| PREHOOK: query: CREATE TABLE dest_j1_n22(key STRING, cnt INT) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@dest_j1_n22 |
| POSTHOOK: query: CREATE TABLE dest_j1_n22(key STRING, cnt INT) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@dest_j1_n22 |
| PREHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE dest_j1_n22 |
| SELECT subq1.key, count(1) as cnt |
| FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN |
| (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) |
| group by subq1.key |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@src |
| PREHOOK: Input: default@src1 |
| PREHOOK: Output: default@dest_j1_n22 |
| POSTHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE dest_j1_n22 |
| SELECT subq1.key, count(1) as cnt |
| FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN |
| (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) |
| group by subq1.key |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@src |
| POSTHOOK: Input: default@src1 |
| POSTHOOK: Output: default@dest_j1_n22 |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-2 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-2 |
| Stage-3 depends on stages: Stage-0 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (BROADCAST_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: x |
| filterExpr: key is not null (type: boolean) |
| Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 25 Data size: 2150 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| keys: key (type: string) |
| minReductionHashAggr: 0.52 |
| mode: hash |
| outputColumnNames: _col0 |
| Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: _col0 (type: string) |
| Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: y |
| filterExpr: key is not null (type: boolean) |
| Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: key is not null (type: boolean) |
| Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: string) |
| outputColumnNames: _col0 |
| Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| keys: _col0 (type: string) |
| minReductionHashAggr: 0.5 |
| mode: hash |
| outputColumnNames: _col0 |
| Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: _col0 (type: string) |
| Statistics: Num rows: 250 Data size: 21750 Basic stats: COMPLETE Column stats: COMPLETE |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| keys: KEY._col0 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0 |
| Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE |
| Map Join Operator |
| condition map: |
| Left Semi Join 0 to 1 |
| keys: |
| 0 _col0 (type: string) |
| 1 _col0 (type: string) |
| outputColumnNames: _col0 |
| input vertices: |
| 1 Map 5 |
| Statistics: Num rows: 12 Data size: 1032 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: count() |
| keys: _col0 (type: string) |
| minReductionHashAggr: 0.5 |
| mode: hash |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: _col0 (type: string) |
| Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: bigint) |
| Reducer 3 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: count(VALUE._col0) |
| keys: KEY._col0 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 6 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.dest_j1_n22 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: int) |
| outputColumnNames: key, cnt |
| Statistics: Num rows: 6 Data size: 540 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(key)), avg(COALESCE(length(key),0)), count(1), count(key), compute_bit_vector(key, 'hll'), min(cnt), max(cnt), count(cnt), compute_bit_vector(cnt, 'hll') |
| minReductionHashAggr: 0.8333333 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 |
| Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col0 (type: int), _col1 (type: struct<count:bigint,sum:double,input:int>), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: int), _col7 (type: bigint), _col8 (type: binary) |
| Reducer 4 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), min(VALUE._col5), max(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 |
| Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'STRING' (type: string), UDFToLong(COALESCE(_col0,0)) (type: bigint), COALESCE(_col1,0) (type: double), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'LONG' (type: string), UDFToLong(_col5) (type: bigint), UDFToLong(_col6) (type: bigint), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 |
| Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| |
| Stage: Stage-2 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.dest_j1_n22 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: key, cnt |
| Column Types: string, int |
| Table: default.dest_j1_n22 |
| |
| PREHOOK: query: INSERT OVERWRITE TABLE dest_j1_n22 |
| SELECT subq1.key, count(1) as cnt |
| FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN |
| (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) |
| group by subq1.key |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@src |
| PREHOOK: Input: default@src1 |
| PREHOOK: Output: default@dest_j1_n22 |
| POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1_n22 |
| SELECT subq1.key, count(1) as cnt |
| FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN |
| (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) |
| group by subq1.key |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@src |
| POSTHOOK: Input: default@src1 |
| POSTHOOK: Output: default@dest_j1_n22 |
| POSTHOOK: Lineage: dest_j1_n22.cnt EXPRESSION [(src1)x.null, ] |
| POSTHOOK: Lineage: dest_j1_n22.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] |
| PREHOOK: query: select * from dest_j1_n22 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@dest_j1_n22 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from dest_j1_n22 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@dest_j1_n22 |
| #### A masked pattern was here #### |
| 128 1 |
| 146 1 |
| 150 1 |
| 213 1 |
| 224 1 |
| 238 1 |
| 255 1 |
| 273 1 |
| 278 1 |
| 311 1 |
| 369 1 |
| 401 1 |
| 406 1 |
| 66 1 |
| 98 1 |
