You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by kg...@apache.org on 2018/09/20 06:16:25 UTC
[1/6] hive git commit: HIVE-20498: Support date type for column stats
autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Repository: hive
Updated Branches:
refs/heads/master ee5566b75 -> 9b376a7b0
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
index 9e59594..07616bb 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_arithmetic.q.out
@@ -80,7 +80,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: interval_arithmetic_1
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -91,7 +91,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8]
selectExpressions: DateColSubtractIntervalYearMonthScalar(col 0:date, val 2-2) -> 3:date, DateColSubtractIntervalYearMonthScalar(col 0:date, val -2-2) -> 4:date, DateColAddIntervalYearMonthScalar(col 0:date, val 2-2) -> 5:date, DateColAddIntervalYearMonthScalar(col 0:date, val -2-2) -> 6:date, IntervalYearMonthScalarAddDateColumn(val -2-2, col 0:interval_year_month) -> 7:date, IntervalYearMonthScalarAddDateColumn(val 2-2, col 0:interval_year_month) -> 8:date
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 19600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -99,7 +99,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 19600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: date), _col2 (type: date), _col3 (type: date), _col4 (type: date), _col5 (type: date), _col6 (type: date)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -128,13 +128,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 19600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 19600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -262,7 +262,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: interval_arithmetic_1
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -273,7 +273,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 5]
selectExpressions: DateColSubtractDateScalar(col 0:date, val 1999-06-07) -> 3:interval_day_time, DateScalarSubtractDateColumn(val 1999-06-07, col 0:date) -> 4:interval_day_time, DateColSubtractDateColumn(col 0:date, col 0:date) -> 5:interval_day_time
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -281,7 +281,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -310,13 +310,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 4600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -444,7 +444,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: interval_arithmetic_1
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -455,7 +455,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 4, 5, 6, 7, 8]
selectExpressions: TimestampColSubtractIntervalYearMonthScalar(col 1:timestamp, val 2-2) -> 3:timestamp, TimestampColSubtractIntervalYearMonthScalar(col 1:timestamp, val -2-2) -> 4:timestamp, TimestampColAddIntervalYearMonthScalar(col 1:timestamp, val 2-2) -> 5:timestamp, TimestampColAddIntervalYearMonthScalar(col 1:timestamp, val -2-2) -> 6:timestamp, IntervalYearMonthScalarAddTimestampColumn(val -2-2, col 1:interval_year_month) -> 7:timestamp, IntervalYearMonthScalarAddTimestampColumn(val 2-2, col 1:interval_year_month) -> 8:timestamp
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -463,7 +463,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -492,13 +492,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -733,7 +733,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: interval_arithmetic_1
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 2800 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -744,7 +744,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8]
selectExpressions: DateColSubtractIntervalDayTimeScalar(col 0:date, val 99 11:22:33.123456789) -> 3:timestamp, DateColSubtractIntervalDayTimeScalar(col 0:date, val -99 11:22:33.123456789) -> 4:timestamp, DateColAddIntervalDayTimeScalar(col 0:date, val 99 11:22:33.123456789) -> 5:timestamp, DateColAddIntervalDayTimeScalar(col 0:date, val -99 11:22:33.123456789) -> 6:timestamp, IntervalDayTimeScalarAddDateColumn(val -99 11:22:33.123456789, col 0:date) -> 7:timestamp, IntervalDayTimeScalarAddDateColumn(val 99 11:22:33.123456789, col 0:date) -> 8:timestamp
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14800 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -752,7 +752,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14800 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -781,13 +781,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14800 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 2744 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14800 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -917,7 +917,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: interval_arithmetic_1
- Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 4800 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -928,7 +928,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 3, 4, 5]
selectExpressions: DateColSubtractTimestampColumn(col 0:date, col 1:timestamp) -> 3:interval_day_time, TimestampColSubtractDateColumn(col 1:timestamp, col 0:date) -> 4:interval_day_time, TimestampColSubtractTimestampColumn(col 1:timestamp, col 1:timestamp) -> 5:interval_day_time
- Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 6600 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -936,7 +936,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 6600 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: timestamp), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -965,13 +965,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4]
- Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 6600 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 4704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 6600 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1101,7 +1101,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: interval_arithmetic_1
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1112,7 +1112,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 4, 5, 6, 7, 8]
selectExpressions: TimestampColSubtractIntervalDayTimeScalar(col 1:timestamp, val 99 11:22:33.123456789) -> 3:timestamp, TimestampColSubtractIntervalDayTimeScalar(col 1:timestamp, val -99 11:22:33.123456789) -> 4:timestamp, TimestampColAddIntervalDayTimeScalar(col 1:timestamp, val 99 11:22:33.123456789) -> 5:timestamp, TimestampColAddIntervalDayTimeScalar(col 1:timestamp, val -99 11:22:33.123456789) -> 6:timestamp, IntervalDayTimeScalarAddTimestampColumn(val -99 11:22:33.123456789, col 1:timestamp) -> 7:timestamp, IntervalDayTimeScalarAddTimestampColumn(val 99 11:22:33.123456789, col 1:timestamp) -> 8:timestamp
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1120,7 +1120,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1149,13 +1149,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 1960 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 14000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out b/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out
index 0de0c33..db98194 100644
--- a/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_orderby_5.q.out
@@ -128,7 +128,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n6
- Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 22860 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -138,7 +138,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3, 7]
- Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 22860 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(b)
Group By Vectorization:
@@ -152,7 +152,7 @@ STAGE PLANS:
keys: bo (type: boolean)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: +
@@ -161,7 +161,7 @@ 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: 2000 Data size: 22812 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -196,7 +196,7 @@ STAGE PLANS:
keys: KEY._col0 (type: boolean)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: boolean)
sort order: -
@@ -204,7 +204,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -222,13 +222,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1000 Data size: 11406 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
index 57a1ea7..5dd8c98 100644
--- a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out
@@ -1898,7 +1898,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_orc_partitioned_timestamp
- Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1908,13 +1908,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2133,7 +2133,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_orc_partitioned_timestamp
- Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -2143,7 +2143,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: int), _col5 (type: timestamp)
sort order: ++
@@ -2151,7 +2151,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float)
Execution mode: vectorized, llap
@@ -2181,13 +2181,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 4, 5, 0, 1]
- Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: int), _col5 (type: timestamp)
sort order: ++
@@ -2195,7 +2195,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float)
Reducer 3
@@ -2214,19 +2214,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 4, 5, 0, 1]
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4323,7 +4323,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_parquet_partitioned_timestamp
- Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4333,13 +4333,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4558,7 +4558,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: flights_tiny_parquet_partitioned_timestamp
- Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -4568,7 +4568,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5]
- Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: int), _col5 (type: timestamp)
sort order: ++
@@ -4576,7 +4576,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float)
Execution mode: vectorized, llap
@@ -4606,13 +4606,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 4, 5, 0, 1]
- Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: int), _col5 (type: timestamp)
sort order: ++
@@ -4620,7 +4620,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float)
Reducer 3
@@ -4639,19 +4639,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [2, 3, 4, 5, 0, 1]
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 25
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/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 a3ad696..f8e2e5c 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce1.q.out
@@ -127,7 +127,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n7
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15344 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -137,7 +137,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [3]
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15344 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: bigint)
sort order: +
@@ -145,7 +145,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15344 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -173,13 +173,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15344 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15344 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/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 8ff51ac..fb30ae1 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce2.q.out
@@ -127,7 +127,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n5
- Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 387636 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -137,7 +137,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [8, 2, 9]
- Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 387636 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
sort order: +++
@@ -145,7 +145,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 387636 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -173,13 +173,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2]
- Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 387636 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2000 Data size: 707172 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 387636 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/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 e26c8b2..03fa93e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_reduce3.q.out
@@ -127,7 +127,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n2
- Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -137,7 +137,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [8]
- Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -145,7 +145,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -173,13 +173,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2000 Data size: 349784 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/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 39578d2..f938a09 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
@@ -340,7 +340,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n0
- Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 106288 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -351,11 +351,11 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [20]
selectExpressions: StringGroupConcatColCol(col 18:string, col 19:string)(children: StringGroupColConcatStringScalar(col 19:string, val -)(children: StringScalarConcatStringGroupCol(val Quarter , col 18:string)(children: CastLongToString(col 14:int)(children: CastDoubleToLong(col 16:double)(children: DoubleColAddDoubleScalar(col 17:double, val 1.0)(children: DoubleColDivideDoubleScalar(col 16:double, val 3.0)(children: CastLongToDouble(col 15:int)(children: LongColSubtractLongScalar(col 14:int, val 1)(children: VectorUDFMonthDate(col 12, field MONTH) -> 14:int) -> 15:int) -> 16:double) -> 17:double) -> 16:double) -> 14:int) -> 18:string) -> 19:string) -> 18:string, CastLongToString(col 14:int)(children: VectorUDFYearDate(col 12, field YEAR) -> 14:int) -> 19:string) -> 20:string
- Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 106288 Basic stats: COMPLETE Column stats: COMPLETE
Top N Key Operator
sort order: +
keys: _col0 (type: string)
- Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 106288 Basic stats: COMPLETE Column stats: COMPLETE
top n: 50
Top N Key Vectorization:
className: VectorTopNKeyOperator
@@ -372,7 +372,7 @@ STAGE PLANS:
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -381,7 +381,7 @@ 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: 2000 Data size: 106456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -414,7 +414,7 @@ STAGE PLANS:
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1000 Data size: 53228 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -422,7 +422,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1000 Data size: 53228 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
Reducer 3
Execution mode: vectorized, llap
@@ -440,19 +440,19 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1000 Data size: 53228 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 92000 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 50
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 50 Data size: 2650 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 50 Data size: 2650 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 50 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vectorized_date_funcs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_date_funcs.q.out b/ql/src/test/results/clientpositive/llap/vectorized_date_funcs.q.out
index 15cd648..41f1a5e 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_date_funcs.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_date_funcs.q.out
@@ -261,7 +261,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: date_udf_flight_orc
- Statistics: Num rows: 137 Data size: 5280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 5480 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -272,13 +272,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21]
selectExpressions: VectorUDFUnixTimeStampTimestamp(col 1:timestamp) -> 3:bigint, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 4:int, VectorUDFMonthTimestamp(col 1:timestamp, field MONTH) -> 5:int, VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 6:int, VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 7:int, VectorUDFDayOfWeekTimestamp(col 1:timestamp, field DAY_OF_WEEK) -> 8:int, VectorUDFWeekOfYearTimestamp(col 1:timestamp, field WEEK_OF_YEAR) -> 9:int, CastTimestampToDate(col 1:timestamp) -> 10:date, VectorUDFDateTimestamp(col 1:timestamp) -> 11:date, VectorUDFDateAddColScalar(col 1:timestamp, val 2) -> 12:date, VectorUDFDateSubColScalar(col 1:timestamp, val 2) -> 13:date, VectorUDFDateDiffColScalar(col 1:timestamp, val 2000-01-01) -> 14:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 15:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 16:int, VectorUDFDateDiffColScalar(col 1:times
tamp, val NULL) -> 17:int, VectorUDFDateDiffColScalar(col 1:timestamp, val 2007-03-14) -> 18:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 19:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 20:int, VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 21:int
- Statistics: Num rows: 137 Data size: 5280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 44936 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 137 Data size: 5280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 44936 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -553,7 +553,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: date_udf_flight_orc
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -564,13 +564,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 5, 6, 7, 8, 9, 0, 0, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
selectExpressions: VectorUDFUnixTimeStampDate(col 0) -> 3:bigint, VectorUDFYearDate(col 0, field YEAR) -> 4:int, VectorUDFMonthDate(col 0, field MONTH) -> 5:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 6:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 7:int, VectorUDFDayOfWeekDate(col 0, field DAY_OF_WEEK) -> 8:int, VectorUDFWeekOfYearDate(col 0, field WEEK_OF_YEAR) -> 9:int, VectorUDFDateAddColScalar(col 0:date, val 2) -> 10:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 11:date, VectorUDFDateDiffColScalar(col 0:date, val 2000-01-01) -> 12:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 13:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 14:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 15:int, VectorUDFDateDiffColScalar(col 0:date, val 2007-03-14) -> 16:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 17:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 18:int, VectorUDFDateDiffColSca
lar(col 0:date, val NULL) -> 19:int
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 47128 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 47128 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -849,7 +849,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: date_udf_flight_orc
- Statistics: Num rows: 137 Data size: 12672 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 13152 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -860,13 +860,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 0, 5, 6, 7, 8, 9, 10, 4, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24]
selectExpressions: LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 3:int, VectorUDFYearDate(col 0, field YEAR) -> 4:int) -> 5:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFMonthTimestamp(col 1:timestamp, field MONTH) -> 3:int, VectorUDFMonthDate(col 0, field MONTH) -> 4:int) -> 6:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 3:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 4:int) -> 7:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFDayOfMonthTimestamp(col 1:timestamp, field DAY_OF_MONTH) -> 3:int, VectorUDFDayOfMonthDate(col 0, field DAY_OF_MONTH) -> 4:int) -> 8:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFDayOfWeekTimestamp(col 1:timestamp, field DAY_OF_WEEK) -> 3:int, VectorUDFDayOfWeekDate(col 0, field DAY_OF_WEEK) -> 4
:int) -> 9:boolean, LongColEqualLongColumn(col 3:int, col 4:int)(children: VectorUDFWeekOfYearTimestamp(col 1:timestamp, field WEEK_OF_YEAR) -> 3:int, VectorUDFWeekOfYearDate(col 0, field WEEK_OF_YEAR) -> 4:int) -> 10:boolean, LongColEqualLongColumn(col 3:date, col 0:date)(children: CastTimestampToDate(col 1:timestamp) -> 3:date) -> 4:boolean, LongColEqualLongColumn(col 3:date, col 0:date)(children: VectorUDFDateTimestamp(col 1:timestamp) -> 3:date, col 0:date) -> 11:boolean, LongColEqualLongColumn(col 3:date, col 12:date)(children: VectorUDFDateAddColScalar(col 1:timestamp, val 2) -> 3:date, VectorUDFDateAddColScalar(col 0:date, val 2) -> 12:date) -> 13:boolean, LongColEqualLongColumn(col 3:date, col 12:date)(children: VectorUDFDateSubColScalar(col 1:timestamp, val 2) -> 3:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 12:date) -> 14:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val 2000-01-01) -> 3:int, VectorUD
FDateDiffColScalar(col 0:date, val 2000-01-01) -> 12:int) -> 15:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 16:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 17:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 18:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val 2007-03-14) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val 2007-03-14) -> 12:int) -> 19:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDat
eDiffColScalar(col 0:date, val NULL) -> 12:int) -> 20:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 21:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 1:timestamp, val NULL) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 22:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 0:date, val 2000-01-01) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 23:boolean, LongColEqualLongColumn(col 3:int, col 12:int)(children: VectorUDFDateDiffColScalar(col 0:date, val 2007-03-14) -> 3:int, VectorUDFDateDiffColScalar(col 0:date, val NULL) -> 12:int) -> 24:boolean
- Statistics: Num rows: 137 Data size: 12672 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 24112 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 137 Data size: 12672 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 24112 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1117,7 +1117,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: date_udf_flight_orc
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1128,19 +1128,19 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 6, 7, 9]
selectExpressions: VectorUDFDateAddColScalar(col 0:date, val 2) -> 3:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 4:date, VectorUDFDateDiffColCol(col 0:date, col 5:date)(children: VectorUDFDateAddColScalar(col 0:date, val 2) -> 5:date) -> 6:int, VectorUDFDateDiffColCol(col 0:date, col 5:date)(children: VectorUDFDateSubColScalar(col 0:date, val 2) -> 5:date) -> 7:int, VectorUDFDateDiffColCol(col 5:date, col 8:date)(children: VectorUDFDateAddColScalar(col 0:date, val 2) -> 5:date, VectorUDFDateSubColScalar(col 0:date, val 2) -> 8:date) -> 9:int
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 24660 Basic stats: COMPLETE Column stats: COMPLETE
Limit
Number of rows: 10
Limit Vectorization:
className: VectorLimitOperator
native: true
- Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 10 Data size: 530 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 10 Data size: 1800 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1244,7 +1244,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: date_udf_flight_orc
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1254,7 +1254,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 137 Data size: 7392 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 137 Data size: 7672 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(fl_date), max(fl_date), count(fl_date), count()
Group By Vectorization:
@@ -1266,14 +1266,14 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 128 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: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: date), _col1 (type: date), _col2 (type: bigint), _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1306,7 +1306,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -1314,7 +1314,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: date), _col2 (type: bigint), _col3 (type: bigint)
Reducer 3
Execution mode: vectorized, llap
@@ -1332,13 +1332,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/test_teradatabinaryfile.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/test_teradatabinaryfile.q.out b/ql/src/test/results/clientpositive/test_teradatabinaryfile.q.out
index 9db1372..a6ba774 100644
--- a/ql/src/test/results/clientpositive/test_teradatabinaryfile.q.out
+++ b/ql/src/test/results/clientpositive/test_teradatabinaryfile.q.out
@@ -444,7 +444,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"test_date\":\"true\",\"test_decimal\":\"true\",\"test_timestamp\":\"true\",\"test_tinyint\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 50
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMerger.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMerger.java b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMerger.java
index 3e0ce07..bcdb56d 100644
--- a/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMerger.java
+++ b/standalone-metastore/metastore-server/src/main/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMerger.java
@@ -19,23 +19,22 @@
package org.apache.hadoop.hive.metastore.columnstats.merge;
+import static org.apache.hadoop.hive.metastore.columnstats.ColumnsStatsUtils.dateInspectorFromStats;
+
import org.apache.hadoop.hive.common.ndv.NumDistinctValueEstimator;
import org.apache.hadoop.hive.metastore.api.ColumnStatisticsObj;
import org.apache.hadoop.hive.metastore.api.Date;
import org.apache.hadoop.hive.metastore.columnstats.cache.DateColumnStatsDataInspector;
-import static org.apache.hadoop.hive.metastore.columnstats.ColumnsStatsUtils.dateInspectorFromStats;
-
public class DateColumnStatsMerger extends ColumnStatsMerger {
@Override
public void merge(ColumnStatisticsObj aggregateColStats, ColumnStatisticsObj newColStats) {
DateColumnStatsDataInspector aggregateData = dateInspectorFromStats(aggregateColStats);
DateColumnStatsDataInspector newData = dateInspectorFromStats(newColStats);
- Date lowValue = aggregateData.getLowValue().compareTo(newData.getLowValue()) < 0 ? aggregateData
- .getLowValue() : newData.getLowValue();
+
+ Date lowValue = min(aggregateData.getLowValue(), newData.getLowValue());
aggregateData.setLowValue(lowValue);
- Date highValue = aggregateData.getHighValue().compareTo(newData.getHighValue()) >= 0 ? aggregateData
- .getHighValue() : newData.getHighValue();
+ Date highValue = max(aggregateData.getHighValue(), newData.getHighValue());
aggregateData.setHighValue(highValue);
aggregateData.setNumNulls(aggregateData.getNumNulls() + newData.getNumNulls());
if (aggregateData.getNdvEstimator() == null || newData.getNdvEstimator() == null) {
@@ -56,4 +55,26 @@ public class DateColumnStatsMerger extends ColumnStatsMerger {
aggregateData.setNumDVs(ndv);
}
}
+
+ private Date min(Date v1, Date v2) {
+ if (v1 == null || v2 == null) {
+ if (v1 != null) {
+ return v1;
+ } else {
+ return v2;
+ }
+ }
+ return v1.compareTo(v2) < 0 ? v1 : v2;
+ }
+
+ private Date max(Date v1, Date v2) {
+ if (v1 == null || v2 == null) {
+ if (v1 != null) {
+ return v1;
+ } else {
+ return v2;
+ }
+ }
+ return v1.compareTo(v2) > 0 ? v1 : v2;
+ }
}
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMergerTest.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMergerTest.java b/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMergerTest.java
new file mode 100644
index 0000000..e41339d
--- /dev/null
+++ b/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DateColumnStatsMergerTest.java
@@ -0,0 +1,108 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license agreements. See the NOTICE file
+ * distributed with this work for additional information
+ * regarding copyright ownership. The ASF licenses this file
+ * to you under the Apache License, Version 2.0 (the
+ * "License"); you may not use this file except in compliance
+ * with the License. You may obtain a copy of the License at
+ *
+ * http://www.apache.org/licenses/LICENSE-2.0
+ *
+ * Unless required by applicable law or agreed to in writing,
+ * software distributed under the License is distributed on an
+ * "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+ * KIND, either express or implied. See the License for the
+ * specific language governing permissions and limitations
+ * under the License.
+ */
+
+package org.apache.hadoop.hive.metastore.columnstats.merge;
+
+import org.apache.hadoop.hive.metastore.annotation.MetastoreUnitTest;
+import org.apache.hadoop.hive.metastore.api.ColumnStatisticsData;
+import org.apache.hadoop.hive.metastore.api.ColumnStatisticsObj;
+import org.apache.hadoop.hive.metastore.api.Date;
+import org.apache.hadoop.hive.metastore.columnstats.cache.DateColumnStatsDataInspector;
+import org.junit.Assert;
+import org.junit.Test;
+import org.junit.experimental.categories.Category;
+
+@Category(MetastoreUnitTest.class)
+public class DateColumnStatsMergerTest {
+
+ private static final Date DATE_1 = new Date(1);
+ private static final Date DATE_2 = new Date(2);
+ private static final Date DATE_3 = new Date(3);
+
+ private ColumnStatsMerger merger = new DateColumnStatsMerger();
+
+ @Test
+ public void testMergeNullMinMaxValues() {
+ ColumnStatisticsObj old = new ColumnStatisticsObj();
+ createData(old, null, null);
+
+ merger.merge(old, old);
+
+ Assert.assertNull(old.getStatsData().getDateStats().getLowValue());
+ Assert.assertNull(old.getStatsData().getDateStats().getHighValue());
+ }
+
+ @Test
+ public void testMergeNulls() {
+ ColumnStatisticsObj oldObj = new ColumnStatisticsObj();
+ createData(oldObj, null, null);
+
+ ColumnStatisticsObj newObj;
+
+ newObj = new ColumnStatisticsObj();
+ createData(newObj, null, null);
+ merger.merge(oldObj, newObj);
+
+ Assert.assertEquals(null, oldObj.getStatsData().getDateStats().getLowValue());
+ Assert.assertEquals(null, oldObj.getStatsData().getDateStats().getHighValue());
+
+ newObj = new ColumnStatisticsObj();
+ createData(newObj, DATE_1, DATE_3);
+ merger.merge(oldObj, newObj);
+
+ newObj = new ColumnStatisticsObj();
+ createData(newObj, null, null);
+ merger.merge(oldObj, newObj);
+
+ Assert.assertEquals(DATE_1, oldObj.getStatsData().getDateStats().getLowValue());
+ Assert.assertEquals(DATE_3, oldObj.getStatsData().getDateStats().getHighValue());
+ }
+
+ @Test
+ public void testMergeNonNullAndNullLowerValuesNewIsNull() {
+ ColumnStatisticsObj oldObj = new ColumnStatisticsObj();
+ createData(oldObj, DATE_2, DATE_2);
+
+ ColumnStatisticsObj newObj;
+
+ newObj = new ColumnStatisticsObj();
+ createData(newObj, DATE_3, DATE_3);
+ merger.merge(oldObj, newObj);
+
+ newObj = new ColumnStatisticsObj();
+ createData(newObj, DATE_1, DATE_1);
+ merger.merge(oldObj, newObj);
+
+ Assert.assertEquals(DATE_1, oldObj.getStatsData().getDateStats().getLowValue());
+ Assert.assertEquals(DATE_3, oldObj.getStatsData().getDateStats().getHighValue());
+ }
+
+ private DateColumnStatsDataInspector createData(ColumnStatisticsObj objNulls, Date lowValue,
+ Date highValue) {
+ ColumnStatisticsData statisticsData = new ColumnStatisticsData();
+ DateColumnStatsDataInspector data = new DateColumnStatsDataInspector();
+
+ statisticsData.setDateStats(data);
+ objNulls.setStatsData(statisticsData);
+
+ data.setLowValue(lowValue);
+ data.setHighValue(highValue);
+ return data;
+ }
+}
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DecimalColumnStatsMergerTest.java
----------------------------------------------------------------------
diff --git a/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DecimalColumnStatsMergerTest.java b/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DecimalColumnStatsMergerTest.java
index 8ec3a2f..ca0a6c0 100644
--- a/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DecimalColumnStatsMergerTest.java
+++ b/standalone-metastore/metastore-server/src/test/java/org/apache/hadoop/hive/metastore/columnstats/merge/DecimalColumnStatsMergerTest.java
@@ -19,8 +19,6 @@
package org.apache.hadoop.hive.metastore.columnstats.merge;
-import java.nio.ByteBuffer;
-
import org.apache.hadoop.hive.metastore.annotation.MetastoreUnitTest;
import org.apache.hadoop.hive.metastore.api.ColumnStatisticsData;
import org.apache.hadoop.hive.metastore.api.ColumnStatisticsObj;
[2/6] hive git commit: HIVE-20498: Support date type for column stats
autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Posted by kg...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out
index a74023f..0c47829 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_2.q.out
@@ -126,7 +126,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_2
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -137,7 +137,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 9, 10, 11, 12, 13, 14, 15, 16, 8, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31]
selectExpressions: LongColEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:boolean, LongColLessEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 10:boolean, LongColLessEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month) -> 11:boolean, LongColLessLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_mo
nth) -> 12:boolean, LongColGreaterEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 13:boolean, LongColGreaterEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 14:boolean, LongColGreaterLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 15:boolean, LongColNotEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month) -> 16
:boolean, IntervalYearMonthColEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:boolean, IntervalYearMonthColLessEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 17:boolean, IntervalYearMonthColLessEqualIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 18:boolean, IntervalYearMonthColLessIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 19:boolean, IntervalYearMonthColGreaterEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 20:boolean, IntervalYearMonthColGreaterEqualIntervalYearMonthScalar(col 7:interval_year_mon
th, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 21:boolean, IntervalYearMonthColGreaterIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 22:boolean, IntervalYearMonthColNotEqualIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 23:boolean, IntervalYearMonthScalarEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 24:boolean, IntervalYearMonthScalarLessEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 25:boolean, IntervalYearMonthScalarLessEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_
year_month) -> 26:boolean, IntervalYearMonthScalarLessIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 27:boolean, IntervalYearMonthScalarGreaterEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 28:boolean, IntervalYearMonthScalarGreaterEqualIntervalYearMonthColumn(val 15, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 29:boolean, IntervalYearMonthScalarGreaterIntervalYearMonthColumn(val 15, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 30:boolean, IntervalYearMonthScalarNotEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 31:boolean
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -145,7 +145,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col19 (type: boolean), _col20 (type: boolean), _col21 (type: boolean), _col22 (type: boolean), _col23 (type: boolean), _col24 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -174,13 +174,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24]
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -332,7 +332,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_2
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 348 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -343,7 +343,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 9, 10, 11, 12, 13, 8, 14, 15, 16, 17, 18, 19, 20, 21, 22]
selectExpressions: LongColNotEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:boolean, LongColGreaterEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month) -> 10:boolean, LongColGreaterLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month) -> 11:boolean, LongColLessEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interva
l_year_month) -> 12:boolean, LongColLessLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 13:boolean, IntervalYearMonthColNotEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:boolean, IntervalYearMonthColGreaterEqualIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 14:boolean, IntervalYearMonthColGreaterIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 15:boolean, IntervalYearMonthColLessEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 16:boole
an, IntervalYearMonthColLessIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 17:boolean, IntervalYearMonthScalarNotEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 18:boolean, IntervalYearMonthScalarGreaterEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 19:boolean, IntervalYearMonthScalarGreaterIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month) -> 20:boolean, IntervalYearMonthScalarLessEqualIntervalYearMonthColumn(val 15, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 21:boolean, IntervalYearMonthScalarLessIntervalYearMonthColumn(val 15, col 7:interv
al_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 22:boolean
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 318 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -351,7 +351,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 318 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -380,13 +380,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 1, 6, 7, 8, 9, 10, 6, 11, 12, 13, 14, 15, 11]
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 318 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 318 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -538,7 +538,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_2
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -549,7 +549,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32]
selectExpressions: IntervalDayTimeColEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 9:boolean, IntervalDayTimeColLessEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 10:boolean, IntervalDayTimeColLessEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time) -> 11:boolean, IntervalDayTimeColLessIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalD
ayTime(col 5:string) -> 8:interval_day_time) -> 12:boolean, IntervalDayTimeColGreaterEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 13:boolean, IntervalDayTimeColGreaterEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 14:boolean, IntervalDayTimeColGreaterIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 15:boolean, IntervalDayTimeColNotEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_d
ay_time, CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time) -> 16:boolean, IntervalDayTimeColEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 17:boolean, IntervalDayTimeColLessEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 18:boolean, IntervalDayTimeColLessEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 19:boolean, IntervalDayTimeColLessIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 20:boolean, IntervalDayTimeColGreaterEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:strin
g) -> 7:interval_day_time) -> 21:boolean, IntervalDayTimeColGreaterEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 22:boolean, IntervalDayTimeColGreaterIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 23:boolean, IntervalDayTimeColNotEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 24:boolean, IntervalDayTimeScalarEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 25:boolean, IntervalDayTimeScalarLessEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 26:boolean
, IntervalDayTimeScalarLessEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 27:boolean, IntervalDayTimeScalarLessIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 28:boolean, IntervalDayTimeScalarGreaterEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 29:boolean, IntervalDayTimeScalarGreaterEqualIntervalDayTimeColumn(val 1 02:03:05.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 30:boolean, IntervalDayTimeScalarGreaterIntervalDayTimeColumn(val 1 02:03:05.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 31:boolean, IntervalDayTimeScalarNotEq
ualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 32:boolean
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 374 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -557,7 +557,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 374 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean), _col18 (type: boolean), _col19 (type: boolean), _col20 (type: boolean), _col21 (type: boolean), _col22 (type: boolean), _col23 (type: boolean), _col24 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -586,13 +586,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24]
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 374 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 374 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -744,7 +744,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_2
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 364 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -755,7 +755,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [4, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23]
selectExpressions: IntervalDayTimeColNotEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 9:boolean, IntervalDayTimeColGreaterEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time) -> 10:boolean, IntervalDayTimeColGreaterIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time) -> 11:boolean, IntervalDayTimeColLessEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time, CastStringTo
IntervalDayTime(col 4:string) -> 8:interval_day_time) -> 12:boolean, IntervalDayTimeColLessIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time) -> 13:boolean, IntervalDayTimeColNotEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 14:boolean, IntervalDayTimeColGreaterEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 15:boolean, IntervalDayTimeColGreaterIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 16:boolean, IntervalDayTimeColLessEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(chil
dren: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 17:boolean, IntervalDayTimeColLessIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 18:boolean, IntervalDayTimeScalarNotEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 19:boolean, IntervalDayTimeScalarGreaterEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 20:boolean, IntervalDayTimeScalarGreaterIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time) -> 21:boolean, IntervalDayTimeScalarLessEqualIntervalDayTimeColumn(val 1 02:03:05.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(c
ol 4:string) -> 7:interval_day_time) -> 22:boolean, IntervalDayTimeScalarLessIntervalDayTimeColumn(val 1 02:03:05.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time) -> 23:boolean
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -763,7 +763,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col15 (type: boolean), _col16 (type: boolean), _col17 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -792,13 +792,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 1, 6, 7, 8, 9, 10, 6, 11, 12, 13, 14, 15, 11]
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 326 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -937,7 +937,7 @@ STAGE PLANS:
TableScan
alias: vector_interval_2
filterExpr: ((CAST( str1 AS INTERVAL YEAR TO MONTH) = CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) = INTERVAL'1-2') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> INTERVAL'1-3') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= INTERVAL'1-3') and (CAST( str1 AS INTERVAL YEAR TO MONTH) < INTERVAL'1-3') and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= INTERVAL'1-2') and (CAST( str2 AS INTERVAL YEAR TO MONTH) > INTERVAL'1-2') and (INTERVAL'1-2' = CAST( str1 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-2' <> CAST( str2 AS INTE
RVAL YEAR TO MONTH)) and (INTERVAL'1-2' <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-2' < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-3' >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-3' > CAST( str1 AS INTERVAL YEAR TO MONTH))) (type: boolean)
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 428 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -946,7 +946,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month), FilterLongColNotEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month), FilterLongColLessEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:interval_year_month), FilterLongColLessLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 3:string) -> 8:inte
rval_year_month), FilterLongColGreaterEqualLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month), FilterLongColGreaterLongColumn(col 7:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month), FilterIntervalYearMonthColEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month), FilterIntervalYearMonthColNotEqualIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month), FilterIntervalYearMonthColLessEqualIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:inte
rval_year_month), FilterIntervalYearMonthColLessIntervalYearMonthScalar(col 7:interval_year_month, val 15)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month), FilterIntervalYearMonthColGreaterEqualIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month), FilterIntervalYearMonthColGreaterIntervalYearMonthScalar(col 7:interval_year_month, val 14)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month), FilterIntervalYearMonthScalarEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month), FilterIntervalYearMonthScalarNotEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month), FilterIntervalYearMonthScalarLessEqualIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children:
CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month), FilterIntervalYearMonthScalarLessIntervalYearMonthColumn(val 14, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 3:string) -> 7:interval_year_month), FilterIntervalYearMonthScalarGreaterEqualIntervalYearMonthColumn(val 15, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month), FilterIntervalYearMonthScalarGreaterIntervalYearMonthColumn(val 15, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month))
predicate: ((CAST( str1 AS INTERVAL YEAR TO MONTH) < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) < INTERVAL'1-3') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) <= INTERVAL'1-3') and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> CAST( str2 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) <> INTERVAL'1-3') and (CAST( str1 AS INTERVAL YEAR TO MONTH) = CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str1 AS INTERVAL YEAR TO MONTH) = INTERVAL'1-2') and (CAST( str2 AS INTERVAL YEAR TO MONTH) > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) > INTERVAL'1-2') and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= CAST( str1 AS INTERVAL YEAR TO MONTH)) and (CAST( str2 AS INTERVAL YEAR TO MONTH) >= INTERVAL'1-2') and (INTERVAL'1-2' < CAST( str2 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-2' <= CAST( str2 AS INT
ERVAL YEAR TO MONTH)) and (INTERVAL'1-2' <> CAST( str2 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-2' = CAST( str1 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-3' > CAST( str1 AS INTERVAL YEAR TO MONTH)) and (INTERVAL'1-3' >= CAST( str1 AS INTERVAL YEAR TO MONTH))) (type: boolean)
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 214 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ts (type: timestamp)
outputColumnNames: _col0
@@ -954,7 +954,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -962,7 +962,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -990,13 +990,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1132,7 +1132,7 @@ STAGE PLANS:
TableScan
alias: vector_interval_2
filterExpr: ((CAST( str3 AS INTERVAL DAY TO SECOND) = CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) = INTERVAL'1 02:03:04.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <> INTERVAL'1 02:03:05.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <= INTERVAL'1 02:03:05.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) < INTERVAL'1 02:03:05.000000000') and (CAST( str4 AS INTERVAL DAY TO SECOND) >= INTERVAL'1 02:03:04.000000000') and (CAST( str4 AS INTERVAL DAY TO SECOND) > INTERVAL'1 02:03:04.000000000'
) and (INTERVAL'1 02:03:04.000000000' = CAST( str3 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:04.000000000' <> CAST( str4 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:04.000000000' <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:04.000000000' < CAST( str4 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:05.000000000' >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:05.000000000' > CAST( str3 AS INTERVAL DAY TO SECOND))) (type: boolean)
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 444 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1141,7 +1141,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterIntervalDayTimeColEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time), FilterIntervalDayTimeColNotEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time), FilterIntervalDayTimeColLessEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 5:string) -> 8:interval_day_time), FilterIntervalDayTimeColLessIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time, CastStrin
gToIntervalDayTime(col 5:string) -> 8:interval_day_time), FilterIntervalDayTimeColGreaterEqualIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time), FilterIntervalDayTimeColGreaterIntervalDayTimeColumn(col 7:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time, CastStringToIntervalDayTime(col 4:string) -> 8:interval_day_time), FilterIntervalDayTimeColEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time), FilterIntervalDayTimeColNotEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time), FilterIntervalDayTimeColLessEqualIntervalDayTimeScalar(col 7:interval_day_time, v
al 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time), FilterIntervalDayTimeColLessIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:05.000000000)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time), FilterIntervalDayTimeColGreaterEqualIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time), FilterIntervalDayTimeColGreaterIntervalDayTimeScalar(col 7:interval_day_time, val 1 02:03:04.000000000)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time), FilterIntervalDayTimeScalarEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time), FilterIntervalDayTimeScalarNotEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:int
erval_day_time), FilterIntervalDayTimeScalarLessEqualIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time), FilterIntervalDayTimeScalarLessIntervalDayTimeColumn(val 1 02:03:04.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 5:string) -> 7:interval_day_time), FilterIntervalDayTimeScalarGreaterEqualIntervalDayTimeColumn(val 1 02:03:05.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time), FilterIntervalDayTimeScalarGreaterIntervalDayTimeColumn(val 1 02:03:05.000000000, col 7:interval_day_time)(children: CastStringToIntervalDayTime(col 4:string) -> 7:interval_day_time))
predicate: ((CAST( str3 AS INTERVAL DAY TO SECOND) < CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) < INTERVAL'1 02:03:05.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) <= INTERVAL'1 02:03:05.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) <> CAST( str4 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) <> INTERVAL'1 02:03:05.000000000') and (CAST( str3 AS INTERVAL DAY TO SECOND) = CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str3 AS INTERVAL DAY TO SECOND) = INTERVAL'1 02:03:04.000000000') and (CAST( str4 AS INTERVAL DAY TO SECOND) > CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) > INTERVAL'1 02:03:04.000000000') and (CAST( str4 AS INTERVAL DAY TO SECOND) >= CAST( str3 AS INTERVAL DAY TO SECOND)) and (CAST( str4 AS INTERVAL DAY TO SECOND) >= INTERVAL'1 02:03:04.000000000
') and (INTERVAL'1 02:03:04.000000000' < CAST( str4 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:04.000000000' <= CAST( str4 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:04.000000000' <> CAST( str4 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:04.000000000' = CAST( str3 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:05.000000000' > CAST( str3 AS INTERVAL DAY TO SECOND)) and (INTERVAL'1 02:03:05.000000000' >= CAST( str3 AS INTERVAL DAY TO SECOND))) (type: boolean)
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 222 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ts (type: timestamp)
outputColumnNames: _col0
@@ -1149,7 +1149,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1157,7 +1157,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1185,13 +1185,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 408 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1317,7 +1317,7 @@ STAGE PLANS:
TableScan
alias: vector_interval_2
filterExpr: ((DATE'2002-03-01' = (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' <= (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' >= (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and ((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) = DATE'2002-03-01') and ((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) <= DATE'2002-03-01') and ((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) >= DATE'2002-03-01') and (dt <> (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' = (dt + INTERVAL'1-2')) and (DATE'2002-03-01' <= (dt + INTERVAL'1-2')) and (DATE'2002-03-01' >= (dt + INTERVAL'1-2')) and ((dt + INTERVAL'1-2') = DATE'2002-03-01') and ((dt + INTERVAL'1-2') <= DATE'2002-03-01') and ((dt + INTERVAL'1-2') >= DATE'2002-03-01') and (dt <> (dt + INTERVAL'1-2'))) (type: boolean)
- Statistics: Num rows: 2 Data size: 560 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1326,7 +1326,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDateScalarEqualDateColumn(val 11747, col 8:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:date), FilterDateScalarLessEqualDateColumn(val 11747, col 8:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:date), FilterDateScalarGreaterEqualDateColumn(val 11747, col 8:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:date), FilterDateColEqualDateScalar(col 8:date, val 11747)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:dat
e), FilterDateColLessEqualDateScalar(col 8:date, val 11747)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:date), FilterDateColGreaterEqualDateScalar(col 8:date, val 11747)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:date), FilterLongColNotEqualLongColumn(col 1:date, col 8:date)(children: DateColAddIntervalYearMonthColumn(col 1:date, col 7:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 7:interval_year_month) -> 8:date), FilterDateScalarEqualDateColumn(val 11747, col 7:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date), FilterDateScalarLessEqualDateColumn(val 11747, col 7:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date), FilterDateScalarGreaterEqualD
ateColumn(val 11747, col 7:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date), FilterDateColEqualDateScalar(col 7:date, val 11747)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date), FilterDateColLessEqualDateScalar(col 7:date, val 11747)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date), FilterDateColGreaterEqualDateScalar(col 7:date, val 11747)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date), FilterLongColNotEqualLongColumn(col 1:date, col 7:date)(children: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 7:date))
predicate: (((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) <= DATE'2002-03-01') and ((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) = DATE'2002-03-01') and ((dt + CAST( str1 AS INTERVAL YEAR TO MONTH)) >= DATE'2002-03-01') and ((dt + INTERVAL'1-2') <= DATE'2002-03-01') and ((dt + INTERVAL'1-2') = DATE'2002-03-01') and ((dt + INTERVAL'1-2') >= DATE'2002-03-01') and (DATE'2002-03-01' <= (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' <= (dt + INTERVAL'1-2')) and (DATE'2002-03-01' = (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' = (dt + INTERVAL'1-2')) and (DATE'2002-03-01' >= (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (DATE'2002-03-01' >= (dt + INTERVAL'1-2')) and (dt <> (dt + CAST( str1 AS INTERVAL YEAR TO MONTH))) and (dt <> (dt + INTERVAL'1-2'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ts (type: timestamp)
outputColumnNames: _col0
@@ -1334,7 +1334,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1342,7 +1342,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1370,13 +1370,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 280 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1502,7 +1502,7 @@ STAGE PLANS:
TableScan
alias: vector_interval_2
filterExpr: ((TIMESTAMP'2002-03-01 01:02:03' = (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-03-01 01:02:03' <= (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-03-01 01:02:03' >= (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-04-01 01:02:03' <> (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-02-01 01:02:03' < (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-04-01 01:02:03' > (ts + INTERVAL'1-2')) and ((ts + INTERVAL'1-2') = TIMESTAMP'2002-03-01 01:02:03') and ((ts + INTERVAL'1-2') >= TIMESTAMP'2002-03-01 01:02:03') and ((ts + INTERVAL'1-2') <= TIMESTAMP'2002-03-01 01:02:03') and ((ts + INTERVAL'1-2') <> TIMESTAMP'2002-04-01 01:02:03') and ((ts + INTERVAL'1-2') > TIMESTAMP'2002-02-01 01:02:03') and ((ts + INTERVAL'1-2') < TIMESTAMP'2002-04-01 01:02:03') and (ts = (ts + INTERVAL'0-0')) and (ts <> (ts + INTERVAL'1-0')) and (ts <= (ts + INTERVAL'1-0')) and (ts < (ts + INTERVAL'1-0')) and (ts >= (ts - INTERVAL'1-0')) and (ts > (ts - INTERVAL'1-0'))) (type: boolean)
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1511,7 +1511,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterTimestampScalarEqualTimestampColumn(val 2002-03-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampScalarLessEqualTimestampColumn(val 2002-03-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampScalarGreaterEqualTimestampColumn(val 2002-03-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampScalarNotEqualTimestampColumn(val 2002-04-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampScalarLessTimestampColumn(val 2002-02-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampScalarGreaterTim
estampColumn(val 2002-04-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampColEqualTimestampScalar(col 7:timestamp, val 2002-03-01 01:02:03)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampColGreaterEqualTimestampScalar(col 7:timestamp, val 2002-03-01 01:02:03)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampColLessEqualTimestampScalar(col 7:timestamp, val 2002-03-01 01:02:03)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampColNotEqualTimestampScalar(col 7:timestamp, val 2002-04-01 01:02:03)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampColGreaterTimestampScalar(col 7:timestamp, val 2002-02-01 01:02:03)(children: TimestampColAddIntervalYearMonthScalar(col 0:timest
amp, val 1-2) -> 7:timestamp), FilterTimestampColLessTimestampScalar(col 7:timestamp, val 2002-04-01 01:02:03)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 7:timestamp), FilterTimestampColEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 0-0) -> 7:timestamp), FilterTimestampColNotEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-0) -> 7:timestamp), FilterTimestampColLessEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-0) -> 7:timestamp), FilterTimestampColLessTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-0) -> 7:timestamp), FilterTimestampColGreaterEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColSubtractIntervalYearMonthS
calar(col 0:timestamp, val 1-0) -> 7:timestamp), FilterTimestampColGreaterTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColSubtractIntervalYearMonthScalar(col 0:timestamp, val 1-0) -> 7:timestamp))
predicate: (((ts + INTERVAL'1-2') < TIMESTAMP'2002-04-01 01:02:03') and ((ts + INTERVAL'1-2') <= TIMESTAMP'2002-03-01 01:02:03') and ((ts + INTERVAL'1-2') <> TIMESTAMP'2002-04-01 01:02:03') and ((ts + INTERVAL'1-2') = TIMESTAMP'2002-03-01 01:02:03') and ((ts + INTERVAL'1-2') > TIMESTAMP'2002-02-01 01:02:03') and ((ts + INTERVAL'1-2') >= TIMESTAMP'2002-03-01 01:02:03') and (TIMESTAMP'2002-02-01 01:02:03' < (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-03-01 01:02:03' <= (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-03-01 01:02:03' = (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-03-01 01:02:03' >= (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-04-01 01:02:03' <> (ts + INTERVAL'1-2')) and (TIMESTAMP'2002-04-01 01:02:03' > (ts + INTERVAL'1-2')) and (ts < (ts + INTERVAL'1-0')) and (ts <= (ts + INTERVAL'1-0')) and (ts <> (ts + INTERVAL'1-0')) and (ts = (ts + INTERVAL'0-0')) and (ts > (ts - INTERVAL'1-0')) and (ts >= (ts - INTERVAL'1-0'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ts (type: timestamp)
outputColumnNames: _col0
@@ -1519,7 +1519,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1527,7 +1527,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1555,13 +1555,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1697,7 +1697,7 @@ STAGE PLANS:
TableScan
alias: vector_interval_2
filterExpr: ((TIMESTAMP'2001-01-01 01:02:03' = (dt + INTERVAL'0 01:02:03.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <> (dt + INTERVAL'0 01:02:04.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <= (dt + INTERVAL'0 01:02:03.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' < (dt + INTERVAL'0 01:02:04.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' >= (dt - INTERVAL'0 01:02:03.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' > (dt - INTERVAL'0 01:02:04.000000000')) and ((dt + INTERVAL'0 01:02:03.000000000') = TIMESTAMP'2001-01-01 01:02:03') and ((dt + INTERVAL'0 01:02:04.000000000') <> TIMESTAMP'2001-01-01 01:02:03') and ((dt + INTERVAL'0 01:02:03.000000000') >= TIMESTAMP'2001-01-01 01:02:03') and ((dt + INTERVAL'0 01:02:04.000000000') > TIMESTAMP'2001-01-01 01:02:03') and ((dt - INTERVAL'0 01:02:03.000000000') <= TIMESTAMP'2001-01-01 01:02:03') and ((dt - INTERVAL'0 01:02:04.000000000') < TIMESTAMP'2001-01-01 01:02:03') and (ts = (dt + INTERVAL'0 01:02:03.0000
00000')) and (ts <> (dt + INTERVAL'0 01:02:04.000000000')) and (ts <= (dt + INTERVAL'0 01:02:03.000000000')) and (ts < (dt + INTERVAL'0 01:02:04.000000000')) and (ts >= (dt - INTERVAL'0 01:02:03.000000000')) and (ts > (dt - INTERVAL'0 01:02:04.000000000'))) (type: boolean)
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1706,7 +1706,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterTimestampScalarEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampScalarNotEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampScalarLessEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampScalarLessTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampScalarGreaterEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: DateColSubtractIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), F
ilterTimestampScalarGreaterTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: DateColSubtractIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampColEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampColNotEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampColGreaterEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampColGreaterTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampColLessEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(c
hildren: DateColSubtractIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampColLessTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: DateColSubtractIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampColEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampColNotEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampColLessEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampColLessTimestampColumn(col 0:timestamp, col 7:timestamp)(children: DateColAddIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp), FilterTimestampColGreaterEqu
alTimestampColumn(col 0:timestamp, col 7:timestamp)(children: DateColSubtractIntervalDayTimeScalar(col 1:date, val 0 01:02:03.000000000) -> 7:timestamp), FilterTimestampColGreaterTimestampColumn(col 0:timestamp, col 7:timestamp)(children: DateColSubtractIntervalDayTimeScalar(col 1:date, val 0 01:02:04.000000000) -> 7:timestamp))
predicate: (((dt + INTERVAL'0 01:02:03.000000000') = TIMESTAMP'2001-01-01 01:02:03') and ((dt + INTERVAL'0 01:02:03.000000000') >= TIMESTAMP'2001-01-01 01:02:03') and ((dt + INTERVAL'0 01:02:04.000000000') <> TIMESTAMP'2001-01-01 01:02:03') and ((dt + INTERVAL'0 01:02:04.000000000') > TIMESTAMP'2001-01-01 01:02:03') and ((dt - INTERVAL'0 01:02:03.000000000') <= TIMESTAMP'2001-01-01 01:02:03') and ((dt - INTERVAL'0 01:02:04.000000000') < TIMESTAMP'2001-01-01 01:02:03') and (TIMESTAMP'2001-01-01 01:02:03' < (dt + INTERVAL'0 01:02:04.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <= (dt + INTERVAL'0 01:02:03.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <> (dt + INTERVAL'0 01:02:04.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' = (dt + INTERVAL'0 01:02:03.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' > (dt - INTERVAL'0 01:02:04.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' >= (dt - INTERVAL'0 01:02:03.000000000')) and (ts < (dt + INTERVAL'0 01:02:04.000
000000')) and (ts <= (dt + INTERVAL'0 01:02:03.000000000')) and (ts <> (dt + INTERVAL'0 01:02:04.000000000')) and (ts = (dt + INTERVAL'0 01:02:03.000000000')) and (ts > (dt - INTERVAL'0 01:02:04.000000000')) and (ts >= (dt - INTERVAL'0 01:02:03.000000000'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ts (type: timestamp)
outputColumnNames: _col0
@@ -1714,7 +1714,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1722,7 +1722,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1750,13 +1750,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1892,7 +1892,7 @@ STAGE PLANS:
TableScan
alias: vector_interval_2
filterExpr: ((TIMESTAMP'2001-01-01 01:02:03' = (ts + INTERVAL'0 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <> (ts + INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <= (ts + INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' < (ts + INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' >= (ts - INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' > (ts - INTERVAL'1 00:00:00.000000000')) and ((ts + INTERVAL'0 00:00:00.000000000') = TIMESTAMP'2001-01-01 01:02:03') and ((ts + INTERVAL'1 00:00:00.000000000') <> TIMESTAMP'2001-01-01 01:02:03') and ((ts + INTERVAL'1 00:00:00.000000000') >= TIMESTAMP'2001-01-01 01:02:03') and ((ts + INTERVAL'1 00:00:00.000000000') > TIMESTAMP'2001-01-01 01:02:03') and ((ts - INTERVAL'1 00:00:00.000000000') <= TIMESTAMP'2001-01-01 01:02:03') and ((ts - INTERVAL'1 00:00:00.000000000') < TIMESTAMP'2001-01-01 01:02:03') and (ts = (ts + INTERVAL'0 00:00:00.0000
00000')) and (ts <> (ts + INTERVAL'1 00:00:00.000000000')) and (ts <= (ts + INTERVAL'1 00:00:00.000000000')) and (ts < (ts + INTERVAL'1 00:00:00.000000000')) and (ts >= (ts - INTERVAL'1 00:00:00.000000000')) and (ts > (ts - INTERVAL'1 00:00:00.000000000'))) (type: boolean)
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Filter Operator
@@ -1901,7 +1901,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterTimestampScalarEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 0 00:00:00.000000000) -> 7:timestamp), FilterTimestampScalarNotEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampScalarLessEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampScalarLessTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampScalarGreaterEqualTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: TimestampColSubtractIntervalDayTimeScalar(col 0:times
tamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampScalarGreaterTimestampColumn(val 2001-01-01 01:02:03, col 7:timestamp)(children: TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 0 00:00:00.000000000) -> 7:timestamp), FilterTimestampColNotEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColGreaterEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColGreaterTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) ->
7:timestamp), FilterTimestampColLessEqualTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColLessTimestampScalar(col 7:timestamp, val 2001-01-01 01:02:03)(children: TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 0 00:00:00.000000000) -> 7:timestamp), FilterTimestampColNotEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColLessEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColLessTimestampColumn(col 0:tim
estamp, col 7:timestamp)(children: TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColGreaterEqualTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp), FilterTimestampColGreaterTimestampColumn(col 0:timestamp, col 7:timestamp)(children: TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 00:00:00.000000000) -> 7:timestamp))
predicate: (((ts + INTERVAL'0 00:00:00.000000000') = TIMESTAMP'2001-01-01 01:02:03') and ((ts + INTERVAL'1 00:00:00.000000000') <> TIMESTAMP'2001-01-01 01:02:03') and ((ts + INTERVAL'1 00:00:00.000000000') > TIMESTAMP'2001-01-01 01:02:03') and ((ts + INTERVAL'1 00:00:00.000000000') >= TIMESTAMP'2001-01-01 01:02:03') and ((ts - INTERVAL'1 00:00:00.000000000') < TIMESTAMP'2001-01-01 01:02:03') and ((ts - INTERVAL'1 00:00:00.000000000') <= TIMESTAMP'2001-01-01 01:02:03') and (TIMESTAMP'2001-01-01 01:02:03' < (ts + INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <= (ts + INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' <> (ts + INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' = (ts + INTERVAL'0 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' > (ts - INTERVAL'1 00:00:00.000000000')) and (TIMESTAMP'2001-01-01 01:02:03' >= (ts - INTERVAL'1 00:00:00.000000000')) and (ts < (ts + INTERVAL'1 00:00:00.000
000000')) and (ts <= (ts + INTERVAL'1 00:00:00.000000000')) and (ts <> (ts + INTERVAL'1 00:00:00.000000000')) and (ts = (ts + INTERVAL'0 00:00:00.000000000')) and (ts > (ts - INTERVAL'1 00:00:00.000000000')) and (ts >= (ts - INTERVAL'1 00:00:00.000000000'))) (type: boolean)
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ts (type: timestamp)
outputColumnNames: _col0
@@ -1909,7 +1909,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -1917,7 +1917,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -1945,13 +1945,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[6/6] hive git commit: HIVE-20498: Support date type for column stats
autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Posted by kg...@apache.org.
HIVE-20498: Support date type for column stats autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Signed-off-by: Zoltan Haindrich <ki...@rxd.hu>
Project: http://git-wip-us.apache.org/repos/asf/hive/repo
Commit: http://git-wip-us.apache.org/repos/asf/hive/commit/9b376a7b
Tree: http://git-wip-us.apache.org/repos/asf/hive/tree/9b376a7b
Diff: http://git-wip-us.apache.org/repos/asf/hive/diff/9b376a7b
Branch: refs/heads/master
Commit: 9b376a7b040f99aa9f894343537584d19ab45056
Parents: ee5566b
Author: Zoltan Haindrich <ki...@rxd.hu>
Authored: Thu Sep 20 08:14:29 2018 +0200
Committer: Zoltan Haindrich <ki...@rxd.hu>
Committed: Thu Sep 20 08:15:34 2018 +0200
----------------------------------------------------------------------
.../ql/parse/ColumnStatsAutoGatherContext.java | 2 +-
.../queries/clientpositive/autoColumnStats_11.q | 28 ++
.../alter_table_update_status.q.out | 358 +++++++++---------
..._table_update_status_disable_bitvector.q.out | 288 +++++++--------
.../clientpositive/autoColumnStats_11.q.out | 362 +++++++++++++++++++
.../results/clientpositive/constprog_type.q.out | 31 +-
.../extrapolate_part_stats_date.q.out | 2 +-
.../clientpositive/llap/orc_llap_counters.q.out | 2 +-
.../llap/orc_llap_counters1.q.out | 2 +-
.../clientpositive/llap/orc_ppd_date.q.out | 28 +-
.../llap/schema_evol_orc_nonvec_part.q.out | 6 +-
...ema_evol_orc_nonvec_part_all_primitive.q.out | 6 +-
..._orc_nonvec_part_all_primitive_llap_io.q.out | 6 +-
.../schema_evol_orc_nonvec_part_llap_io.q.out | 6 +-
.../llap/schema_evol_orc_vec_part.q.out | 6 +-
...schema_evol_orc_vec_part_all_primitive.q.out | 6 +-
...vol_orc_vec_part_all_primitive_llap_io.q.out | 6 +-
.../llap/schema_evol_text_nonvec_part.q.out | 6 +-
...ma_evol_text_nonvec_part_all_primitive.q.out | 6 +-
...text_nonvec_part_all_primitive_llap_io.q.out | 12 +-
.../schema_evol_text_nonvec_part_llap_io.q.out | 6 +-
.../llap/schema_evol_text_vec_part.q.out | 6 +-
...chema_evol_text_vec_part_all_primitive.q.out | 6 +-
...ol_text_vec_part_all_primitive_llap_io.q.out | 12 +-
.../schema_evol_text_vec_part_llap_io.q.out | 6 +-
.../schema_evol_text_vec_table_llap_io.q.out | 6 +-
.../llap/schema_evol_text_vecrow_part.q.out | 6 +-
...ma_evol_text_vecrow_part_all_primitive.q.out | 6 +-
...text_vecrow_part_all_primitive_llap_io.q.out | 12 +-
.../schema_evol_text_vecrow_part_llap_io.q.out | 12 +-
.../schema_evol_text_vecrow_table_llap_io.q.out | 12 +-
.../clientpositive/llap/subquery_scalar.q.out | 68 ++--
.../llap/vector_aggregate_9.q.out | 42 +--
.../llap/vector_case_when_2.q.out | 30 +-
.../clientpositive/llap/vector_date_1.q.out | 68 ++--
.../clientpositive/llap/vector_distinct_2.q.out | 14 +-
.../clientpositive/llap/vector_groupby_3.q.out | 14 +-
.../clientpositive/llap/vector_interval_1.q.out | 80 ++--
.../clientpositive/llap/vector_interval_2.q.out | 112 +++---
.../llap/vector_interval_arithmetic.q.out | 60 +--
.../clientpositive/llap/vector_orderby_5.q.out | 16 +-
.../llap/vector_partitioned_date_time.q.out | 48 +--
.../clientpositive/llap/vector_reduce1.q.out | 10 +-
.../clientpositive/llap/vector_reduce2.q.out | 10 +-
.../clientpositive/llap/vector_reduce3.q.out | 10 +-
.../llap/vector_string_concat.q.out | 20 +-
.../llap/vectorized_date_funcs.q.out | 42 +--
.../test_teradatabinaryfile.q.out | 2 +-
.../merge/DateColumnStatsMerger.java | 33 +-
.../merge/DateColumnStatsMergerTest.java | 108 ++++++
.../merge/DecimalColumnStatsMergerTest.java | 2 -
51 files changed, 1297 insertions(+), 751 deletions(-)
----------------------------------------------------------------------
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
----------------------------------------------------------------------
diff --git a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
index de0282f..11ccff4 100644
--- a/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
+++ b/ql/src/java/org/apache/hadoop/hive/ql/parse/ColumnStatsAutoGatherContext.java
@@ -277,7 +277,7 @@ public class ColumnStatsAutoGatherContext {
case VARCHAR:
case BINARY:
case DECIMAL:
- // TODO: Support case DATE:
+ case DATE:
break;
default:
return false;
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/queries/clientpositive/autoColumnStats_11.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/autoColumnStats_11.q b/ql/src/test/queries/clientpositive/autoColumnStats_11.q
new file mode 100644
index 0000000..a75f153
--- /dev/null
+++ b/ql/src/test/queries/clientpositive/autoColumnStats_11.q
@@ -0,0 +1,28 @@
+-- Checking autogathering column stats for DATE cols
+set hive.stats.column.autogather=true;
+
+create table acs_t11(a int,b int,d date);
+
+-- should produce compute_stats aggregations
+explain insert into acs_t11 values(1,1,'2011-11-11');
+
+insert into acs_t11 values(1,1,'2011-11-11');
+describe formatted acs_t11 d;
+
+insert into acs_t11 values(1,1,NULL);
+describe formatted acs_t11 d;
+
+insert into acs_t11 values(1,1,'2006-11-11');
+describe formatted acs_t11 d;
+
+insert into acs_t11 values(1,1,'2001-11-11');
+describe formatted acs_t11 d;
+
+insert into acs_t11 values(1,1,'2004-11-11');
+describe formatted acs_t11 d;
+
+explain analyze table acs_t11 compute statistics for columns;
+analyze table acs_t11 compute statistics for columns;
+
+-- should be the same as before analyze
+describe formatted acs_t11 d;
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/alter_table_update_status.q.out b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
index b855379..ec8a64c 100644
--- a/ql/src/test/results/clientpositive/alter_table_update_status.q.out
+++ b/ql/src/test/results/clientpositive/alter_table_update_status.q.out
@@ -339,17 +339,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name s
data_type smallint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 3
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 i
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -358,17 +358,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name i
data_type int
-min
-max
-num_nulls
-distinct_count
+min 0
+max 45
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 b
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -377,17 +377,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name b
data_type bigint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 456
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 f
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -396,17 +396,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name f
data_type float
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 45454.3984375
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 d
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -415,17 +415,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name d
data_type double
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 454.6565
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 dem
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -434,17 +434,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name dem
data_type decimal(10,0)
-min
-max
-num_nulls
-distinct_count
+min 2355
+max 2355
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 ts
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -453,17 +453,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name ts
data_type timestamp
-min
-max
-num_nulls
-distinct_count
+min 0
+max 1325379723
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 dt
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -472,17 +472,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name dt
data_type date
-min
-max
-num_nulls
-distinct_count
+min 2012-01-01
+max 2012-01-01
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 str
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -493,15 +493,15 @@ col_name str
data_type string
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 17.0
+max_col_len 17
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 v
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -512,15 +512,15 @@ col_name v
data_type varchar(12)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 5.0
+max_col_len 5
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 c
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -531,15 +531,15 @@ col_name c
data_type char(5)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 4.0
+max_col_len 4
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 bl
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -550,15 +550,15 @@ col_name bl
data_type boolean
min
max
-num_nulls
+num_nulls 1
distinct_count
avg_col_len
max_col_len
-num_trues
-num_falses
+num_trues 1
+num_falses 0
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 bin
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -569,15 +569,15 @@ col_name bin
data_type binary
min
max
-num_nulls
+num_nulls 1
distinct_count
-avg_col_len
-max_col_len
+avg_col_len 3.0
+max_col_len 3
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 t
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -586,17 +586,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name t
data_type tinyint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 2
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column t SET ('numDVs'='232','numNulls'='233','highValue'='234','lowValue'='35')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -621,9 +621,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 s
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -632,17 +632,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name s
data_type smallint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 3
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column s SET ('numDVs'='56','numNulls'='56','highValue'='489','lowValue'='25')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -667,9 +667,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 i
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -678,17 +678,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name i
data_type int
-min
-max
-num_nulls
-distinct_count
+min 0
+max 45
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column i SET ('numDVs'='59','numNulls'='1','highValue'='889','lowValue'='5')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -713,9 +713,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 b
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -724,17 +724,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name b
data_type bigint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 456
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column b SET ('numDVs'='9','numNulls'='14','highValue'='89','lowValue'='8')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -759,9 +759,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 f
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -770,17 +770,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name f
data_type float
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 45454.3984375
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column f SET ('numDVs'='563','numNulls'='45','highValue'='2345.656','lowValue'='8.00')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -805,9 +805,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 d
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -816,17 +816,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name d
data_type double
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 454.6565
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column d SET ('numDVs'='5677','numNulls'='12','highValue'='560.3367','lowValue'='0.00455')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -851,9 +851,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 dem
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -862,17 +862,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name dem
data_type decimal(10,0)
-min
-max
-num_nulls
-distinct_count
+min 2355
+max 2355
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column dem SET ('numDVs'='57','numNulls'='912','highValue'='560','lowValue'='0')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -897,9 +897,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 ts
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -908,17 +908,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name ts
data_type timestamp
-min
-max
-num_nulls
-distinct_count
+min 0
+max 1325379723
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column ts SET ('numDVs'='7','numNulls'='12','highValue'='1357030923','lowValue'='1357030924')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -943,9 +943,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 dt
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -954,17 +954,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats_n0
col_name dt
data_type date
-min
-max
-num_nulls
-distinct_count
+min 2012-01-01
+max 2012-01-01
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column dt SET ('numDVs'='57','numNulls'='912','highValue'='2012-01-01','lowValue'='2001-02-04')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -989,9 +989,9 @@ avg_col_len
max_col_len
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 str
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -1002,15 +1002,15 @@ col_name str
data_type string
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 17.0
+max_col_len 17
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column str SET ('numDVs'='232','numNulls'='233','avgColLen'='2.34','maxColLen'='235')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -1035,9 +1035,9 @@ avg_col_len 2.34
max_col_len 235
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 v
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -1048,15 +1048,15 @@ col_name v
data_type varchar(12)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 5.0
+max_col_len 5
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column v SET ('numDVs'='22','numNulls'='33','avgColLen'='4.40','maxColLen'='25')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -1081,9 +1081,9 @@ avg_col_len 4.4
max_col_len 25
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 c
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -1094,15 +1094,15 @@ col_name c
data_type char(5)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 4.0
+max_col_len 4
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column c SET ('numDVs'='2','numNulls'='03','avgColLen'='9.00','maxColLen'='58')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -1127,9 +1127,9 @@ avg_col_len 9.0
max_col_len 58
num_trues
num_falses
-bitVector
+bitVector HL
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 bl
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -1140,15 +1140,15 @@ col_name bl
data_type boolean
min
max
-num_nulls
+num_nulls 1
distinct_count
avg_col_len
max_col_len
-num_trues
-num_falses
+num_trues 1
+num_falses 0
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column bl SET ('numNulls'='1','numTrues'='9','numFalses'='8')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
@@ -1175,7 +1175,7 @@ num_trues 9
num_falses 8
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats_n0 bin
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats_n0
@@ -1186,15 +1186,15 @@ col_name bin
data_type binary
min
max
-num_nulls
+num_nulls 1
distinct_count
-avg_col_len
-max_col_len
+avg_col_len 3.0
+max_col_len 3
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats_n0 UPDATE STATISTICS for column bin SET ('numNulls'='8','avgColLen'='2.0','maxColLen'='8')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats_n0
[4/6] hive git commit: HIVE-20498: Support date type for column stats
autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Posted by kg...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out
index a838d6f..6aaf494 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive.q.out
@@ -638,14 +638,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n6
- Statistics: Num rows: 6 Data size: 6973 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive_llap_io.q.out
index 9bb5648..4ff233d 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_all_primitive_llap_io.q.out
@@ -640,14 +640,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n5
- Statistics: Num rows: 6 Data size: 6973 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_llap_io.q.out
index 3575daa..dea1afe 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part_llap_io.q.out
@@ -530,14 +530,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n2
- Statistics: Num rows: 6 Data size: 12449 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
index 345af27..b3fb197 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
@@ -605,7 +605,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n4
- Statistics: Num rows: 6 Data size: 12449 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:string, 2:c2:char(50), 3:c3:char(15), 4:c4:varchar(50), 5:c5:varchar(15), 6:c6:string, 7:c7:char(50), 8:c8:char(15), 9:c9:varchar(50), 10:c10:varchar(15), 11:b:string, 12:part:int, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -616,13 +616,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
index 1076cf6..80879a7 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
@@ -690,7 +690,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n0
- Statistics: Num rows: 6 Data size: 6973 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:timestamp, 2:c2:timestamp, 3:c3:timestamp, 4:c4:timestamp, 5:c5:timestamp, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:c11:timestamp, 12:c12:timestamp, 13:b:string, 14:part:int, 15:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -701,13 +701,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive_llap_io.q.out
index 8429db6..51589ca 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive_llap_io.q.out
@@ -692,7 +692,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n4
- Statistics: Num rows: 6 Data size: 6973 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:timestamp, 2:c2:timestamp, 3:c3:timestamp, 4:c4:timestamp, 5:c5:timestamp, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:c11:timestamp, 12:c12:timestamp, 13:b:string, 14:part:int, 15:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -703,13 +703,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out
index a50a2b4..3dc5f05 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part.q.out
@@ -527,14 +527,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n8
- Statistics: Num rows: 6 Data size: 9960 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out
index 710f586..9dd9cbd 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive.q.out
@@ -638,14 +638,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n2
- Statistics: Num rows: 6 Data size: 4915 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive_llap_io.q.out
index 1f123bf..a8e8540 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_all_primitive_llap_io.q.out
@@ -683,14 +683,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n1
- Statistics: Num rows: 5 Data size: 4830 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: boolean), c2 (type: tinyint), c3 (type: smallint), c4 (type: int), c5 (type: bigint), c6 (type: float), c7 (type: double), c8 (type: decimal(38,18)), c9 (type: string), c10 (type: char(25)), c11 (type: varchar(25)), c12 (type: date), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 5 Data size: 3990 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 5 Data size: 3990 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -775,14 +775,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n1
- Statistics: Num rows: 6 Data size: 4915 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_llap_io.q.out
index f362f86..5952fe7 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_nonvec_part_llap_io.q.out
@@ -530,14 +530,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n1
- Statistics: Num rows: 6 Data size: 9960 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out
index 2d6dde8..84581a6 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part.q.out
@@ -605,7 +605,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n10
- Statistics: Num rows: 6 Data size: 9960 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:string, 2:c2:char(50), 3:c3:char(15), 4:c4:varchar(50), 5:c5:varchar(15), 6:c6:string, 7:c7:char(50), 8:c8:char(15), 9:c9:varchar(50), 10:c10:varchar(15), 11:b:string, 12:part:int, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -616,13 +616,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out
index 7c87d12..36abdcb 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive.q.out
@@ -690,7 +690,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n8
- Statistics: Num rows: 6 Data size: 4915 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:timestamp, 2:c2:timestamp, 3:c3:timestamp, 4:c4:timestamp, 5:c5:timestamp, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:c11:timestamp, 12:c12:timestamp, 13:b:string, 14:part:int, 15:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -701,13 +701,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive_llap_io.q.out
index d0fae32..f91ea38 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_all_primitive_llap_io.q.out
@@ -745,7 +745,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n3
- Statistics: Num rows: 5 Data size: 4830 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:boolean, 2:c2:tinyint, 3:c3:smallint, 4:c4:int, 5:c5:bigint, 6:c6:float, 7:c7:double, 8:c8:decimal(38,18), 9:c9:string, 10:c10:char(25), 11:c11:varchar(25), 12:c12:date, 13:b:string, 14:part:int, 15:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -756,13 +756,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 5 Data size: 3990 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5 Data size: 3990 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -863,14 +863,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n3
- Statistics: Num rows: 6 Data size: 4915 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_llap_io.q.out
index ed00e24..6c1057a 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_part_llap_io.q.out
@@ -408,7 +408,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n0
- Statistics: Num rows: 5 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2900 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:date, 2:c2:date, 3:c3:date, 4:c4:date, 5:c5:date, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:b:string, 12:part:int, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -419,13 +419,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 5 Data size: 3360 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2900 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5 Data size: 3360 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2900 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_table_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_table_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_table_llap_io.q.out
index 008e52c..53fac4b 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_table_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vec_table_llap_io.q.out
@@ -682,7 +682,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: table_change_date_group_string_group_date_group_n1
- Statistics: Num rows: 5 Data size: 3340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:date, 2:c2:date, 3:c3:date, 4:c4:date, 5:c5:date, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:b:string, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -693,13 +693,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 5 Data size: 3340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5 Data size: 3340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out
index f47d6c9..98b3ebd 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part.q.out
@@ -605,7 +605,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n11
- Statistics: Num rows: 6 Data size: 9960 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:string, 2:c2:char(50), 3:c3:char(15), 4:c4:varchar(50), 5:c5:varchar(15), 6:c6:string, 7:c7:char(50), 8:c8:char(15), 9:c9:varchar(50), 10:c10:varchar(15), 11:b:string, 12:part:int, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -616,13 +616,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
index fe844dc..5cbfde8 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
@@ -690,7 +690,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp_n7
- Statistics: Num rows: 6 Data size: 4915 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:timestamp, 2:c2:timestamp, 3:c3:timestamp, 4:c4:timestamp, 5:c5:timestamp, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:c11:timestamp, 12:c12:timestamp, 13:b:string, 14:part:int, 15:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -701,13 +701,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive_llap_io.q.out
index 4ff8855..3361a5f 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive_llap_io.q.out
@@ -707,7 +707,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp
- Statistics: Num rows: 5 Data size: 4830 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:boolean, 2:c2:tinyint, 3:c3:smallint, 4:c4:int, 5:c5:bigint, 6:c6:float, 7:c7:double, 8:c8:decimal(38,18), 9:c9:string, 10:c10:char(25), 11:c11:varchar(25), 12:c12:date, 13:b:string, 14:part:int, 15:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -718,13 +718,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
- Statistics: Num rows: 5 Data size: 3990 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5 Data size: 3990 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 3028 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -809,14 +809,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_various_various_timestamp
- Statistics: Num rows: 6 Data size: 4915 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 4032 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 840 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_llap_io.q.out
index f5f4ba5..0363512 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_llap_io.q.out
@@ -665,7 +665,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp
- Statistics: Num rows: 5 Data size: 4185 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2900 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:date, 2:c2:date, 3:c3:date, 4:c4:date, 5:c5:date, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:b:string, 12:part:int, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -676,13 +676,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 5 Data size: 3360 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2900 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5 Data size: 3360 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 5 Data size: 2900 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -781,14 +781,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp
- Statistics: Num rows: 6 Data size: 9960 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table_llap_io.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table_llap_io.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table_llap_io.q.out
index 7b9fe43..b8cf3ac 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table_llap_io.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table_llap_io.q.out
@@ -682,7 +682,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: table_change_date_group_string_group_date_group_n11
- Statistics: Num rows: 5 Data size: 3340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:date, 2:c2:date, 3:c3:date, 4:c4:date, 5:c5:date, 6:c6:timestamp, 7:c7:timestamp, 8:c8:timestamp, 9:c9:timestamp, 10:c10:timestamp, 11:b:string, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -693,13 +693,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 5 Data size: 3340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 5 Data size: 3340 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 2880 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -795,7 +795,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: table_change_date_group_string_group_date_group_n11
- Statistics: Num rows: 6 Data size: 8928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 8376 Basic stats: COMPLETE Column stats: PARTIAL
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:insert_num:int, 1:c1:string, 2:c2:char(50), 3:c3:char(15), 4:c4:varchar(50), 5:c5:varchar(15), 6:c6:string, 7:c7:char(50), 8:c8:char(15), 9:c9:varchar(50), 10:c10:varchar(15), 11:b:string, 12:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -806,13 +806,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
- Statistics: Num rows: 6 Data size: 8928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 8376 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 6 Data size: 8928 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 8376 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
index 7e7f4fe..feadbcd 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
@@ -4616,16 +4616,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: emps_n4
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -4662,17 +4662,17 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: CASE WHEN (_col11 is null) THEN ((UDFToLong(_col2) <> 0)) ELSE ((UDFToLong(_col2) <> _col10)) END (type: boolean)
- Statistics: Num rows: 2 Data size: 1390 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 714 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 2 Data size: 1390 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 2 Data size: 1390 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 702 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4740,19 +4740,19 @@ STAGE PLANS:
TableScan
alias: emps_n4
filterExpr: deptno is not null (type: boolean)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: deptno is not null (type: boolean)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -4790,14 +4790,14 @@ STAGE PLANS:
1 _col1 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
residual filter predicates: {(_col1 > _col10)}
- Statistics: Num rows: 1 Data size: 695 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 535 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 1 Data size: 695 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 351 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 695 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 351 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -4862,16 +4862,16 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: emps_n4
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -4923,19 +4923,19 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11
- Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1674 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: CASE WHEN (_col11 is null) THEN ((UDFToLong(_col2) <> 0)) ELSE ((UDFToLong(_col2) <> _col10)) END (type: boolean)
- Statistics: Num rows: 2 Data size: 1390 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 714 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 2 Data size: 1390 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 714 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col2 (type: int)
sort order: +
Map-reduce partition columns: _col2 (type: int)
- Statistics: Num rows: 2 Data size: 1390 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 714 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
Reducer 3
Execution mode: llap
@@ -4947,17 +4947,17 @@ STAGE PLANS:
0 _col2 (type: int)
1 _col2 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col13, _col14
- Statistics: Num rows: 2 Data size: 1529 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 726 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: CASE WHEN (_col14 is null) THEN ((UDFToLong(_col0) > 0)) ELSE ((UDFToLong(_col0) > _col13)) END (type: boolean)
- Statistics: Num rows: 1 Data size: 764 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 363 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 1 Data size: 764 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 351 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 764 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 351 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -5047,19 +5047,19 @@ STAGE PLANS:
TableScan
alias: emps_n4
filterExpr: name is not null (type: boolean)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: name is not null (type: boolean)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: empno (type: int), name (type: string), deptno (type: int), gender (type: string), city (type: string), empid (type: int), age (type: int), slacker (type: boolean), manager (type: boolean), joinedat (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string)
sort order: +
Map-reduce partition columns: _col1 (type: string)
- Statistics: Num rows: 5 Data size: 3160 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 5 Data size: 1650 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
Execution mode: vectorized, llap
LLAP IO: no inputs
@@ -5117,10 +5117,10 @@ STAGE PLANS:
1 _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
residual filter predicates: {(UDFToLong(_col2) <> _col10)}
- Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 359 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 5 Data size: 3476 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 359 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
Reducer 3
Execution mode: llap
@@ -5133,14 +5133,14 @@ STAGE PLANS:
1
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col12
residual filter predicates: {(UDFToLong(_col0) > _col12)}
- Statistics: Num rows: 1 Data size: 704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 359 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: int), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: date)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 1 Data size: 704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 351 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 704 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 351 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
index a9971d4..51e510b 100644
--- a/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
@@ -127,7 +127,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n4
- Statistics: Num rows: 2000 Data size: 212912 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 212800 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:tinyint, 1:si:smallint, 2:i:int, 3:b:bigint, 4:f:float, 5:d:double, 6:dc:decimal(38,18), 7:bo:boolean, 8:s:string, 9:s2:string, 10:ts:timestamp, 11:ts2:timestamp, 12:dt:date, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -138,7 +138,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [6]
- Statistics: Num rows: 2000 Data size: 212912 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 212800 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(dc), max(dc), sum(dc), count(dc)
Group By Vectorization:
@@ -150,7 +150,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -158,7 +158,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:decimal(38,18), 1:decimal(38,18), 2:decimal(38,18), 3:bigint
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -204,7 +204,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), (_col2 / _col3) (type: decimal(38,18))
outputColumnNames: _col0, _col1, _col2, _col3
@@ -213,13 +213,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 5]
selectExpressions: DecimalColDivideDecimalColumn(col 2:decimal(38,18), col 4:decimal(19,0))(children: CastLongToDecimal(col 3:bigint) -> 4:decimal(19,0)) -> 5:decimal(38,18)
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -266,7 +266,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n4
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:tinyint, 1:si:smallint, 2:i:int, 3:b:bigint, 4:f:float, 5:d:double, 6:dc:decimal(38,18), 7:bo:boolean, 8:s:string, 9:s2:string, 10:ts:timestamp, 11:ts2:timestamp, 12:dt:date, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -277,7 +277,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [5]
- Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 15208 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(d), max(d), sum(d), count(d)
Group By Vectorization:
@@ -289,7 +289,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -297,7 +297,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:double, 1:double, 2:double, 3:bigint
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -343,7 +343,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: double), _col1 (type: double), _col2 (type: double), (_col2 / _col3) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -352,13 +352,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 4]
selectExpressions: DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 4:double
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 40 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -405,7 +405,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n4
- Statistics: Num rows: 2000 Data size: 76040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 80000 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:t:tinyint, 1:si:smallint, 2:i:int, 3:b:bigint, 4:f:float, 5:d:double, 6:dc:decimal(38,18), 7:bo:boolean, 8:s:string, 9:s2:string, 10:ts:timestamp, 11:ts2:timestamp, 12:dt:date, 13:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -416,7 +416,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [10]
- Statistics: Num rows: 2000 Data size: 76040 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 80000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: min(ts), max(ts), sum(ts), count(ts)
Group By Vectorization:
@@ -428,7 +428,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Reduce Sink Vectorization:
@@ -436,7 +436,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 0:timestamp, 1:timestamp, 2:double, 3:bigint
- Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: timestamp), _col1 (type: timestamp), _col2 (type: double), _col3 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -482,7 +482,7 @@ STAGE PLANS:
projectedOutputColumnNums: [0, 1, 2, 3]
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: timestamp), _col1 (type: timestamp), _col2 (type: double), (_col2 / _col3) (type: double)
outputColumnNames: _col0, _col1, _col2, _col3
@@ -491,13 +491,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 2, 4]
selectExpressions: DoubleColDivideLongColumn(col 2:double, col 3:bigint) -> 4:double
- Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 136 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[5/6] hive git commit: HIVE-20498: Support date type for column stats
autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Posted by kg...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out b/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
index fd4bb7b..1b787af 100644
--- a/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
+++ b/ql/src/test/results/clientpositive/alter_table_update_status_disable_bitvector.q.out
@@ -339,17 +339,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name s
data_type smallint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 3
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats i
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -358,17 +358,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name i
data_type int
-min
-max
-num_nulls
-distinct_count
+min 0
+max 45
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats b
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -377,17 +377,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name b
data_type bigint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 456
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats f
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -396,17 +396,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name f
data_type float
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 45454.3984375
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats d
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -415,17 +415,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name d
data_type double
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 454.6565
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats dem
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -434,17 +434,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name dem
data_type decimal(10,0)
-min
-max
-num_nulls
-distinct_count
+min 2355
+max 2355
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats ts
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -453,17 +453,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name ts
data_type timestamp
-min
-max
-num_nulls
-distinct_count
+min 0
+max 1325379723
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats dt
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -472,17 +472,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name dt
data_type date
-min
-max
-num_nulls
-distinct_count
+min 2012-01-01
+max 2012-01-01
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats str
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -493,15 +493,15 @@ col_name str
data_type string
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 17.0
+max_col_len 17
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats v
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -512,15 +512,15 @@ col_name v
data_type varchar(12)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 5.0
+max_col_len 5
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats c
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -531,15 +531,15 @@ col_name c
data_type char(5)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 4.0
+max_col_len 4
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats bl
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -550,15 +550,15 @@ col_name bl
data_type boolean
min
max
-num_nulls
+num_nulls 1
distinct_count
avg_col_len
max_col_len
-num_trues
-num_falses
+num_trues 1
+num_falses 0
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats bin
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -569,15 +569,15 @@ col_name bin
data_type binary
min
max
-num_nulls
+num_nulls 1
distinct_count
-avg_col_len
-max_col_len
+avg_col_len 3.0
+max_col_len 3
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats t
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -586,17 +586,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name t
data_type tinyint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 2
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column t SET ('numDVs'='232','numNulls'='233','highValue'='234','lowValue'='35')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -623,7 +623,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats s
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -632,17 +632,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name s
data_type smallint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 3
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column s SET ('numDVs'='56','numNulls'='56','highValue'='489','lowValue'='25')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -669,7 +669,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats i
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -678,17 +678,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name i
data_type int
-min
-max
-num_nulls
-distinct_count
+min 0
+max 45
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column i SET ('numDVs'='59','numNulls'='1','highValue'='889','lowValue'='5')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -715,7 +715,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats b
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -724,17 +724,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name b
data_type bigint
-min
-max
-num_nulls
-distinct_count
+min 0
+max 456
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column b SET ('numDVs'='9','numNulls'='14','highValue'='89','lowValue'='8')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -761,7 +761,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats f
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -770,17 +770,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name f
data_type float
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 45454.3984375
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column f SET ('numDVs'='563','numNulls'='45','highValue'='2345.656','lowValue'='8.00')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -807,7 +807,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats d
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -816,17 +816,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name d
data_type double
-min
-max
-num_nulls
-distinct_count
+min 0.0
+max 454.6565
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column d SET ('numDVs'='5677','numNulls'='12','highValue'='560.3367','lowValue'='0.00455')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -853,7 +853,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats dem
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -862,17 +862,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name dem
data_type decimal(10,0)
-min
-max
-num_nulls
-distinct_count
+min 2355
+max 2355
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column dem SET ('numDVs'='57','numNulls'='912','highValue'='560','lowValue'='0')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -899,7 +899,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats ts
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -908,17 +908,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name ts
data_type timestamp
-min
-max
-num_nulls
-distinct_count
+min 0
+max 1325379723
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column ts SET ('numDVs'='7','numNulls'='12','highValue'='1357030923','lowValue'='1357030924')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -945,7 +945,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats dt
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -954,17 +954,17 @@ POSTHOOK: type: DESCTABLE
POSTHOOK: Input: default@datatype_stats
col_name dt
data_type date
-min
-max
-num_nulls
-distinct_count
+min 2012-01-01
+max 2012-01-01
+num_nulls 1
+distinct_count 1
avg_col_len
max_col_len
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column dt SET ('numDVs'='57','numNulls'='912','highValue'='2012-01-01','lowValue'='2001-02-04')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -991,7 +991,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats str
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -1002,15 +1002,15 @@ col_name str
data_type string
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 17.0
+max_col_len 17
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column str SET ('numDVs'='232','numNulls'='233','avgColLen'='2.34','maxColLen'='235')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -1037,7 +1037,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats v
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -1048,15 +1048,15 @@ col_name v
data_type varchar(12)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 5.0
+max_col_len 5
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column v SET ('numDVs'='22','numNulls'='33','avgColLen'='4.40','maxColLen'='25')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -1083,7 +1083,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats c
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -1094,15 +1094,15 @@ col_name c
data_type char(5)
min
max
-num_nulls
-distinct_count
-avg_col_len
-max_col_len
+num_nulls 1
+distinct_count 1
+avg_col_len 4.0
+max_col_len 4
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column c SET ('numDVs'='2','numNulls'='03','avgColLen'='9.00','maxColLen'='58')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -1129,7 +1129,7 @@ num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats bl
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -1140,15 +1140,15 @@ col_name bl
data_type boolean
min
max
-num_nulls
+num_nulls 1
distinct_count
avg_col_len
max_col_len
-num_trues
-num_falses
+num_trues 1
+num_falses 0
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column bl SET ('numNulls'='1','numTrues'='9','numFalses'='8')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
@@ -1175,7 +1175,7 @@ num_trues 9
num_falses 8
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: DESC FORMATTED datatype_stats bin
PREHOOK: type: DESCTABLE
PREHOOK: Input: default@datatype_stats
@@ -1186,15 +1186,15 @@ col_name bin
data_type binary
min
max
-num_nulls
+num_nulls 1
distinct_count
-avg_col_len
-max_col_len
+avg_col_len 3.0
+max_col_len 3
num_trues
num_falses
bitVector
comment from deserializer
-COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bl\":\"true\",\"c\":\"true\",\"d\":\"true\",\"dem\":\"true\",\"dt\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"str\":\"true\",\"t\":\"true\",\"ts\":\"true\",\"v\":\"true\"}}
PREHOOK: query: ALTER TABLE default.datatype_stats UPDATE STATISTICS for column bin SET ('numNulls'='8','avgColLen'='2.0','maxColLen'='8')
PREHOOK: type: ALTERTABLE_UPDATETABLESTATS
PREHOOK: Input: default@datatype_stats
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/autoColumnStats_11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/autoColumnStats_11.q.out b/ql/src/test/results/clientpositive/autoColumnStats_11.q.out
new file mode 100644
index 0000000..550c563
--- /dev/null
+++ b/ql/src/test/results/clientpositive/autoColumnStats_11.q.out
@@ -0,0 +1,362 @@
+PREHOOK: query: create table acs_t11(a int,b int,d date)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@acs_t11
+POSTHOOK: query: create table acs_t11(a int,b int,d date)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@acs_t11
+PREHOOK: query: explain insert into acs_t11 values(1,1,'2011-11-11')
+PREHOOK: type: QUERY
+POSTHOOK: query: explain insert into acs_t11 values(1,1,'2011-11-11')
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+ Stage-4
+ Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
+ Stage-2 depends on stages: Stage-0
+ Stage-3
+ Stage-5
+ Stage-6 depends on stages: Stage-5
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: _dummy_table
+ Row Limit Per Split: 1
+ Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: array(const struct(1,1,'2011-11-11')) (type: array<struct<col1:int,col2:int,col3:string>>)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
+ UDTF Operator
+ Statistics: Num rows: 1 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
+ function name: inline
+ Select Operator
+ expressions: col1 (type: int), col2 (type: int), CAST( col3 AS DATE) (type: date)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.acs_t11
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int), _col2 (type: date)
+ outputColumnNames: a, b, d
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(d, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1368 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1368 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:date,max:date,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1416 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-7
+ Conditional Operator
+
+ Stage: Stage-4
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+ Stage: Stage-0
+ Move Operator
+ tables:
+ replace: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.acs_t11
+
+ Stage: Stage-2
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, b, d
+ Column Types: int, int, date
+ Table: default.acs_t11
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.acs_t11
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.acs_t11
+
+ Stage: Stage-6
+ Move Operator
+ files:
+ hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: insert into acs_t11 values(1,1,'2011-11-11')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acs_t11
+POSTHOOK: query: insert into acs_t11 values(1,1,'2011-11-11')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acs_t11
+POSTHOOK: Lineage: acs_t11.a SCRIPT []
+POSTHOOK: Lineage: acs_t11.b SCRIPT []
+POSTHOOK: Lineage: acs_t11.d SCRIPT []
+PREHOOK: query: describe formatted acs_t11 d
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@acs_t11
+POSTHOOK: query: describe formatted acs_t11 d
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@acs_t11
+col_name d
+data_type date
+min 2011-11-11
+max 2011-11-11
+num_nulls 0
+distinct_count 1
+avg_col_len
+max_col_len
+num_trues
+num_falses
+bitVector HL
+comment from deserializer
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"d\":\"true\"}}
+PREHOOK: query: insert into acs_t11 values(1,1,NULL)
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acs_t11
+POSTHOOK: query: insert into acs_t11 values(1,1,NULL)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acs_t11
+POSTHOOK: Lineage: acs_t11.a SCRIPT []
+POSTHOOK: Lineage: acs_t11.b SCRIPT []
+POSTHOOK: Lineage: acs_t11.d EXPRESSION []
+PREHOOK: query: describe formatted acs_t11 d
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@acs_t11
+POSTHOOK: query: describe formatted acs_t11 d
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@acs_t11
+col_name d
+data_type date
+min 2011-11-11
+max 2011-11-11
+num_nulls 1
+distinct_count 1
+avg_col_len
+max_col_len
+num_trues
+num_falses
+bitVector HL
+comment from deserializer
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"d\":\"true\"}}
+PREHOOK: query: insert into acs_t11 values(1,1,'2006-11-11')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acs_t11
+POSTHOOK: query: insert into acs_t11 values(1,1,'2006-11-11')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acs_t11
+POSTHOOK: Lineage: acs_t11.a SCRIPT []
+POSTHOOK: Lineage: acs_t11.b SCRIPT []
+POSTHOOK: Lineage: acs_t11.d SCRIPT []
+PREHOOK: query: describe formatted acs_t11 d
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@acs_t11
+POSTHOOK: query: describe formatted acs_t11 d
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@acs_t11
+col_name d
+data_type date
+min 2006-11-11
+max 2011-11-11
+num_nulls 1
+distinct_count 2
+avg_col_len
+max_col_len
+num_trues
+num_falses
+bitVector HL
+comment from deserializer
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"d\":\"true\"}}
+PREHOOK: query: insert into acs_t11 values(1,1,'2001-11-11')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acs_t11
+POSTHOOK: query: insert into acs_t11 values(1,1,'2001-11-11')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acs_t11
+POSTHOOK: Lineage: acs_t11.a SCRIPT []
+POSTHOOK: Lineage: acs_t11.b SCRIPT []
+POSTHOOK: Lineage: acs_t11.d SCRIPT []
+PREHOOK: query: describe formatted acs_t11 d
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@acs_t11
+POSTHOOK: query: describe formatted acs_t11 d
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@acs_t11
+col_name d
+data_type date
+min 2001-11-11
+max 2011-11-11
+num_nulls 1
+distinct_count 3
+avg_col_len
+max_col_len
+num_trues
+num_falses
+bitVector HL
+comment from deserializer
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"d\":\"true\"}}
+PREHOOK: query: insert into acs_t11 values(1,1,'2004-11-11')
+PREHOOK: type: QUERY
+PREHOOK: Input: _dummy_database@_dummy_table
+PREHOOK: Output: default@acs_t11
+POSTHOOK: query: insert into acs_t11 values(1,1,'2004-11-11')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: _dummy_database@_dummy_table
+POSTHOOK: Output: default@acs_t11
+POSTHOOK: Lineage: acs_t11.a SCRIPT []
+POSTHOOK: Lineage: acs_t11.b SCRIPT []
+POSTHOOK: Lineage: acs_t11.d SCRIPT []
+PREHOOK: query: describe formatted acs_t11 d
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@acs_t11
+POSTHOOK: query: describe formatted acs_t11 d
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@acs_t11
+col_name d
+data_type date
+min 2001-11-11
+max 2011-11-11
+num_nulls 1
+distinct_count 4
+avg_col_len
+max_col_len
+num_trues
+num_falses
+bitVector HL
+comment from deserializer
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"d\":\"true\"}}
+PREHOOK: query: explain analyze table acs_t11 compute statistics for columns
+PREHOOK: type: ANALYZE_TABLE
+POSTHOOK: query: explain analyze table acs_t11 compute statistics for columns
+POSTHOOK: type: ANALYZE_TABLE
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+ Stage-1 depends on stages: Stage-0
+
+STAGE PLANS:
+ Stage: Stage-0
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: acs_t11
+ Statistics: Num rows: 5 Data size: 62 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: a (type: int), b (type: int), d (type: date)
+ outputColumnNames: a, b, d
+ Statistics: Num rows: 5 Data size: 62 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(a, 'hll'), compute_stats(b, 'hll'), compute_stats(d, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1368 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1368 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:date,max:date,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1416 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1416 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
+
+ Stage: Stage-1
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: a, b, d
+ Column Types: int, int, date
+ Table: default.acs_t11
+
+PREHOOK: query: analyze table acs_t11 compute statistics for columns
+PREHOOK: type: ANALYZE_TABLE
+PREHOOK: Input: default@acs_t11
+PREHOOK: Output: default@acs_t11
+#### A masked pattern was here ####
+POSTHOOK: query: analyze table acs_t11 compute statistics for columns
+POSTHOOK: type: ANALYZE_TABLE
+POSTHOOK: Input: default@acs_t11
+POSTHOOK: Output: default@acs_t11
+#### A masked pattern was here ####
+PREHOOK: query: describe formatted acs_t11 d
+PREHOOK: type: DESCTABLE
+PREHOOK: Input: default@acs_t11
+POSTHOOK: query: describe formatted acs_t11 d
+POSTHOOK: type: DESCTABLE
+POSTHOOK: Input: default@acs_t11
+col_name d
+data_type date
+min 2001-11-11
+max 2011-11-11
+num_nulls 1
+distinct_count 4
+avg_col_len
+max_col_len
+num_trues
+num_falses
+bitVector HL
+comment from deserializer
+COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\",\"d\":\"true\"}}
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/constprog_type.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/constprog_type.q.out b/ql/src/test/results/clientpositive/constprog_type.q.out
index a3f6358..9c7676a 100644
--- a/ql/src/test/results/clientpositive/constprog_type.q.out
+++ b/ql/src/test/results/clientpositive/constprog_type.q.out
@@ -46,7 +46,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1_n26
- Execution mode: vectorized
+ Select Operator
+ expressions: DATE'2013-11-17' (type: date), TIMESTAMP'2011-04-30 03:46:56.4485' (type: timestamp)
+ outputColumnNames: d, t
+ Statistics: Num rows: 500 Data size: 48000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: compute_stats(d, 'hll'), compute_stats(t, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 944 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 944 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: struct<columntype:string,min:date,max:date,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 976 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 976 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-7
Conditional Operator
@@ -70,6 +95,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: d, t
+ Column Types: date, timestamp
+ Table: default.dest1_n26
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/extrapolate_part_stats_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/extrapolate_part_stats_date.q.out b/ql/src/test/results/clientpositive/extrapolate_part_stats_date.q.out
index eadaaca..3569eb5 100644
--- a/ql/src/test/results/clientpositive/extrapolate_part_stats_date.q.out
+++ b/ql/src/test/results/clientpositive/extrapolate_part_stats_date.q.out
@@ -273,7 +273,7 @@ STAGE PLANS:
partition values:
d_date_sk 2416948
properties:
- COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"}
+ COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"d_date":"true"}}
bucket_count -1
column.name.delimiter ,
columns d_date
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/orc_llap_counters.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_llap_counters.q.out b/ql/src/test/results/clientpositive/llap/orc_llap_counters.q.out
index 0a8a8a8..3b16379 100644
--- a/ql/src/test/results/clientpositive/llap/orc_llap_counters.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_llap_counters.q.out
@@ -230,7 +230,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bo\":\"true\",\"c\":\"true\",\"d\":\"true\",\"da\":\"true\",\"dec\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"si\":\"true\",\"t\":\"true\",\"v\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 2100
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/orc_llap_counters1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_llap_counters1.q.out b/ql/src/test/results/clientpositive/llap/orc_llap_counters1.q.out
index 4d8400e..cbf615f 100644
--- a/ql/src/test/results/clientpositive/llap/orc_llap_counters1.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_llap_counters1.q.out
@@ -230,7 +230,7 @@ Retention: 0
#### A masked pattern was here ####
Table Type: MANAGED_TABLE
Table Parameters:
- COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"}
+ COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"b\":\"true\",\"bin\":\"true\",\"bo\":\"true\",\"c\":\"true\",\"d\":\"true\",\"da\":\"true\",\"dec\":\"true\",\"f\":\"true\",\"i\":\"true\",\"s\":\"true\",\"si\":\"true\",\"t\":\"true\",\"v\":\"true\"}}
bucketing_version 2
numFiles 1
numRows 2100
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/orc_ppd_date.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/orc_ppd_date.q.out b/ql/src/test/results/clientpositive/llap/orc_ppd_date.q.out
index f86fe77..6a18e59 100644
--- a/ql/src/test/results/clientpositive/llap/orc_ppd_date.q.out
+++ b/ql/src/test/results/clientpositive/llap/orc_ppd_date.q.out
@@ -335,20 +335,20 @@ STAGE PLANS:
TableScan
alias: test_lrl
filterExpr: (c = DATE'1900-01-01') (type: boolean)
- Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (c = DATE'1900-01-01') (type: boolean)
- Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 64 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: 64 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -359,10 +359,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 64 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: 64 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
@@ -451,20 +451,20 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: test_lrl
- Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: (c like '1900-01-01%') (type: boolean)
- Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 64 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: 64 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: all inputs
@@ -475,10 +475,10 @@ STAGE PLANS:
aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 64 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: 64 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
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out
index 48ab0d2..c7b6d2c 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_nonvec_part.q.out
@@ -527,14 +527,14 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_change_date_group_string_group_date_timestamp_n7
- Statistics: Num rows: 6 Data size: 12449 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
Select Operator
expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
File Output Operator
compressed: false
- Statistics: Num rows: 6 Data size: 8952 Basic stats: COMPLETE Column stats: PARTIAL
+ Statistics: Num rows: 6 Data size: 600 Basic stats: COMPLETE Column stats: PARTIAL
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
[3/6] hive git commit: HIVE-20498: Support date type for column stats
autogather (Zoltan Haindrich reviewed by Prasanth Jayachandran)
Posted by kg...@apache.org.
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_case_when_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_case_when_2.q.out b/ql/src/test/results/clientpositive/llap/vector_case_when_2.q.out
index 781f990..243e55e 100644
--- a/ql/src/test/results/clientpositive/llap/vector_case_when_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_case_when_2.q.out
@@ -135,15 +135,15 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: timestamps
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 12597 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), CASE WHEN ((ctimestamp2 <= TIMESTAMP'1800-12-31 00:00:00')) THEN ('1800s or Earlier') WHEN ((ctimestamp2 < TIMESTAMP'1900-01-01 00:00:00')) THEN ('1900s') WHEN (ctimestamp2 BETWEEN TIMESTAMP'2006-01-01 00:00:00' AND TIMESTAMP'2010-12-31 23:59:59.999999999') THEN ('Late 2000s') WHEN ((ctimestamp2 <= TIMESTAMP'2015-12-31 23:59:59.999999999')) THEN ('Early 2010s') ELSE ('Unknown') END (type: string), CASE WHEN ((ctimestamp2 <= TIMESTAMP'2000-12-31 23:59:59.999999999')) THEN ('Old') WHEN ((ctimestamp2 < TIMESTAMP'2006-01-01 00:00:00')) THEN ('Early 2000s') WHEN (ctimestamp2 BETWEEN TIMESTAMP'2006-01-01 00:00:00' AND TIMESTAMP'2010-12-31 23:59:59.999999999') THEN ('Late 2000s') WHEN ((ctimestamp2 <= TIMESTAMP'2015-12-31 23:59:59.999999999')) THEN ('Early 2010s') ELSE (null) END (type: string), CASE WHEN ((ctimestamp2 <= TIMESTAMP'2000-12-31 23:59:59.999999999')) THEN ('Old') WHEN ((ctimestamp2
< TIMESTAMP'2006-01-01 00:00:00')) THEN ('Early 2000s') WHEN (ctimestamp2 BETWEEN TIMESTAMP'2006-01-01 00:00:00' AND TIMESTAMP'2010-12-31 23:59:59.999999999') THEN ('Late 2000s') WHEN ((ctimestamp2 <= TIMESTAMP'2015-12-31 23:59:59.999999999')) THEN (null) ELSE (null) END (type: string), if((ctimestamp1 < TIMESTAMP'1974-10-04 17:21:03.989'), year(ctimestamp1), year(ctimestamp2)) (type: int), CASE WHEN ((stimestamp1 like '%19%')) THEN (stimestamp1) ELSE (TIMESTAMP'2018-03-08 23:04:59') END (type: string), if((ctimestamp1 = TIMESTAMP'2021-09-24 03:18:32.413655165'), null, minute(ctimestamp1)) (type: int), if(((ctimestamp2 >= TIMESTAMP'5344-10-04 18:40:08.165') and (ctimestamp2 < TIMESTAMP'6631-11-13 16:31:29.702202248')), minute(ctimestamp1), null) (type: int), if(((UDFToDouble(ctimestamp1) % 500.0D) > 100.0D), date_add(cdate, 1), date_add(cdate, 365)) (type: date), stimestamp1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 50745 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col10 (type: string), _col1 (type: timestamp)
sort order: +++
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 50745 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: date)
Execution mode: llap
LLAP IO: all inputs
@@ -176,13 +176,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 45084 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 45084 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -397,7 +397,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: timestamps
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 12597 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cdate:date, 1:ctimestamp1:timestamp, 2:stimestamp1:string, 3:ctimestamp2:timestamp, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -409,7 +409,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 10, 12, 13, 14, 11, 7, 16, 23, 2]
selectExpressions: IfExprStringScalarStringGroupColumn(col 5:boolean, val 1800s or Earliercol 9:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 1800-12-31 00:00:00) -> 5:boolean, IfExprStringScalarStringGroupColumn(col 6:boolean, val 1900scol 10:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 1900-01-01 00:00:00) -> 6:boolean, IfExprStringScalarStringGroupColumn(col 7:boolean, val Late 2000scol 9:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 7:boolean, IfExprStringScalarStringScalar(col 8:boolean, val Early 2010s, val Unknown)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 8:boolean) -> 9:string) -> 10:string) -> 9:string) -> 10:string, IfExprStringScalarStringGroupColumn(col 5:boolean, val Oldcol 11:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2
000-12-31 23:59:59.999999999) -> 5:boolean, IfExprStringScalarStringGroupColumn(col 6:boolean, val Early 2000scol 12:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 6:boolean, IfExprStringScalarStringGroupColumn(col 7:boolean, val Late 2000scol 11:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 7:boolean, IfExprColumnNull(col 8:boolean, col 9:string, null)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 8:boolean, ConstantVectorExpression(val Early 2010s) -> 9:string) -> 11:string) -> 12:string) -> 11:string) -> 12:string, IfExprStringScalarStringGroupColumn(col 5:boolean, val Oldcol 11:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 5:boolean, IfExprStringScalarStringGroupColumn(col 6:boolean, val Early 2000scol 13:string)(children: TimestampCol
LessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 6:boolean, IfExprStringScalarStringGroupColumn(col 7:boolean, val Late 2000scol 11:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 7:boolean, IfExprNullNull(null, null) -> 11:string) -> 13:string) -> 11:string) -> 13:string, IfExprLongColumnLongColumn(col 5:boolean, col 6:int, col 7:int)(children: TimestampColLessTimestampScalar(col 1:timestamp, val 1974-10-04 17:21:03.989) -> 5:boolean, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 6:int, VectorUDFYearTimestamp(col 3:timestamp, field YEAR) -> 7:int) -> 14:int, VectorUDFAdaptor(CASE WHEN ((stimestamp1 like '%19%')) THEN (stimestamp1) ELSE (TIMESTAMP'2018-03-08 23:04:59') END)(children: SelectStringColLikeStringScalar(col 2:string) -> 5:boolean) -> 11:string, IfExprNullColumn(col 5:boolean, null, col 6)(children: TimestampColEqualTimestampScalar(col 1:timestamp, val 2021-09-24 03:18:3
2.413655165) -> 5:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 6:int) -> 7:int, IfExprColumnNull(col 17:boolean, col 15:int, null)(children: ColAndCol(col 15:boolean, col 16:boolean)(children: TimestampColGreaterEqualTimestampScalar(col 3:timestamp, val 5344-10-04 18:40:08.165) -> 15:boolean, TimestampColLessTimestampScalar(col 3:timestamp, val 6631-11-13 16:31:29.702202248) -> 16:boolean) -> 17:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 15:int) -> 16:int, IfExprLongColumnLongColumn(col 20:boolean, col 21:date, col 22:date)(children: DoubleColGreaterDoubleScalar(col 19:double, val 100.0)(children: DoubleColModuloDoubleScalar(col 18:double, val 500.0)(children: CastTimestampToDouble(col 1:timestamp) -> 18:double) -> 19:double) -> 20:boolean, VectorUDFDateAddColScalar(col 0:date, val 1) -> 21:date, VectorUDFDateAddColScalar(col 0:date, val 365) -> 22:date) -> 23:date
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 50745 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col10 (type: string), _col1 (type: timestamp)
sort order: +++
@@ -419,7 +419,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 10:string, 12:string, 13:string, 14:int, 11:string, 7:int, 16:int, 23:date
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 50745 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: date)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -461,13 +461,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 45084 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 45084 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -682,7 +682,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: timestamps
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 12597 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:cdate:date, 1:ctimestamp1:timestamp, 2:stimestamp1:string, 3:ctimestamp2:timestamp, 4:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -694,7 +694,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 3, 15, 26, 36, 40, 42, 44, 46, 53, 2]
selectExpressions: IfExprColumnCondExpr(col 5:boolean, col 6:stringcol 14:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 1800-12-31 00:00:00) -> 5:boolean, ConstantVectorExpression(val 1800s or Earlier) -> 6:string, IfExprColumnCondExpr(col 7:boolean, col 8:stringcol 13:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 1900-01-01 00:00:00) -> 7:boolean, ConstantVectorExpression(val 1900s) -> 8:string, IfExprColumnCondExpr(col 9:boolean, col 10:stringcol 12:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 9:boolean, ConstantVectorExpression(val Late 2000s) -> 10:string, IfExprStringScalarStringScalar(col 11:boolean, val Early 2010s, val Unknown)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 11:boolean) -> 12:string) -> 13:string) -> 14:string) -> 15:string, IfExprColumnCondExpr(co
l 11:boolean, col 16:stringcol 25:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 11:boolean, ConstantVectorExpression(val Old) -> 16:string, IfExprColumnCondExpr(col 17:boolean, col 18:stringcol 24:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 17:boolean, ConstantVectorExpression(val Early 2000s) -> 18:string, IfExprColumnCondExpr(col 19:boolean, col 20:stringcol 23:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 19:boolean, ConstantVectorExpression(val Late 2000s) -> 20:string, IfExprColumnNull(col 21:boolean, col 22:string, null)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2015-12-31 23:59:59.999999999) -> 21:boolean, ConstantVectorExpression(val Early 2010s) -> 22:string) -> 23:string) -> 24:string) -> 25:string) -> 26:string, IfExprColumnCondExpr(col 27:boolean, col 28
:stringcol 35:string)(children: TimestampColLessEqualTimestampScalar(col 3:timestamp, val 2000-12-31 23:59:59.999999999) -> 27:boolean, ConstantVectorExpression(val Old) -> 28:string, IfExprColumnCondExpr(col 29:boolean, col 30:stringcol 34:string)(children: TimestampColLessTimestampScalar(col 3:timestamp, val 2006-01-01 00:00:00) -> 29:boolean, ConstantVectorExpression(val Early 2000s) -> 30:string, IfExprColumnCondExpr(col 31:boolean, col 32:stringcol 33:string)(children: TimestampColumnBetween(col 3:timestamp, left 2005-12-31 16:00:00.0, right 2010-12-31 15:59:59.999999999) -> 31:boolean, ConstantVectorExpression(val Late 2000s) -> 32:string, IfExprNullNull(null, null) -> 33:string) -> 34:string) -> 35:string) -> 36:string, IfExprCondExprCondExpr(col 37:boolean, col 38:intcol 39:int)(children: TimestampColLessTimestampScalar(col 1:timestamp, val 1974-10-04 17:21:03.989) -> 37:boolean, VectorUDFYearTimestamp(col 1:timestamp, field YEAR) -> 38:int, VectorUDFYearTimestamp(col 3:time
stamp, field YEAR) -> 39:int) -> 40:int, VectorUDFAdaptor(CASE WHEN ((stimestamp1 like '%19%')) THEN (stimestamp1) ELSE (TIMESTAMP'2018-03-08 23:04:59') END)(children: SelectStringColLikeStringScalar(col 2:string) -> 41:boolean) -> 42:string, IfExprNullCondExpr(col 41:boolean, null, col 43:int)(children: TimestampColEqualTimestampScalar(col 1:timestamp, val 2021-09-24 03:18:32.413655165) -> 41:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 43:int) -> 44:int, IfExprCondExprNull(col 47:boolean, col 45:int, null)(children: ColAndCol(col 45:boolean, col 46:boolean)(children: TimestampColGreaterEqualTimestampScalar(col 3:timestamp, val 5344-10-04 18:40:08.165) -> 45:boolean, TimestampColLessTimestampScalar(col 3:timestamp, val 6631-11-13 16:31:29.702202248) -> 46:boolean) -> 47:boolean, VectorUDFMinuteTimestamp(col 1:timestamp, field MINUTE) -> 45:int) -> 46:int, IfExprCondExprCondExpr(col 50:boolean, col 51:datecol 52:date)(children: DoubleColGreaterDoubleScalar(col
49:double, val 100.0)(children: DoubleColModuloDoubleScalar(col 48:double, val 500.0)(children: CastTimestampToDouble(col 1:timestamp) -> 48:double) -> 49:double) -> 50:boolean, VectorUDFDateAddColScalar(col 0:date, val 1) -> 51:date, VectorUDFDateAddColScalar(col 0:date, val 365) -> 52:date) -> 53:date
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 50745 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp), _col10 (type: string), _col1 (type: timestamp)
sort order: +++
@@ -704,7 +704,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 15:string, 26:string, 36:string, 40:int, 42:string, 44:int, 46:int, 53:date
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 50745 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: int), _col8 (type: int), _col9 (type: date)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -746,13 +746,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 45084 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 51 Data size: 16000 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 51 Data size: 45084 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_date_1.q.out b/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
index 1d16d65..5d275de 100644
--- a/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_date_1.q.out
@@ -110,7 +110,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_date_1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -122,7 +122,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 3, 4, 5, 6, 7, 8, 9, 10]
selectExpressions: LongColEqualLongColumn(col 0:date, col 0:date) -> 3:boolean, LongColNotEqualLongColumn(col 0:date, col 1:date) -> 4:boolean, LongColLessEqualLongColumn(col 0:date, col 0:date) -> 5:boolean, LongColLessEqualLongColumn(col 0:date, col 1:date) -> 6:boolean, LongColLessLongColumn(col 0:date, col 1:date) -> 7:boolean, LongColGreaterEqualLongColumn(col 1:date, col 1:date) -> 8:boolean, LongColGreaterEqualLongColumn(col 1:date, col 0:date) -> 9:boolean, LongColGreaterLongColumn(col 1:date, col 0:date) -> 10:boolean
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -132,7 +132,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:date, 3:boolean, 4:boolean, 5:boolean, 6:boolean, 7:boolean, 8:boolean, 9:boolean, 10:boolean
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -174,13 +174,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -275,7 +275,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_date_1
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -287,7 +287,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 1, 3, 4, 5, 6, 7, 8, 9, 10]
selectExpressions: LongColNotEqualLongColumn(col 0:date, col 0:date) -> 3:boolean, LongColEqualLongColumn(col 0:date, col 1:date) -> 4:boolean, LongColLessLongColumn(col 0:date, col 0:date) -> 5:boolean, LongColGreaterEqualLongColumn(col 0:date, col 1:date) -> 6:boolean, LongColGreaterLongColumn(col 0:date, col 1:date) -> 7:boolean, LongColGreaterLongColumn(col 1:date, col 1:date) -> 8:boolean, LongColLessEqualLongColumn(col 1:date, col 0:date) -> 9:boolean, LongColLessLongColumn(col 1:date, col 0:date) -> 10:boolean
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -297,7 +297,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:date, 3:boolean, 4:boolean, 5:boolean, 6:boolean, 7:boolean, 8:boolean, 9:boolean, 10:boolean
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: date), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean), _col7 (type: boolean), _col8 (type: boolean), _col9 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -339,13 +339,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 432 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -440,7 +440,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_date_1
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -452,7 +452,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 5, 6, 7]
selectExpressions: DateColNotEqualDateScalar(col 0:date, date 1970-01-01) -> 3:boolean, DateColGreaterEqualDateScalar(col 0:date, date 1970-01-01) -> 4:boolean, DateColGreaterDateScalar(col 0:date, date 1970-01-01) -> 5:boolean, DateColLessEqualDateScalar(col 0:date, date 2100-01-01) -> 6:boolean, DateColLessDateScalar(col 0:date, date 2100-01-01) -> 7:boolean
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -462,7 +462,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:boolean, 4:boolean, 5:boolean, 6:boolean, 7:boolean
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -504,13 +504,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -605,7 +605,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_date_1
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -617,7 +617,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 4, 5, 6, 7]
selectExpressions: DateColEqualDateScalar(col 0:date, date 1970-01-01) -> 3:boolean, DateColLessEqualDateScalar(col 0:date, date 1970-01-01) -> 4:boolean, DateColLessDateScalar(col 0:date, date 1970-01-01) -> 5:boolean, DateColGreaterEqualDateScalar(col 0:date, date 2100-01-01) -> 6:boolean, DateColGreaterDateScalar(col 0:date, date 2100-01-01) -> 7:boolean
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -627,7 +627,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 3:boolean, 4:boolean, 5:boolean, 6:boolean, 7:boolean
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -669,13 +669,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 1, 2, 3]
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -769,7 +769,7 @@ STAGE PLANS:
TableScan
alias: vector_date_1
filterExpr: ((dt1 = dt1) and (dt1 <> dt2) and (dt1 < dt2) and (dt1 <= dt2) and (dt2 > dt1) and (dt2 >= dt1)) (type: boolean)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -779,7 +779,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterLongColEqualLongColumn(col 0:date, col 0:date), FilterLongColNotEqualLongColumn(col 0:date, col 1:date), FilterLongColLessLongColumn(col 0:date, col 1:date), FilterLongColLessEqualLongColumn(col 0:date, col 1:date), FilterLongColGreaterLongColumn(col 1:date, col 0:date), FilterLongColGreaterEqualLongColumn(col 1:date, col 0:date))
predicate: ((dt1 < dt2) and (dt1 <= dt2) and (dt1 <> dt2) and (dt1 = dt1) and (dt2 > dt1) and (dt2 >= dt1)) (type: boolean)
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: dt1 (type: date), dt2 (type: date)
outputColumnNames: _col0, _col1
@@ -787,7 +787,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -797,7 +797,7 @@ STAGE PLANS:
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
valueColumns: 1:date
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: date)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -839,13 +839,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1]
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -937,7 +937,7 @@ STAGE PLANS:
TableScan
alias: vector_date_1
filterExpr: ((dt1 = DATE'2001-01-01') and (dt1 <> DATE'1970-01-01')) (type: boolean)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -947,7 +947,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterExprAndExpr(children: FilterDateColEqualDateScalar(col 0:date, val 11323), FilterDateColNotEqualDateScalar(col 0:date, val 0))
predicate: ((dt1 <> DATE'1970-01-01') and (dt1 = DATE'2001-01-01')) (type: boolean)
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: DATE'2001-01-01' (type: date), dt2 (type: date)
outputColumnNames: _col0, _col1
@@ -956,13 +956,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [3, 1]
selectExpressions: ConstantVectorExpression(val 11323) -> 3:date
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 336 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1050,7 +1050,7 @@ STAGE PLANS:
TableScan
alias: vector_date_1
filterExpr: (dt1) IN (DATE'1970-01-01', DATE'2001-01-01') (type: boolean)
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
vectorizationSchemaColumns: [0:dt1:date, 1:dt2:date, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>]
@@ -1060,7 +1060,7 @@ STAGE PLANS:
native: true
predicateExpression: FilterLongColumnInList(col 0:date, values [0, 11323])
predicate: (dt1) IN (DATE'1970-01-01', DATE'2001-01-01') (type: boolean)
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: dt1 (type: date)
outputColumnNames: _col0
@@ -1068,13 +1068,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0]
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 3 Data size: 168 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out b/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out
index 747b74a..6037324 100644
--- a/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_distinct_2.q.out
@@ -127,7 +127,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n3
- Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 195620 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -137,7 +137,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 8]
- Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 195620 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
Group By Vectorization:
className: VectorGroupByOperator
@@ -149,7 +149,7 @@ STAGE PLANS:
keys: t (type: tinyint), s (type: string)
mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 97812 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: string)
sort order: ++
@@ -158,7 +158,7 @@ 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: 2000 Data size: 357388 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 97812 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: vectorized, llap
LLAP IO: all inputs
Map Vectorization:
@@ -190,7 +190,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1000 Data size: 178694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 97812 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: tinyint)
outputColumnNames: _col0, _col1
@@ -198,13 +198,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1, 0]
- Statistics: Num rows: 1000 Data size: 178694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 97812 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1000 Data size: 178694 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 97812 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out
index a118b2e..759a09d 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out
@@ -127,7 +127,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vectortab2korc_n8
- Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 210964 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -137,7 +137,7 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 3, 8]
- Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2000 Data size: 210964 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: max(b)
Group By Vectorization:
@@ -151,7 +151,7 @@ STAGE PLANS:
keys: t (type: tinyint), s (type: string)
mode: hash
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 105812 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: tinyint), _col1 (type: string)
sort order: ++
@@ -160,7 +160,7 @@ 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: 2000 Data size: 372596 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 105812 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col2 (type: bigint)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -195,7 +195,7 @@ STAGE PLANS:
keys: KEY._col0 (type: tinyint), KEY._col1 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1000 Data size: 186298 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 105812 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint)
outputColumnNames: _col0, _col1, _col2
@@ -203,13 +203,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [1, 0, 2]
- Statistics: Num rows: 1000 Data size: 186298 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 105812 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 1000 Data size: 186298 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1000 Data size: 105812 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/9b376a7b/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out b/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out
index 6e0663c..d4afffb 100644
--- a/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_interval_1.q.out
@@ -86,7 +86,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -97,7 +97,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [2, 5, 6]
selectExpressions: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month, CastStringToIntervalDayTime(col 3:string) -> 6:interval_day_time
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 214 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -105,7 +105,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 214 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_year_month), _col2 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -135,13 +135,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 3, 1, 4, 2]
selectExpressions: ConstantVectorExpression(val 14) -> 3:interval_year_month, ConstantVectorExpression(val 1 02:03:04.000000000) -> 4:interval_day_time
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 254 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 254 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -215,7 +215,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 286 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -226,7 +226,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 7, 6, 9, 8]
selectExpressions: IntervalYearMonthColAddIntervalYearMonthColumn(col 5:interval_year_month, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 7:interval_year_month, IntervalYearMonthScalarAddIntervalYearMonthColumn(val 14, col 5:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month) -> 6:interval_year_month, IntervalYearMonthColSubtractIntervalYearMonthColumn(col 5:interval_year_month, col 8:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month, CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:interval_year_month, IntervalYearMonthScalarSubtractIntervalYearMonthColumn(val 14, col 5:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 5:interval_year_month) -> 8:interval_year_month
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -234,7 +234,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 176 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_year_month), _col2 (type: interval_year_month), _col3 (type: interval_year_month), _col4 (type: interval_year_month)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -264,13 +264,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 5, 1, 2, 6, 3, 4]
selectExpressions: ConstantVectorExpression(val 28) -> 5:interval_year_month, ConstantVectorExpression(val 0) -> 6:interval_year_month
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -352,7 +352,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 294 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -363,7 +363,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 7, 6, 9, 8]
selectExpressions: IntervalDayTimeColAddIntervalDayTimeColumn(col 5:interval_day_time, col 6:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time, CastStringToIntervalDayTime(col 3:string) -> 6:interval_day_time) -> 7:interval_day_time, IntervalDayTimeScalarAddIntervalDayTimeColumn(val 1 02:03:04.000000000, col 5:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time) -> 6:interval_day_time, IntervalDayTimeColSubtractIntervalDayTimeColumn(col 5:interval_day_time, col 8:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time, CastStringToIntervalDayTime(col 3:string) -> 8:interval_day_time) -> 9:interval_day_time, IntervalDayTimeScalarSubtractIntervalDayTimeColumn(val 1 02:03:04.000000000, col 5:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 5:interval_day_time) -> 8:interval_day_time
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -371,7 +371,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -401,13 +401,13 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 5, 1, 2, 6, 3, 4]
selectExpressions: ConstantVectorExpression(val 2 04:06:08.000000000) -> 5:interval_day_time, ConstantVectorExpression(val 0 00:00:00.000000000) -> 6:interval_day_time
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 480 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -501,7 +501,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 468 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -512,7 +512,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 5, 7, 6, 9, 8, 11, 12, 14, 15, 16, 17, 18]
selectExpressions: DateColAddIntervalYearMonthScalar(col 1:date, val 1-2) -> 5:date, DateColAddIntervalYearMonthColumn(col 1:date, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 7:date, IntervalYearMonthScalarAddDateColumn(val 1-2, col 1:interval_year_month) -> 6:date, IntervalYearMonthColAddDateColumn(col 8:interval_year_month, col 1:date)(children: CastStringToIntervalYearMonth(col 2:string) -> 8:interval_year_month) -> 9:date, DateColSubtractIntervalYearMonthScalar(col 1:date, val 1-2) -> 8:date, DateColSubtractIntervalYearMonthColumn(col 1:date, col 10:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 10:interval_year_month) -> 11:date, DateColAddIntervalDayTimeScalar(col 1:date, val 1 02:03:04.000000000) -> 12:timestamp, DateColAddIntervalDayTimeColumn(col 1:date, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time)
-> 14:timestamp, IntervalDayTimeScalarAddDateColumn(val 1 02:03:04.000000000, col 1:date) -> 15:timestamp, IntervalDayTimeColAddDateColumn(col 13:interval_day_time, col 1:date)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 16:timestamp, DateColSubtractIntervalDayTimeScalar(col 1:date, val 1 02:03:04.000000000) -> 17:timestamp, DateColSubtractIntervalDayTimeColumn(col 1:date, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 18:timestamp
- Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1264 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -520,7 +520,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1264 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: date), _col2 (type: date), _col3 (type: date), _col4 (type: date), _col5 (type: date), _col6 (type: date), _col7 (type: timestamp), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -549,13 +549,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
- Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1264 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1264 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -661,7 +661,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 436 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -672,7 +672,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 5, 7, 8, 9, 10, 11, 12, 14, 15, 16, 17, 18]
selectExpressions: TimestampColAddIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 5:timestamp, TimestampColAddIntervalYearMonthColumn(col 0:timestamp, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 7:timestamp, IntervalYearMonthScalarAddTimestampColumn(val 1-2, col 0:interval_year_month) -> 8:timestamp, IntervalYearMonthColAddTimestampColumn(col 6:interval_year_month, col 0:timestamp)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 9:timestamp, TimestampColSubtractIntervalYearMonthScalar(col 0:timestamp, val 1-2) -> 10:timestamp, TimestampColSubtractIntervalYearMonthColumn(col 0:timestamp, col 6:interval_year_month)(children: CastStringToIntervalYearMonth(col 2:string) -> 6:interval_year_month) -> 11:timestamp, TimestampColAddIntervalDayTimeScalar(col 0:timestamp, val 1 02:03:04.000000000) -> 12:timestamp, TimestampColAddIntervalDayTimeColumn(col 0:timestamp
, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 14:timestamp, IntervalDayTimeScalarAddTimestampColumn(val 1 02:03:04.000000000, col 0:timestamp) -> 15:timestamp, IntervalDayTimeColAddTimestampColumn(col 13:interval_day_time, col 0:timestamp)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 16:timestamp, TimestampColSubtractIntervalDayTimeScalar(col 0:timestamp, val 1 02:03:04.000000000) -> 17:timestamp, TimestampColSubtractIntervalDayTimeColumn(col 0:timestamp, col 13:interval_day_time)(children: CastStringToIntervalDayTime(col 3:string) -> 13:interval_day_time) -> 18:timestamp
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -680,7 +680,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: timestamp), _col2 (type: timestamp), _col3 (type: timestamp), _col4 (type: timestamp), _col5 (type: timestamp), _col6 (type: timestamp), _col7 (type: timestamp), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: timestamp), _col11 (type: timestamp), _col12 (type: timestamp)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -709,13 +709,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 816 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 1040 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -803,7 +803,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -814,7 +814,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [0, 5, 6, 7]
selectExpressions: TimestampColSubtractTimestampColumn(col 0:timestamp, col 0:timestamp) -> 5:interval_day_time, TimestampScalarSubtractTimestampColumn(val 2001-01-01 01:02:03, col 0:timestamp) -> 6:interval_day_time, TimestampColSubtractTimestampScalar(col 0:timestamp, val 2001-01-01 01:02:03) -> 7:interval_day_time
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: timestamp)
sort order: +
@@ -822,7 +822,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -851,13 +851,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 152 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -927,7 +927,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -938,7 +938,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 5, 6, 7]
selectExpressions: DateColSubtractDateColumn(col 1:date, col 1:date) -> 5:interval_day_time, DateScalarSubtractDateColumn(val 2001-01-01, col 1:date) -> 6:interval_day_time, DateColSubtractDateScalar(col 1:date, val 2001-01-01) -> 7:interval_day_time
- Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -946,7 +946,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -975,13 +975,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3]
- Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 112 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1057,7 +1057,7 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: vector_interval_1
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
TableScan Vectorization:
native: true
Select Operator
@@ -1068,7 +1068,7 @@ STAGE PLANS:
native: true
projectedOutputColumnNums: [1, 5, 6, 7, 8, 9, 10]
selectExpressions: TimestampColSubtractDateColumn(col 0:timestamp, col 1:date) -> 5:interval_day_time, TimestampScalarSubtractDateColumn(val 2001-01-01 01:02:03, col 1:date) -> 6:interval_day_time, TimestampColSubtractDateScalar(col 0:timestamp, val 2001-01-01) -> 7:interval_day_time, DateColSubtractTimestampColumn(col 1:date, col 0:timestamp) -> 8:interval_day_time, DateColSubtractTimestampScalar(col 1:date, val 2001-01-01 01:02:03) -> 9:interval_day_time, DateScalarSubtractTimestampColumn(val 2001-01-01, col 0:timestamp) -> 10:interval_day_time
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: date)
sort order: +
@@ -1076,7 +1076,7 @@ STAGE PLANS:
className: VectorReduceSinkObjectHashOperator
native: true
nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: interval_day_time), _col2 (type: interval_day_time), _col3 (type: interval_day_time), _col4 (type: interval_day_time), _col5 (type: interval_day_time), _col6 (type: interval_day_time)
Execution mode: vectorized, llap
LLAP IO: all inputs
@@ -1105,13 +1105,13 @@ STAGE PLANS:
className: VectorSelectOperator
native: true
projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6]
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
File Sink Vectorization:
className: VectorFileSinkOperator
native: false
- Statistics: Num rows: 2 Data size: 192 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 2 Data size: 256 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat