| PREHOOK: query: DROP TABLE parquet_complex_types_staging |
| PREHOOK: type: DROPTABLE |
| POSTHOOK: query: DROP TABLE parquet_complex_types_staging |
| POSTHOOK: type: DROPTABLE |
| PREHOOK: query: DROP TABLE parquet_complex_types |
| PREHOOK: type: DROPTABLE |
| POSTHOOK: query: DROP TABLE parquet_complex_types |
| POSTHOOK: type: DROPTABLE |
| PREHOOK: query: CREATE TABLE parquet_complex_types_staging ( |
| id int, |
| m1 map<string, varchar(5)>, |
| l1 array<int>, |
| st1 struct<c1:int, c2:string>, |
| listIndex int |
| ) ROW FORMAT DELIMITED |
| FIELDS TERMINATED BY '|' |
| COLLECTION ITEMS TERMINATED BY ',' |
| MAP KEYS TERMINATED BY ':' |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@parquet_complex_types_staging |
| POSTHOOK: query: CREATE TABLE parquet_complex_types_staging ( |
| id int, |
| m1 map<string, varchar(5)>, |
| l1 array<int>, |
| st1 struct<c1:int, c2:string>, |
| listIndex int |
| ) ROW FORMAT DELIMITED |
| FIELDS TERMINATED BY '|' |
| COLLECTION ITEMS TERMINATED BY ',' |
| MAP KEYS TERMINATED BY ':' |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@parquet_complex_types_staging |
| PREHOOK: query: CREATE TABLE parquet_complex_types ( |
| id int, |
| m1 map<string, varchar(5)>, |
| l1 array<int>, |
| st1 struct<c1:int, c2:string>, |
| listIndex int |
| ) STORED AS PARQUET |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@parquet_complex_types |
| POSTHOOK: query: CREATE TABLE parquet_complex_types ( |
| id int, |
| m1 map<string, varchar(5)>, |
| l1 array<int>, |
| st1 struct<c1:int, c2:string>, |
| listIndex int |
| ) STORED AS PARQUET |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@parquet_complex_types |
| PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/parquet_complex_types.txt' OVERWRITE INTO TABLE parquet_complex_types_staging |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@parquet_complex_types_staging |
| POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/parquet_complex_types.txt' OVERWRITE INTO TABLE parquet_complex_types_staging |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@parquet_complex_types_staging |
| PREHOOK: query: INSERT OVERWRITE TABLE parquet_complex_types |
| SELECT id, m1, l1, st1, listIndex FROM parquet_complex_types_staging where id < 1024 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types_staging |
| PREHOOK: Output: default@parquet_complex_types |
| POSTHOOK: query: INSERT OVERWRITE TABLE parquet_complex_types |
| SELECT id, m1, l1, st1, listIndex FROM parquet_complex_types_staging where id < 1024 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types_staging |
| POSTHOOK: Output: default@parquet_complex_types |
| POSTHOOK: Lineage: parquet_complex_types.id SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:id, type:int, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.l1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:l1, type:array<int>, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.listindex SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:listindex, type:int, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.m1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:m1, type:map<string,varchar(5)>, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.st1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:st1, type:struct<c1:int,c2:string>, comment:null), ] |
| PREHOOK: query: select count(*) from parquet_complex_types |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select count(*) from parquet_complex_types |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| 1023 |
| PREHOOK: query: explain vectorization expression select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization expression select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-0 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: parquet_complex_types |
| Statistics: Num rows: 1023 Data size: 5115 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| Select Operator |
| expressions: l1 (type: array<int>), l1[0] (type: int), l1[1] (type: int), l1[listindex] (type: int), listindex (type: int) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [2, 6, 7, 8, 4] |
| selectExpressions: ListIndexColScalar(col 2:array<int>, col 0:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 1:int) -> 7:int, ListIndexColColumn(col 2:array<int>, col 4:int) -> 8:int |
| Statistics: Num rows: 1023 Data size: 5115 Basic stats: COMPLETE Column stats: NONE |
| Limit |
| Number of rows: 10 |
| Limit Vectorization: |
| className: VectorLimitOperator |
| native: true |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| |
| Stage: Stage-0 |
| Fetch Operator |
| limit: 10 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| [100,101] 100 101 100 0 |
| [102,103] 102 103 103 1 |
| [104,105] 104 105 104 0 |
| [106,107] 106 107 107 1 |
| [108,109] 108 109 108 0 |
| [110,111] 110 111 111 1 |
| [112,113] 112 113 112 0 |
| [114,115] 114 115 115 1 |
| [116,117] 116 117 116 0 |
| [118,119] 118 119 119 1 |
| PREHOOK: query: explain vectorization expression select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] limit 10 |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization expression select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] limit 10 |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-2 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-2 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: parquet_complex_types |
| Statistics: Num rows: 1023 Data size: 5115 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| Filter Operator |
| Filter Vectorization: |
| className: VectorFilterOperator |
| native: true |
| predicateExpression: FilterLongColGreaterLongScalar(col 6:int, val 1000)(children: ListIndexColScalar(col 2:array<int>, col 0:int) -> 6:int) |
| predicate: (l1[0] > 1000) (type: boolean) |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: l1[1] (type: int), l1[0] (type: int) |
| outputColumnNames: _col0, _col1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [6, 7] |
| selectExpressions: ListIndexColScalar(col 2:array<int>, col 1:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 0:int) -> 7:int |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: sum(_col1) |
| Group By Vectorization: |
| aggregators: VectorUDAFSumLong(col 7:int) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 6:int |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: int) |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkOperator |
| native: false |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| TopN Hash Memory Usage: 0.1 |
| value expressions: _col1 (type: bigint) |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Vectorization: |
| enabled: false |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true |
| enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: sum(VALUE._col0) |
| keys: KEY._col0 (type: int) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: _col1 (type: bigint), _col0 (type: int) |
| outputColumnNames: _col0, _col2 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| |
| Stage: Stage-2 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| TableScan Vectorization: |
| native: true |
| Reduce Output Operator |
| key expressions: _col2 (type: int) |
| sort order: + |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkOperator |
| native: false |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| TopN Hash Memory Usage: 0.1 |
| value expressions: _col0 (type: bigint) |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Vectorization: |
| enabled: false |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true |
| enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Reduce Operator Tree: |
| Select Operator |
| expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: int) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| Limit |
| Number of rows: 10 |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 10 Data size: 50 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-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] desc limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] desc limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| 2144 2145 |
| 2142 2143 |
| 2140 2141 |
| 2138 2139 |
| 2136 2137 |
| 2134 2135 |
| 2132 2133 |
| 2130 2131 |
| 2128 2129 |
| 2126 2127 |
| PREHOOK: query: INSERT OVERWRITE TABLE parquet_complex_types |
| SELECT id, m1, l1, st1, listIndex FROM parquet_complex_types_staging where id < 1025 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types_staging |
| PREHOOK: Output: default@parquet_complex_types |
| POSTHOOK: query: INSERT OVERWRITE TABLE parquet_complex_types |
| SELECT id, m1, l1, st1, listIndex FROM parquet_complex_types_staging where id < 1025 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types_staging |
| POSTHOOK: Output: default@parquet_complex_types |
| POSTHOOK: Lineage: parquet_complex_types.id SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:id, type:int, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.l1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:l1, type:array<int>, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.listindex SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:listindex, type:int, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.m1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:m1, type:map<string,varchar(5)>, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.st1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:st1, type:struct<c1:int,c2:string>, comment:null), ] |
| PREHOOK: query: select count(*) from parquet_complex_types |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select count(*) from parquet_complex_types |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| 1024 |
| PREHOOK: query: explain vectorization expression select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization expression select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-0 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: parquet_complex_types |
| Statistics: Num rows: 1024 Data size: 5120 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| Select Operator |
| expressions: l1 (type: array<int>), l1[0] (type: int), l1[1] (type: int), l1[listindex] (type: int), listindex (type: int) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [2, 6, 7, 8, 4] |
| selectExpressions: ListIndexColScalar(col 2:array<int>, col 0:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 1:int) -> 7:int, ListIndexColColumn(col 2:array<int>, col 4:int) -> 8:int |
| Statistics: Num rows: 1024 Data size: 5120 Basic stats: COMPLETE Column stats: NONE |
| Limit |
| Number of rows: 10 |
| Limit Vectorization: |
| className: VectorLimitOperator |
| native: true |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| |
| Stage: Stage-0 |
| Fetch Operator |
| limit: 10 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| [100,101] 100 101 100 0 |
| [102,103] 102 103 103 1 |
| [104,105] 104 105 104 0 |
| [106,107] 106 107 107 1 |
| [108,109] 108 109 108 0 |
| [110,111] 110 111 111 1 |
| [112,113] 112 113 112 0 |
| [114,115] 114 115 115 1 |
| [116,117] 116 117 116 0 |
| [118,119] 118 119 119 1 |
| PREHOOK: query: explain vectorization expression select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] limit 10 |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization expression select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] limit 10 |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-2 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-2 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: parquet_complex_types |
| Statistics: Num rows: 1024 Data size: 5120 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| Filter Operator |
| Filter Vectorization: |
| className: VectorFilterOperator |
| native: true |
| predicateExpression: FilterLongColGreaterLongScalar(col 6:int, val 1000)(children: ListIndexColScalar(col 2:array<int>, col 0:int) -> 6:int) |
| predicate: (l1[0] > 1000) (type: boolean) |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: l1[1] (type: int), l1[0] (type: int) |
| outputColumnNames: _col0, _col1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [6, 7] |
| selectExpressions: ListIndexColScalar(col 2:array<int>, col 1:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 0:int) -> 7:int |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: sum(_col1) |
| Group By Vectorization: |
| aggregators: VectorUDAFSumLong(col 7:int) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 6:int |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: int) |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkOperator |
| native: false |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| TopN Hash Memory Usage: 0.1 |
| value expressions: _col1 (type: bigint) |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Vectorization: |
| enabled: false |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true |
| enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: sum(VALUE._col0) |
| keys: KEY._col0 (type: int) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: _col1 (type: bigint), _col0 (type: int) |
| outputColumnNames: _col0, _col2 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| |
| Stage: Stage-2 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| TableScan Vectorization: |
| native: true |
| Reduce Output Operator |
| key expressions: _col2 (type: int) |
| sort order: + |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkOperator |
| native: false |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| TopN Hash Memory Usage: 0.1 |
| value expressions: _col0 (type: bigint) |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Vectorization: |
| enabled: false |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true |
| enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Reduce Operator Tree: |
| Select Operator |
| expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: int) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| Limit |
| Number of rows: 10 |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 10 Data size: 50 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-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] desc limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] desc limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| 2146 2147 |
| 2144 2145 |
| 2142 2143 |
| 2140 2141 |
| 2138 2139 |
| 2136 2137 |
| 2134 2135 |
| 2132 2133 |
| 2130 2131 |
| 2128 2129 |
| PREHOOK: query: INSERT OVERWRITE TABLE parquet_complex_types |
| SELECT id, m1, l1, st1, listIndex FROM parquet_complex_types_staging |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types_staging |
| PREHOOK: Output: default@parquet_complex_types |
| POSTHOOK: query: INSERT OVERWRITE TABLE parquet_complex_types |
| SELECT id, m1, l1, st1, listIndex FROM parquet_complex_types_staging |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types_staging |
| POSTHOOK: Output: default@parquet_complex_types |
| POSTHOOK: Lineage: parquet_complex_types.id SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:id, type:int, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.l1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:l1, type:array<int>, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.listindex SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:listindex, type:int, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.m1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:m1, type:map<string,varchar(5)>, comment:null), ] |
| POSTHOOK: Lineage: parquet_complex_types.st1 SIMPLE [(parquet_complex_types_staging)parquet_complex_types_staging.FieldSchema(name:st1, type:struct<c1:int,c2:string>, comment:null), ] |
| PREHOOK: query: select count(*) from parquet_complex_types |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select count(*) from parquet_complex_types |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| 1025 |
| PREHOOK: query: explain vectorization expression select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization expression select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-0 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: parquet_complex_types |
| Statistics: Num rows: 1025 Data size: 5125 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| Select Operator |
| expressions: l1 (type: array<int>), l1[0] (type: int), l1[1] (type: int), l1[listindex] (type: int), listindex (type: int) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [2, 6, 7, 8, 4] |
| selectExpressions: ListIndexColScalar(col 2:array<int>, col 0:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 1:int) -> 7:int, ListIndexColColumn(col 2:array<int>, col 4:int) -> 8:int |
| Statistics: Num rows: 1025 Data size: 5125 Basic stats: COMPLETE Column stats: NONE |
| Limit |
| Number of rows: 10 |
| Limit Vectorization: |
| className: VectorLimitOperator |
| native: true |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| |
| Stage: Stage-0 |
| Fetch Operator |
| limit: 10 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select l1, l1[0], l1[1], l1[listIndex], listIndex from parquet_complex_types limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| [100,101] 100 101 100 0 |
| [102,103] 102 103 103 1 |
| [104,105] 104 105 104 0 |
| [106,107] 106 107 107 1 |
| [108,109] 108 109 108 0 |
| [110,111] 110 111 111 1 |
| [112,113] 112 113 112 0 |
| [114,115] 114 115 115 1 |
| [116,117] 116 117 116 0 |
| [118,119] 118 119 119 1 |
| PREHOOK: query: explain vectorization expression select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] limit 10 |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization expression select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] limit 10 |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-2 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-2 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: parquet_complex_types |
| Statistics: Num rows: 1025 Data size: 5125 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| Filter Operator |
| Filter Vectorization: |
| className: VectorFilterOperator |
| native: true |
| predicateExpression: FilterLongColGreaterLongScalar(col 6:int, val 1000)(children: ListIndexColScalar(col 2:array<int>, col 0:int) -> 6:int) |
| predicate: (l1[0] > 1000) (type: boolean) |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: l1[1] (type: int), l1[0] (type: int) |
| outputColumnNames: _col0, _col1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [6, 7] |
| selectExpressions: ListIndexColScalar(col 2:array<int>, col 1:int) -> 6:int, ListIndexColScalar(col 2:array<int>, col 0:int) -> 7:int |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: sum(_col1) |
| Group By Vectorization: |
| aggregators: VectorUDAFSumLong(col 7:int) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 6:int |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: int) |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkOperator |
| native: false |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Statistics: Num rows: 341 Data size: 1705 Basic stats: COMPLETE Column stats: NONE |
| TopN Hash Memory Usage: 0.1 |
| value expressions: _col1 (type: bigint) |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.parquet.MapredParquetInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Vectorization: |
| enabled: false |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true |
| enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: sum(VALUE._col0) |
| keys: KEY._col0 (type: int) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: _col1 (type: bigint), _col0 (type: int) |
| outputColumnNames: _col0, _col2 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe |
| |
| Stage: Stage-2 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| TableScan Vectorization: |
| native: true |
| Reduce Output Operator |
| key expressions: _col2 (type: int) |
| sort order: + |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkOperator |
| native: false |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| TopN Hash Memory Usage: 0.1 |
| value expressions: _col0 (type: bigint) |
| Execution mode: vectorized |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [] |
| featureSupportInUse: [] |
| inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Vectorization: |
| enabled: false |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true |
| enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| Reduce Operator Tree: |
| Select Operator |
| expressions: VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: int) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 170 Data size: 850 Basic stats: COMPLETE Column stats: NONE |
| Limit |
| Number of rows: 10 |
| Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 10 Data size: 50 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-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] desc limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| POSTHOOK: query: select sum(l1[0]), l1[1] from parquet_complex_types where l1[0] > 1000 group by l1[1] order by l1[1] desc limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@parquet_complex_types |
| #### A masked pattern was here #### |
| 2148 2149 |
| 2146 2147 |
| 2144 2145 |
| 2142 2143 |
| 2140 2141 |
| 2138 2139 |
| 2136 2137 |
| 2134 2135 |
| 2132 2133 |
| 2130 2131 |
