http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out index 2ab11da..b7db028 100644 --- a/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_partitioned_date_time.q.out @@ -979,7 +979,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_date - Statistics: Num rows: 137 Data size: 94360 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -989,13 +989,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 62584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 62584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1242,7 +1242,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_date - Statistics: Num rows: 137 Data size: 94360 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -1252,7 +1252,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 94360 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -1260,7 +1260,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 94360 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Execution mode: vectorized, llap @@ -1290,13 +1290,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 62584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -1304,7 +1304,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Reducer 3 @@ -1323,19 +1323,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2018,7 +2018,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_timestamp - Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -2028,13 +2028,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2281,7 +2281,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_orc_partitioned_timestamp - Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -2291,7 +2291,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -2299,7 +2299,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 96472 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Execution mode: vectorized, llap @@ -2329,13 +2329,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -2343,7 +2343,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Reducer 3 @@ -2362,19 +2362,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3580,7 +3580,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_date - Statistics: Num rows: 137 Data size: 63269 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -3590,13 +3590,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 62584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 62584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3843,7 +3843,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_date - Statistics: Num rows: 137 Data size: 63269 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -3853,7 +3853,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 63269 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -3861,7 +3861,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 63269 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Execution mode: vectorized, llap @@ -3891,13 +3891,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 62584 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: date) sort order: ++ @@ -3905,7 +3905,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: timestamp), _col3 (type: float) Reducer 3 @@ -3924,19 +3924,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4619,7 +4619,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_timestamp - Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -4629,13 +4629,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4882,7 +4882,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: flights_tiny_parquet_partitioned_timestamp - Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -4892,7 +4892,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5] - Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -4900,7 +4900,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 137 Data size: 63189 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Execution mode: vectorized, llap @@ -4930,13 +4930,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 137 Data size: 62504 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 137 Data size: 39593 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col4 (type: int), _col5 (type: timestamp) sort order: ++ @@ -4944,7 +4944,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: date), _col3 (type: float) Reducer 3 @@ -4963,19 +4963,19 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [2, 3, 4, 5, 0, 1] - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 25 Limit Vectorization: className: VectorLimitOperator native: true - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 25 Data size: 11800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 25 Data size: 7225 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/load_dyn_part1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/load_dyn_part1.q.out b/ql/src/test/results/clientpositive/load_dyn_part1.q.out index ae0779c..6b48d8d 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part1.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part1.q.out @@ -65,11 +65,13 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0, Stage-5 + Stage-5 depends on stages: Stage-2 + Stage-7 depends on stages: Stage-1, Stage-5 + Stage-6 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-2 @@ -85,11 +87,28 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Filter Operator predicate: (ds > '2008-04-08') (type: boolean) Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE @@ -97,12 +116,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, hr + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: '2008-12-31' (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 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 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -131,7 +194,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part1_n0 - Stage: Stage-3 + Stage: Stage-4 Stats Work Basic Stats Work: Column Stats Desc: @@ -139,7 +202,45 @@ STAGE PLANS: Column Types: string, string Table: default.nzhang_part1_n0 - Stage: Stage-4 + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: '2008-12-31' (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Execution mode: vectorized + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: '2008-12-31' (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '2008-12-31' (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 333 Data size: 3537 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-7 + Stats Work + Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.nzhang_part2_n0 + + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -176,14 +277,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part2_n0 - Stage: Stage-5 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.nzhang_part2_n0 - PREHOOK: query: from srcpart insert overwrite table nzhang_part1_n0 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table nzhang_part2_n0 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08' http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/load_dyn_part10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/load_dyn_part10.q.out b/ql/src/test/results/clientpositive/load_dyn_part10.q.out index c6d9b6c..a5b75bc 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part10.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part10.q.out @@ -50,8 +50,9 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -65,11 +66,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - sort order: + - Map-reduce partition columns: _col2 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), '2008-12-31' (type: string), _col2 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 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-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string) + sort order: + + Map-reduce partition columns: _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -98,7 +144,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part10 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/load_dyn_part3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/load_dyn_part3.q.out b/ql/src/test/results/clientpositive/load_dyn_part3.q.out index ebf3c52..440e39b 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part3.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part3.q.out @@ -52,8 +52,9 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -67,11 +68,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 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-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -100,7 +146,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part3 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/load_dyn_part4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/load_dyn_part4.q.out b/ql/src/test/results/clientpositive/load_dyn_part4.q.out index e30d6ae..f102e0e 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part4.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part4.q.out @@ -62,8 +62,9 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -77,11 +78,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1000 Data size: 10624 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-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -110,7 +156,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part4 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/load_dyn_part8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/load_dyn_part8.q.out b/ql/src/test/results/clientpositive/load_dyn_part8.q.out index 1037a33..86c2910 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part8.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part8.q.out @@ -57,11 +57,13 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0 - Stage-4 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-4 - Stage-5 depends on stages: Stage-1 + Stage-3 depends on stages: Stage-2 + Stage-0 depends on stages: Stage-3 + Stage-4 depends on stages: Stage-0 + Stage-5 depends on stages: Stage-2 + Stage-7 depends on stages: Stage-1, Stage-5 + Stage-6 depends on stages: Stage-2 + Stage-1 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-2 @@ -79,14 +81,43 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - null sort order: aa - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types string,string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Filter Operator isSamplingPred: false predicate: (ds > '2008-04-08') (type: boolean) @@ -95,6 +126,34 @@ STAGE PLANS: expressions: key (type: string), value (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, hr + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: '2008-12-31' (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types string,string,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false File Output Operator compressed: false GlobalTableId: 0 @@ -113,7 +172,6 @@ STAGE PLANS: TotalFiles: 1 GatherStats: false MultiFileSpray: false - Execution mode: vectorized Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -320,6 +378,82 @@ STAGE PLANS: /srcpart/ds=2008-04-09/hr=12 [srcpart] Needs Tagging: false Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + tag: -1 + value expressions: _col0 (type: string), _col1 (type: string) + auto parallelism: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10004 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types string,string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types string,string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: +#### A masked pattern was here #### + Needs Tagging: false + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 @@ -382,12 +516,99 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part8_n0 - Stage: Stage-3 + Stage: Stage-4 Stats Work Basic Stats Work: #### A masked pattern was here #### - Stage: Stage-4 + Stage: Stage-5 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + key expressions: '2008-12-31' (type: string), _col1 (type: string) + null sort order: aa + sort order: ++ + Map-reduce partition columns: '2008-12-31' (type: string), _col1 (type: string) + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10005 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types string,string,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types string,string,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary> + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: +#### A masked pattern was here #### + Needs Tagging: false + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: '2008-12-31' (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), '2008-12-31' (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-7 + Stats Work + Basic Stats Work: +#### A masked pattern was here #### + Column Stats Desc: + Columns: key, value + Column Types: string, string + Table: default.nzhang_part8_n0 + Is Table Level Stats: false + + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -406,7 +627,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -mr-10004 + base file name: -mr-10006 input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: @@ -493,16 +714,6 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part8_n0 - Stage: Stage-5 - Stats Work - Basic Stats Work: -#### A masked pattern was here #### - Column Stats Desc: - Columns: key, value - Column Types: string, string - Table: default.nzhang_part8_n0 - Is Table Level Stats: false - PREHOOK: query: from srcpart insert overwrite table nzhang_part8_n0 partition (ds, hr) select key, value, ds, hr where ds <= '2008-04-08' insert overwrite table nzhang_part8_n0 partition(ds='2008-12-31', hr) select key, value, hr where ds > '2008-04-08' http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/load_dyn_part9.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/load_dyn_part9.q.out b/ql/src/test/results/clientpositive/load_dyn_part9.q.out index 4e272bb..af34de5 100644 --- a/ql/src/test/results/clientpositive/load_dyn_part9.q.out +++ b/ql/src/test/results/clientpositive/load_dyn_part9.q.out @@ -50,8 +50,9 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - Stage-2 depends on stages: Stage-0 + Stage-2 depends on stages: Stage-1 + Stage-0 depends on stages: Stage-2 + Stage-3 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 @@ -65,11 +66,56 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string), _col3 (type: string) - sort order: ++ - Map-reduce partition columns: _col2 (type: string), _col3 (type: string) - value expressions: _col0 (type: string), _col1 (type: string) + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) + outputColumnNames: key, value, ds, hr + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), hr (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 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-2 + Map Reduce + Map Operator Tree: + TableScan + Reduce Output Operator + key expressions: _col2 (type: string), _col3 (type: string) + sort order: ++ + Map-reduce partition columns: _col2 (type: string), _col3 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized Reduce Operator Tree: Select Operator @@ -98,7 +144,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.nzhang_part9 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: Column Stats Desc: http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/merge3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/merge3.q.out b/ql/src/test/results/clientpositive/merge3.q.out index 0b4da94..fc115bd 100644 --- a/ql/src/test/results/clientpositive/merge3.q.out +++ b/ql/src/test/results/clientpositive/merge3.q.out @@ -2394,13 +2394,14 @@ FROM `default`.`merge_src_part` WHERE `ds` IS NOT NULL STAGE DEPENDENCIES: Stage-1 is a root stage - Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5 - Stage-4 - Stage-0 depends on stages: Stage-4, Stage-3, Stage-6 - Stage-2 depends on stages: Stage-0 - Stage-3 + Stage-2 depends on stages: Stage-1 + Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 - Stage-6 depends on stages: Stage-5 + Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 + Stage-3 depends on stages: Stage-0 + Stage-4 + Stage-6 + Stage-7 depends on stages: Stage-6 STAGE PLANS: Stage: Stage-1 @@ -2415,15 +2416,43 @@ STAGE PLANS: expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col2 (type: string) - tag: -1 - value expressions: _col0 (type: string), _col1 (type: string) - auto parallelism: false - Execution mode: vectorized + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + auto parallelism: false + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2 + columns.types string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -2528,6 +2557,82 @@ STAGE PLANS: /merge_src_part/ds=2008-04-09 [merge_src_part] Needs Tagging: false Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + + Stage: Stage-2 + Map Reduce + Map Operator Tree: + TableScan + GatherStats: false + Reduce Output Operator + key expressions: _col2 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col2 (type: string) + tag: -1 + value expressions: _col0 (type: string), _col1 (type: string) + auto parallelism: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### + Partition + base file name: -mr-10002 + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2 + columns.types string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2 + columns.types string,string,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Truncated Path -> Alias: +#### A masked pattern was here #### + Needs Tagging: false + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY._col2 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -2562,10 +2667,10 @@ STAGE PLANS: GatherStats: true MultiFileSpray: false - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-4 + Stage: Stage-5 Move Operator files: hdfs directory: true @@ -2598,7 +2703,7 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.merge_src_part2 - Stage: Stage-2 + Stage: Stage-3 Stats Work Basic Stats Work: #### A masked pattern was here #### @@ -2608,7 +2713,7 @@ STAGE PLANS: Table: default.merge_src_part2 Is Table Level Stats: false - Stage: Stage-3 + Stage: Stage-4 Map Reduce Map Operator Tree: TableScan @@ -2645,7 +2750,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -ext-10002 + base file name: -ext-10003 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -2686,7 +2791,7 @@ STAGE PLANS: Truncated Path -> Alias: #### A masked pattern was here #### - Stage: Stage-5 + Stage: Stage-6 Map Reduce Map Operator Tree: TableScan @@ -2723,7 +2828,7 @@ STAGE PLANS: Path -> Partition: #### A masked pattern was here #### Partition - base file name: -ext-10002 + base file name: -ext-10003 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -2764,7 +2869,7 @@ STAGE PLANS: Truncated Path -> Alias: #### A masked pattern was here #### - Stage: Stage-6 + Stage: Stage-7 Move Operator files: hdfs directory: true
