Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,712 @@ +PREHOOK: query: create table smb_bucket_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@smb_bucket_1 +POSTHOOK: query: create table smb_bucket_1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@smb_bucket_1 +PREHOOK: query: create table smb_bucket_2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@smb_bucket_2 +POSTHOOK: query: create table smb_bucket_2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@smb_bucket_2 +PREHOOK: query: create table smb_bucket_3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@smb_bucket_3 +POSTHOOK: query: create table smb_bucket_3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 1 BUCKETS STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@smb_bucket_3 +PREHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' overwrite into table smb_bucket_1 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@smb_bucket_1 +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' overwrite into table smb_bucket_1 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@smb_bucket_1 +PREHOOK: query: load data local inpath '../../data/files/smbbucket_2.rc' overwrite into table smb_bucket_2 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@smb_bucket_2 +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_2.rc' overwrite into table smb_bucket_2 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@smb_bucket_2 +PREHOOK: query: load data local inpath '../../data/files/smbbucket_3.rc' overwrite into table smb_bucket_3 +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@smb_bucket_3 +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_3.rc' overwrite into table smb_bucket_3 +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@smb_bucket_3 +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 114 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 228 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 NULL NULL +5 val_5 NULL NULL +10 val_10 NULL NULL +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 228 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +NULL NULL 20 val_20 +NULL NULL 23 val_23 +NULL NULL 25 val_25 +NULL NULL 30 val_30 +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 228 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 NULL NULL +5 val_5 NULL NULL +10 val_10 NULL NULL +NULL NULL 20 val_20 +NULL NULL 23 val_23 +NULL NULL 25 val_25 +NULL NULL 30 val_30 +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 114 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 228 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 NULL NULL +5 val_5 NULL NULL +10 val_10 NULL NULL +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 228 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +NULL NULL 20 val_20 +NULL NULL 23 val_23 +NULL NULL 25 val_25 +NULL NULL 30 val_30 +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) + Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Outer Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 {KEY.reducesinkkey0} {VALUE._col0} + outputColumnNames: _col0, _col1, _col5, _col6 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 228 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a full outer join smb_bucket_2 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_2 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 NULL NULL +5 val_5 NULL NULL +10 val_10 NULL NULL +NULL NULL 20 val_20 +NULL NULL 23 val_23 +NULL NULL 25 val_25 +NULL NULL 30 val_30
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_10.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,141 @@ +PREHOOK: query: create table tmp_smb_bucket_10(userid int, pageid int, postid int, type string) partitioned by (ds string) CLUSTERED BY (userid) SORTED BY (pageid, postid, type, userid) INTO 2 BUCKETS STORED AS RCFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tmp_smb_bucket_10 +POSTHOOK: query: create table tmp_smb_bucket_10(userid int, pageid int, postid int, type string) partitioned by (ds string) CLUSTERED BY (userid) SORTED BY (pageid, postid, type, userid) INTO 2 BUCKETS STORED AS RCFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tmp_smb_bucket_10 +PREHOOK: query: alter table tmp_smb_bucket_10 add partition (ds = '1') +PREHOOK: type: ALTERTABLE_ADDPARTS +PREHOOK: Output: default@tmp_smb_bucket_10 +POSTHOOK: query: alter table tmp_smb_bucket_10 add partition (ds = '1') +POSTHOOK: type: ALTERTABLE_ADDPARTS +POSTHOOK: Output: default@tmp_smb_bucket_10 +POSTHOOK: Output: default@tmp_smb_bucket_10@ds=1 +PREHOOK: query: alter table tmp_smb_bucket_10 add partition (ds = '2') +PREHOOK: type: ALTERTABLE_ADDPARTS +PREHOOK: Output: default@tmp_smb_bucket_10 +POSTHOOK: query: alter table tmp_smb_bucket_10 add partition (ds = '2') +POSTHOOK: type: ALTERTABLE_ADDPARTS +POSTHOOK: Output: default@tmp_smb_bucket_10 +POSTHOOK: Output: default@tmp_smb_bucket_10@ds=2 +PREHOOK: query: -- add dummy files to make sure that the number of files in each partition is same as number of buckets + +load data local inpath '../../data/files/smbbucket_1.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='1') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmp_smb_bucket_10@ds=1 +POSTHOOK: query: -- add dummy files to make sure that the number of files in each partition is same as number of buckets + +load data local inpath '../../data/files/smbbucket_1.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='1') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmp_smb_bucket_10@ds=1 +PREHOOK: query: load data local inpath '../../data/files/smbbucket_2.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='1') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmp_smb_bucket_10@ds=1 +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_2.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='1') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmp_smb_bucket_10@ds=1 +PREHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='2') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmp_smb_bucket_10@ds=2 +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_1.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='2') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmp_smb_bucket_10@ds=2 +PREHOOK: query: load data local inpath '../../data/files/smbbucket_2.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='2') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@tmp_smb_bucket_10@ds=2 +POSTHOOK: query: load data local inpath '../../data/files/smbbucket_2.rc' INTO TABLE tmp_smb_bucket_10 partition(ds='2') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@tmp_smb_bucket_10@ds=2 +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from tmp_smb_bucket_10 a join tmp_smb_bucket_10 b +on (a.ds = '1' and b.ds = '2' and + a.userid = b.userid and + a.pageid = b.pageid and + a.postid = b.postid and + a.type = b.type) +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(a)*/ * from tmp_smb_bucket_10 a join tmp_smb_bucket_10 b +on (a.ds = '1' and b.ds = '2' and + a.userid = b.userid and + a.pageid = b.pageid and + a.postid = b.postid and + a.type = b.type) +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((userid is not null and pageid is not null) and postid is not null) and type is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: userid (type: int), pageid (type: int), postid (type: int), type (type: string) + sort order: ++++ + Map-reduce partition columns: userid (type: int), pageid (type: int), postid (type: int), type (type: string) + Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE + value expressions: ds (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (((userid is not null and pageid is not null) and postid is not null) and type is not null) (type: boolean) + Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: userid (type: int), pageid (type: int), postid (type: int), type (type: string) + sort order: ++++ + Map-reduce partition columns: userid (type: int), pageid (type: int), postid (type: int), type (type: string) + Statistics: Num rows: 1 Data size: 138 Basic stats: COMPLETE Column stats: NONE + value expressions: ds (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {KEY.reducesinkkey1} {KEY.reducesinkkey2} {KEY.reducesinkkey3} {VALUE._col0} + 1 {KEY.reducesinkkey0} {KEY.reducesinkkey1} {KEY.reducesinkkey2} {KEY.reducesinkkey3} {VALUE._col0} + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col8, _col9, _col10, _col11, _col12 + Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col3 (type: string), _col4 (type: string), _col8 (type: int), _col9 (type: int), _col10 (type: int), _col11 (type: string), _col12 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + Statistics: Num rows: 1 Data size: 151 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 151 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 + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +
