http://git-wip-us.apache.org/repos/asf/hive/blob/2b5e215e/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out index 629a6c4..cc19038 100644 --- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out +++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out @@ -59,51 +59,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -113,32 +73,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -171,51 +122,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -225,32 +136,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -283,8 +185,6 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -296,64 +196,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - Left Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Left Outer Join 0 to 1 + Left Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -391,77 +250,34 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - Right Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Left Outer Join 0 to 1 + Right Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -614,51 +430,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -668,32 +444,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -728,77 +495,34 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Left Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Left Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -835,77 +559,34 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Right Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Right Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1055,51 +736,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -1109,32 +750,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/2b5e215e/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out index 7d09340..4690703 100644 --- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out +++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out @@ -59,51 +59,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -113,32 +73,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -171,51 +122,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -225,32 +136,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -283,8 +185,6 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 @@ -296,64 +196,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - Left Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Left Outer Join 0 to 1 + Left Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -391,77 +250,34 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Left Outer Join 0 to 1 - Right Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Left Outer Join 0 to 1 + Right Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -614,51 +430,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -668,32 +444,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -728,77 +495,34 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Left Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Left Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -835,77 +559,34 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Right Outer Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Right Outer Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator @@ -1055,51 +736,11 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2080 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: 1 Data size: 2080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 3 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 2060 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: 1 Data size: 2060 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Map 4 - Map Operator Tree: - TableScan alias: c Statistics: Num rows: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -1109,32 +750,23 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 2220 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: 1 Data size: 2220 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Execution mode: vectorized - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Right Outer Join 0 to 1 - Inner Join 1 to 2 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - 2 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Sorted Merge Bucket Map Join Operator + condition map: + Right Outer Join 0 to 1 + Inner Join 1 to 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 2 Data size: 4576 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator