Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out?rev=1646998&r1=1646997&r2=1646998&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_13.q.out Sat Dec 20 14:55:13 2014 @@ -128,8 +128,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (SORT, 1) + Reducer 2 <- Map 1 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -142,14 +141,29 @@ STAGE PLANS: isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: value (type: string) - auto parallelism: false + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {value} + 1 {value} {key} + keys: + 0 key (type: int) + 1 value (type: int) + outputColumnNames: _col0, _col1, _col5, _col6 + Position of Big Table: 0 + Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: @@ -203,100 +217,7 @@ STAGE PLANS: name: default.test_table1 Truncated Path -> Alias: /test_table1 [a] - Map 4 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: value (type: int) - sort order: + - Map-reduce partition columns: value (type: int) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: key (type: string) - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### A masked pattern was here #### - Partition - base file name: test_table2 - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name value - columns value,key - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.test_table2 - numFiles 16 - numRows 0 - rawDataSize 0 - serialization.ddl struct test_table2 { i32 value, string key} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE true - SORTBUCKETCOLSPREFIX TRUE - bucket_count 16 - bucket_field_name value - columns value,key - columns.comments - columns.types int:string -#### A masked pattern was here #### - name default.test_table2 - numFiles 16 - numRows 0 - rawDataSize 0 - serialization.ddl struct test_table2 { i32 value, string key} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table2 - name: default.test_table2 - Truncated Path -> Alias: - /test_table2 [b] Reducer 2 - Needs Tagging: true - 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: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Reducer 3 Needs Tagging: false Reduce Operator Tree: Select Operator @@ -409,41 +330,41 @@ TOK_QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: - Map 1 + Map 3 Map Operator Tree: TableScan - alias: a + alias: b Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: UDFToDouble(key) is not null (type: boolean) + predicate: UDFToDouble(value) is not null (type: boolean) Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(key) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(key) (type: double) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - tag: 0 - value expressions: key (type: int), value (type: string) - auto parallelism: false + Spark HashTable Sink Operator + condition expressions: + 0 {key} {value} + 1 {key} {value} + keys: + 0 UDFToDouble(key) (type: double) + 1 UDFToDouble(value) (type: double) + Position of Big Table: 0 + Local Work: + Map Reduce Local Work Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: test_table3 + base file name: test_table4 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -455,11 +376,11 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.test_table3 + name default.test_table4 numFiles 16 numRows 0 rawDataSize 0 - serialization.ddl struct test_table3 { i32 key, string value} + serialization.ddl struct test_table4 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -477,44 +398,70 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.test_table3 + name default.test_table4 numFiles 16 numRows 0 rawDataSize 0 - serialization.ddl struct test_table3 { i32 key, string value} + serialization.ddl struct test_table4 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table3 - name: default.test_table3 + name: default.test_table4 + name: default.test_table4 Truncated Path -> Alias: - /test_table3 [a] - Map 4 + /test_table4 [b] + + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 Map Operator Tree: TableScan - alias: b + alias: a Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: UDFToDouble(value) is not null (type: boolean) + predicate: UDFToDouble(key) is not null (type: boolean) Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: UDFToDouble(value) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(value) (type: double) - Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE - tag: 1 - value expressions: key (type: int), value (type: string) - auto parallelism: false + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} {value} + 1 {key} {value} + keys: + 0 UDFToDouble(key) (type: double) + 1 UDFToDouble(value) (type: double) + outputColumnNames: _col0, _col1, _col5, _col6 + input vertices: + 1 Map 3 + Position of Big Table: 0 + Statistics: Num rows: 30 Data size: 3253 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: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE + tag: -1 + value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) + auto parallelism: false + Local Work: + Map Reduce Local Work Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition - base file name: test_table4 + base file name: test_table3 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: @@ -526,11 +473,11 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.test_table4 + name default.test_table3 numFiles 16 numRows 0 rawDataSize 0 - serialization.ddl struct test_table4 { i32 key, string value} + serialization.ddl struct test_table3 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 @@ -548,43 +495,21 @@ STAGE PLANS: columns.comments columns.types int:string #### A masked pattern was here #### - name default.test_table4 + name default.test_table3 numFiles 16 numRows 0 rawDataSize 0 - serialization.ddl struct test_table4 { i32 key, string value} + serialization.ddl struct test_table3 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.test_table4 - name: default.test_table4 + name: default.test_table3 + name: default.test_table3 Truncated Path -> Alias: - /test_table4 [b] + /test_table3 [a] Reducer 2 - Needs Tagging: true - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {VALUE._col0} {VALUE._col1} - 1 {VALUE._col0} {VALUE._col1} - outputColumnNames: _col0, _col1, _col5, _col6 - Statistics: Num rows: 30 Data size: 3253 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: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE - tag: -1 - value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) - auto parallelism: false - Reducer 3 Needs Tagging: false Reduce Operator Tree: Select Operator
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out?rev=1646998&r1=1646997&r2=1646998&view=diff ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out (original) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_14.q.out Sat Dec 20 14:55:13 2014 @@ -58,56 +58,38 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 key (type: int) + 1 key (type: int) + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -174,61 +156,43 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 3) - Reducer 4 <- Reducer 3 (SORT, 1) + Reducer 2 <- Map 1 (GROUP, 3) + Reducer 3 <- Reducer 2 (SORT, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} + 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 38 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: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 38 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: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) @@ -240,7 +204,7 @@ STAGE PLANS: sort order: + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) - Reducer 4 + Reducer 3 Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: bigint) @@ -316,61 +280,43 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 3) - Reducer 4 <- Reducer 3 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 3) + Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {key} + 1 + keys: + 0 key (type: int) + 1 key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + keys: _col0 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 5 Data size: 38 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: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 {KEY.reducesinkkey0} - 1 - outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 38 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: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: int) @@ -388,7 +334,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) - Reducer 4 + Reducer 3 Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -464,8 +410,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -480,48 +425,27 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -600,60 +524,38 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 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: 7 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 key (type: int) + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -756,8 +658,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -772,48 +673,27 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 7 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: 7 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -906,8 +786,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -922,48 +801,27 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 8) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 3 Data size: 23 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -1025,15 +883,13 @@ select /*+mapjoin(subq1)*/ count(*) from on subq1.key = subq2.key POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-1 is a root stage + Stage-2 is a root stage + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-1 + Stage: Stage-2 Spark - Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -1048,12 +904,23 @@ STAGE PLANS: Filter Operator predicate: _col0 is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Map 4 + Spark HashTable Sink Operator + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Local Work: + Map Reduce Local Work + + Stage: Stage-1 + Spark + Edges: + Reducer 3 <- Map 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 2 Map Operator Tree: TableScan alias: a @@ -1065,29 +932,29 @@ STAGE PLANS: Filter Operator predicate: _col0 is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + input vertices: + 0 Map 1 + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) + Local Work: + Map Reduce Local Work Reducer 3 Reduce Operator Tree: Group By Operator @@ -1154,8 +1021,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -1164,50 +1030,29 @@ STAGE PLANS: alias: a Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 key (type: int) + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -1268,8 +1113,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -1284,44 +1128,27 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 key (type: int) + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -1392,8 +1219,7 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 @@ -1408,67 +1234,30 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Map 5 - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key < 6) (type: boolean) - Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 3 Data size: 21 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: 3 Data size: 21 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + Inner Join 0 to 2 + condition expressions: + 0 + 1 + 2 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + 2 _col0 (type: int) + Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - condition expressions: - 0 - 1 - 2 - Statistics: Num rows: 6 Data size: 46 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial @@ -1555,60 +1344,38 @@ STAGE PLANS: Stage: Stage-1 Spark Edges: - Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3) - Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 2 <- Map 1 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (((key < 8) and (key < 6)) and key is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 7 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 7 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: 7 Basic stats: COMPLETE Column stats: NONE - Map 4 - Map Operator Tree: - TableScan alias: b Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 5 Data size: 35 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: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Sorted Merge Bucket Map Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + keys: + 0 _col0 (type: int) + 1 key (type: int) + Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Reducer 2 Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - condition expressions: - 0 - 1 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial
