| PREHOOK: query: CREATE TABLE T1_n90(key STRING, val STRING) STORED AS TEXTFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T1_n90 |
| POSTHOOK: query: CREATE TABLE T1_n90(key STRING, val STRING) STORED AS TEXTFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T1_n90 |
| PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n90 |
| PREHOOK: type: LOAD |
| #### A masked pattern was here #### |
| PREHOOK: Output: default@t1_n90 |
| POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/T1.txt' INTO TABLE T1_n90 |
| POSTHOOK: type: LOAD |
| #### A masked pattern was here #### |
| POSTHOOK: Output: default@t1_n90 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 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) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| 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) -> 3:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: key (type: string), val (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: key:string, val:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint] |
| 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: 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: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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 |
| 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 key, val, count(1) FROM T1_n90 GROUP BY CUBE(key, val) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, count(1) FROM T1_n90 GROUP BY CUBE(key, val) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 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) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| 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) -> 3:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: key (type: string), val (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: key:string, val:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint] |
| 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: 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: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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 |
| 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 key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 1 11 1 |
| 1 NULL 1 |
| 2 12 1 |
| 2 NULL 1 |
| 3 13 1 |
| 3 NULL 1 |
| 7 17 1 |
| 7 NULL 1 |
| 8 18 1 |
| 8 28 1 |
| 8 NULL 2 |
| NULL 11 1 |
| NULL 12 1 |
| NULL 13 1 |
| NULL 17 1 |
| NULL 18 1 |
| NULL 28 1 |
| NULL NULL 6 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, GROUPING__ID, count(1) FROM T1_n90 GROUP BY key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, GROUPING__ID, count(1) FROM T1_n90 GROUP BY key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 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) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: _col0, _col1 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| 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) -> 3:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: _col0 (type: string), _col1 (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: key:string, val:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint] |
| 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: 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, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint), _col3 (type: bigint) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1, 2, 3] |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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 |
| 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 key, val, GROUPING__ID, count(1) FROM T1_n90 GROUP BY key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT key, val, GROUPING__ID, count(1) FROM T1_n90 GROUP BY key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 1 11 0 1 |
| 1 NULL 1 1 |
| 2 12 0 1 |
| 2 NULL 1 1 |
| 3 13 0 1 |
| 3 NULL 1 1 |
| 7 17 0 1 |
| 7 NULL 1 1 |
| 8 18 0 1 |
| 8 28 0 1 |
| 8 NULL 1 2 |
| NULL 11 2 1 |
| NULL 12 2 1 |
| NULL 13 2 1 |
| NULL 17 2 1 |
| NULL 18 2 1 |
| NULL 28 2 1 |
| NULL NULL 3 6 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 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) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: count(DISTINCT val) |
| keys: key (type: string), 0L (type: bigint), val (type: string) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint) |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Execution mode: llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| notVectorizedReason: Aggregation Function expression for GROUPBY operator: DISTINCT with Groupingsets not supported |
| vectorized: false |
| Reducer 2 |
| 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: GROUPBY operator: DISTINCT not supported |
| vectorized: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(DISTINCT KEY._col2:0._col0) |
| keys: KEY._col0 (type: string), KEY._col1 (type: bigint) |
| mode: mergepartial |
| outputColumnNames: _col0, _col2 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col2 (type: bigint) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 368 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 key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 1 1 |
| 2 1 |
| 3 1 |
| 7 1 |
| 8 2 |
| NULL 6 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 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_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| 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) -> 3:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: key (type: string), val (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: rand() (type: double) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| 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 |
| partitionColumns: 4:double |
| valueColumns: 3:bigint |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: key:string, val:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint] |
| 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: 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: PARTIALS |
| 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: partials |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| 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 |
| partitionColumns: 0:string, 1:string |
| valueColumns: 3:bigint |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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: 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: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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 |
| 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 key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT key, val, count(1) FROM T1_n90 GROUP BY key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 1 11 1 |
| 1 NULL 1 |
| 2 12 1 |
| 2 NULL 1 |
| 3 13 1 |
| 3 NULL 1 |
| 7 17 1 |
| 7 NULL 1 |
| 8 18 1 |
| 8 28 1 |
| 8 NULL 2 |
| NULL 11 1 |
| NULL 12 1 |
| NULL 13 1 |
| NULL 17 1 |
| NULL 18 1 |
| NULL 28 1 |
| NULL NULL 6 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| SELECT key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 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_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: count(DISTINCT val) |
| keys: key (type: string), 0L (type: bigint), val (type: string) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: _col0 (type: string) |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Execution mode: llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| notVectorizedReason: Aggregation Function expression for GROUPBY operator: DISTINCT with Groupingsets not supported |
| vectorized: false |
| Reducer 2 |
| 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: GROUPBY operator: DISTINCT not supported |
| vectorized: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(DISTINCT KEY._col2:0._col0) |
| keys: KEY._col0 (type: string), KEY._col1 (type: bigint) |
| mode: partials |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: bigint) |
| null sort order: zz |
| sort order: ++ |
| Map-reduce partition columns: _col0 (type: string) |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col2 (type: bigint) |
| Reducer 3 |
| 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: GROUPBY operator: DISTINCT not supported |
| vectorized: false |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(VALUE._col0) |
| keys: KEY._col0 (type: string), KEY._col1 (type: bigint) |
| mode: final |
| outputColumnNames: _col0, _col2 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col2 (type: bigint) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 368 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 key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| POSTHOOK: query: SELECT key, count(distinct val) FROM T1_n90 GROUP BY key with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| #### A masked pattern was here #### |
| 1 1 |
| 2 1 |
| 3 1 |
| 7 1 |
| 8 2 |
| NULL 6 |
| PREHOOK: query: CREATE TABLE T2_n55(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T2_n55 |
| POSTHOOK: query: CREATE TABLE T2_n55(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T2_n55 |
| PREHOOK: query: CREATE TABLE T3_n19(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T3_n19 |
| POSTHOOK: query: CREATE TABLE T3_n19(key1 STRING, key2 STRING, val INT) STORED AS TEXTFILE |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T3_n19 |
| PREHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| FROM T1_n90 |
| INSERT OVERWRITE TABLE T2_n55 SELECT key, val, count(1) group by key, val with cube |
| INSERT OVERWRITE TABLE T3_n19 SELECT key, val, sum(1) group by key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| PREHOOK: Output: default@t2_n55 |
| PREHOOK: Output: default@t3_n19 |
| POSTHOOK: query: EXPLAIN VECTORIZATION DETAIL |
| FROM T1_n90 |
| INSERT OVERWRITE TABLE T2_n55 SELECT key, val, count(1) group by key, val with cube |
| INSERT OVERWRITE TABLE T3_n19 SELECT key, val, sum(1) group by key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| POSTHOOK: Output: default@t2_n55 |
| POSTHOOK: Output: default@t3_n19 |
| PLAN VECTORIZATION: |
| enabled: true |
| enabledConditionsMet: [hive.vectorized.execution.enabled IS true] |
| |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-0 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-0 |
| Stage-1 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| 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 <- Map 1 (SIMPLE_EDGE) |
| Reducer 6 <- Reducer 5 (SIMPLE_EDGE) |
| Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: t1_n90 |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| TableScan Vectorization: |
| native: true |
| vectorizationSchemaColumns: [0:key:string, 1:val:string, 2:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: count(1) |
| Group By Vectorization: |
| aggregators: VectorUDAFCount(ConstantVectorExpression(val 1) -> 4:int) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 3:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: key (type: string), val (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: rand() (type: double) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| 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 |
| partitionColumns: 4:double |
| valueColumns: 3:bigint |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Select Operator |
| expressions: key (type: string), val (type: string) |
| outputColumnNames: key, val |
| Select Vectorization: |
| className: VectorSelectOperator |
| native: true |
| projectedOutputColumnNums: [0, 1] |
| Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: sum(1) |
| Group By Vectorization: |
| aggregators: VectorUDAFSumLong(ConstantVectorExpression(val 1) -> 6:int) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: HASH |
| keyExpressions: col 0:string, col 1:string, ConstantVectorExpression(val 0) -> 5:bigint |
| native: false |
| vectorProcessingMode: HASH |
| projectedOutputColumnNums: [0] |
| keys: key (type: string), val (type: string), 0L (type: bigint) |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) |
| null sort order: zzz |
| sort order: +++ |
| Map-reduce partition columns: rand() (type: double) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| 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 |
| partitionColumns: 4:double |
| valueColumns: 3:bigint |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map Vectorization: |
| enabled: true |
| enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true |
| inputFormatFeatureSupport: [DECIMAL_64] |
| featureSupportInUse: [DECIMAL_64] |
| inputFileFormats: org.apache.hadoop.mapred.TextInputFormat |
| allNative: false |
| usesVectorUDFAdaptor: false |
| vectorized: true |
| rowBatchContext: |
| dataColumnCount: 2 |
| includeColumns: [0, 1] |
| dataColumns: key:string, val:string |
| partitionColumnCount: 0 |
| scratchColumnTypeNames: [bigint, bigint, bigint, bigint] |
| 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: 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: PARTIALS |
| 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: partials |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| 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 |
| partitionColumns: 0:string, 1:string |
| valueColumns: 3:bigint |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Reducer 3 |
| 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: count(VALUE._col0) |
| keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) |
| mode: final |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int) |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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.t2_n55 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) |
| outputColumnNames: key1, key2, val |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: max(length(key1)), avg(COALESCE(length(key1),0)), count(1), count(key1), compute_bit_vector(key1, 'hll'), max(length(key2)), avg(COALESCE(length(key2),0)), count(key2), compute_bit_vector(key2, 'hll'), min(val), max(val), count(val), compute_bit_vector(val, 'hll') |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: int), _col11 (type: bigint), _col12 (type: binary) |
| 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(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8), min(VALUE._col9), max(VALUE._col10), count(VALUE._col11), compute_bit_vector(VALUE._col12) |
| mode: final |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'LONG' (type: string), UDFToLong(_col9) (type: bigint), UDFToLong(_col10) (type: bigint), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1000 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 |
| Reducer 5 |
| 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: sum(VALUE._col0) |
| Group By Vectorization: |
| aggregators: VectorUDAFSumLong(col 3:bigint) -> bigint |
| className: VectorGroupByOperator |
| groupByMode: PARTIALS |
| 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: partials |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| 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) |
| Reduce Sink Vectorization: |
| className: VectorReduceSinkObjectHashOperator |
| 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 |
| partitionColumns: 0:string, 1:string |
| valueColumns: 3:bigint |
| Statistics: Num rows: 4 Data size: 1472 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col3 (type: bigint) |
| Reducer 6 |
| 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: sum(VALUE._col0) |
| keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: bigint) |
| mode: final |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| pruneGroupingSetId: true |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), UDFToInteger(_col3) (type: int) |
| outputColumnNames: _col0, _col1, _col2 |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| 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.t3_n19 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int) |
| outputColumnNames: key1, key2, val |
| Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE |
| Group By Operator |
| aggregations: max(length(key1)), avg(COALESCE(length(key1),0)), count(1), count(key1), compute_bit_vector(key1, 'hll'), max(length(key2)), avg(COALESCE(length(key2),0)), count(key2), compute_bit_vector(key2, 'hll'), min(val), max(val), count(val), compute_bit_vector(val, 'hll') |
| minReductionHashAggr: 0.99 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: int), _col11 (type: bigint), _col12 (type: binary) |
| Reducer 7 |
| 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), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8), min(VALUE._col9), max(VALUE._col10), count(VALUE._col11), compute_bit_vector(VALUE._col12) |
| mode: final |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'LONG' (type: string), UDFToLong(_col9) (type: bigint), UDFToLong(_col10) (type: bigint), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17 |
| Statistics: Num rows: 1 Data size: 1000 Basic stats: COMPLETE Column stats: NONE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1000 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-3 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| 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.t2_n55 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: key1, key2, val |
| Column Types: string, string, int |
| Table: default.t2_n55 |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| 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.t3_n19 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: key1, key2, val |
| Column Types: string, string, int |
| Table: default.t3_n19 |
| |
| PREHOOK: query: FROM T1_n90 |
| INSERT OVERWRITE TABLE T2_n55 SELECT key, val, count(1) group by key, val with cube |
| INSERT OVERWRITE TABLE T3_n19 SELECT key, val, sum(1) group by key, val with cube |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t1_n90 |
| PREHOOK: Output: default@t2_n55 |
| PREHOOK: Output: default@t3_n19 |
| POSTHOOK: query: FROM T1_n90 |
| INSERT OVERWRITE TABLE T2_n55 SELECT key, val, count(1) group by key, val with cube |
| INSERT OVERWRITE TABLE T3_n19 SELECT key, val, sum(1) group by key, val with cube |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t1_n90 |
| POSTHOOK: Output: default@t2_n55 |
| POSTHOOK: Output: default@t3_n19 |
| POSTHOOK: Lineage: t2_n55.key1 SIMPLE [(t1_n90)t1_n90.FieldSchema(name:key, type:string, comment:null), ] |
| POSTHOOK: Lineage: t2_n55.key2 SIMPLE [(t1_n90)t1_n90.FieldSchema(name:val, type:string, comment:null), ] |
| POSTHOOK: Lineage: t2_n55.val EXPRESSION [(t1_n90)t1_n90.null, ] |
| POSTHOOK: Lineage: t3_n19.key1 SIMPLE [(t1_n90)t1_n90.FieldSchema(name:key, type:string, comment:null), ] |
| POSTHOOK: Lineage: t3_n19.key2 SIMPLE [(t1_n90)t1_n90.FieldSchema(name:val, type:string, comment:null), ] |
| POSTHOOK: Lineage: t3_n19.val EXPRESSION [(t1_n90)t1_n90.null, ] |
