| PREHOOK: query: CREATE TABLE orc_table_1(v1 STRING, a INT) STORED AS ORC |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@orc_table_1 |
| POSTHOOK: query: CREATE TABLE orc_table_1(v1 STRING, a INT) STORED AS ORC |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@orc_table_1 |
| PREHOOK: query: CREATE TABLE orc_table_2(c INT, v2 STRING) STORED AS ORC |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@orc_table_2 |
| POSTHOOK: query: CREATE TABLE orc_table_2(c INT, v2 STRING) STORED AS ORC |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@orc_table_2 |
| PREHOOK: query: insert into table orc_table_1 values ("<null1>", null),("one", 1),("one", 1),("two", 2),("three", 3),("<null2>", null) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: _dummy_database@_dummy_table |
| PREHOOK: Output: default@orc_table_1 |
| POSTHOOK: query: insert into table orc_table_1 values ("<null1>", null),("one", 1),("one", 1),("two", 2),("three", 3),("<null2>", null) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: _dummy_database@_dummy_table |
| POSTHOOK: Output: default@orc_table_1 |
| POSTHOOK: Lineage: orc_table_1.a SCRIPT [] |
| POSTHOOK: Lineage: orc_table_1.v1 SCRIPT [] |
| PREHOOK: query: insert into table orc_table_2 values (0, "ZERO"),(2, "TWO"), (3, "THREE"),(null, "<NULL1>"),(4, "FOUR"),(null, "<NULL2>") |
| PREHOOK: type: QUERY |
| PREHOOK: Input: _dummy_database@_dummy_table |
| PREHOOK: Output: default@orc_table_2 |
| POSTHOOK: query: insert into table orc_table_2 values (0, "ZERO"),(2, "TWO"), (3, "THREE"),(null, "<NULL1>"),(4, "FOUR"),(null, "<NULL2>") |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: _dummy_database@_dummy_table |
| POSTHOOK: Output: default@orc_table_2 |
| POSTHOOK: Lineage: orc_table_2.c SCRIPT [] |
| POSTHOOK: Lineage: orc_table_2.v2 SCRIPT [] |
| PREHOOK: query: select * from orc_table_1 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@orc_table_1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from orc_table_1 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@orc_table_1 |
| #### A masked pattern was here #### |
| <null1> NULL |
| <null2> NULL |
| one 1 |
| one 1 |
| three 3 |
| two 2 |
| PREHOOK: query: select * from orc_table_2 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@orc_table_2 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from orc_table_2 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@orc_table_2 |
| #### A masked pattern was here #### |
| 0 ZERO |
| 2 TWO |
| 3 THREE |
| 4 FOUR |
| NULL <NULL1> |
| NULL <NULL2> |
| PREHOOK: query: explain vectorization detail |
| select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 left outer join orc_table_2 t2 on t1.a = t2.c |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization detail |
| select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 left outer join orc_table_2 t2 on t1.a = t2.c |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-4 is a root stage |
| Stage-3 depends on stages: Stage-4 |
| Stage-0 depends on stages: Stage-3 |
| |
| STAGE PLANS: |
| Stage: Stage-4 |
| Map Reduce Local Work |
| Alias -> Map Local Tables: |
| $hdt$_1:t2 |
| Fetch Operator |
| limit: -1 |
| Alias -> Map Local Operator Tree: |
| $hdt$_1:t2 |
| TableScan |
| alias: t2 |
| Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: c (type: int), v2 (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE |
| HashTable Sink Operator |
| keys: |
| 0 _col1 (type: int) |
| 1 _col0 (type: int) |
| |
| Stage: Stage-3 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: t1 |
| Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:v1:string, 1:a:int, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: v1 (type: string), a (type: int) |
| outputColumnNames: _col0, _col1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE |
| Map Join Operator |
| condition map: |
| Left Outer Join 0 to 1 |
| keys: |
| 0 _col1 (type: int) |
| 1 _col0 (type: int) |
| Map Join Vectorization: |
| bigTableKeyExpressions: col 1:int |
| bigTableValueExpressions: col 0:string, col 1:int |
| className: VectorMapJoinOperator |
| native: false |
| nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 6 Data size: 598 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 6 Data size: 598 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: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: v1:string, a:int |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint, string] |
| Local Work: |
| Map Reduce Local Work |
| |
| Stage: Stage-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 left outer join orc_table_2 t2 on t1.a = t2.c |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@orc_table_1 |
| PREHOOK: Input: default@orc_table_2 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 left outer join orc_table_2 t2 on t1.a = t2.c |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@orc_table_1 |
| POSTHOOK: Input: default@orc_table_2 |
| #### A masked pattern was here #### |
| <null1> NULL NULL NULL |
| <null2> NULL NULL NULL |
| one 1 NULL NULL |
| one 1 NULL NULL |
| three 3 3 THREE |
| two 2 2 TWO |
| PREHOOK: query: explain vectorization detail |
| select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 right outer join orc_table_2 t2 on t1.a = t2.c |
| PREHOOK: type: QUERY |
| POSTHOOK: query: explain vectorization detail |
| select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 right outer join orc_table_2 t2 on t1.a = t2.c |
| POSTHOOK: type: QUERY |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-4 is a root stage |
| Stage-3 depends on stages: Stage-4 |
| Stage-0 depends on stages: Stage-3 |
| |
| STAGE PLANS: |
| Stage: Stage-4 |
| Map Reduce Local Work |
| Alias -> Map Local Tables: |
| $hdt$_0:t1 |
| Fetch Operator |
| limit: -1 |
| Alias -> Map Local Operator Tree: |
| $hdt$_0:t1 |
| TableScan |
| alias: t1 |
| Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: v1 (type: string), a (type: int) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 6 Data size: 544 Basic stats: COMPLETE Column stats: NONE |
| HashTable Sink Operator |
| keys: |
| 0 _col1 (type: int) |
| 1 _col0 (type: int) |
| |
| Stage: Stage-3 |
| Map Reduce |
| Map Operator Tree: |
| TableScan |
| alias: t2 |
| Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:c:int, 1:v2:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: c (type: int), v2 (type: string) |
| outputColumnNames: _col0, _col1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 6 Data size: 550 Basic stats: COMPLETE Column stats: NONE |
| Map Join Operator |
| condition map: |
| Right Outer Join 0 to 1 |
| keys: |
| 0 _col1 (type: int) |
| 1 _col0 (type: int) |
| Map Join Vectorization: |
| bigTableKeyExpressions: col 0:int |
| bigTableValueExpressions: col 0:int, col 1:string |
| className: VectorMapJoinOperator |
| native: false |
| nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true |
| nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 6 Data size: 598 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 6 Data size: 598 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: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: c:int, v2:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [string, bigint] |
| Local Work: |
| Map Reduce Local Work |
| |
| Stage: Stage-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 right outer join orc_table_2 t2 on t1.a = t2.c |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@orc_table_1 |
| PREHOOK: Input: default@orc_table_2 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select t1.v1, t1.a, t2.c, t2.v2 from orc_table_1 t1 right outer join orc_table_2 t2 on t1.a = t2.c |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@orc_table_1 |
| POSTHOOK: Input: default@orc_table_2 |
| #### A masked pattern was here #### |
| NULL NULL 0 ZERO |
| NULL NULL 4 FOUR |
| NULL NULL NULL <NULL1> |
| NULL NULL NULL <NULL2> |
| three 3 3 THREE |
| two 2 2 TWO |