http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/mergejoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out index cec7c7e..ff0b1f1 100644 --- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out @@ -410,7 +410,7 @@ STAGE PLANS: TableScan alias: a filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -420,7 +420,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 22498 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -428,7 +428,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 22498 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -439,7 +439,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 22498 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -463,7 +463,7 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -473,7 +473,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 46458 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -481,7 +481,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 475 Data size: 46458 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -492,7 +492,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 46458 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -520,15 +520,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 522 Data size: 51103 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -557,13 +557,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1592,7 +1592,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -1603,7 +1603,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1614,7 +1614,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1637,7 +1637,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -1648,7 +1648,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1659,7 +1659,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1687,15 +1687,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 53794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1724,13 +1724,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1788,7 +1788,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -1799,7 +1799,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1810,7 +1810,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1833,7 +1833,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -1844,7 +1844,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1855,7 +1855,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1883,15 +1883,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 53794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 4000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1920,13 +1920,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1984,7 +1984,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -1995,7 +1995,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2006,7 +2006,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 242 Data size: 23672 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2029,7 +2029,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2040,7 +2040,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2051,7 +2051,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 500 Data size: 48904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2079,15 +2079,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 550 Data size: 53794 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 742 Data size: 5936 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2116,13 +2116,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2170,11 +2170,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Reducer 6 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 1 <- Reducer 7 (BROADCAST_EDGE) + Map 8 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2182,7 +2184,7 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter)))) (type: boolean) - Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2192,7 +2194,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:string), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 1:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue)) predicate: ((value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter))) and key is not null and value is not null) (type: boolean) - Statistics: Num rows: 218 Data size: 39121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 @@ -2200,7 +2202,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 218 Data size: 39121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + @@ -2211,7 +2213,7 @@ STAGE PLANS: 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 valueColumnNums: [0] - Statistics: Num rows: 218 Data size: 39121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2231,7 +2233,7 @@ STAGE PLANS: partitionColumnCount: 1 partitionColumns: ds:string scratchColumnTypeNames: [] - Map 5 + Map 6 Map Operator Tree: TableScan alias: c @@ -2314,12 +2316,12 @@ STAGE PLANS: dataColumns: key:string, value:string partitionColumnCount: 0 scratchColumnTypeNames: [] - Map 7 + Map 8 Map Operator Tree: TableScan alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter)))) (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2327,9 +2329,9 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) - predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 0:int, left 0, right 0), VectorInBloomFilterColDynamicValue)) + predicate: ((key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter))) and key is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -2337,7 +2339,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2348,7 +2350,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2377,12 +2379,25 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 239 Data size: 43033 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 239 Data size: 43033 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 39 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=25) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2392,15 +2407,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -2429,18 +2444,56 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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 - Reducer 6 + 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: + reduceColumnSortOrder: + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: VALUE._col0:int, VALUE._col1:int, VALUE._col2:binary + partitionColumnCount: 0 + scratchColumnTypeNames: [] + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=25) + Group By Vectorization: + aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary + className: VectorGroupByOperator + groupByMode: FINAL + native: false + vectorProcessingMode: STREAMING + projectedOutputColumnNums: [0, 1, 2] + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + keyColumnNums: [] + 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 + valueColumnNums: [0, 1, 2] + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Reducer 7 Execution mode: vectorized, llap Reduce Vectorization: enabled: true @@ -2530,7 +2583,7 @@ STAGE PLANS: TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 65252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2540,7 +2593,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 1:string) predicate: value is not null (type: boolean) - Statistics: Num rows: 230 Data size: 62016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 @@ -2548,7 +2601,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 230 Data size: 62016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + @@ -2559,7 +2612,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 62016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2583,7 +2636,7 @@ STAGE PLANS: TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 134584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2593,7 +2646,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 1:string) predicate: value is not null (type: boolean) - Statistics: Num rows: 475 Data size: 127854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 @@ -2601,7 +2654,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 475 Data size: 127854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + @@ -2612,7 +2665,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 127854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2640,15 +2693,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - Statistics: Num rows: 522 Data size: 140639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2677,13 +2730,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2746,7 +2799,7 @@ STAGE PLANS: TableScan alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2756,7 +2809,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -2764,7 +2817,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2775,7 +2828,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2799,7 +2852,7 @@ STAGE PLANS: TableScan alias: s3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2809,7 +2862,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -2817,7 +2870,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2828,7 +2881,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2852,7 +2905,7 @@ STAGE PLANS: TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2862,7 +2915,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -2870,7 +2923,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2881,7 +2934,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 483 Data size: 1843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 624 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2905,7 +2958,7 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -2915,7 +2968,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -2923,7 +2976,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -2934,7 +2987,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2963,12 +3016,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 253 Data size: 965 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 1528 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 483 Data size: 1843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 624 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -2978,15 +3031,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 531 Data size: 2027 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1009 Data size: 8072 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -3015,13 +3068,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3063,7 +3116,7 @@ STAGE PLANS: TableScan alias: a filterExpr: value is not null (type: boolean) - Statistics: Num rows: 242 Data size: 65252 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3073,7 +3126,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 1:string) predicate: value is not null (type: boolean) - Statistics: Num rows: 230 Data size: 62016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 @@ -3081,7 +3134,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 230 Data size: 62016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + @@ -3092,7 +3145,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 62016 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22022 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3116,7 +3169,7 @@ STAGE PLANS: TableScan alias: b filterExpr: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 134584 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3126,7 +3179,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 1:string) predicate: value is not null (type: boolean) - Statistics: Num rows: 475 Data size: 127854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: value (type: string) outputColumnNames: _col1 @@ -3134,7 +3187,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1] - Statistics: Num rows: 475 Data size: 127854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + @@ -3145,7 +3198,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 127854 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3173,15 +3226,15 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - Statistics: Num rows: 522 Data size: 140639 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -3210,13 +3263,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3262,11 +3315,13 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Reducer 6 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Map 1 <- Reducer 7 (BROADCAST_EDGE) + Map 8 <- Reducer 5 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 3 <- Map 8 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE) + Reducer 5 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -3274,7 +3329,7 @@ STAGE PLANS: TableScan alias: a filterExpr: (key is not null and value is not null and (value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter)))) (type: boolean) - Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3284,7 +3339,7 @@ STAGE PLANS: native: true predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), SelectColumnIsNotNull(col 1:string), FilterExprAndExpr(children: FilterStringColumnBetweenDynamicValue(col 1:string, left NULL, right NULL), VectorInBloomFilterColDynamicValue)) predicate: ((value BETWEEN DynamicValue(RS_10_c_value_min) AND DynamicValue(RS_10_c_value_max) and in_bloom_filter(value, DynamicValue(RS_10_c_value_bloom_filter))) and key is not null and value is not null) (type: boolean) - Statistics: Num rows: 218 Data size: 39121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 @@ -3292,7 +3347,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1] - Statistics: Num rows: 218 Data size: 39121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + @@ -3303,7 +3358,7 @@ STAGE PLANS: 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 valueColumnNums: [0] - Statistics: Num rows: 218 Data size: 39121 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 22990 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: all inputs @@ -3323,7 +3378,7 @@ STAGE PLANS: partitionColumnCount: 1 partitionColumns: ds:string scratchColumnTypeNames: [] - Map 5 + Map 6 Map Operator Tree: TableScan alias: c @@ -3406,12 +3461,12 @@ STAGE PLANS: dataColumns: key:string, value:string partitionColumnCount: 0 scratchColumnTypeNames: [] - Map 7 + Map 8 Map Operator Tree: TableScan alias: b - filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE + filterExpr: (key is not null and (key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter)))) (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3419,9 +3474,9 @@ STAGE PLANS: Filter Vectorization: className: VectorFilterOperator native: true - predicateExpression: SelectColumnIsNotNull(col 0:int) - predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + predicateExpression: FilterExprAndExpr(children: SelectColumnIsNotNull(col 0:int), FilterExprAndExpr(children: FilterLongColumnBetweenDynamicValue(col 0:int, left 0, right 0), VectorInBloomFilterColDynamicValue)) + predicate: ((key BETWEEN DynamicValue(RS_12_a_key_min) AND DynamicValue(RS_12_a_key_max) and in_bloom_filter(key, DynamicValue(RS_12_a_key_bloom_filter))) and key is not null) (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -3429,7 +3484,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -3440,7 +3495,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3469,12 +3524,25 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 239 Data size: 43033 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 239 Data size: 43033 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 39 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 39 Data size: 156 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=25) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -3484,15 +3552,15 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -3521,18 +3589,56 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 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 - Reducer 6 + 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: + reduceColumnSortOrder: + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + rowBatchContext: + dataColumnCount: 3 + dataColumns: VALUE._col0:int, VALUE._col1:int, VALUE._col2:binary + partitionColumnCount: 0 + scratchColumnTypeNames: [] + Reduce Operator Tree: + Group By Operator + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=25) + Group By Vectorization: + aggregators: VectorUDAFMinLong(col 0:int) -> int, VectorUDAFMaxLong(col 1:int) -> int, VectorUDAFBloomFilterMerge(col 2:binary) -> binary + className: VectorGroupByOperator + groupByMode: FINAL + native: false + vectorProcessingMode: STREAMING + projectedOutputColumnNums: [0, 1, 2] + mode: final + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Reduce Sink Vectorization: + className: VectorReduceSinkEmptyKeyOperator + keyColumnNums: [] + 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 + valueColumnNums: [0, 1, 2] + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: binary) + Reducer 7 Execution mode: vectorized, llap Reduce Vectorization: enabled: true @@ -3630,7 +3736,7 @@ STAGE PLANS: TableScan alias: s1 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3640,7 +3746,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -3648,7 +3754,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -3659,7 +3765,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3683,7 +3789,7 @@ STAGE PLANS: TableScan alias: s3 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3693,7 +3799,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -3701,7 +3807,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -3712,7 +3818,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3736,7 +3842,7 @@ STAGE PLANS: TableScan alias: s2 filterExpr: key is not null (type: boolean) - Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3746,7 +3852,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -3754,7 +3860,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -3765,7 +3871,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 483 Data size: 1843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 624 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3789,7 +3895,7 @@ STAGE PLANS: TableScan alias: b filterExpr: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:key:int, 1:value:string, 2:ds:string, 3:ROW__ID:struct<transactionid:bigint,bucketid:int,rowid:bigint>] @@ -3799,7 +3905,7 @@ STAGE PLANS: native: true predicateExpression: SelectColumnIsNotNull(col 0:int) predicate: key is not null (type: boolean) - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int) outputColumnNames: _col0 @@ -3807,7 +3913,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -3818,7 +3924,7 @@ STAGE PLANS: 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 valueColumnNums: [] - Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3847,12 +3953,12 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 253 Data size: 965 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 382 Data size: 1528 Basic stats: COMPLETE C
<TRUNCATED>
