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 00:24:02 UTC
[03/35] 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/vectorized_dynamic_semijoin_reduction.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
index a1924ce..3681739 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_semijoin_reduction.q.out
@@ -58,7 +58,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -67,7 +67,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 1:int, left 0, right 0), VectorInBloomFilterColDynamicValue))
predicate: ((key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -75,7 +75,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -84,7 +84,7 @@ STAGE PLANS:
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: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -101,7 +101,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_int is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -110,7 +110,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: key_int is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -118,7 +118,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -127,7 +127,7 @@ STAGE PLANS:
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: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
@@ -135,9 +135,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 1:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilter(col 1:int) -> binary
className: VectorGroupByOperator
@@ -147,14 +147,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 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: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -176,15 +176,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 94 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -209,13 +209,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 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: 8 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
@@ -230,7 +230,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -240,14 +240,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 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: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
@@ -301,7 +301,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -310,7 +310,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 0:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue))
predicate: ((key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and key_str is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -318,7 +318,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -327,7 +327,7 @@ STAGE PLANS:
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: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -344,7 +344,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_str is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 10304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -353,7 +353,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key_str is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -361,7 +361,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -370,7 +370,7 @@ STAGE PLANS:
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: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
@@ -378,9 +378,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 0:string) -> string, VectorUDAFBloomFilter(col 0:string) -> binary
className: VectorGroupByOperator
@@ -390,14 +390,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 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: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -419,15 +419,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 522 Data size: 91524 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 90 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -452,13 +452,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 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: 8 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
@@ -473,7 +473,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 1:string) -> string, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -483,14 +483,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 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: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
@@ -544,7 +544,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_str is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -553,7 +553,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 0:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue))
predicate: ((key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and key_str is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -561,7 +561,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -570,7 +570,7 @@ STAGE PLANS:
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: 475 Data size: 83204 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -587,7 +587,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_str is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 10304 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -596,7 +596,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 0:string)
predicate: key_str is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string)
outputColumnNames: _col0
@@ -604,7 +604,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -613,7 +613,7 @@ STAGE PLANS:
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: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
@@ -621,9 +621,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 55 Data size: 9942 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 0:string) -> string, VectorUDAFBloomFilter(col 0:string) -> binary
className: VectorGroupByOperator
@@ -633,14 +633,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 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: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -662,15 +662,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- Statistics: Num rows: 522 Data size: 91524 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 90 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -695,13 +695,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 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: 8 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
@@ -716,7 +716,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 1:string) -> string, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -726,14 +726,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 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: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
@@ -787,7 +787,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -796,7 +796,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 1:int, left 0, right 0), VectorInBloomFilterColDynamicValue))
predicate: ((key_int BETWEEN DynamicValue(RS_10_b_key_int_min) AND DynamicValue(RS_10_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_10_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -804,7 +804,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -813,7 +813,7 @@ STAGE PLANS:
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: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -830,7 +830,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: key_int is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -839,7 +839,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: key_int is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -847,7 +847,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -856,7 +856,7 @@ STAGE PLANS:
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: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
@@ -864,9 +864,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=55)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 1:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilter(col 1:int) -> binary
className: VectorGroupByOperator
@@ -876,14 +876,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 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: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -901,7 +901,7 @@ STAGE PLANS:
TableScan
alias: c
filterExpr: key_int is not null (type: boolean)
- Statistics: Num rows: 57 Data size: 224 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -910,7 +910,7 @@ STAGE PLANS:
native: true
predicateExpression: SelectColumnIsNotNull(col 1:int)
predicate: key_int is not null (type: boolean)
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -918,7 +918,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -927,7 +927,7 @@ STAGE PLANS:
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: 55 Data size: 216 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -950,15 +950,15 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
2 _col0 (type: int)
- Statistics: Num rows: 1045 Data size: 3977 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 94 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -983,13 +983,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 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: 8 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
@@ -1004,7 +1004,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=55)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -1014,14 +1014,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 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: 16 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
@@ -1075,7 +1075,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_str is not null and key_int is not null and (key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1084,7 +1084,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 0:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue))
predicate: ((key_str BETWEEN DynamicValue(RS_7_b_key_str_min) AND DynamicValue(RS_7_b_key_str_max) and in_bloom_filter(key_str, DynamicValue(RS_7_b_key_str_bloom_filter))) and key_int is not null and key_str is not null) (type: boolean)
- Statistics: Num rows: 450 Data size: 80539 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string), key_int (type: int)
outputColumnNames: _col0, _col1
@@ -1092,7 +1092,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 450 Data size: 80539 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
@@ -1101,7 +1101,7 @@ 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: 450 Data size: 80539 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1118,7 +1118,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: (key_str is not null and key_int is not null) (type: boolean)
- Statistics: Num rows: 57 Data size: 10528 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1127,7 +1127,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:string), SelectColumnIsNotNull(col 1:int))
predicate: (key_int is not null and key_str is not null) (type: boolean)
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_str (type: string), key_int (type: int)
outputColumnNames: _col0, _col1
@@ -1135,7 +1135,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int)
sort order: ++
@@ -1144,7 +1144,7 @@ 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: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5130 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
@@ -1152,9 +1152,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 53 Data size: 9789 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 4902 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=53)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 0:string) -> string, VectorUDAFBloomFilter(col 0:string) -> binary
className: VectorGroupByOperator
@@ -1164,14 +1164,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 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: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1193,15 +1193,15 @@ STAGE PLANS:
keys:
0 _col0 (type: string), _col1 (type: int)
1 _col0 (type: string), _col1 (type: int)
- Statistics: Num rows: 495 Data size: 88592 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 90 Data size: 720 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1226,13 +1226,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 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: 8 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
@@ -1247,7 +1247,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=53)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=57)
Group By Vectorization:
aggregators: VectorUDAFMinString(col 0:string) -> string, VectorUDAFMaxString(col 1:string) -> string, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -1257,14 +1257,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 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: 740 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: binary)
Stage: Stage-0
@@ -1318,7 +1318,7 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1327,7 +1327,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 1:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 1:int, left 0, right 0), VectorInBloomFilterColDynamicValue))
predicate: ((key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -1335,7 +1335,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -1344,7 +1344,7 @@ STAGE PLANS:
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: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1361,7 +1361,7 @@ STAGE PLANS:
TableScan
alias: b
filterExpr: ((value) IN ('nonexistent1', 'nonexistent2') and key_int is not null) (type: boolean)
- Statistics: Num rows: 57 Data size: 10528 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 57 Data size: 5358 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1370,7 +1370,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterStringColumnInList(col 2, values nonexistent1, nonexistent2), SelectColumnIsNotNull(col 1:int))
predicate: ((value) IN ('nonexistent1', 'nonexistent2') and key_int is not null) (type: boolean)
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
@@ -1378,7 +1378,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
@@ -1387,7 +1387,7 @@ STAGE PLANS:
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: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int)
outputColumnNames: _col0
@@ -1395,9 +1395,9 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1]
- Statistics: Num rows: 8 Data size: 1477 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=8)
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=2)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 1:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilter(col 1:int) -> binary
className: VectorGroupByOperator
@@ -1407,14 +1407,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 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: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1436,15 +1436,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
MergeJoin Vectorization:
enabled: false
@@ -1469,13 +1469,13 @@ STAGE PLANS:
projectedOutputColumnNums: [0]
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 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: 8 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
@@ -1490,7 +1490,7 @@ STAGE PLANS:
vectorized: true
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=8)
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=2)
Group By Vectorization:
aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary
className: VectorGroupByOperator
@@ -1500,14 +1500,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2]
mode: final
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 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: 200 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary)
Stage: Stage-0
@@ -1575,19 +1575,19 @@ STAGE PLANS:
TableScan
alias: a
filterExpr: (key_int is not null and (key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter)))) (type: boolean)
- Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((key_int BETWEEN DynamicValue(RS_7_b_key_int_min) AND DynamicValue(RS_7_b_key_int_max) and in_bloom_filter(key_int, DynamicValue(RS_7_b_key_int_bloom_filter))) and key_int is not null) (type: boolean)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key_int (type: int)
outputColumnNames: _col0
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map 4
@@ -1632,15 +1632,15 @@ STAGE PLANS:
keys:
0 _col0 (type: int)
1 _col0 (type: int)
- Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 94 Data size: 752 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1649,10 +1649,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 8 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