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 2017/10/29 20:40:02 UTC
[23/51] [partial] hive git commit: HIVE-17433: Vectorization: Support
Decimal64 in Hive Query Engine (Matt McCline, reviewed by Teddy Choi)
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_between_in.q.out b/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
index 05b7831..e02f64c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_between_in.q.out
@@ -39,12 +39,11 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterLongColumnInList(col 3, values [-67, -171]) -> boolean
+ predicateExpression: FilterLongColumnInList(col 3:date, values [-67, -171])
predicate: (cdate) IN (1969-10-26, 1969-07-14) (type: boolean)
Statistics: Num rows: 10 Data size: 532 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -53,7 +52,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [3]
+ projectedOutputColumnNums: [3]
Statistics: Num rows: 10 Data size: 532 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
@@ -68,7 +67,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -78,7 +78,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -89,7 +88,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 10 Data size: 532 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -135,19 +134,18 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsFalse(col 4)(children: LongColumnInList(col 3, values [-67, -171, 20]) -> 4:boolean) -> boolean
+ predicateExpression: SelectColumnIsFalse(col 5:boolean)(children: LongColumnInList(col 3, values [-67, -171, 20]) -> 5:boolean)
predicate: (not (cdate) IN (1969-10-26, 1969-07-14, 1970-01-21)) (type: boolean)
Statistics: Num rows: 12273 Data size: 653001 Basic stats: COMPLETE Column stats: NONE
Select Operator
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
Statistics: Num rows: 12273 Data size: 653001 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -155,10 +153,9 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
@@ -175,7 +172,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -185,7 +183,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -193,13 +190,12 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 0) -> bigint
+ aggregators: VectorUDAFCountMerge(col 0:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
native: false
vectorProcessingMode: GLOBAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
@@ -247,12 +243,11 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterDecimalColumnInList(col 1, values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> boolean
+ predicateExpression: FilterDecimalColumnInList(col 1:decimal(20,10), values [2365.8945945946, 881.0135135135, -3367.6517567568])
predicate: (cdecimal1) IN (2365.8945945946, 881.0135135135, -3367.6517567568) (type: boolean)
Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -261,7 +256,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [1]
+ projectedOutputColumnNums: [1]
Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: decimal(20,10))
@@ -276,7 +271,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -286,7 +282,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -297,7 +292,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 15 Data size: 1596 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -343,19 +338,18 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsFalse(col 4)(children: DecimalColumnInList(col 1, values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 4:boolean) -> boolean
+ predicateExpression: SelectColumnIsFalse(col 5:boolean)(children: DecimalColumnInList(col 1:decimal(20,10), values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 5:boolean)
predicate: (not (cdecimal1) IN (2365.8945945946, 881.0135135135, -3367.6517567568)) (type: boolean)
Statistics: Num rows: 12273 Data size: 1306003 Basic stats: COMPLETE Column stats: NONE
Select Operator
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
Statistics: Num rows: 12273 Data size: 1306003 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -363,10 +357,9 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
@@ -383,7 +376,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -393,7 +387,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -401,13 +394,12 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 0) -> bigint
+ aggregators: VectorUDAFCountMerge(col 0:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
native: false
vectorProcessingMode: GLOBAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
@@ -455,12 +447,11 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterLongColumnBetween(col 3, left -2, right 1) -> boolean
+ predicateExpression: FilterLongColumnBetween(col 3:date, left -2, right 1)
predicate: cdate BETWEEN 1969-12-30 AND 1970-01-02 (type: boolean)
Statistics: Num rows: 1365 Data size: 72626 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -469,7 +460,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [3]
+ projectedOutputColumnNums: [3]
Statistics: Num rows: 1365 Data size: 72626 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
@@ -484,7 +475,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -494,7 +486,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -505,7 +496,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 1365 Data size: 72626 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -551,12 +542,11 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterLongColumnNotBetween(col 3, left -610, right 608) -> boolean
+ predicateExpression: FilterLongColumnNotBetween(col 3:date, left -610, right 608)
predicate: cdate NOT BETWEEN 1968-05-01 AND 1971-09-01 (type: boolean)
Statistics: Num rows: 10923 Data size: 581173 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -565,7 +555,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [3]
+ projectedOutputColumnNums: [3]
Statistics: Num rows: 10923 Data size: 581173 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: date)
@@ -580,7 +570,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -590,7 +581,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -601,7 +591,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 10923 Data size: 581173 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -647,12 +637,11 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterDecimalColumnBetween(col 1, left -20, right 45.9918918919) -> boolean
+ predicateExpression: FilterDecimalColumnBetween(col 1:decimal(20,10), left -20, right 45.9918918919)
predicate: cdecimal1 BETWEEN -20 AND 45.9918918919 (type: boolean)
Statistics: Num rows: 1365 Data size: 145253 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -661,7 +650,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [1]
+ projectedOutputColumnNums: [1]
Statistics: Num rows: 1365 Data size: 145253 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: decimal(20,10))
@@ -676,7 +665,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -686,7 +676,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -697,7 +686,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 1365 Data size: 145253 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -743,19 +732,18 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: FilterDecimalColumnNotBetween(col 1, left -2000, right 4390.1351351351) -> boolean
+ predicateExpression: FilterDecimalColumnNotBetween(col 1:decimal(20,10), left -2000, right 4390.1351351351)
predicate: cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351 (type: boolean)
Statistics: Num rows: 10923 Data size: 1162346 Basic stats: COMPLETE Column stats: NONE
Select Operator
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: []
+ projectedOutputColumnNums: []
Statistics: Num rows: 10923 Data size: 1162346 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -763,10 +751,9 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
@@ -783,7 +770,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -793,7 +781,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -801,13 +788,12 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 0) -> bigint
+ aggregators: VectorUDAFCountMerge(col 0:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
native: false
vectorProcessingMode: GLOBAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 120 Basic stats: COMPLETE Column stats: NONE
@@ -1101,15 +1087,14 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Select Operator
expressions: (cdate) IN (1969-10-26, 1969-07-14) (type: boolean)
outputColumnNames: _col0
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [4]
- selectExpressions: LongColumnInList(col 3, values [-67, -171]) -> 4:boolean
+ projectedOutputColumnNums: [5]
+ selectExpressions: LongColumnInList(col 3, values [-67, -171]) -> 5:boolean
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1117,11 +1102,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 4
+ keyExpressions: col 5:boolean
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
@@ -1141,7 +1125,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -1151,7 +1136,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1159,14 +1143,13 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:boolean
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -1185,7 +1168,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1196,7 +1178,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6144 Data size: 326900 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -1243,15 +1225,14 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Select Operator
expressions: (cdecimal1) IN (2365.8945945946, 881.0135135135, -3367.6517567568) (type: boolean)
outputColumnNames: _col0
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [4]
- selectExpressions: DecimalColumnInList(col 1, values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 4:boolean
+ projectedOutputColumnNums: [5]
+ selectExpressions: DecimalColumnInList(col 1:decimal(20,10), values [2365.8945945946, 881.0135135135, -3367.6517567568]) -> 5:boolean
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1259,11 +1240,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 4
+ keyExpressions: col 5:boolean
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
@@ -1283,7 +1263,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -1293,7 +1274,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1301,14 +1281,13 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:boolean
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -1327,7 +1306,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1338,7 +1316,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6144 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -1385,15 +1363,14 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Select Operator
expressions: cdate BETWEEN 1969-12-30 AND 1970-01-02 (type: boolean)
outputColumnNames: _col0
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [4]
- selectExpressions: VectorUDFAdaptor(cdate BETWEEN 1969-12-30 AND 1970-01-02) -> 4:boolean
+ projectedOutputColumnNums: [5]
+ selectExpressions: VectorUDFAdaptor(cdate BETWEEN 1969-12-30 AND 1970-01-02) -> 5:boolean
Statistics: Num rows: 12288 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1401,11 +1378,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 4
+ keyExpressions: col 5:boolean
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
@@ -1425,7 +1401,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: true
@@ -1435,7 +1412,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1443,14 +1419,13 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:boolean
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -1469,7 +1444,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1480,7 +1454,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6144 Data size: 326900 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -1527,15 +1501,14 @@ STAGE PLANS:
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3]
Select Operator
expressions: cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351 (type: boolean)
outputColumnNames: _col0
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [4]
- selectExpressions: VectorUDFAdaptor(cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351) -> 4:boolean
+ projectedOutputColumnNums: [5]
+ selectExpressions: VectorUDFAdaptor(cdecimal1 NOT BETWEEN -2000 AND 4390.1351351351) -> 5:boolean
Statistics: Num rows: 12288 Data size: 1307600 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -1543,11 +1516,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 4
+ keyExpressions: col 5:boolean
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: _col0 (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
@@ -1567,7 +1539,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: true
@@ -1577,7 +1550,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1585,14 +1557,13 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:boolean
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -1611,7 +1582,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -1622,7 +1592,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 6144 Data size: 653800 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out b/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out
index 3710e6c..c0e4f67 100644
--- a/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_binary_join_groupby.q.out
@@ -130,12 +130,11 @@ STAGE PLANS:
Statistics: Num rows: 100 Data size: 49536 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsNotNull(col 10) -> boolean
+ predicateExpression: SelectColumnIsNotNull(col 10:binary)
predicate: bin is not null (type: boolean)
Statistics: Num rows: 95 Data size: 47059 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -144,7 +143,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Statistics: Num rows: 95 Data size: 47059 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -166,19 +165,18 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [21]
- selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11,_col12,_col13,_col14,_col15,_col16,_col17,_col18,_col19,_col20,_col21)) -> 21:int
+ projectedOutputColumnNums: [22]
+ selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7,_col8,_col9,_col10,_col11,_col12,_col13,_col14,_col15,_col16,_col17,_col18,_col19,_col20,_col21)) -> 22:int
Statistics: Num rows: 104 Data size: 51764 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col0)
Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 21) -> bigint
+ aggregators: VectorUDAFSumLong(col 22:int) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
@@ -195,7 +193,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: true
@@ -207,12 +206,11 @@ STAGE PLANS:
Statistics: Num rows: 100 Data size: 49536 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsNotNull(col 10) -> boolean
+ predicateExpression: SelectColumnIsNotNull(col 10:binary)
predicate: bin is not null (type: boolean)
Statistics: Num rows: 95 Data size: 47059 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -221,7 +219,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
+ projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Statistics: Num rows: 95 Data size: 47059 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col10 (type: binary)
@@ -238,7 +236,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -248,7 +247,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -256,13 +254,12 @@ STAGE PLANS:
Group By Operator
aggregations: sum(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 0) -> bigint
+ aggregators: VectorUDAFSumLong(col 0:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
native: false
vectorProcessingMode: GLOBAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
@@ -279,7 +276,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -290,7 +286,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -358,14 +354,13 @@ STAGE PLANS:
Statistics: Num rows: 100 Data size: 13824 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Select Operator
expressions: bin (type: binary)
outputColumnNames: bin
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [10]
+ projectedOutputColumnNums: [10]
Statistics: Num rows: 100 Data size: 13824 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count()
@@ -373,11 +368,10 @@ STAGE PLANS:
aggregators: VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 10
+ keyExpressions: col 10:binary
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: bin (type: binary)
mode: hash
outputColumnNames: _col0, _col1
@@ -397,7 +391,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -407,7 +402,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -415,14 +409,13 @@ STAGE PLANS:
Group By Operator
aggregations: count(VALUE._col0)
Group By Vectorization:
- aggregators: VectorUDAFCountMerge(col 1) -> bigint
+ aggregators: VectorUDAFCountMerge(col 1:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:binary
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0]
+ projectedOutputColumnNums: [0]
keys: KEY._col0 (type: binary)
mode: mergepartial
outputColumnNames: _col0, _col1
@@ -433,7 +426,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [1, 0]
+ projectedOutputColumnNums: [1, 0]
Statistics: Num rows: 50 Data size: 6912 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col1 (type: binary)
@@ -449,7 +442,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -460,7 +452,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [1, 0]
+ projectedOutputColumnNums: [1, 0]
Statistics: Num rows: 50 Data size: 6912 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -550,12 +542,11 @@ STAGE PLANS:
Statistics: Num rows: 100 Data size: 14208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsNotNull(col 2) -> boolean
+ predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: i is not null (type: boolean)
Statistics: Num rows: 95 Data size: 13497 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -564,7 +555,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2, 10]
+ projectedOutputColumnNums: [2, 10]
Statistics: Num rows: 95 Data size: 13497 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -586,7 +577,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2, 10, 11]
+ projectedOutputColumnNums: [2, 10, 12]
Statistics: Num rows: 104 Data size: 14846 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -603,7 +594,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -615,12 +607,11 @@ STAGE PLANS:
Statistics: Num rows: 100 Data size: 14208 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Filter Operator
Filter Vectorization:
className: VectorFilterOperator
native: true
- predicateExpression: SelectColumnIsNotNull(col 2) -> boolean
+ predicateExpression: SelectColumnIsNotNull(col 2:int)
predicate: i is not null (type: boolean)
Statistics: Num rows: 95 Data size: 13497 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -629,7 +620,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2, 10]
+ projectedOutputColumnNums: [2, 10]
Statistics: Num rows: 95 Data size: 13497 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
key expressions: _col0 (type: int)
@@ -646,7 +637,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: true
usesVectorUDFAdaptor: false
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_bround.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_bround.q.out b/ql/src/test/results/clientpositive/llap/vector_bround.q.out
index d463f1a..ffec163 100644
--- a/ql/src/test/results/clientpositive/llap/vector_bround.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_bround.q.out
@@ -32,22 +32,75 @@ POSTHOOK: type: QUERY
POSTHOOK: Output: default@test_vector_bround
POSTHOOK: Lineage: test_vector_bround.v0 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
POSTHOOK: Lineage: test_vector_bround.v1 EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
-PREHOOK: query: explain vectorization select bround(v0), bround(v1, 1) from test_vector_bround
+PREHOOK: query: explain vectorization detail
+select bround(v0), bround(v1, 1) from test_vector_bround
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization select bround(v0), bround(v1, 1) from test_vector_bround
+POSTHOOK: query: explain vectorization detail
+select bround(v0), bround(v1, 1) from test_vector_bround
POSTHOOK: type: QUERY
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=8 width=16)
- Output:["_col0","_col1"]
- TableScan [TS_0] (rows=8 width=16)
- default@test_vector_bround,test_vector_bround,Tbl:COMPLETE,Col:NONE,Output:["v0","v1"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: test_vector_bround
+ Statistics: Num rows: 8 Data size: 128 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ vectorizationSchemaColumns: [0:v0:double, 1:v1:double, 2:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>]
+ Select Operator
+ expressions: bround(v0) (type: double), bround(v1, 1) (type: double)
+ outputColumnNames: _col0, _col1
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumnNums: [3, 4]
+ selectExpressions: FuncBRoundDoubleToDouble(col 0:double) -> 3:double, BRoundWithNumDigitsDoubleToDouble(col 1, decimalPlaces 1) -> 4:double
+ Statistics: Num rows: 8 Data size: 128 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 8 Data size: 128 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, llap
+ LLAP IO: all inputs
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ includeColumns: [0, 1]
+ dataColumns: v0:double, v1:double
+ partitionColumnCount: 0
+ scratchColumnTypeNames: [double, double]
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select bround(v0), bround(v1, 1) from test_vector_bround
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_bucket.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_bucket.q.out b/ql/src/test/results/clientpositive/llap/vector_bucket.q.out
index e6d57d6..0f97d43 100644
--- a/ql/src/test/results/clientpositive/llap/vector_bucket.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_bucket.q.out
@@ -37,14 +37,13 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
Select Operator
expressions: tmp_values_col1 (type: string), tmp_values_col2 (type: string)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
@@ -60,7 +59,9 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: [DECIMAL_64]
+ vectorizationSupportRemovedReasons: [DECIMAL_64 disabled because LLAP is enabled]
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
allNative: true
usesVectorUDFAdaptor: false
@@ -70,7 +71,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -81,8 +81,8 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2, 1]
- selectExpressions: CastStringToLong(col 0) -> 2:int
+ projectedOutputColumnNums: [2, 1]
+ selectExpressions: CastStringToLong(col 0:string) -> 2:int
Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
index e85229b..7c78fe5 100644
--- a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out
@@ -133,26 +133,24 @@ STAGE PLANS:
Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
Select Operator
expressions: i (type: int)
outputColumnNames: _col0
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [2]
+ projectedOutputColumnNums: [2]
Statistics: Num rows: 1049 Data size: 3992 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: avg(50), avg(50.0), avg(50)
Group By Vectorization:
- aggregators: VectorUDAFAvgLong(ConstantVectorExpression(val 50) -> 11:long) -> struct<count:bigint,sum:double,input:bigint>, VectorUDAFAvgDouble(ConstantVectorExpression(val 50.0) -> 12:double) -> struct<count:bigint,sum:double,input:double>, VectorUDAFAvgDecimal(ConstantVectorExpression(val 50) -> 13:decimal(10,0)) -> struct<count:bigint,sum:decimal(20,0),input:decimal(20,0)>
+ aggregators: VectorUDAFAvgLong(ConstantVectorExpression(val 50) -> 12:int) -> struct<count:bigint,sum:double,input:int>, VectorUDAFAvgDouble(ConstantVectorExpression(val 50.0) -> 13:double) -> struct<count:bigint,sum:double,input:double>, VectorUDAFAvgDecimal(ConstantVectorExpression(val 50) -> 14:decimal(10,0)) -> struct<count:bigint,sum:decimal(20,0),input:decimal(10,0)>
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 2
+ keyExpressions: col 2:int
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0, 1, 2]
+ projectedOutputColumnNums: [0, 1, 2]
keys: _col0 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
@@ -173,7 +171,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -183,7 +182,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -191,14 +189,13 @@ STAGE PLANS:
Group By Operator
aggregations: avg(VALUE._col0), avg(VALUE._col1), avg(VALUE._col2)
Group By Vectorization:
- aggregators: VectorUDAFAvgFinal(col 1) -> double, VectorUDAFAvgFinal(col 2) -> double, VectorUDAFAvgDecimalFinal(col 3) -> decimal(16,4)
+ aggregators: VectorUDAFAvgFinal(col 1:struct<count:bigint,sum:double,input:int>) -> double, VectorUDAFAvgFinal(col 2:struct<count:bigint,sum:double,input:double>) -> double, VectorUDAFAvgDecimalFinal(col 3:struct<count:bigint,sum:decimal(12,0),input:decimal(10,0)>) -> decimal(14,4)
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:int
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0, 1, 2]
+ projectedOutputColumnNums: [0, 1, 2]
keys: KEY._col0 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
@@ -218,7 +215,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -229,7 +225,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2, 3]
+ projectedOutputColumnNums: [0, 1, 2, 3]
Statistics: Num rows: 524 Data size: 1994 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 10
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_char_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_char_2.q.out b/ql/src/test/results/clientpositive/llap/vector_char_2.q.out
index 94791ce..e1dc02d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_char_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_char_2.q.out
@@ -83,27 +83,25 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
Select Operator
expressions: value (type: char(20)), UDFToInteger(key) (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [1, 2]
- selectExpressions: CastStringToLong(col 0) -> 2:int
+ projectedOutputColumnNums: [1, 3]
+ selectExpressions: CastStringToLong(col 0:char(10)) -> 3:int
Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count()
Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 2) -> bigint, VectorUDAFCountStar(*) -> bigint
+ aggregators: VectorUDAFSumLong(col 3:int) -> bigint, VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 1
+ keyExpressions: col 1:char(20)
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
keys: _col0 (type: char(20))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -124,7 +122,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -134,7 +133,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -142,14 +140,13 @@ STAGE PLANS:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 1) -> bigint, VectorUDAFCountMerge(col 2) -> bigint
+ aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:char(20)
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: char(20))
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -169,7 +166,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -180,7 +176,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2]
+ projectedOutputColumnNums: [0, 1, 2]
Statistics: Num rows: 250 Data size: 47124 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 5
@@ -283,27 +279,25 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1]
Select Operator
expressions: value (type: char(20)), UDFToInteger(key) (type: int)
outputColumnNames: _col0, _col1
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [1, 2]
- selectExpressions: CastStringToLong(col 0) -> 2:int
+ projectedOutputColumnNums: [1, 3]
+ selectExpressions: CastStringToLong(col 0:char(10)) -> 3:int
Statistics: Num rows: 500 Data size: 94248 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: sum(_col1), count()
Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 2) -> bigint, VectorUDAFCountStar(*) -> bigint
+ aggregators: VectorUDAFSumLong(col 3:int) -> bigint, VectorUDAFCountStar(*) -> bigint
className: VectorGroupByOperator
groupByMode: HASH
- vectorOutput: true
- keyExpressions: col 1
+ keyExpressions: col 1:char(20)
native: false
vectorProcessingMode: HASH
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
keys: _col0 (type: char(20))
mode: hash
outputColumnNames: _col0, _col1, _col2
@@ -324,7 +318,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: false
@@ -334,7 +329,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -342,14 +336,13 @@ STAGE PLANS:
Group By Operator
aggregations: sum(VALUE._col0), count(VALUE._col1)
Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 1) -> bigint, VectorUDAFCountMerge(col 2) -> bigint
+ aggregators: VectorUDAFSumLong(col 1:bigint) -> bigint, VectorUDAFCountMerge(col 2:bigint) -> bigint
className: VectorGroupByOperator
groupByMode: MERGEPARTIAL
- vectorOutput: true
- keyExpressions: col 0
+ keyExpressions: col 0:char(20)
native: false
vectorProcessingMode: MERGE_PARTIAL
- projectedOutputColumns: [0, 1]
+ projectedOutputColumnNums: [0, 1]
keys: KEY._col0 (type: char(20))
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
@@ -369,7 +362,6 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
@@ -380,7 +372,7 @@ STAGE PLANS:
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [0, 1, 2]
+ projectedOutputColumnNums: [0, 1, 2]
Statistics: Num rows: 250 Data size: 47124 Basic stats: COMPLETE Column stats: NONE
Limit
Number of rows: 5
http://git-wip-us.apache.org/repos/asf/hive/blob/e63ebccc/ql/src/test/results/clientpositive/llap/vector_char_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_char_4.q.out b/ql/src/test/results/clientpositive/llap/vector_char_4.q.out
index 0bf1a40..0e4b276 100644
--- a/ql/src/test/results/clientpositive/llap/vector_char_4.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_char_4.q.out
@@ -149,15 +149,14 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
Select Operator
expressions: CAST( t AS CHAR(10) (type: char(10)), CAST( si AS CHAR(10) (type: char(10)), CAST( i AS CHAR(20) (type: char(20)), CAST( b AS CHAR(30) (type: char(30)), CAST( f AS CHAR(20) (type: char(20)), CAST( d AS CHAR(20) (type: char(20)), CAST( s AS CHAR(50) (type: char(50))
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Select Vectorization:
className: VectorSelectOperator
native: true
- projectedOutputColumns: [13, 14, 15, 16, 17, 18, 19]
- selectExpressions: CastLongToChar(col 0, maxLength 10) -> 13:Char, CastLongToChar(col 1, maxLength 10) -> 14:Char, CastLongToChar(col 2, maxLength 20) -> 15:Char, CastLongToChar(col 3, maxLength 30) -> 16:Char, VectorUDFAdaptor(CAST( f AS CHAR(20)) -> 17:char(20), VectorUDFAdaptor(CAST( d AS CHAR(20)) -> 18:char(20), CastStringGroupToChar(col 8, maxLength 50) -> 19:Char
+ projectedOutputColumnNums: [14, 15, 16, 17, 18, 19, 20]
+ selectExpressions: CastLongToChar(col 0:tinyint, maxLength 10) -> 14:char(10), CastLongToChar(col 1:smallint, maxLength 10) -> 15:char(10), CastLongToChar(col 2:int, maxLength 20) -> 16:char(20), CastLongToChar(col 3:bigint, maxLength 30) -> 17:char(30), VectorUDFAdaptor(CAST( f AS CHAR(20)) -> 18:char(20), VectorUDFAdaptor(CAST( d AS CHAR(20)) -> 19:char(20), CastStringGroupToChar(col 8:string, maxLength 50) -> 20:char(50)
Statistics: Num rows: 2000 Data size: 410616 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
@@ -175,7 +174,8 @@ STAGE PLANS:
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: true
+ inputFormatFeatureSupport: []
+ featureSupportInUse: []
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
allNative: false
usesVectorUDFAdaptor: true