PREHOOK: query: -- Create two bucketed and sorted tables CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table1 POSTHOOK: query: -- Create two bucketed and sorted tables CREATE TABLE test_table1 (key INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table1 PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table2 POSTHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table2 PREHOOK: query: CREATE TABLE test_table3 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (key2) SORTED BY (key2) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table3 POSTHOOK: query: CREATE TABLE test_table3 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (key2) SORTED BY (key2) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table3 PREHOOK: query: FROM src INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * where key < 10 PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@test_table1@ds=1 POSTHOOK: query: FROM src INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * where key < 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table1@ds=1 POSTHOOK: Lineage: test_table1 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table1 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: FROM src INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') SELECT * where key < 100 PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@test_table2@ds=1 POSTHOOK: query: FROM src INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') SELECT * where key < 100 POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table2@ds=1 POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table -- This should be a map-only operation, since the insert is happening on the bucketing position EXPLAIN INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.key, concat(a.value, b.value) FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' PREHOOK: type: QUERY POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table -- This should be a map-only operation, since the insert is happening on the bucketing position EXPLAIN INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.key, concat(a.value, b.value) FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1, _col7 Select Operator expressions: _col0 (type: int), _col0 (type: int), concat(_col1, _col7) (type: string) outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 Stage: Stage-0 Move Operator tables: partition: ds 1 replace: true table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 Stage: Stage-2 Stats-Aggr Operator PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.key, concat(a.value, b.value) FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table1 PREHOOK: Input: default@test_table1@ds=1 PREHOOK: Input: default@test_table2 PREHOOK: Input: default@test_table2@ds=1 PREHOOK: Output: default@test_table3@ds=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.key, concat(a.value, b.value) FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table1@ds=1 POSTHOOK: Input: default@test_table2 POSTHOOK: Input: default@test_table2@ds=1 POSTHOOK: Output: default@test_table3@ds=1 POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key2 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)a.FieldSchema(name:value, type:string, comment:null), (test_table2)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table3 PREHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table3 POSTHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 0 0 val_0val_0 1 2 2 val_2val_2 1 4 4 val_4val_4 1 8 8 val_8val_8 1 PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table3 PREHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table3 POSTHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 5 5 val_5val_5 1 9 9 val_9val_9 1 PREHOOK: query: DROP TABLE test_table3 PREHOOK: type: DROPTABLE PREHOOK: Input: default@test_table3 PREHOOK: Output: default@test_table3 POSTHOOK: query: DROP TABLE test_table3 POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@test_table3 POSTHOOK: Output: default@test_table3 PREHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table3 POSTHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table3 PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table -- This should be a map-reduce operation, since the insert is happening on a non-bucketing position EXPLAIN INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' PREHOOK: type: QUERY POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table -- This should be a map-reduce operation, since the insert is happening on a non-bucketing position EXPLAIN INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-6 is a root stage , consists of Stage-7, Stage-8, Stage-1 Stage-7 has a backup stage: Stage-1 Stage-4 depends on stages: Stage-7 Stage-0 depends on stages: Stage-1, Stage-4, Stage-5 Stage-2 depends on stages: Stage-0 Stage-8 has a backup stage: Stage-1 Stage-5 depends on stages: Stage-8 Stage-1 STAGE PLANS: Stage: Stage-6 Conditional Operator Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: b TableScan alias: b Filter Operator predicate: key is not null (type: boolean) HashTable Sink Operator keys: 0 key (type: int) 1 key (type: int) Stage: Stage-4 Map Reduce Map Operator Tree: TableScan alias: a Filter Operator predicate: key is not null (type: boolean) Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) value expressions: _col0 (type: int), _col1 (type: string) Local Work: Map Reduce Local Work Reduce Operator Tree: Extract File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 Stage: Stage-0 Move Operator tables: partition: ds 1 replace: true table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 Stage: Stage-2 Stats-Aggr Operator Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: a TableScan alias: a Filter Operator predicate: key is not null (type: boolean) HashTable Sink Operator keys: 0 key (type: int) 1 key (type: int) Stage: Stage-5 Map Reduce Map Operator Tree: TableScan alias: b Filter Operator predicate: key is not null (type: boolean) Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) value expressions: _col0 (type: int), _col1 (type: string) Local Work: Map Reduce Local Work Reduce Operator Tree: Extract File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) value expressions: _col0 (type: int), _col1 (type: string) Reduce Operator Tree: Extract File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table1 PREHOOK: Input: default@test_table1@ds=1 PREHOOK: Input: default@test_table2 PREHOOK: Input: default@test_table2@ds=1 PREHOOK: Output: default@test_table3@ds=1 POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.value FROM test_table1 a JOIN test_table2 b ON a.key = b.key WHERE a.ds = '1' and b.ds = '1' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table1@ds=1 POSTHOOK: Input: default@test_table2 POSTHOOK: Input: default@test_table2@ds=1 POSTHOOK: Output: default@test_table3@ds=1 POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table3 PREHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### POSTHOOK: query: select * from test_table3 tablesample (bucket 1 out of 2) s where ds = '1' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table3 POSTHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### 0 val_0 1 0 val_0 1 0 val_0 1 0 val_0 1 0 val_0 1 0 val_0 1 0 val_0 1 0 val_0 1 0 val_0 1 2 val_2 1 4 val_4 1 8 val_8 1 PREHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1' PREHOOK: type: QUERY PREHOOK: Input: default@test_table3 PREHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### POSTHOOK: query: select * from test_table3 tablesample (bucket 2 out of 2) s where ds = '1' POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table3 POSTHOOK: Input: default@test_table3@ds=1 #### A masked pattern was here #### 5 val_5 1 5 val_5 1 5 val_5 1 5 val_5 1 5 val_5 1 5 val_5 1 5 val_5 1 5 val_5 1 5 val_5 1 9 val_9 1 PREHOOK: query: DROP TABLE test_table3 PREHOOK: type: DROPTABLE PREHOOK: Input: default@test_table3 PREHOOK: Output: default@test_table3 POSTHOOK: query: DROP TABLE test_table3 POSTHOOK: type: DROPTABLE POSTHOOK: Input: default@test_table3 POSTHOOK: Output: default@test_table3