| PREHOOK: query: CREATE TABLE T1_text_n1(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T1_text_n1 |
| POSTHOOK: query: CREATE TABLE T1_text_n1(a STRING, b STRING, c STRING) ROW FORMAT DELIMITED FIELDS TERMINATED BY ' ' STORED AS TEXTFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T1_text_n1 |
| PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_text_n1 |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@t1_text_n1 |
| POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/grouping_sets.txt' INTO TABLE T1_text_n1 |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@t1_text_n1 |
| PREHOOK: query: CREATE TABLE T1_n33 STORED AS ORC AS SELECT * FROM T1_text_n1 |
| PREHOOK: type: CREATETABLE_AS_SELECT |
| PREHOOK: Input: default@t1_text_n1 |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T1_n33 |
| POSTHOOK: query: CREATE TABLE T1_n33 STORED AS ORC AS SELECT * FROM T1_text_n1 |
| POSTHOOK: type: CREATETABLE_AS_SELECT |
| POSTHOOK: Input: default@t1_text_n1 |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T1_n33 |
| POSTHOOK: Lineage: t1_n33.a SIMPLE [(t1_text_n1)t1_text_n1.FieldSchema(name:a, type:string, comment:null), ] |
| POSTHOOK: Lineage: t1_n33.b SIMPLE [(t1_text_n1)t1_text_n1.FieldSchema(name:b, type:string, comment:null), ] |
| POSTHOOK: Lineage: t1_n33.c SIMPLE [(t1_text_n1)t1_text_n1.FieldSchema(name:c, type:string, comment:null), ] |
| t1_text_n1.a t1_text_n1.b t1_text_n1.c |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| Explain |
| 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 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n33 |
| Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: a (type: string), b (type: string) |
| outputColumnNames: a, b |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [] |
| keys: a (type: string), b (type: string) |
| minReductionHashAggr: 0.16666669 |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string) |
| null sort order: zz |
| sort order: ++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string |
| 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: 3 Data size: 510 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: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 3 |
| includeColumns: [0, 1] |
| dataColumns: a:string, b:string, c:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| 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 |
| reduceColumnNullOrder: zz |
| reduceColumnSortOrder: ++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| dataColumns: KEY._col0:string, KEY._col1:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| Reduce Operator Tree: |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: MERGEPARTIAL |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: MERGE_PARTIAL |
| projectedOutputColumnNums: [] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: count() |
| Group By Vectorization: |
| aggregators: VectorUDAFCountStar(*) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 2:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.0 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string, 2:bigint |
| 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:bigint |
| Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col3 (type: bigint) |
| 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 |
| reduceColumnNullOrder: zzz |
| reduceColumnSortOrder: +++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 4 |
| dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:bigint |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(VALUE._col0) |
| Group By Vectorization: |
| aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: MERGEPARTIAL |
| keyExpressions: col 0:string, col 1:string, col 2:bigint |
| native: false |
| vectorProcessingMode: MERGE_PARTIAL |
| projectedOutputColumnNums: [0] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) |
| outputColumnNames: _col0, _col1, _col2 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1, 2] |
| Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 6 Data size: 1068 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-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by cube(a, b) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by cube(a, b) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| Explain |
| 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 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n33 |
| Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: a (type: string), b (type: string) |
| outputColumnNames: a, b |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [] |
| keys: a (type: string), b (type: string) |
| minReductionHashAggr: 0.16666669 |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string) |
| null sort order: zz |
| sort order: ++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string |
| 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: 3 Data size: 510 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: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 3 |
| includeColumns: [0, 1] |
| dataColumns: a:string, b:string, c:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| 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 |
| reduceColumnNullOrder: zz |
| reduceColumnSortOrder: ++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| dataColumns: KEY._col0:string, KEY._col1:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| Reduce Operator Tree: |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: MERGEPARTIAL |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: MERGE_PARTIAL |
| projectedOutputColumnNums: [] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: count() |
| Group By Vectorization: |
| aggregators: VectorUDAFCountStar(*) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 2:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.0 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string, 2:bigint |
| 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:bigint |
| Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col3 (type: bigint) |
| 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 |
| reduceColumnNullOrder: zzz |
| reduceColumnSortOrder: +++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 4 |
| dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:bigint |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(VALUE._col0) |
| Group By Vectorization: |
| aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: MERGEPARTIAL |
| keyExpressions: col 0:string, col 1:string, col 2:bigint |
| native: false |
| vectorProcessingMode: MERGE_PARTIAL |
| projectedOutputColumnNums: [0] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 6 Data size: 1116 Basic stats: COMPLETE Column stats: COMPLETE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) |
| outputColumnNames: _col0, _col1, _col2 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1, 2] |
| Statistics: Num rows: 6 Data size: 1068 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 6 Data size: 1068 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-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| a b _c2 |
| 1 1 1 |
| 1 NULL 1 |
| 2 2 1 |
| 2 3 1 |
| 2 NULL 2 |
| 3 2 1 |
| 3 NULL 1 |
| 5 2 1 |
| 5 NULL 1 |
| 8 1 1 |
| 8 NULL 1 |
| NULL 1 2 |
| NULL 2 3 |
| NULL 3 1 |
| NULL NULL 6 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| Explain |
| 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 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| Reducer 4 <- Reducer 3 (SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n33 |
| Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:a:string, 1:b:string, 2:c:string, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: a (type: string), b (type: string) |
| outputColumnNames: a, b |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 6 Data size: 1020 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [] |
| keys: a (type: string), b (type: string) |
| minReductionHashAggr: 0.16666669 |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string) |
| null sort order: zz |
| sort order: ++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string |
| 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: 3 Data size: 510 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: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 3 |
| includeColumns: [0, 1] |
| dataColumns: a:string, b:string, c:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| 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 |
| reduceColumnNullOrder: zz |
| reduceColumnSortOrder: ++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| dataColumns: KEY._col0:string, KEY._col1:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| Reduce Operator Tree: |
| Group By Operator |
| Group By Vectorization: |
| className: VectorGroupByOperator |
| groupByMode: MERGEPARTIAL |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: MERGE_PARTIAL |
| projectedOutputColumnNums: [] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 510 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: count() |
| Group By Vectorization: |
| aggregators: VectorUDAFCountStar(*) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: string), _col1 (type: string) |
| minReductionHashAggr: 0.6666666 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string) |
| null sort order: zz |
| sort order: ++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string |
| 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: 2:bigint |
| Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col2 (type: bigint) |
| 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 |
| reduceColumnNullOrder: zz |
| reduceColumnSortOrder: ++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 3 |
| dataColumns: KEY._col0:string, KEY._col1:string, VALUE._col0:bigint |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint] |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(VALUE._col0) |
| Group By Vectorization: |
| aggregators: VectorUDAFCountMerge(col 2:bigint) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: PARTIALS |
| keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:bigint |
| native: false |
| vectorProcessingMode: STREAMING |
| projectedOutputColumnNums: [0] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string), 0L (type: bigint) |
| mode: partials |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkMultiKeyOperator |
| keyColumns: 0:string, 1:string, 2:bigint |
| 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:bigint |
| Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col3 (type: bigint) |
| Reducer 4 |
| 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 |
| reduceColumnNullOrder: zzz |
| reduceColumnSortOrder: +++ |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 4 |
| dataColumns: KEY._col0:string, KEY._col1:string, KEY._col2:bigint, VALUE._col0:bigint |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [] |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(VALUE._col0) |
| Group By Vectorization: |
| aggregators: VectorUDAFCountMerge(col 3:bigint) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: FINAL |
| keyExpressions: col 0:string, col 1:string, col 2:bigint |
| native: false |
| vectorProcessingMode: STREAMING |
| projectedOutputColumnNums: [0] |
| keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) |
| mode: final |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 4 Data size: 744 Basic stats: COMPLETE Column stats: COMPLETE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: bigint) |
| outputColumnNames: _col0, _col1, _col2 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1, 2] |
| Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| File Sink Vectorization: |
| className: VectorFileSinkOperator |
| native: false |
| Statistics: Num rows: 4 Data size: 712 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-0 |
| Fetch Operator |
| limit: -1 |
| Processor Tree: |
| ListSink |
| |
| PREHOOK: query: SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT a, b, count(*) FROM |
| (SELECT a, b, count(1) from T1_n33 group by a, b) subq1 group by a, b with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n33 |
| #### A masked pattern was here #### |
| a b _c2 |
| 1 1 1 |
| 1 NULL 1 |
| 2 2 1 |
| 2 3 1 |
| 2 NULL 2 |
| 3 2 1 |
| 3 NULL 1 |
| 5 2 1 |
| 5 NULL 1 |
| 8 1 1 |
| 8 NULL 1 |
| NULL 1 2 |
| NULL 2 3 |
| NULL 3 1 |
| NULL NULL 6 |