| PREHOOK: query: CREATE TABLE srcorc_n1 STORED AS ORC AS SELECT * FROM src |
| PREHOOK: type: CREATETABLE_AS_SELECT |
| PREHOOK: Input: default@src |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@srcorc_n1 |
| POSTHOOK: query: CREATE TABLE srcorc_n1 STORED AS ORC AS SELECT * FROM src |
| POSTHOOK: type: CREATETABLE_AS_SELECT |
| POSTHOOK: Input: default@src |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@srcorc_n1 |
| POSTHOOK: Lineage: srcorc_n1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] |
| POSTHOOK: Lineage: srcorc_n1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] |
| PREHOOK: query: CREATE TABLE dest1_n154(c1 STRING) STORED AS ORC |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@dest1_n154 |
| POSTHOOK: query: CREATE TABLE dest1_n154(c1 STRING) STORED AS ORC |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@dest1_n154 |
| PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION |
| FROM srcorc_n1 |
| INSERT OVERWRITE TABLE dest1_n154 SELECT substr(srcorc_n1.key,1,1) GROUP BY substr(srcorc_n1.key,1,1) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@srcorc_n1 |
| PREHOOK: Output: default@dest1_n154 |
| POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION |
| FROM srcorc_n1 |
| INSERT OVERWRITE TABLE dest1_n154 SELECT substr(srcorc_n1.key,1,1) GROUP BY substr(srcorc_n1.key,1,1) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@srcorc_n1 |
| POSTHOOK: Output: default@dest1_n154 |
| 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-3 depends on stages: Stage-0 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) |
| Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: srcorc_n1 |
| Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |
| TableScan Vectorization: |
| native: true |
| Select Operator |
| expressions: substr(key, 1, 1) (type: string) |
| outputColumnNames: _col0 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [3] |
| selectExpressions: StringSubstrColStartLen(col 0:string, start 0, length 1) -> 3:string |
| Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: rand() (type: double) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| native: true |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| 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: true |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reducer 2 |
| Execution mode: vectorized, llap |
| Reduce Vectorization: |
| enabled: true |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Operator Tree: |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: PARTIAL1 |
| keyExpressions: col 0:string |
| native: false |
| vectorProcessingMode: STREAMING |
| projectedOutputColumnNums: [] |
| keys: KEY._col0 (type: string) |
| mode: partial1 |
| outputColumnNames: _col0 |
| Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: _col0 (type: string) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkStringOperator |
| native: true |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| Statistics: Num rows: 500 Data size: 42500 Basic stats: COMPLETE Column stats: COMPLETE |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Vectorization: |
| enabled: true |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| Reduce Operator Tree: |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: FINAL |
| keyExpressions: col 0:string |
| native: false |
| vectorProcessingMode: STREAMING |
| projectedOutputColumnNums: [] |
| keys: KEY._col0 (type: string) |
| mode: final |
| outputColumnNames: _col0 |
| Statistics: Num rows: 316 Data size: 26860 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 316 Data size: 26860 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| name: default.dest1_n154 |
| Select Operator |
| expressions: _col0 (type: string) |
| outputColumnNames: c1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0] |
| Statistics: Num rows: 316 Data size: 26860 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Map-reduce partition columns: rand() (type: double) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| native: true |
| nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true |
| valueExpressions: StringLength(col 0:string) -> 1:int, VectorCoalesce(columns [2, 3])(children: StringLength(col 0:string) -> 2:int, ConstantVectorExpression(val 0) -> 3:int) -> 4:int |
| Statistics: Num rows: 316 Data size: 26860 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: length(c1) (type: int), COALESCE(length(c1),0) (type: int), c1 (type: string) |
| Reducer 4 |
| Execution mode: llap |
| Reduce Vectorization: |
| enabled: true |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true |
| notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_bit_vector not supported |
| vectorized: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(1), count(VALUE._col3), compute_bit_vector(VALUE._col3, 'hll') |
| mode: partial1 |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4 |
| Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 240 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary) |
| Reducer 5 |
| Execution mode: llap |
| Reduce Vectorization: |
| enabled: true |
| enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true |
| notVectorizedReason: Aggregation Function expression for GROUPBY operator: UDF compute_bit_vector not supported |
| vectorized: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4) |
| mode: final |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4 |
| Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 |
| Statistics: Num rows: 1 Data size: 266 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 266 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-2 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| name: default.dest1_n154 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: c1 |
| Column Types: string |
| Table: default.dest1_n154 |
| |
| PREHOOK: query: FROM srcorc_n1 |
| INSERT OVERWRITE TABLE dest1_n154 SELECT substr(srcorc_n1.key,1,1) GROUP BY substr(srcorc_n1.key,1,1) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@srcorc_n1 |
| PREHOOK: Output: default@dest1_n154 |
| POSTHOOK: query: FROM srcorc_n1 |
| INSERT OVERWRITE TABLE dest1_n154 SELECT substr(srcorc_n1.key,1,1) GROUP BY substr(srcorc_n1.key,1,1) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@srcorc_n1 |
| POSTHOOK: Output: default@dest1_n154 |
| POSTHOOK: Lineage: dest1_n154.c1 EXPRESSION [(srcorc_n1)srcorc_n1.FieldSchema(name:key, type:string, comment:null), ] |
| PREHOOK: query: SELECT dest1_n154.* FROM dest1_n154 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@dest1_n154 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT dest1_n154.* FROM dest1_n154 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@dest1_n154 |
| #### A masked pattern was here #### |
| 0 |
| 1 |
| 2 |
| 3 |
| 4 |
| 5 |
| 6 |
| 7 |
| 8 |
| 9 |