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 2017/05/08 05:38:07 UTC
[07/12] hive git commit: HIVE-16275: Vectorization: Add ReduceSink
support for TopN (in specialized native classes) (Matt McCline,
reviewed by Gopal Vijayaraghavan)
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_ptf_part_simple.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_ptf_part_simple.q.out b/ql/src/test/results/clientpositive/llap/vector_ptf_part_simple.q.out
index 9929550..dbf90b0 100644
--- a/ql/src/test/results/clientpositive/llap/vector_ptf_part_simple.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_ptf_part_simple.q.out
@@ -143,7 +143,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_name (type: string), p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -368,7 +368,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -593,7 +593,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -812,7 +812,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_name (type: string), p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -1005,7 +1005,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -1198,7 +1198,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -1391,7 +1391,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -1626,7 +1626,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 12792 Basic stats: COMPLETE Column stats: NONE
value expressions: p_name (type: string), p_retailprice (type: decimal(38,18))
Execution mode: vectorized, llap
@@ -1819,7 +1819,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 12792 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: decimal(38,18))
Execution mode: vectorized, llap
@@ -2032,7 +2032,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_name (type: string), p_bigint (type: bigint)
Execution mode: vectorized, llap
@@ -2225,7 +2225,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_bigint (type: bigint)
Execution mode: vectorized, llap
@@ -2412,7 +2412,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -2576,7 +2576,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -2741,7 +2741,7 @@ STAGE PLANS:
className: VectorReduceSinkMultiKeyOperator
keyExpressions: VectorUDFAdaptor(CASE WHEN ((p_mfgr = 'Manufacturer#2')) THEN (2000-01-01 00:00:00.0) ELSE (null) END)(children: StringGroupColEqualStringScalar(col 0, val Manufacturer#2) -> 3:boolean) -> 4:timestamp
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_name (type: string), p_retailprice (type: double)
Execution mode: vectorized, llap
@@ -2907,7 +2907,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
keyExpressions: VectorUDFAdaptor(CASE WHEN ((p_mfgr = 'Manufacturer#2')) THEN (2000-01-01 00:00:00.0) ELSE (null) END)(children: StringGroupColEqualStringScalar(col 0, val Manufacturer#2) -> 3:boolean) -> 4:timestamp
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 40 Data size: 9048 Basic stats: COMPLETE Column stats: NONE
value expressions: p_retailprice (type: double)
Execution mode: vectorized, llap
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out b/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out
index 794e595..4a4e710 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out
@@ -145,7 +145,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out b/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out
index 170ea9c..d937146 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out
@@ -145,7 +145,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out b/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out
index 3d2992f..382841f 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out
@@ -145,7 +145,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE
Execution mode: vectorized, llap
LLAP IO: all inputs
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/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 964e63d..7348af8 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
@@ -78,10 +78,9 @@ STAGE PLANS:
sort order: ++++
Map-reduce partition columns: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14))
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 6102 Data size: 1440072 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col4 (type: decimal(20,10))
@@ -122,10 +121,9 @@ STAGE PLANS:
key expressions: _col0 (type: int), _col1 (type: double), _col2 (type: decimal(20,10)), _col3 (type: decimal(23,14))
sort order: ++++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 3051 Data size: 720036 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
value expressions: _col4 (type: decimal(20,10))
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_string_concat.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_string_concat.q.out b/ql/src/test/results/clientpositive/llap/vector_string_concat.q.out
index 8b19c58..fb9e121 100644
--- a/ql/src/test/results/clientpositive/llap/vector_string_concat.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_string_concat.q.out
@@ -369,10 +369,9 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ className: VectorReduceSinkStringOperator
+ 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: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
@@ -410,10 +409,9 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE
TopN Hash Memory Usage: 0.1
Reducer 3
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_string_decimal.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_string_decimal.q.out b/ql/src/test/results/clientpositive/llap/vector_string_decimal.q.out
index c036d69..6b4ca6c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_string_decimal.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_string_decimal.q.out
@@ -62,28 +62,44 @@ STAGE PLANS:
TableScan
alias: orc_decimal
Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0]
Filter Operator
- predicate: (id) IN ('100000000', '200000000') (type: boolean)
+ Filter Vectorization:
+ className: VectorFilterOperator
+ native: true
+ predicateExpression: FilterDoubleColumnInList(col 1, values [1.0E8, 2.0E8])(children: CastDecimalToDouble(col 0) -> 1:double) -> boolean
+ predicate: (UDFToDouble(id)) IN (1.0E8, 2.0E8) (type: boolean)
Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: id (type: decimal(18,0))
outputColumnNames: _col0
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0]
Statistics: Num rows: 2 Data size: 224 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 2 Data size: 224 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: llap
+ Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
enabled: true
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- notVectorizedReason: Predicate expression for FILTER operator: Cannot vectorize IN() - casting a column is not supported. Column type is decimal(18,0) but the common type is string
- vectorized: false
+ allNative: false
+ usesVectorUDFAdaptor: false
+ vectorized: true
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out b/ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out
index 31b834a..3a431b6 100644
--- a/ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_tablesample_rows.q.out
@@ -264,7 +264,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out b/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out
index b219869..52f78da 100644
--- a/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_varchar_simple.q.out
@@ -93,7 +93,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
@@ -213,7 +213,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
@@ -335,10 +335,9 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 10 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int)
@@ -349,7 +348,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vector_when_case_null.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_when_case_null.q.out b/ql/src/test/results/clientpositive/llap/vector_when_case_null.q.out
index 8104f3e..06dde80 100644
--- a/ql/src/test/results/clientpositive/llap/vector_when_case_null.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_when_case_null.q.out
@@ -73,7 +73,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkStringOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 5 Data size: 452 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
index d2897ba..73fb9b1 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_0.q.out
@@ -63,7 +63,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: tinyint), _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -103,7 +103,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: tinyint), _col2 (type: bigint), _col3 (type: bigint)
Reducer 3
@@ -219,7 +219,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
@@ -259,7 +259,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
@@ -520,7 +520,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -560,7 +560,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint)
Reducer 3
@@ -676,7 +676,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: vectorized, llap
@@ -716,7 +716,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
@@ -977,7 +977,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: float), _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint)
Execution mode: vectorized, llap
@@ -1017,7 +1017,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: float), _col2 (type: bigint), _col3 (type: bigint)
Reducer 3
@@ -1133,7 +1133,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double)
Execution mode: vectorized, llap
@@ -1173,7 +1173,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
Execution mode: vectorized, llap
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_7.q.out b/ql/src/test/results/clientpositive/llap/vectorization_7.q.out
index 9925959..ba49bed 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_7.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_7.q.out
@@ -96,10 +96,9 @@ STAGE PLANS:
key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint)
sort order: +++++++++++++++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
@@ -109,7 +108,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
@@ -332,10 +331,9 @@ STAGE PLANS:
key expressions: _col0 (type: boolean), _col1 (type: bigint), _col2 (type: smallint), _col3 (type: tinyint), _col4 (type: timestamp), _col5 (type: string), _col6 (type: bigint), _col7 (type: int), _col8 (type: smallint), _col9 (type: tinyint), _col10 (type: int), _col11 (type: bigint), _col12 (type: int), _col13 (type: tinyint), _col14 (type: tinyint)
sort order: +++++++++++++++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 7281 Data size: 1231410 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
@@ -345,7 +343,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_8.q.out b/ql/src/test/results/clientpositive/llap/vectorization_8.q.out
index 42f12e9..9e9f2c7 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_8.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_8.q.out
@@ -92,10 +92,9 @@ STAGE PLANS:
key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double)
sort order: ++++++++++++++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 3060 Data size: 557456 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
@@ -105,7 +104,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
@@ -315,10 +314,9 @@ STAGE PLANS:
key expressions: _col0 (type: timestamp), _col1 (type: double), _col2 (type: boolean), _col3 (type: string), _col4 (type: float), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: float), _col9 (type: double), _col10 (type: double), _col11 (type: float), _col12 (type: float), _col13 (type: double)
sort order: ++++++++++++++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 3060 Data size: 557456 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
@@ -328,7 +326,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out b/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out
index 2b5e5a8..2ff5c54 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_div0.q.out
@@ -227,10 +227,9 @@ STAGE PLANS:
key expressions: _col0 (type: bigint), _col1 (type: double)
sort order: ++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 1365 Data size: 174720 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: decimal(22,21))
@@ -241,7 +240,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
@@ -447,10 +446,9 @@ STAGE PLANS:
key expressions: _col0 (type: double), _col1 (type: double)
sort order: ++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 1365 Data size: 65520 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: double), _col4 (type: double), _col5 (type: double)
@@ -461,7 +459,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out
index c38a215..5701676 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out
@@ -64,17 +64,17 @@ POSTHOOK: query: SELECT cbigint, cdouble FROM alltypesorc WHERE cbigint < cdoubl
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--1887561756 1839.0
-1887561756 -10011.0
-1887561756 -13877.0
--1887561756 10361.0
--1887561756 -8881.0
-1887561756 -2281.0
+-1887561756 -8881.0
+-1887561756 10361.0
+-1887561756 1839.0
-1887561756 9531.0
-PREHOOK: query: explain vectorization expression
+PREHOOK: query: explain vectorization detail
select ctinyint,cdouble,csmallint from alltypesorc where ctinyint is not null order by ctinyint,cdouble limit 20
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain vectorization detail
select ctinyint,cdouble,csmallint from alltypesorc where ctinyint is not null order by ctinyint,cdouble limit 20
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
@@ -120,10 +120,9 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.3
value expressions: _col2 (type: smallint)
@@ -134,18 +133,29 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0, 1, 5]
+ dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aa
+ reduceColumnSortOrder: ++
groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 3
+ dataColumns: KEY.reducesinkkey0:tinyint, KEY.reducesinkkey1:double, VALUE._col0:smallint
+ partitionColumnCount: 0
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: tinyint), KEY.reducesinkkey1 (type: double), VALUE._col0 (type: smallint)
@@ -186,10 +196,17 @@ POSTHOOK: query: select ctinyint,cdouble,csmallint from alltypesorc where ctinyi
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
--64 -15920.0 -15920
-64 -10462.0 -10462
--64 -9842.0 -9842
--64 -8080.0 -8080
+-64 -15920.0 -15920
+-64 -1600.0 -1600
+-64 -200.0 -200
+-64 -2919.0 -2919
+-64 -3097.0 -3097
+-64 -3586.0 -3586
+-64 -4018.0 -4018
+-64 -4040.0 -4040
+-64 -4803.0 -4803
+-64 -6907.0 -6907
-64 -7196.0 -7196
-64 -7196.0 -7196
-64 -7196.0 -7196
@@ -197,19 +214,12 @@ POSTHOOK: Input: default@alltypesorc
-64 -7196.0 -7196
-64 -7196.0 -7196
-64 -7196.0 -7196
--64 -6907.0 -6907
--64 -4803.0 -4803
--64 -4040.0 -4040
--64 -4018.0 -4018
--64 -3586.0 -3586
--64 -3097.0 -3097
--64 -2919.0 -2919
--64 -1600.0 -1600
--64 -200.0 -200
-PREHOOK: query: explain vectorization expression
+-64 -8080.0 -8080
+-64 -9842.0 -9842
+PREHOOK: query: explain vectorization detail
select ctinyint,avg(cdouble + 1) from alltypesorc group by ctinyint order by ctinyint limit 20
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain vectorization detail
select ctinyint,avg(cdouble + 1) from alltypesorc group by ctinyint order by ctinyint limit 20
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
@@ -276,6 +286,12 @@ STAGE PLANS:
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0, 5]
+ dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
+ scratchColumnTypeNames: double
Reducer 2
Execution mode: llap
Reduce Vectorization:
@@ -315,30 +331,30 @@ POSTHOOK: query: select ctinyint,avg(cdouble + 1) from alltypesorc group by ctin
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-NULL 9370.0945309795
--64 373.52941176470586
--63 2178.7272727272725
--62 245.69387755102042
--61 914.3404255319149
--60 1071.82
--59 318.27272727272725
--58 3483.2444444444445
--57 1867.0535714285713
--56 2595.818181818182
--55 2385.595744680851
--54 2712.7272727272725
--53 -532.7567567567568
--52 2810.705882352941
--51 -96.46341463414635
--50 -960.0192307692307
--49 768.7659574468086
--48 1672.909090909091
--47 -574.6428571428571
-46 3033.55
-PREHOOK: query: explain vectorization expression
+-47 -574.6428571428571
+-48 1672.909090909091
+-49 768.7659574468086
+-50 -960.0192307692307
+-51 -96.46341463414635
+-52 2810.705882352941
+-53 -532.7567567567568
+-54 2712.7272727272725
+-55 2385.595744680851
+-56 2595.818181818182
+-57 1867.0535714285713
+-58 3483.2444444444445
+-59 318.27272727272725
+-60 1071.82
+-61 914.3404255319149
+-62 245.69387755102042
+-63 2178.7272727272725
+-64 373.52941176470586
+NULL 9370.0945309795
+PREHOOK: query: explain vectorization detail
select distinct(ctinyint) from alltypesorc limit 20
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain vectorization detail
select distinct(ctinyint) from alltypesorc limit 20
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
@@ -389,10 +405,9 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: tinyint)
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ className: VectorReduceSinkLongOperator
+ 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: 95 Data size: 288 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.3
Execution mode: vectorized, llap
@@ -405,15 +420,26 @@ STAGE PLANS:
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0]
+ dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 1
+ dataColumns: KEY._col0:tinyint
+ partitionColumnCount: 0
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
@@ -457,30 +483,30 @@ POSTHOOK: query: select distinct(ctinyint) from alltypesorc limit 20
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-NULL
--64
--63
--62
--61
--60
--59
--58
--57
--56
--55
--54
--53
--52
--51
--50
--49
--48
--47
-46
-PREHOOK: query: explain vectorization expression
+-47
+-48
+-49
+-50
+-51
+-52
+-53
+-54
+-55
+-56
+-57
+-58
+-59
+-60
+-61
+-62
+-63
+-64
+NULL
+PREHOOK: query: explain vectorization detail
select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint order by ctinyint limit 20
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain vectorization detail
select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint order by ctinyint limit 20
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
@@ -533,7 +559,7 @@ STAGE PLANS:
Reduce Sink Vectorization:
className: VectorReduceSinkObjectHashOperator
native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS 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: 6144 Data size: 55052 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -545,15 +571,26 @@ STAGE PLANS:
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0, 5]
+ dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aa
+ reduceColumnSortOrder: ++
groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY._col0:tinyint, KEY._col1:double
+ partitionColumnCount: 0
Reduce Operator Tree:
Group By Operator
Group By Vectorization:
@@ -610,30 +647,30 @@ POSTHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesorc grou
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-NULL 2932
--64 24
--63 19
--62 27
--61 25
--60 27
--59 31
--58 23
--57 35
--56 36
--55 29
--54 26
--53 22
--52 33
--51 21
--50 30
--49 26
--48 29
--47 22
-46 24
-PREHOOK: query: explain vectorization expression
+-47 22
+-48 29
+-49 26
+-50 30
+-51 21
+-52 33
+-53 22
+-54 26
+-55 29
+-56 36
+-57 35
+-58 23
+-59 31
+-60 27
+-61 25
+-62 27
+-63 19
+-64 24
+NULL 2932
+PREHOOK: query: explain vectorization detail
select ctinyint,cdouble from alltypesorc order by ctinyint limit 0
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain vectorization detail
select ctinyint,cdouble from alltypesorc order by ctinyint limit 0
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
@@ -658,10 +695,10 @@ POSTHOOK: query: select ctinyint,cdouble from alltypesorc order by ctinyint limi
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-PREHOOK: query: explain vectorization expression
+PREHOOK: query: explain vectorization detail
select cdouble, sum(ctinyint) as sum from alltypesorc where ctinyint is not null group by cdouble order by sum, cdouble limit 20
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain vectorization detail
select cdouble, sum(ctinyint) as sum from alltypesorc where ctinyint is not null group by cdouble order by sum, cdouble limit 20
POSTHOOK: type: QUERY
PLAN VECTORIZATION:
@@ -696,37 +733,29 @@ STAGE PLANS:
predicateExpression: SelectColumnIsNotNull(col 0) -> boolean
predicate: ctinyint is not null (type: boolean)
Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: cdouble (type: double), ctinyint (type: tinyint)
- outputColumnNames: cdouble, ctinyint
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumns: [5, 0]
- Statistics: Num rows: 9173 Data size: 82188 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: sum(ctinyint)
- Group By Vectorization:
- aggregators: VectorUDAFSumLong(col 0) -> bigint
- className: VectorGroupByOperator
- vectorOutput: true
- keyExpressions: col 5
- native: false
- projectedOutputColumns: [0]
- keys: cdouble (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
+ Group By Operator
+ aggregations: sum(ctinyint)
+ Group By Vectorization:
+ aggregators: VectorUDAFSumLong(col 0) -> bigint
+ className: VectorGroupByOperator
+ vectorOutput: true
+ keyExpressions: col 5
+ native: false
+ projectedOutputColumns: [0]
+ keys: cdouble (type: double)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
+ Reduce Sink Vectorization:
+ 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: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Reduce Sink Vectorization:
- className: VectorReduceSinkMultiKeyOperator
- native: true
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint)
+ value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -737,15 +766,26 @@ STAGE PLANS:
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0, 5]
+ dataColumns: ctinyint:tinyint, csmallint:smallint, cint:int, cbigint:bigint, cfloat:float, cdouble:double, cstring1:string, cstring2:string, ctimestamp1:timestamp, ctimestamp2:timestamp, cboolean1:boolean, cboolean2:boolean
+ partitionColumnCount: 0
Reducer 2
Execution mode: vectorized, llap
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: a
+ reduceColumnSortOrder: +
groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY._col0:double, VALUE._col0:bigint
+ partitionColumnCount: 0
Reduce Operator Tree:
Group By Operator
aggregations: sum(VALUE._col0)
@@ -764,10 +804,9 @@ STAGE PLANS:
key expressions: _col1 (type: bigint), _col0 (type: double)
sort order: ++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 3185 Data size: 44512 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.3
Reducer 3
@@ -775,10 +814,16 @@ STAGE PLANS:
Reduce Vectorization:
enabled: true
enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
+ reduceColumnNullOrder: aa
+ reduceColumnSortOrder: ++
groupByVectorOutput: true
allNative: false
usesVectorUDFAdaptor: false
vectorized: true
+ rowBatchContext:
+ dataColumnCount: 2
+ dataColumns: KEY.reducesinkkey0:bigint, KEY.reducesinkkey1:double
+ partitionColumnCount: 0
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey1 (type: double), KEY.reducesinkkey0 (type: bigint)
@@ -819,23 +864,23 @@ POSTHOOK: query: select cdouble, sum(ctinyint) as sum from alltypesorc where cti
POSTHOOK: type: QUERY
POSTHOOK: Input: default@alltypesorc
#### A masked pattern was here ####
-NULL -32768
+-10462.0 -64
+-1121.0 -89
+-11322.0 -101
+-11492.0 -78
+-15920.0 -64
+-4803.0 -64
+-6907.0 -64
-7196.0 -2009
+-8080.0 -64
+-8118.0 -80
+-9842.0 -64
+10496.0 -67
15601.0 -1733
-4811.0 -115
--11322.0 -101
--1121.0 -89
-7705.0 -88
3520.0 -86
--8118.0 -80
+4811.0 -115
5241.0 -80
--11492.0 -78
-9452.0 -76
557.0 -75
-10496.0 -67
--15920.0 -64
--10462.0 -64
--9842.0 -64
--8080.0 -64
--6907.0 -64
--4803.0 -64
+7705.0 -88
+9452.0 -76
+NULL -32768
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out b/ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out
index f1fe221..bdfe78e 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_offset_limit.q.out
@@ -116,10 +116,9 @@ STAGE PLANS:
key expressions: _col0 (type: tinyint), _col1 (type: double)
sort order: ++
Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- nativeConditionsNotMet: No TopN IS false
+ 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: 9173 Data size: 109584 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col2 (type: smallint)
@@ -130,7 +129,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2
http://git-wip-us.apache.org/repos/asf/hive/blob/ec8c390e/ql/src/test/results/clientpositive/llap/vectorization_part_project.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorization_part_project.q.out b/ql/src/test/results/clientpositive/llap/vectorization_part_project.q.out
index 872e7f3..85c4dd0 100644
--- a/ql/src/test/results/clientpositive/llap/vectorization_part_project.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorization_part_project.q.out
@@ -87,7 +87,7 @@ STAGE PLANS:
enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
groupByVectorOutput: true
inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
+ allNative: true
usesVectorUDFAdaptor: false
vectorized: true
Reducer 2