You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2019/01/04 00:24:04 UTC
[05/35] hive git commit: HIVE-16957: Support CTAS for auto gather
column stats (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out b/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
index 62887c4..a0051f1 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce_groupby_decimal.q.out
@@ -54,7 +54,7 @@ STAGE PLANS:
TableScan
alias: decimal_test_n2
filterExpr: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean)
- Statistics: Num rows: 6102 Data size: 1368328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -63,11 +63,11 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 2:decimal(20,10)), SelectColumnIsNotNull(col 3:decimal(23,14)))
predicate: (cdecimal1 is not null and cdecimal2 is not null) (type: boolean)
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: ++++
keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14))
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: COMPLETE
top n: 50
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -86,7 +86,7 @@ STAGE PLANS:
keys: cint (type: int), cdouble (type: double), cdecimal1 (type: decimal(20,10)), cdecimal2 (type: decimal(23,14))
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14))
sort order: ++++
@@ -95,7 +95,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 5492 Data size: 1231540 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col4 (type: decimal(20,10))
Execution mode: vectorized, llap
@@ -131,7 +131,7 @@ STAGE PLANS:
keys: KEY._col0 (type: int), KEY._col1 (type: double), KEY._col2 (type: decimal(20,10)), KEY._col3 (type: decimal(23,14))
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14))
sort order: ++++
@@ -139,7 +139,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col4 (type: decimal(20,10))
Reducer 3
@@ -158,19 +158,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
- Statistics: Num rows: 2746 Data size: 615770 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6102 Data size: 2123496 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 50
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 50 Data size: 11200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 17400 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 11200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 17400 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_udf2.q.out b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
index 0e1ab60..266211c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_udf2.q.out
@@ -187,7 +187,7 @@ STAGE PLANS:
TableScan
alias: hive_14349
filterExpr: (a like 'XYZ%a%') (type: boolean)
- Statistics: Num rows: 2 Data size: 180 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -196,7 +196,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterStringColLikeStringScalar(col 0:string, pattern XYZ%a%)
predicate: (a like 'XYZ%a%') (type: boolean)
- Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string)
outputColumnNames: _col0
@@ -204,13 +204,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 90 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -279,7 +279,7 @@ STAGE PLANS:
TableScan
alias: hive_14349
filterExpr: (a like 'XYZ%a_') (type: boolean)
- Statistics: Num rows: 6 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 6 Data size: 1104 Basic stats: COMPLETE Column stats: NONE
TableScan Vectorization:
native: true
Filter Operator
@@ -288,7 +288,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterStringColLikeStringScalar(col 0:string, pattern XYZ%a_)
predicate: (a like 'XYZ%a_') (type: boolean)
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: a (type: string)
outputColumnNames: _col0
@@ -296,13 +296,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
index 0cfd81c..f8b3223 100644
--- a/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out
@@ -154,14 +154,14 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Map Join Operator
condition map:
Inner Join 0 to 1
@@ -171,11 +171,11 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
1 Map 3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(10))
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -193,19 +193,19 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: varchar(10))
sort order: +
Map-reduce partition columns: _col1 (type: varchar(10))
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -230,10 +230,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: varchar(10))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -279,8 +279,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -288,20 +288,29 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: varchar(20))
- sort order: +
- Map-reduce partition columns: _col1 (type: varchar(20))
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: varchar(20))
+ 1 _col1 (type: varchar(20))
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(20))
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -313,34 +322,25 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(20))
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 324 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: varchar(20))
- 1 _col1 (type: varchar(20))
- outputColumnNames: _col0, _col1, _col2, _col3
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: varchar(20))
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: varchar(20))
+ sort order: +
+ Map-reduce partition columns: _col1 (type: varchar(20))
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -352,7 +352,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -364,10 +364,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: varchar(20))
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -415,8 +415,8 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 2 <- Map 1 (BROADCAST_EDGE)
- Reducer 3 <- Map 2 (SIMPLE_EDGE)
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -424,20 +424,33 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: varchar(10)), CAST( c2 AS STRING) (type: string)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col2 (type: string)
- sort order: +
- Map-reduce partition columns: _col2 (type: string)
- Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: varchar(10))
+ Statistics: Num rows: 3 Data size: 828 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: varchar(10)), _col3 (type: int), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -449,38 +462,25 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: b
filterExpr: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: c2 is not null (type: boolean)
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: c1 (type: int), c2 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- input vertices:
- 0 Map 1
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: varchar(10)), _col3 (type: int), _col4 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 3 Data size: 276 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -492,7 +492,7 @@ STAGE PLANS:
allNative: true
usesVectorUDFAdaptor: false
vectorized: true
- Reducer 3
+ Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
@@ -504,10 +504,10 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(10)), VALUE._col1 (type: int), VALUE._col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
index c69beb9..2af57ed 100644
--- a/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_windowing_navfn.q.out
@@ -1641,7 +1641,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1655,7 +1655,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -1684,7 +1684,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -1722,14 +1722,14 @@ STAGE PLANS:
name: first_value
window function: GenericUDAFFirstValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), first_value_window_0 (type: int), first_value_window_1 (type: int), first_value_window_2 (type: int), first_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1816,7 +1816,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1830,7 +1830,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -1859,7 +1859,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -1897,14 +1897,14 @@ STAGE PLANS:
name: first_value
window function: GenericUDAFFirstValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), first_value_window_0 (type: int), first_value_window_1 (type: int), first_value_window_2 (type: int), first_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1991,7 +1991,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2005,7 +2005,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -2034,7 +2034,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -2072,14 +2072,14 @@ STAGE PLANS:
name: last_value
window function: GenericUDAFLastValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), last_value_window_0 (type: int), last_value_window_1 (type: int), last_value_window_2 (type: int), last_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2166,7 +2166,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: wtest
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:a:int, 1:b:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -2180,7 +2180,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
partitionColumns: 0:int
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: no inputs
Map Vectorization:
@@ -2209,7 +2209,7 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
Input definition
@@ -2247,14 +2247,14 @@ STAGE PLANS:
name: last_value
window function: GenericUDAFLastValueEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(1)
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 4116 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: int), last_value_window_0 (type: int), last_value_window_1 (type: int), last_value_window_2 (type: int), last_value_window_3 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 15 Data size: 120 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 15 Data size: 308 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
index f81d927..41d12ba 100644
--- a/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_windowing_streaming.q.out
@@ -798,7 +798,7 @@ PLAN VECTORIZATION:
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-4 depends on stages: Stage-2, Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-2
Stage-3 depends on stages: Stage-4
Stage-0 depends on stages: Stage-1
@@ -808,6 +808,7 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -847,28 +848,16 @@ STAGE PLANS:
partitionColumnCount: 0
scratchColumnTypeNames: []
Reducer 2
- Execution mode: vectorized, llap
+ Execution mode: llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- reduceColumnNullOrder: az
- reduceColumnSortOrder: ++
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- dataColumns: KEY.reducesinkkey0:tinyint, KEY.reducesinkkey1:double
- partitionColumnCount: 0
- scratchColumnTypeNames: [bigint]
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double)
outputColumnNames: _col0, _col5
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1]
Statistics: Num rows: 12288 Data size: 3403280 Basic stats: COMPLETE Column stats: COMPLETE
PTF Operator
Function definitions:
@@ -890,46 +879,55 @@ STAGE PLANS:
window function: GenericUDAFRankEvaluator
window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
- PTF Vectorization:
- className: VectorPTFOperator
- evaluatorClasses: [VectorPTFEvaluatorRank]
- functionInputExpressions: [col 1:double]
- functionNames: [rank]
- keyInputColumns: [0, 1]
- native: true
- nonKeyInputColumns: []
- orderExpressions: [col 1:double]
- outputColumns: [2, 0, 1]
- outputTypes: [int, tinyint, double]
- partitionExpressions: [col 0:tinyint]
- streamingColumns: [2]
Statistics: Num rows: 12288 Data size: 3403280 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- Filter Vectorization:
- className: VectorFilterOperator
- native: true
- predicateExpression: FilterLongColLessLongScalar(col 2:int, val 5)
predicate: (rank_window_0 < 5) (type: boolean)
Statistics: Num rows: 4096 Data size: 1121976 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: tinyint), _col5 (type: double), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumnNums: [0, 1, 2]
Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.sD
+ Select Operator
+ expressions: _col0 (type: tinyint), _col1 (type: double), _col2 (type: int)
+ outputColumnNames: col1, col2, col3
+ Statistics: Num rows: 4096 Data size: 40632 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(col1, 'hll'), compute_stats(col2, 'hll'), compute_stats(col3, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reducer 3
+ Execution mode: llap
+ Reduce Vectorization:
+ enabled: true
+ enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_stats not supported
+ vectorized: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 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-2
Dependency Collection
@@ -947,6 +945,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: ctinyint, cdouble, r
+ Column Types: tinyint, double, int
+ Table: default.sD
Stage: Stage-0
Move Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out b/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
index 6502ff5..a68b9e0 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_decimal_date.q.out
@@ -38,7 +38,7 @@ STAGE PLANS:
TableScan
alias: date_decimal_test
filterExpr: (cint is not null and cdouble is not null) (type: boolean)
- Statistics: Num rows: 12288 Data size: 2101500 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 1651440 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -47,7 +47,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:double))
predicate: (cdouble is not null and cint is not null) (type: boolean)
- Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6848 Data size: 920460 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: cdate (type: date), cint (type: int), cdecimal (type: decimal(20,10))
outputColumnNames: _col0, _col1, _col2
@@ -55,19 +55,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 0, 3]
- Statistics: Num rows: 11060 Data size: 1891486 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6848 Data size: 879548 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 1710 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1376 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/138b00ca/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
index 10de402..19fd205 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out
@@ -3915,7 +3915,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -3925,7 +3925,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(ctinyint)
Group By Vectorization:
@@ -3937,14 +3937,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -3977,13 +3977,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4034,7 +4034,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4044,7 +4044,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cint)
Group By Vectorization:
@@ -4056,14 +4056,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4096,13 +4096,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4153,7 +4153,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4163,7 +4163,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [4]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cfloat)
Group By Vectorization:
@@ -4175,14 +4175,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4215,13 +4215,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4272,7 +4272,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 2148200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4282,7 +4282,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [6]
- Statistics: Num rows: 12288 Data size: 2148200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 84 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cstring1)
Group By Vectorization:
@@ -4294,14 +4294,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4334,13 +4334,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4391,7 +4391,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: alltypesnullorc
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4401,7 +4401,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [10]
- Statistics: Num rows: 12288 Data size: 46700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 12288 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count(cboolean1)
Group By Vectorization:
@@ -4413,14 +4413,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
className: VectorReduceSinkEmptyKeyOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -4453,13 +4453,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat