PREHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest_j1(key STRING, cnt1 INT, cnt2 INT) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_j1 POSTHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest_j1(key STRING, cnt1 INT, cnt2 INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_j1 PREHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin EXPLAIN INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.cnt FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) PREHOOK: type: QUERY POSTHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin EXPLAIN INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.cnt FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) POSTHOOK: type: QUERY STAGE DEPENDENCIES: Stage-1 is a root stage Stage-7 depends on stages: Stage-1, Stage-4 , consists of Stage-8, Stage-9, Stage-2 Stage-8 has a backup stage: Stage-2 Stage-5 depends on stages: Stage-8 Stage-0 depends on stages: Stage-2, Stage-5, Stage-6 Stage-3 depends on stages: Stage-0 Stage-9 has a backup stage: Stage-2 Stage-6 depends on stages: Stage-9 Stage-2 Stage-4 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-7 Conditional Operator Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $INTNAME1 TableScan HashTable Sink Operator keys: 0 _col0 (type: string) 1 _col0 (type: string) Stage: Stage-5 Map Reduce Map Operator Tree: TableScan Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Select Operator expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) 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.dest_j1 Local Work: Map Reduce Local Work Stage: Stage-0 Move Operator tables: replace: true table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 Stage: Stage-3 Stats-Aggr Operator Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $INTNAME TableScan HashTable Sink Operator keys: 0 _col0 (type: string) 1 _col0 (type: string) Stage: Stage-6 Map Reduce Map Operator Tree: TableScan Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Select Operator expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) 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.dest_j1 Local Work: Map Reduce Local Work Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) TableScan Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), UDFToInteger(_col3) (type: int), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false Statistics: Num rows: 137 Data size: 1460 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.dest_j1 Stage: Stage-4 Map Reduce Map Operator Tree: TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.cnt FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Output: default@dest_j1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.cnt FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.cnt1 EXPRESSION [(src1)x.null, ] POSTHOOK: Lineage: dest_j1.cnt2 EXPRESSION [(src)y.null, ] POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 #### A masked pattern was here #### POSTHOOK: query: select * from dest_j1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_j1 #### A masked pattern was here #### 128 1 3 146 1 2 150 1 1 213 1 2 224 1 2 238 1 2 255 1 2 273 1 3 278 1 2 311 1 3 369 1 3 401 1 5 406 1 4 66 1 1 98 1 2