| PREHOOK: query: CREATE TABLE T_A ( id STRING, val STRING ) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T_A |
| POSTHOOK: query: CREATE TABLE T_A ( id STRING, val STRING ) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T_A |
| PREHOOK: query: CREATE TABLE T_B ( id STRING, val STRING ) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@T_B |
| POSTHOOK: query: CREATE TABLE T_B ( id STRING, val STRING ) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@T_B |
| PREHOOK: query: CREATE TABLE join_result_1 ( ida STRING, vala STRING, idb STRING, valb STRING ) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@join_result_1 |
| POSTHOOK: query: CREATE TABLE join_result_1 ( ida STRING, vala STRING, idb STRING, valb STRING ) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@join_result_1 |
| PREHOOK: query: CREATE TABLE join_result_3 ( ida STRING, vala STRING, idb STRING, valb STRING ) |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: CREATE TABLE join_result_3 ( ida STRING, vala STRING, idb STRING, valb STRING ) |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@join_result_3 |
| PREHOOK: query: INSERT INTO TABLE T_A |
| VALUES ('Id_1', 'val_101'), ('Id_2', 'val_102'), ('Id_3', 'val_103') |
| PREHOOK: type: QUERY |
| PREHOOK: Input: _dummy_database@_dummy_table |
| PREHOOK: Output: default@t_a |
| POSTHOOK: query: INSERT INTO TABLE T_A |
| VALUES ('Id_1', 'val_101'), ('Id_2', 'val_102'), ('Id_3', 'val_103') |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: _dummy_database@_dummy_table |
| POSTHOOK: Output: default@t_a |
| POSTHOOK: Lineage: t_a.id SCRIPT [] |
| POSTHOOK: Lineage: t_a.val SCRIPT [] |
| PREHOOK: query: INSERT INTO TABLE T_B |
| VALUES ('Id_1', 'val_103'), ('Id_2', 'val_104') |
| PREHOOK: type: QUERY |
| PREHOOK: Input: _dummy_database@_dummy_table |
| PREHOOK: Output: default@t_b |
| POSTHOOK: query: INSERT INTO TABLE T_B |
| VALUES ('Id_1', 'val_103'), ('Id_2', 'val_104') |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: _dummy_database@_dummy_table |
| POSTHOOK: Output: default@t_b |
| POSTHOOK: Lineage: t_b.id SCRIPT [] |
| POSTHOOK: Lineage: t_b.val SCRIPT [] |
| Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product |
| PREHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| POSTHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_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 (XPROD_EDGE), Map 4 (XPROD_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: (id = 'Id_1') (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: (id = 'Id_1') (type: boolean) |
| Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: val (type: string) |
| outputColumnNames: _col0 |
| Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col0 (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 4 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 |
| 1 |
| outputColumnNames: _col0 |
| Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'Id_1' (type: string), _col0 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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.join_result_1 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| Warning: Shuffle Join MERGEJOIN[20][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product |
| PREHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_3 |
| 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 (XPROD_EDGE), Map 4 (XPROD_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((id = 'Id_2') and (val <> 'val_104')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: val (type: string) |
| outputColumnNames: _col0 |
| Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col0 (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 4 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((id = 'Id_2') and (val = 'val_104')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 179 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 |
| 1 |
| outputColumnNames: _col0 |
| Statistics: Num rows: 1 Data size: 91 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'Id_2' (type: string), _col0 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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.join_result_3 |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |
| PREHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' AND a.val <> b.val |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_1 |
| POSTHOOK: Output: default@join_result_3 |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-1 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-0 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Left Outer Join 0 to 1 |
| keys: |
| 0 id (type: string) |
| 1 id (type: string) |
| outputColumnNames: _col0, _col1, _col6, _col7 |
| Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((_col7 = 'val_104') and (_col6 = 'Id_2') and (_col1 <> _col7)) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Filter Operator |
| predicate: ((_col6 = 'Id_1') and (_col7 = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Reducer 4 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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-3 |
| Dependency Collection |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_3 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |
| 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.join_result_1 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| PREHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a LEFT JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_1 |
| POSTHOOK: Output: default@join_result_3 |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-0 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-0 |
| Stage-1 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Left Outer Join 0 to 1 |
| keys: |
| 0 id (type: string) |
| 1 id (type: string) |
| outputColumnNames: _col0, _col1, _col6, _col7 |
| Statistics: Num rows: 3 Data size: 1074 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((_col6 = 'Id_1') and (_col7 = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Filter Operator |
| predicate: ((_col7 = 'val_104') and (_col6 = 'Id_2')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Reducer 4 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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-3 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_1 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_3 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |
| PREHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.*, b.* |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.*, b.* |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_1 |
| POSTHOOK: Output: default@join_result_3 |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-0 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-0 |
| Stage-1 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 id (type: string) |
| 1 id (type: string) |
| outputColumnNames: _col0, _col1, _col6, _col7 |
| Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((_col6 = 'Id_1') and (_col7 = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Filter Operator |
| predicate: ((_col7 = 'val_104') and (_col6 = 'Id_2')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Reducer 4 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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-3 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_1 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_3 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |
| PREHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT * |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT * |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT * |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT * |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_1 |
| POSTHOOK: Output: default@join_result_3 |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-0 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-0 |
| Stage-1 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: id (type: string) |
| null sort order: z |
| sort order: + |
| Map-reduce partition columns: id (type: string) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: val (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 id (type: string) |
| 1 id (type: string) |
| outputColumnNames: _col0, _col1, _col6, _col7 |
| Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((_col6 = 'Id_1') and (_col7 = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Filter Operator |
| predicate: ((_col7 = 'val_104') and (_col6 = 'Id_2')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Reducer 4 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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-3 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_1 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_3 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |
| PREHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.id, a.val, b.id, b.val |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.id, a.val, b.id, b.val |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.id, a.val, b.id, b.val |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.id, a.val, b.id, b.val |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_1 |
| POSTHOOK: Output: default@join_result_3 |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-0 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-0 |
| Stage-1 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: id (type: string), val (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 537 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: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: id (type: string), val (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 2 Data size: 358 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: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: string) |
| 1 _col0 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((_col3 = 'Id_1') and (_col2 = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Filter Operator |
| predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Reducer 4 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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-3 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_1 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_3 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |
| PREHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.val, a.id, b.id, b.val |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.id, b.val, b.id, a.val |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@t_a |
| PREHOOK: Input: default@t_b |
| PREHOOK: Output: default@join_result_1 |
| PREHOOK: Output: default@join_result_3 |
| POSTHOOK: query: explain |
| FROM T_A a JOIN T_B b ON a.id = b.id |
| INSERT OVERWRITE TABLE join_result_1 |
| SELECT a.val, a.id, b.id, b.val |
| WHERE b.id = 'Id_1' AND b.val = 'val_103' |
| INSERT OVERWRITE TABLE join_result_3 |
| SELECT a.id, b.val, b.id, a.val |
| WHERE b.val = 'val_104' AND b.id = 'Id_2' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@t_a |
| POSTHOOK: Input: default@t_b |
| POSTHOOK: Output: default@join_result_1 |
| POSTHOOK: Output: default@join_result_3 |
| STAGE DEPENDENCIES: |
| Stage-2 is a root stage |
| Stage-3 depends on stages: Stage-2 |
| Stage-0 depends on stages: Stage-3 |
| Stage-4 depends on stages: Stage-0 |
| Stage-1 depends on stages: Stage-3 |
| Stage-5 depends on stages: Stage-1 |
| |
| STAGE PLANS: |
| Stage: Stage-2 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| Reducer 4 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: a |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: id (type: string), val (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 3 Data size: 537 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: 3 Data size: 537 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Map 5 |
| Map Operator Tree: |
| TableScan |
| alias: b |
| filterExpr: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: id is not null (type: boolean) |
| Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: id (type: string), val (type: string) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 2 Data size: 358 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: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: string) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Merge Join Operator |
| condition map: |
| Inner Join 0 to 1 |
| keys: |
| 0 _col0 (type: string) |
| 1 _col0 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 2 Data size: 716 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: ((_col3 = 'Id_1') and (_col2 = 'val_103')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col1 (type: string), _col0 (type: string), _col3 (type: string), _col2 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_1 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Filter Operator |
| predicate: ((_col2 = 'val_104') and (_col3 = 'Id_2')) (type: boolean) |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: _col0 (type: string), _col2 (type: string), _col3 (type: string), _col1 (type: string) |
| outputColumnNames: _col0, _col1, _col2, _col3 |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 358 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.join_result_3 |
| Select Operator |
| expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) |
| outputColumnNames: ida, vala, idb, valb |
| Statistics: Num rows: 1 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: max(length(ida)), avg(COALESCE(length(ida),0)), count(1), count(ida), compute_bit_vector_hll(ida), max(length(vala)), avg(COALESCE(length(vala),0)), count(vala), compute_bit_vector_hll(vala), max(length(idb)), avg(COALESCE(length(idb),0)), count(idb), compute_bit_vector_hll(idb), max(length(valb)), avg(COALESCE(length(valb),0)), count(valb), compute_bit_vector_hll(valb) |
| minReductionHashAggr: 0.4 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 936 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 936 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: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary), _col9 (type: int), _col10 (type: struct<count:bigint,sum:double,input:int>), _col11 (type: bigint), _col12 (type: binary), _col13 (type: int), _col14 (type: struct<count:bigint,sum:double,input:int>), _col15 (type: bigint), _col16 (type: binary) |
| Reducer 3 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| Reducer 4 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: max(VALUE._col0), avg(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector_hll(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector_hll(VALUE._col8), max(VALUE._col9), avg(VALUE._col10), count(VALUE._col11), compute_bit_vector_hll(VALUE._col12), max(VALUE._col13), avg(VALUE._col14), count(VALUE._col15), compute_bit_vector_hll(VALUE._col16) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16 |
| Statistics: Num rows: 1 Data size: 664 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), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col9,0)) (type: bigint), COALESCE(_col10,0) (type: double), (_col2 - _col11) (type: bigint), COALESCE(ndv_compute_bit_vector(_col12),0) (type: bigint), _col12 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col13,0)) (type: bigint), COALESCE(_col14,0) (type: double), (_col2 - _col15) (type: bigint), COALESCE(ndv_compute_bit_vector(_col16),0) (type: bigint), _col16 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 |
| Statistics: Num rows: 1 Data size: 1064 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 1064 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-3 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_1 |
| |
| Stage: Stage-4 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_1 |
| |
| Stage: Stage-1 |
| Move Operator |
| tables: |
| replace: true |
| table: |
| input format: org.apache.hadoop.mapred.TextInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| name: default.join_result_3 |
| |
| Stage: Stage-5 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: ida, vala, idb, valb |
| Column Types: string, string, string, string |
| Table: default.join_result_3 |
| |