| PREHOOK: query: CREATE TABLE test_table1_n20 (key INT, value STRING) PARTITIONED BY (ds STRING) |
| CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@test_table1_n20 |
| POSTHOOK: query: CREATE TABLE test_table1_n20 (key INT, value STRING) PARTITIONED BY (ds STRING) |
| CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@test_table1_n20 |
| PREHOOK: query: CREATE TABLE test_table2_n19 (key INT, value STRING) PARTITIONED BY (ds STRING) |
| CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@test_table2_n19 |
| POSTHOOK: query: CREATE TABLE test_table2_n19 (key INT, value STRING) PARTITIONED BY (ds STRING) |
| CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@test_table2_n19 |
| PREHOOK: query: CREATE TABLE test_table3_n11 (key INT, value STRING) PARTITIONED BY (ds STRING) |
| CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@test_table3_n11 |
| POSTHOOK: query: CREATE TABLE test_table3_n11 (key INT, value STRING) PARTITIONED BY (ds STRING) |
| CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@test_table3_n11 |
| PREHOOK: query: FROM src |
| INSERT OVERWRITE TABLE test_table1_n20 PARTITION (ds = '1') SELECT * where key < 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@src |
| PREHOOK: Output: default@test_table1_n20@ds=1 |
| POSTHOOK: query: FROM src |
| INSERT OVERWRITE TABLE test_table1_n20 PARTITION (ds = '1') SELECT * where key < 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@src |
| POSTHOOK: Output: default@test_table1_n20@ds=1 |
| POSTHOOK: Lineage: test_table1_n20 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] |
| POSTHOOK: Lineage: test_table1_n20 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] |
| PREHOOK: query: FROM src |
| INSERT OVERWRITE TABLE test_table2_n19 PARTITION (ds = '1') SELECT * where key < 100 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@src |
| PREHOOK: Output: default@test_table2_n19@ds=1 |
| POSTHOOK: query: FROM src |
| INSERT OVERWRITE TABLE test_table2_n19 PARTITION (ds = '1') SELECT * where key < 100 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@src |
| POSTHOOK: Output: default@test_table2_n19@ds=1 |
| POSTHOOK: Lineage: test_table2_n19 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] |
| POSTHOOK: Lineage: test_table2_n19 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] |
| PREHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM test_table1_n20 a JOIN test_table2_n19 b |
| ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' |
| and (a.key = 0 or a.key = 5) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table1_n20 |
| PREHOOK: Input: default@test_table1_n20@ds=1 |
| PREHOOK: Input: default@test_table2_n19 |
| PREHOOK: Input: default@test_table2_n19@ds=1 |
| PREHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM test_table1_n20 a JOIN test_table2_n19 b |
| ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' |
| and (a.key = 0 or a.key = 5) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table1_n20 |
| POSTHOOK: Input: default@test_table1_n20@ds=1 |
| POSTHOOK: Input: default@test_table2_n19 |
| POSTHOOK: Input: default@test_table2_n19@ds=1 |
| POSTHOOK: Output: default@test_table3_n11@ds=1 |
| 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) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE |
| Dummy Store |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: int), concat(_col1, _col3) (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: llap |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Select Operator |
| expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 3 Data size: 564 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.test_table3_n11 |
| Select Operator |
| expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) |
| outputColumnNames: key, value, ds |
| Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: min(key), max(key), count(1), count(key), compute_bit_vector(key, 'hll'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll') |
| keys: ds (type: string) |
| minReductionHashAggr: 0.6666666 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 |
| Statistics: Num rows: 1 Data size: 485 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: 1 Data size: 485 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary), _col6 (type: int), _col7 (type: struct<count:bigint,sum:double,input:int>), _col8 (type: bigint), _col9 (type: binary) |
| Reducer 3 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8) |
| keys: KEY._col0 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 |
| Statistics: Num rows: 1 Data size: 417 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'LONG' (type: string), UDFToLong(_col1) (type: bigint), UDFToLong(_col2) (type: bigint), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col6,0)) (type: bigint), COALESCE(_col7,0) (type: double), (_col3 - _col8) (type: bigint), COALESCE(ndv_compute_bit_vector(_col9),0) (type: bigint), _col9 (type: binary), _col0 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 615 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 615 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: |
| partition: |
| ds 1 |
| 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.test_table3_n11 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: key, value |
| Column Types: int, string |
| Table: default.test_table3_n11 |
| |
| PREHOOK: query: INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM test_table1_n20 a JOIN test_table2_n19 b |
| ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' |
| and (a.key = 0 or a.key = 5) |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table1_n20 |
| PREHOOK: Input: default@test_table1_n20@ds=1 |
| PREHOOK: Input: default@test_table2_n19 |
| PREHOOK: Input: default@test_table2_n19@ds=1 |
| PREHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: query: INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM test_table1_n20 a JOIN test_table2_n19 b |
| ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' |
| and (a.key = 0 or a.key = 5) |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table1_n20 |
| POSTHOOK: Input: default@test_table1_n20@ds=1 |
| POSTHOOK: Input: default@test_table2_n19 |
| POSTHOOK: Input: default@test_table2_n19@ds=1 |
| POSTHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: Lineage: test_table3_n11 PARTITION(ds=1).key SIMPLE [(test_table1_n20)a.FieldSchema(name:key, type:int, comment:null), ] |
| POSTHOOK: Lineage: test_table3_n11 PARTITION(ds=1).value EXPRESSION [(test_table1_n20)a.FieldSchema(name:value, type:string, comment:null), (test_table2_n19)b.FieldSchema(name:value, type:string, comment:null), ] |
| PREHOOK: query: select * from test_table3_n11 tablesample (bucket 1 out of 2) s where ds = '1' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table3_n11 |
| PREHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from test_table3_n11 tablesample (bucket 1 out of 2) s where ds = '1' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table3_n11 |
| POSTHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| PREHOOK: query: select * from test_table3_n11 tablesample (bucket 2 out of 2) s where ds = '1' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table3_n11 |
| PREHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from test_table3_n11 tablesample (bucket 2 out of 2) s where ds = '1' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table3_n11 |
| POSTHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| PREHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and (key = 0 or key = 5)) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and (key = 0 or key = 5)) b |
| ON a.key = b.key |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table1_n20 |
| PREHOOK: Input: default@test_table1_n20@ds=1 |
| PREHOOK: Input: default@test_table2_n19 |
| PREHOOK: Input: default@test_table2_n19@ds=1 |
| PREHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and (key = 0 or key = 5)) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and (key = 0 or key = 5)) b |
| ON a.key = b.key |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table1_n20 |
| POSTHOOK: Input: default@test_table1_n20@ds=1 |
| POSTHOOK: Input: default@test_table2_n19 |
| POSTHOOK: Input: default@test_table2_n19@ds=1 |
| POSTHOOK: Output: default@test_table3_n11@ds=1 |
| 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) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: test_table2_n19 |
| filterExpr: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE |
| Dummy Store |
| Map Operator Tree: |
| TableScan |
| alias: test_table1_n20 |
| filterExpr: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: (key) IN (0, 5) (type: boolean) |
| Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: int), concat(_col1, _col3) (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: llap |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Select Operator |
| expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 3 Data size: 564 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.test_table3_n11 |
| Select Operator |
| expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) |
| outputColumnNames: key, value, ds |
| Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: min(key), max(key), count(1), count(key), compute_bit_vector(key, 'hll'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll') |
| keys: ds (type: string) |
| minReductionHashAggr: 0.6666666 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 |
| Statistics: Num rows: 1 Data size: 485 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: 1 Data size: 485 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary), _col6 (type: int), _col7 (type: struct<count:bigint,sum:double,input:int>), _col8 (type: bigint), _col9 (type: binary) |
| Reducer 3 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8) |
| keys: KEY._col0 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 |
| Statistics: Num rows: 1 Data size: 417 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'LONG' (type: string), UDFToLong(_col1) (type: bigint), UDFToLong(_col2) (type: bigint), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col6,0)) (type: bigint), COALESCE(_col7,0) (type: double), (_col3 - _col8) (type: bigint), COALESCE(ndv_compute_bit_vector(_col9),0) (type: bigint), _col9 (type: binary), _col0 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 615 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 615 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: |
| partition: |
| ds 1 |
| 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.test_table3_n11 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: key, value |
| Column Types: int, string |
| Table: default.test_table3_n11 |
| |
| PREHOOK: query: INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and (key = 0 or key = 5)) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and (key = 0 or key = 5)) b |
| ON a.key = b.key |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table1_n20 |
| PREHOOK: Input: default@test_table1_n20@ds=1 |
| PREHOOK: Input: default@test_table2_n19 |
| PREHOOK: Input: default@test_table2_n19@ds=1 |
| PREHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: query: INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and (key = 0 or key = 5)) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and (key = 0 or key = 5)) b |
| ON a.key = b.key |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table1_n20 |
| POSTHOOK: Input: default@test_table1_n20@ds=1 |
| POSTHOOK: Input: default@test_table2_n19 |
| POSTHOOK: Input: default@test_table2_n19@ds=1 |
| POSTHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: Lineage: test_table3_n11 PARTITION(ds=1).key SIMPLE [(test_table1_n20)test_table1_n20.FieldSchema(name:key, type:int, comment:null), ] |
| POSTHOOK: Lineage: test_table3_n11 PARTITION(ds=1).value EXPRESSION [(test_table1_n20)test_table1_n20.FieldSchema(name:value, type:string, comment:null), (test_table2_n19)test_table2_n19.FieldSchema(name:value, type:string, comment:null), ] |
| PREHOOK: query: select * from test_table3_n11 tablesample (bucket 1 out of 2) s where ds = '1' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table3_n11 |
| PREHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from test_table3_n11 tablesample (bucket 1 out of 2) s where ds = '1' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table3_n11 |
| POSTHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| PREHOOK: query: select * from test_table3_n11 tablesample (bucket 2 out of 2) s where ds = '1' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table3_n11 |
| PREHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from test_table3_n11 tablesample (bucket 2 out of 2) s where ds = '1' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table3_n11 |
| POSTHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| PREHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and key < 8) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and key < 8) b |
| ON a.key = b.key |
| WHERE a.key = 0 or a.key = 5 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table1_n20 |
| PREHOOK: Input: default@test_table1_n20@ds=1 |
| PREHOOK: Input: default@test_table2_n19 |
| PREHOOK: Input: default@test_table2_n19@ds=1 |
| PREHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: query: EXPLAIN |
| INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and key < 8) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and key < 8) b |
| ON a.key = b.key |
| WHERE a.key = 0 or a.key = 5 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table1_n20 |
| POSTHOOK: Input: default@test_table1_n20@ds=1 |
| POSTHOOK: Input: default@test_table2_n19 |
| POSTHOOK: Input: default@test_table2_n19@ds=1 |
| POSTHOOK: Output: default@test_table3_n11@ds=1 |
| 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) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: test_table2_n19 |
| filterExpr: ((key < 8) and (key) IN (0, 5)) (type: boolean) |
| Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((key < 8) and (key) IN (0, 5)) (type: boolean) |
| Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 282 Basic stats: COMPLETE Column stats: COMPLETE |
| Dummy Store |
| Map Operator Tree: |
| TableScan |
| alias: test_table1_n20 |
| filterExpr: ((key < 8) and (key) IN (0, 5)) (type: boolean) |
| Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((key < 8) and (key) IN (0, 5)) (type: boolean) |
| Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: key (type: int), value (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 279 Basic stats: COMPLETE Column stats: COMPLETE |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: int) |
| 1 _col0 (type: int) |
| outputColumnNames: _col0, _col1, _col3 |
| Statistics: Num rows: 3 Data size: 549 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: int), concat(_col1, _col3) (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: llap |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Select Operator |
| expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 564 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 3 Data size: 564 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.test_table3_n11 |
| Select Operator |
| expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) |
| outputColumnNames: key, value, ds |
| Statistics: Num rows: 3 Data size: 819 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: min(key), max(key), count(1), count(key), compute_bit_vector(key, 'hll'), max(length(value)), avg(COALESCE(length(value),0)), count(value), compute_bit_vector(value, 'hll') |
| keys: ds (type: string) |
| minReductionHashAggr: 0.6666666 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 |
| Statistics: Num rows: 1 Data size: 485 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: 1 Data size: 485 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: binary), _col6 (type: int), _col7 (type: struct<count:bigint,sum:double,input:int>), _col8 (type: bigint), _col9 (type: binary) |
| Reducer 3 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8) |
| keys: KEY._col0 (type: string) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 |
| Statistics: Num rows: 1 Data size: 417 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'LONG' (type: string), UDFToLong(_col1) (type: bigint), UDFToLong(_col2) (type: bigint), (_col3 - _col4) (type: bigint), COALESCE(ndv_compute_bit_vector(_col5),0) (type: bigint), _col5 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col6,0)) (type: bigint), COALESCE(_col7,0) (type: double), (_col3 - _col8) (type: bigint), COALESCE(ndv_compute_bit_vector(_col9),0) (type: bigint), _col9 (type: binary), _col0 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12 |
| Statistics: Num rows: 1 Data size: 615 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 615 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: |
| partition: |
| ds 1 |
| 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.test_table3_n11 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: key, value |
| Column Types: int, string |
| Table: default.test_table3_n11 |
| |
| PREHOOK: query: INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and key < 8) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and key < 8) b |
| ON a.key = b.key |
| WHERE a.key = 0 or a.key = 5 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table1_n20 |
| PREHOOK: Input: default@test_table1_n20@ds=1 |
| PREHOOK: Input: default@test_table2_n19 |
| PREHOOK: Input: default@test_table2_n19@ds=1 |
| PREHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: query: INSERT OVERWRITE TABLE test_table3_n11 PARTITION (ds = '1') |
| SELECT a.key, concat(a.value, b.value) |
| FROM |
| (select key, value from test_table1_n20 where ds = '1' and key < 8) a |
| JOIN |
| (select key, value from test_table2_n19 where ds = '1' and key < 8) b |
| ON a.key = b.key |
| WHERE a.key = 0 or a.key = 5 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table1_n20 |
| POSTHOOK: Input: default@test_table1_n20@ds=1 |
| POSTHOOK: Input: default@test_table2_n19 |
| POSTHOOK: Input: default@test_table2_n19@ds=1 |
| POSTHOOK: Output: default@test_table3_n11@ds=1 |
| POSTHOOK: Lineage: test_table3_n11 PARTITION(ds=1).key SIMPLE [(test_table1_n20)test_table1_n20.FieldSchema(name:key, type:int, comment:null), ] |
| POSTHOOK: Lineage: test_table3_n11 PARTITION(ds=1).value EXPRESSION [(test_table1_n20)test_table1_n20.FieldSchema(name:value, type:string, comment:null), (test_table2_n19)test_table2_n19.FieldSchema(name:value, type:string, comment:null), ] |
| PREHOOK: query: select * from test_table3_n11 tablesample (bucket 1 out of 2) s where ds = '1' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table3_n11 |
| PREHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from test_table3_n11 tablesample (bucket 1 out of 2) s where ds = '1' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table3_n11 |
| POSTHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| PREHOOK: query: select * from test_table3_n11 tablesample (bucket 2 out of 2) s where ds = '1' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@test_table3_n11 |
| PREHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| POSTHOOK: query: select * from test_table3_n11 tablesample (bucket 2 out of 2) s where ds = '1' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@test_table3_n11 |
| POSTHOOK: Input: default@test_table3_n11@ds=1 |
| #### A masked pattern was here #### |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 0 val_0val_0 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
| 5 val_5val_5 1 |
