18:30:40 2024 +0900
HIVE-28327: Missing null-check in TruncDateFromTimestamp (Seonggon Namgung,
reviewed by Denys Kuzmenko, Shohei Okumiya)
Closes #5300
---
.../test/resources/testconfiguration.properties | 1 -
.../vector/expressions/TruncDateFromTimestamp.java | 4 +-
.../{ => llap}/vector_udf_trunc.q.out | 990 ++++++++++++---------
3 files changed, 569 insertions(+), 426 deletions(-)
diff --git a/itests/src/test/resources/testconfiguration.properties
b/itests/src/test/resources/testconfiguration.properties
index 66d4e56de0a..67a718dfd00 100644
--- a/itests/src/test/resources/testconfiguration.properties
+++ b/itests/src/test/resources/testconfiguration.properties
@@ -307,7 +307,6 @@ mr.query.files=\
udf_count.q,\
udf_using.q,\
uniquejoin.q,\
- vector_udf_trunc.q,\
windowing_windowspec.q
encrypted.query.files=\
diff --git
a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/TruncDateFromTimestamp.java
b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/TruncDateFromTimestamp.java
index cd8a42fa359..1d7133065b8 100644
---
a/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/TruncDateFromTimestamp.java
+++
b/ql/src/java/org/apache/hadoop/hive/ql/exec/vector/expressions/TruncDateFromTimestamp.java
@@ -126,7 +126,9 @@ public class TruncDateFromTimestamp extends
VectorExpression {
for (int j = 0; j != n; j++) {
int i = sel[j];
outputIsNull[i] = inputIsNull[i];
- truncDate(inputColVector, outputColVector, i);
+ if (!inputIsNull[i]) {
+ truncDate(inputColVector, outputColVector, i);
+ }
}
} else {
System.arraycopy(inputIsNull, 0, outputIsNull, 0, n);
diff --git a/ql/src/test/results/clientpositive/vector_udf_trunc.q.out
b/ql/src/test/results/clientpositive/llap/vector_udf_trunc.q.out
similarity index 52%
rename from ql/src/test/results/clientpositive/vector_udf_trunc.q.out
rename to ql/src/test/results/clientpositive/llap/vector_udf_trunc.q.out
index 88f4b508572..3f19546713f 100644
--- a/ql/src/test/results/clientpositive/vector_udf_trunc.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_udf_trunc.q.out
@@ -93,49 +93,53 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 366960 Basic stats:
COMPLETE Column stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:ctinyint:tinyint,
1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float,
5:cdouble:double, 6:cstring1:string, 7:cstring2:string,
8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean,
11:cboolean2:boolean,
12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
13:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: trunc(ctimestamp1, 'MM') (type: string)
- outputColumnNames: _col0
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [14]
- selectExpressions: TruncDateFromTimestamp(col 8, format MM)
-> 14:string
- Statistics: Num rows: 12288 Data size: 2260992 Basic stats:
COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 12288 Data size: 2260992 Basic stats:
COMPLETE Column stats: COMPLETE
- 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: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 12
- includeColumns: [8]
- dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int,
cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string,
ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean,
cboolean2:boolean
- partitionColumnCount: 0
- scratchColumnTypeNames: [string]
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: alltypesorc
+ Statistics: Num rows: 12288 Data size: 366960 Basic stats:
COMPLETE Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:ctinyint:tinyint,
1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float,
5:cdouble:double, 6:cstring1:string, 7:cstring2:string,
8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean,
11:cboolean2:boolean,
12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
13:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: trunc(ctimestamp1, 'MM') (type: string)
+ outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [14]
+ selectExpressions: TruncDateFromTimestamp(col 8,
format MM) -> 14:string
+ Statistics: Num rows: 12288 Data size: 2260992 Basic
stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12288 Data size: 2260992 Basic
stats: COMPLETE Column stats: COMPLETE
+ 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, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [8]
+ dataColumns: ctinyint:tinyint, csmallint:smallint,
cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string,
cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp,
cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [string]
Stage: Stage-0
Fetch Operator
@@ -215,49 +219,53 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 366960 Basic stats:
COMPLETE Column stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:ctinyint:tinyint,
1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float,
5:cdouble:double, 6:cstring1:string, 7:cstring2:string,
8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean,
11:cboolean2:boolean,
12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
13:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: trunc(CAST( ctimestamp1 AS STRING), 'MM') (type:
string)
- outputColumnNames: _col0
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [15]
- selectExpressions: TruncDateFromString(col 14, format
MM)(children: CastTimestampToString(col 8:timestamp) -> 14:string) -> 15:string
- Statistics: Num rows: 12288 Data size: 2260992 Basic stats:
COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 12288 Data size: 2260992 Basic stats:
COMPLETE Column stats: COMPLETE
- 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: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 12
- includeColumns: [8]
- dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int,
cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string,
ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean,
cboolean2:boolean
- partitionColumnCount: 0
- scratchColumnTypeNames: [string, string]
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: alltypesorc
+ Statistics: Num rows: 12288 Data size: 366960 Basic stats:
COMPLETE Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:ctinyint:tinyint,
1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float,
5:cdouble:double, 6:cstring1:string, 7:cstring2:string,
8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean,
11:cboolean2:boolean,
12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
13:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: trunc(CAST( ctimestamp1 AS STRING), 'MM')
(type: string)
+ outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [15]
+ selectExpressions: TruncDateFromString(col 14, format
MM)(children: CastTimestampToString(col 8:timestamp) -> 14:string) -> 15:string
+ Statistics: Num rows: 12288 Data size: 2260992 Basic
stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12288 Data size: 2260992 Basic
stats: COMPLETE Column stats: COMPLETE
+ 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, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [8]
+ dataColumns: ctinyint:tinyint, csmallint:smallint,
cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string,
cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp,
cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [string, string]
Stage: Stage-0
Fetch Operator
@@ -337,49 +345,53 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: alltypesorc
- Statistics: Num rows: 12288 Data size: 366960 Basic stats:
COMPLETE Column stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:ctinyint:tinyint,
1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float,
5:cdouble:double, 6:cstring1:string, 7:cstring2:string,
8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean,
11:cboolean2:boolean,
12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
13:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: trunc(CAST( ctimestamp1 AS DATE), 'MM') (type:
string)
- outputColumnNames: _col0
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [15]
- selectExpressions: TruncDateFromDate(col 14, format
MM)(children: CastTimestampToDate(col 8:timestamp) -> 14:date) -> 15:string
- Statistics: Num rows: 12288 Data size: 2260992 Basic stats:
COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 12288 Data size: 2260992 Basic stats:
COMPLETE Column stats: COMPLETE
- 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: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 12
- includeColumns: [8]
- dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int,
cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string,
ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean,
cboolean2:boolean
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint, string]
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: alltypesorc
+ Statistics: Num rows: 12288 Data size: 366960 Basic stats:
COMPLETE Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:ctinyint:tinyint,
1:csmallint:smallint, 2:cint:int, 3:cbigint:bigint, 4:cfloat:float,
5:cdouble:double, 6:cstring1:string, 7:cstring2:string,
8:ctimestamp1:timestamp, 9:ctimestamp2:timestamp, 10:cboolean1:boolean,
11:cboolean2:boolean,
12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
13:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: trunc(CAST( ctimestamp1 AS DATE), 'MM')
(type: string)
+ outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [15]
+ selectExpressions: TruncDateFromDate(col 14, format
MM)(children: CastTimestampToDate(col 8:timestamp) -> 14:date) -> 15:string
+ Statistics: Num rows: 12288 Data size: 2260992 Basic
stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 12288 Data size: 2260992 Basic
stats: COMPLETE Column stats: COMPLETE
+ 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, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [8]
+ dataColumns: ctinyint:tinyint, csmallint:smallint,
cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string,
cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp,
cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [bigint, string]
Stage: Stage-0
Fetch Operator
@@ -479,66 +491,92 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: trunc_number
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column
stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: c (type: double), trunc(c, 0) (type: double)
- outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 3]
- selectExpressions: TruncFloat(col 0, scale 0) -> 3:double
- Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE
Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- null sort order: z
- 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]
IS false
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: trunc_number
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE
Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: c (type: double), trunc(c, 0) (type: double)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3]
+ selectExpressions: TruncFloat(col 0, scale 0) ->
3:double
+ Statistics: Num rows: 4 Data size: 64 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ null sort order: z
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumns: 0:double
+ native: true
+ nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine
tez IN [tez] IS true, No PTF TopN IS true, No DISTINCT columns IS true,
BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: 3:double
+ Statistics: Num rows: 4 Data size: 64 Basic stats:
COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: double)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 1
+ includeColumns: [0]
+ dataColumns: c:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [double]
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled
IS true, hive.execution.engine tez IN [tez] IS true
+ reduceColumnNullOrder: z
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:double, VALUE._col0:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: double), VALUE._col0
(type: double)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE
Column stats: COMPLETE
- value expressions: _col1 (type: double)
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS
true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: c:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [double]
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez] IS false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type:
double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column
stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column
stats: COMPLETE
- 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
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE
Column stats: COMPLETE
+ 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
@@ -602,66 +640,92 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: trunc_number
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column
stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: c (type: double), trunc(UDFToFloat(c), 0) (type:
float)
- outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 3]
- selectExpressions: TruncFloat(col 0, scale 0)(children: col
0:double) -> 3:float
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE
Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- null sort order: z
- 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]
IS false
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: trunc_number
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE
Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: c (type: double), trunc(UDFToFloat(c), 0)
(type: float)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3]
+ selectExpressions: TruncFloat(col 0, scale
0)(children: col 0:double) -> 3:float
+ Statistics: Num rows: 4 Data size: 48 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ null sort order: z
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumns: 0:double
+ native: true
+ nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine
tez IN [tez] IS true, No PTF TopN IS true, No DISTINCT columns IS true,
BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: 3:float
+ Statistics: Num rows: 4 Data size: 48 Basic stats:
COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: float)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 1
+ includeColumns: [0]
+ dataColumns: c:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [double]
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled
IS true, hive.execution.engine tez IN [tez] IS true
+ reduceColumnNullOrder: z
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:double, VALUE._col0:float
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: double), VALUE._col0
(type: float)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE
Column stats: COMPLETE
- value expressions: _col1 (type: float)
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS
true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: c:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [double]
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez] IS false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type:
float)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column
stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE Column
stats: COMPLETE
- 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
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 4 Data size: 48 Basic stats: COMPLETE
Column stats: COMPLETE
+ 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
@@ -725,66 +789,92 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: trunc_number
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column
stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: c (type: double), trunc(CAST( c AS decimal(10,5)),
0) (type: decimal(5,0))
- outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 4]
- selectExpressions: TruncDecimal(col 3, scale 0)(children:
CastDoubleToDecimal(col 0:double) -> 3:decimal(10,5)) -> 4:decimal(5,0)
- Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- null sort order: z
- 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]
IS false
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: trunc_number
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE
Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: c (type: double), trunc(CAST( c AS
decimal(10,5)), 0) (type: decimal(5,0))
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 4]
+ selectExpressions: TruncDecimal(col 3, scale
0)(children: CastDoubleToDecimal(col 0:double) -> 3:decimal(10,5)) ->
4:decimal(5,0)
+ Statistics: Num rows: 4 Data size: 480 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ null sort order: z
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumns: 0:double
+ native: true
+ nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine
tez IN [tez] IS true, No PTF TopN IS true, No DISTINCT columns IS true,
BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: 4:decimal(5,0)
+ Statistics: Num rows: 4 Data size: 480 Basic stats:
COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(5,0))
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 1
+ includeColumns: [0]
+ dataColumns: c:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [decimal(10,5), decimal(5,0)]
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled
IS true, hive.execution.engine tez IN [tez] IS true
+ reduceColumnNullOrder: z
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:double,
VALUE._col0:decimal(5,0)/DECIMAL_64
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: double), VALUE._col0
(type: decimal(5,0))
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
- value expressions: _col1 (type: decimal(5,0))
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS
true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: c:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [decimal(10,5), decimal(5,0)]
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez] IS false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type:
decimal(5,0))
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE Column
stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
- 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
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
+ 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
@@ -848,66 +938,92 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: trunc_number
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column
stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: c (type: double), trunc(c) (type: double)
- outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 3]
- selectExpressions: TruncFloatNoScale(col 0, scale 0) ->
3:double
- Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE
Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- null sort order: z
- 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]
IS false
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: trunc_number
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE
Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: c (type: double), trunc(c) (type: double)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 3]
+ selectExpressions: TruncFloatNoScale(col 0, scale 0)
-> 3:double
+ Statistics: Num rows: 4 Data size: 64 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ null sort order: z
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumns: 0:double
+ native: true
+ nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine
tez IN [tez] IS true, No PTF TopN IS true, No DISTINCT columns IS true,
BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: 3:double
+ Statistics: Num rows: 4 Data size: 64 Basic stats:
COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: double)
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 1
+ includeColumns: [0]
+ dataColumns: c:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [double]
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled
IS true, hive.execution.engine tez IN [tez] IS true
+ reduceColumnNullOrder: z
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:double, VALUE._col0:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: double), VALUE._col0
(type: double)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE
Column stats: COMPLETE
- value expressions: _col1 (type: double)
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS
true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: c:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [double]
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez] IS false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type:
double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column
stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE Column
stats: COMPLETE
- 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
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 4 Data size: 64 Basic stats: COMPLETE
Column stats: COMPLETE
+ 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
@@ -947,66 +1063,92 @@ STAGE DEPENDENCIES:
STAGE PLANS:
Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: trunc_number
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column
stats: COMPLETE
- TableScan Vectorization:
- native: true
- vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
- Select Operator
- expressions: c (type: double), trunc(CAST( c AS decimal(10,5)))
(type: decimal(5,0))
- outputColumnNames: _col0, _col1
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 4]
- selectExpressions: TruncDecimalNoScale(col 3, scale
0)(children: CastDoubleToDecimal(col 0:double) -> 3:decimal(10,5)) ->
4:decimal(5,0)
- Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- null sort order: z
- 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]
IS false
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: trunc_number
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE
Column stats: COMPLETE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:c:double,
1:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>,
2:ROW__IS__DELETED:boolean]
+ Select Operator
+ expressions: c (type: double), trunc(CAST( c AS
decimal(10,5))) (type: decimal(5,0))
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 4]
+ selectExpressions: TruncDecimalNoScale(col 3, scale
0)(children: CastDoubleToDecimal(col 0:double) -> 3:decimal(10,5)) ->
4:decimal(5,0)
+ Statistics: Num rows: 4 Data size: 480 Basic stats:
COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ null sort order: z
+ sort order: +
+ Reduce Sink Vectorization:
+ className: VectorReduceSinkObjectHashOperator
+ keyColumns: 0:double
+ native: true
+ nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine
tez IN [tez] IS true, No PTF TopN IS true, No DISTINCT columns IS true,
BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
+ valueColumns: 4:decimal(5,0)
+ Statistics: Num rows: 4 Data size: 480 Basic stats:
COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(5,0))
+ Execution mode: vectorized, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet:
hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ featureSupportInUse: [DECIMAL_64]
+ inputFileFormats:
org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: true
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 1
+ includeColumns: [0]
+ dataColumns: c:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [decimal(10,5), decimal(5,0)]
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled
IS true, hive.execution.engine tez IN [tez] IS true
+ reduceColumnNullOrder: z
+ reduceColumnSortOrder: +
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:double,
VALUE._col0:decimal(5,0)/DECIMAL_64
+ partitionColumnCount: 0
+ scratchColumnTypeNames: []
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: double), VALUE._col0
(type: decimal(5,0))
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
- value expressions: _col1 (type: decimal(5,0))
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS
true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 1
- includeColumns: [0]
- dataColumns: c:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [decimal(10,5), decimal(5,0)]
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez] IS false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: double), VALUE._col0 (type:
decimal(5,0))
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE Column
stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
- 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
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 4 Data size: 480 Basic stats: COMPLETE
Column stats: COMPLETE
+ 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