http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out new file mode 100644 index 0000000..4b4a95e --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out @@ -0,0 +1,1239 @@ +PREHOOK: query: -- Create two bucketed and sorted tables +CREATE TABLE test_table1 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key, key2) SORTED BY (key ASC, key2 DESC) 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, key2 INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key, key2) SORTED BY (key ASC, key2 DESC) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table1 +PREHOOK: query: CREATE TABLE test_table2 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key, key2) SORTED BY (key ASC, key2 DESC) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_table2 +POSTHOOK: query: CREATE TABLE test_table2 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key, key2) SORTED BY (key ASC, key2 DESC) 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 (key, key2) SORTED BY (key ASC, key2 DESC) 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 (key, key2) SORTED BY (key ASC, key2 DESC) 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 key, key+1, value 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 key, key+1, value 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).key2 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 key, key+1, value 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 key, key+1, value 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).key2 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 sort-order matches +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, a.key2, concat(a.value, b.value) +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 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 sort-order matches +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, a.key2, concat(a.value, b.value) +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: +- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, a.key2, concat(a.value, b.value) +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 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.key2, concat(a.value, b.value) +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 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:key2, 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 #### +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 #### +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +2 3 val_2val_2 1 +4 5 val_4val_4 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +8 9 val_8val_8 1 +9 10 val_9val_9 1 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation, since the sort-order matches +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq1.key, subq1.key2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +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 sort-order matches +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq1.key, subq1.key2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: +- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq1.key, subq1.key2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +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 subq1.key, subq1.key2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +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:key2, 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 #### +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 #### +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +2 3 val_2val_2 1 +4 5 val_4val_4 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +8 9 val_8val_8 1 +9 10 val_9val_9 1 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key2, a.key, concat(a.value, b.value) +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 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 +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key2, a.key, concat(a.value, b.value) +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col0 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: +- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq1.key2, subq1.key, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq1.key2, subq1.key, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: int), _col0 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: +- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq2.key, subq2.key2, subq2.value from +( +SELECT subq1.key2, subq1.key, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq2.key, subq2.key2, subq2.value from +( +SELECT subq1.key2, subq1.key, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: +- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq2.key, subq2.key2, subq2.value from +( +SELECT subq1.key2, subq1.key, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +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 subq2.key, subq2.key2, subq2.value from +( +SELECT subq1.key2, subq1.key, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +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:key2, 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 #### +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 #### +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +2 3 val_2val_2 1 +4 5 val_4val_4 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +8 9 val_8val_8 1 +9 10 val_9val_9 1 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq2.k2, subq2.k1, subq2.value from +( +SELECT subq1.key2 as k1, subq1.key as k2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq2.k2, subq2.k1, subq2.value from +( +SELECT subq1.key2 as k1, subq1.key as k2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: +- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT subq2.k2, subq2.k1, subq2.value from +( +SELECT subq1.key2 as k1, subq1.key as k2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +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 subq2.k2, subq2.k1, subq2.value from +( +SELECT subq1.key2 as k1, subq1.key as k2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +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:key2, 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 #### +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 #### +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +0 1 val_0val_0 1 +2 3 val_2val_2 1 +4 5 val_4val_4 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +5 6 val_5val_5 1 +8 9 val_8val_8 1 +9 10 val_9val_9 1 +PREHOOK: query: CREATE TABLE test_table4 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key, key2) SORTED BY (key DESC, key2 DESC) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_table4 +POSTHOOK: query: CREATE TABLE test_table4 (key INT, key2 INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key, key2) SORTED BY (key DESC, key2 DESC) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table4 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table4 PARTITION (ds = '1') +SELECT subq2.k2, subq2.k1, subq2.value from +( +SELECT subq1.key2 as k1, subq1.key as k2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table4 PARTITION (ds = '1') +SELECT subq2.k2, subq2.k1, subq2.value from +( +SELECT subq1.key2 as k1, subq1.key as k2, subq1.value from +( +SELECT a.key, a.key2, concat(a.value, b.value) as value +FROM test_table1 a JOIN test_table2 b +ON a.key = b.key and a.key2 = b.key2 WHERE a.ds = '1' and b.ds = '1' +)subq1 +)subq2 +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: ++ + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 10 Data size: 171 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and key2 is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), key2 (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 84 Data size: 1651 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int), _col1 (type: int) + 1 _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1, _col2, _col6 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: int) + sort order: -- + Map-reduce partition columns: _col0 (type: int), _col1 (type: int) + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1816 Basic stats: COMPLETE Column stats: NONE + 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_table4 + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table4 + + Stage: Stage-3 + Stats-Aggr Operator +
http://git-wip-us.apache.org/repos/asf/hive/blob/f562dfb5/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out new file mode 100644 index 0000000..11de932 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out @@ -0,0 +1,621 @@ +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, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_table3 +POSTHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table3 +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 +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT 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' +and (a.key = 0 or a.key = 5) +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT 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' +and (a.key = 0 or a.key = 5) +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col4 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), concat(_col1, _col4) (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT 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' +and (a.key = 0 or a.key = 5) +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, 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' +and (a.key = 0 or a.key = 5) +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 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 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +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_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +PREHOOK: query: -- This should be a map-only job +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and (key = 0 or key = 5)) a +JOIN +(select key, value from test_table2 where ds = '1' and (key = 0 or key = 5)) b +ON a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: -- This should be a map-only job +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and (key = 0 or key = 5)) a +JOIN +(select key, value from test_table2 where ds = '1' and (key = 0 or key = 5)) b +ON a.key = b.key +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test_table1 + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: test_table2 + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 0 Map 1 + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), concat(_col1, _col3) (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 92 Data size: 1548 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and (key = 0 or key = 5)) a +JOIN +(select key, value from test_table2 where ds = '1' and (key = 0 or key = 5)) b +ON a.key = b.key +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, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and (key = 0 or key = 5)) a +JOIN +(select key, value from test_table2 where ds = '1' and (key = 0 or key = 5)) b +ON a.key = b.key +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)test_table1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.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_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +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_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +PREHOOK: query: -- This should be a map-only job +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and key < 8) a +JOIN +(select key, value from test_table2 where ds = '1' and key < 8) b +ON a.key = b.key +WHERE a.key = 0 or a.key = 5 +PREHOOK: type: QUERY +POSTHOOK: query: -- This should be a map-only job +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and key < 8) a +JOIN +(select key, value from test_table2 where ds = '1' and key < 8) b +ON a.key = b.key +WHERE a.key = 0 or a.key = 5 +POSTHOOK: type: QUERY +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: + Map 2 <- Map 1 (BROADCAST_EDGE) + Reducer 3 <- Map 2 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test_table1 + Statistics: Num rows: 10 Data size: 150 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) + Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 2 Data size: 30 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map 2 + Map Operator Tree: + TableScan + alias: test_table2 + Statistics: Num rows: 84 Data size: 1408 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key < 8) and ((key = 0) or (key = 5))) (type: boolean) + Statistics: Num rows: 28 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 28 Data size: 469 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col1, _col3 + input vertices: + 0 Map 1 + Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), concat(_col1, _col3) (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 30 Data size: 515 Basic stats: COMPLETE Column stats: NONE + 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 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 1 + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table3 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.key, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and key < 8) a +JOIN +(select key, value from test_table2 where ds = '1' and key < 8) b +ON a.key = b.key +WHERE a.key = 0 or a.key = 5 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +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, concat(a.value, b.value) +FROM +(select key, value from test_table1 where ds = '1' and key < 8) a +JOIN +(select key, value from test_table2 where ds = '1' and key < 8) b +ON a.key = b.key +WHERE a.key = 0 or a.key = 5 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +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)test_table1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value EXPRESSION [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), (test_table2)test_table2.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_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +0 val_0val_0 1 +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_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1 +5 val_5val_5 1
