Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,720 @@ +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_3 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_3 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 111 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: 111 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +4 val_4 4 val_4 +10 val_10 10 val_10 +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_3 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_3 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: 2 Data size: 222 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: 222 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 4 val_4 +5 val_5 NULL NULL +10 val_10 10 val_10 +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_3 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_3 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: 2 Data size: 222 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: 222 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +4 val_4 4 val_4 +10 val_10 10 val_10 +NULL NULL 17 val_17 +NULL NULL 19 val_19 +NULL NULL 20 val_20 +NULL NULL 23 val_23 +PREHOOK: query: explain +select /*+mapjoin(a)*/ * from smb_bucket_1 a full outer join smb_bucket_3 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_3 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: 2 Data size: 222 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: 222 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(a)*/ * from smb_bucket_1 a full outer join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 4 val_4 +5 val_5 NULL NULL +10 val_10 10 val_10 +NULL NULL 17 val_17 +NULL NULL 19 val_19 +NULL NULL 20 val_20 +NULL NULL 23 val_23 +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_3 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 1 Data size: 111 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: 111 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +4 val_4 4 val_4 +10 val_10 10 val_10 +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_3 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_3 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: 2 Data size: 222 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: 222 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 4 val_4 +5 val_5 NULL NULL +10 val_10 10 val_10 +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_3 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_3 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: 2 Data size: 222 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: 222 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +4 val_4 4 val_4 +10 val_10 10 val_10 +NULL NULL 17 val_17 +NULL NULL 19 val_19 +NULL NULL 20 val_20 +NULL NULL 23 val_23 +PREHOOK: query: explain +select /*+mapjoin(b)*/ * from smb_bucket_1 a full outer join smb_bucket_3 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_3 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: 2 Data size: 222 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: 222 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_3 b on a.key = b.key +PREHOOK: type: QUERY +PREHOOK: Input: default@smb_bucket_1 +PREHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +POSTHOOK: query: select /*+mapjoin(b)*/ * from smb_bucket_1 a full outer join smb_bucket_3 b on a.key = b.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@smb_bucket_1 +POSTHOOK: Input: default@smb_bucket_3 +#### A masked pattern was here #### +1 val_1 NULL NULL +3 val_3 NULL NULL +4 val_4 4 val_4 +5 val_5 NULL NULL +10 val_10 10 val_10 +NULL NULL 17 val_17 +NULL NULL 19 val_19 +NULL NULL 20 val_20 +NULL NULL 23 val_23
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_20.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_20.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_20.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_20.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,366 @@ +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 STRING, value1 STRING, value2 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 STRING, value1 STRING, value2 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: FROM src +INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@test_table1@ds=1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * +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: -- Insert data into the bucketed table by selecting from another bucketed table +-- with different datatypes. This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- with different datatypes. This should be a map-reduce operation +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToString(_col0) (type: string) + sort order: + + Map-reduce partition columns: UDFToString(_col0) (type: string) + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +PREHOOK: Input: default@test_table1@ds=1 +PREHOOK: Output: default@test_table2@ds=1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +POSTHOOK: Input: default@test_table1@ds=1 +POSTHOOK: Output: default@test_table2@ds=1 +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: test_table2 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(*) from test_table2 where ds = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +PREHOOK: Input: default@test_table2@ds=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 where ds = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +POSTHOOK: Input: default@test_table2@ds=1 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +PREHOOK: Input: default@test_table2@ds=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +POSTHOOK: Input: default@test_table2@ds=1 +#### A masked pattern was here #### +242 +PREHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +PREHOOK: Input: default@test_table2@ds=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 where ds = '1' and hash(key) % 2 = 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +POSTHOOK: Input: default@test_table2@ds=1 +#### A masked pattern was here #### +258 +PREHOOK: query: CREATE TABLE test_table3 (key STRING, value1 int, value2 string) PARTITIONED BY (ds STRING) +CLUSTERED BY (value1) SORTED BY (value1) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_table3 +POSTHOOK: query: CREATE TABLE test_table3 (key STRING, value1 int, value2 string) PARTITIONED BY (ds STRING) +CLUSTERED BY (value1) SORTED BY (value1) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table3 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation, although the bucketing positions dont match +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.value, a.key, a.value FROM test_table1 a WHERE a.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, although the bucketing positions dont match +EXPLAIN +INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.value, a.key, a.value FROM test_table1 a WHERE a.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 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: value (type: string), key (type: int), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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.value, a.key, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +PREHOOK: Input: default@test_table1@ds=1 +PREHOOK: Output: default@test_table3@ds=1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') +SELECT a.value, a.key, a.value FROM test_table1 a WHERE a.ds = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +POSTHOOK: Input: default@test_table1@ds=1 +POSTHOOK: Output: default@test_table3@ds=1 +POSTHOOK: Lineage: test_table3 PARTITION(ds=1).key SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value1 SIMPLE [(test_table1)a.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table3 PARTITION(ds=1).value2 SIMPLE [(test_table1)a.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(*) from test_table3 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 count(*) from test_table3 where ds = '1' +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table3 +POSTHOOK: Input: default@test_table3@ds=1 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 0 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table3 +PREHOOK: Input: default@test_table3@ds=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 0 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table3 +POSTHOOK: Input: default@test_table3@ds=1 +#### A masked pattern was here #### +247 +PREHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 1 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table3 +PREHOOK: Input: default@test_table3@ds=1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table3 where ds = '1' and hash(value1) % 2 = 1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table3 +POSTHOOK: Input: default@test_table3@ds=1 +#### A masked pattern was here #### +253 +PREHOOK: query: select count(*) 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 count(*) 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 #### +247 +PREHOOK: query: select count(*) 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 count(*) 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 #### +253 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- However, since an expression is being selected, it should involve a reducer +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2') +SELECT a.key+a.key, a.value, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- However, since an expression is being selected, it should involve a reducer +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '2') +SELECT a.key+a.key, a.value, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: (key + key) (type: int), value (type: string), value (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToString(_col0) (type: string) + sort order: + + Map-reduce partition columns: UDFToString(_col0) (type: string) + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + partition: + ds 2 + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_21.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_21.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_21.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_21.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,538 @@ +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: FROM src +INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@test_table1@ds=1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE test_table1 PARTITION (ds = '1') SELECT * +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: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-only operation +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: drop table test_table2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table2 +PREHOOK: Output: default@test_table2 +POSTHOOK: query: drop table test_table2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table2 +POSTHOOK: Output: default@test_table2 +PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key) SORTED BY (key desc) 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 desc) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the sort orders does not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the sort orders does not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 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: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: drop table test_table2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table2 +PREHOOK: Output: default@test_table2 +POSTHOOK: query: drop table test_table2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table2 +POSTHOOK: Output: default@test_table2 +PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key) SORTED BY (key, value) 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, value) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the sort columns do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the sort columns do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: drop table test_table2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table2 +PREHOOK: Output: default@test_table2 +POSTHOOK: query: drop table test_table2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table2 +POSTHOOK: Output: default@test_table2 +PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key) SORTED BY (value) 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 (value) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the sort columns do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the sort columns do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: drop table test_table2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table2 +PREHOOK: Output: default@test_table2 +POSTHOOK: query: drop table test_table2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table2 +POSTHOOK: Output: default@test_table2 +PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED BY (key) SORTED BY (key) INTO 4 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 4 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the number of buckets do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since the number of buckets do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 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: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: drop table test_table2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table2 +PREHOOK: Output: default@test_table2 +POSTHOOK: query: drop table test_table2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table2 +POSTHOOK: Output: default@test_table2 +PREHOOK: query: CREATE TABLE test_table2 (key INT, value STRING) PARTITIONED BY (ds STRING) +CLUSTERED 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) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since sort columns do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.ds = '1' +PREHOOK: type: QUERY +POSTHOOK: query: -- Insert data into the bucketed table by selecting from another bucketed table +-- This should be a map-reduce operation since sort columns do not match +EXPLAIN +INSERT OVERWRITE TABLE test_table2 PARTITION (ds = '1') +SELECT a.key, a.value FROM test_table1 a WHERE a.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 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int), _col1 (type: string) + Reducer 2 + Reduce Operator Tree: + Extract + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + 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_table2 + + Stage: Stage-3 + Stats-Aggr Operator + Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_22.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_22.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_22.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_22.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,292 @@ +PREHOOK: query: -- Create two bucketed and sorted tables +CREATE TABLE test_table1 (key INT, value 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) +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) +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) +CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: FROM src +INSERT OVERWRITE TABLE test_table1 SELECT * +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@test_table1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE test_table1 SELECT * +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@test_table1 +POSTHOOK: Lineage: test_table1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table1.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_table2 +SELECT * FROM test_table1 +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_table2 +SELECT * FROM test_table1 +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 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test_table1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table2 +SELECT * FROM test_table1 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +PREHOOK: Output: default@test_table2 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 +SELECT * FROM test_table1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +POSTHOOK: Output: default@test_table2 +POSTHOOK: Lineage: test_table2.key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2.value SIMPLE [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(*) from test_table1 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from test_table1 tablesample (bucket 2 out of 2) s +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 2 out of 2) s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +#### A masked pattern was here #### +253 +PREHOOK: query: select count(*) from test_table2 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +#### A masked pattern was here #### +253 +PREHOOK: query: drop table test_table1 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table1 +PREHOOK: Output: default@test_table1 +POSTHOOK: query: drop table test_table1 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table1 +POSTHOOK: Output: default@test_table1 +PREHOOK: query: drop table test_table2 +PREHOOK: type: DROPTABLE +PREHOOK: Input: default@test_table2 +PREHOOK: Output: default@test_table2 +POSTHOOK: query: drop table test_table2 +POSTHOOK: type: DROPTABLE +POSTHOOK: Input: default@test_table2 +POSTHOOK: Output: default@test_table2 +PREHOOK: query: CREATE TABLE test_table1 (key INT, value STRING) +CLUSTERED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@test_table1 +POSTHOOK: query: CREATE TABLE test_table1 (key INT, value STRING) +CLUSTERED 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) +CLUSTERED 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) +CLUSTERED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@test_table2 +PREHOOK: query: FROM src +INSERT OVERWRITE TABLE test_table1 SELECT * +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@test_table1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: FROM src +INSERT OVERWRITE TABLE test_table1 SELECT * +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@test_table1 +POSTHOOK: Lineage: test_table1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: test_table1.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_table2 +SELECT * FROM test_table1 +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_table2 +SELECT * FROM test_table1 +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 + Spark +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: test_table1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 55 Data size: 5812 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_table2 + + Stage: Stage-2 + Dependency Collection + + Stage: Stage-0 + Move Operator + tables: + replace: true + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + name: default.test_table2 + + Stage: Stage-3 + Stats-Aggr Operator + +PREHOOK: query: INSERT OVERWRITE TABLE test_table2 +SELECT * FROM test_table1 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +PREHOOK: Output: default@test_table2 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: INSERT OVERWRITE TABLE test_table2 +SELECT * FROM test_table1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +POSTHOOK: Output: default@test_table2 +POSTHOOK: Lineage: test_table2.key SIMPLE [(test_table1)test_table1.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: test_table2.value SIMPLE [(test_table1)test_table1.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: select count(*) from test_table1 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from test_table1 tablesample (bucket 2 out of 2) s +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table1 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table1 tablesample (bucket 2 out of 2) s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table1 +#### A masked pattern was here #### +253 +PREHOOK: query: select count(*) from test_table2 +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +#### A masked pattern was here #### +500 +PREHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s +PREHOOK: type: QUERY +PREHOOK: Input: default@test_table2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) from test_table2 tablesample (bucket 2 out of 2) s +POSTHOOK: type: QUERY +POSTHOOK: Input: default@test_table2 +#### A masked pattern was here #### +253
