Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,1356 @@ +PREHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl1 +POSTHOOK: query: CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl1 +PREHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl2 +POSTHOOK: query: CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl2 +PREHOOK: query: CREATE TABLE tbl3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl3 +POSTHOOK: query: CREATE TABLE tbl3(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl3 +PREHOOK: query: CREATE TABLE tbl4(key int, value string) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tbl4 +POSTHOOK: query: CREATE TABLE tbl4(key int, value string) CLUSTERED BY (value) SORTED BY (value) INTO 2 BUCKETS +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tbl4 +PREHOOK: query: insert overwrite table tbl1 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl1 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: insert overwrite table tbl1 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl1 +POSTHOOK: Lineage: tbl1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table tbl2 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl2 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: insert overwrite table tbl2 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl2 +POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table tbl3 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl3 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: insert overwrite table tbl3 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl3 +POSTHOOK: Lineage: tbl3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: insert overwrite table tbl4 select * from src +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Output: default@tbl4 +[Error 30017]: Skipping stats aggregation by error org.apache.hadoop.hive.ql.metadata.HiveException: [Error 30015]: Stats aggregator of type counter cannot be connected to +POSTHOOK: query: insert overwrite table tbl4 select * from src +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Output: default@tbl4 +POSTHOOK: Lineage: tbl4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] +POSTHOOK: Lineage: tbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key + +-- Three tests below are all the same query with different alias, which changes dispatch order of GenMapRedWalker +-- This is dependent to iteration order of HashMap, so can be meaningless in non-sun jdk +-- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- c = TS[1]-RS[7]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key + +-- Three tests below are all the same query with different alias, which changes dispatch order of GenMapRedWalker +-- This is dependent to iteration order of HashMap, so can be meaningless in non-sun jdk +-- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- c = TS[1]-RS[7]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 6 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 1479 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: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 878 Data size: 3517 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 4 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- d = TS[0]-RS[7]-JOIN[8]-SEL[9]-FS[10] +-- b = TS[1]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- d = TS[0]-RS[7]-JOIN[8]-SEL[9]-FS[10] +-- b = TS[1]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8] +-- a = TS[2]-MAPJOIN[11] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) + Reducer 5 <- Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: d + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 6 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 1479 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: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 878 Data size: 3517 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 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Reducer 5 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src d on d.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- a = TS[1]-MAPJOIN[11] +-- h = TS[2]-RS[7]-JOIN[8] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- b = TS[0]-OP[13]-MAPJOIN[11]-RS[6]-JOIN[8]-SEL[9]-FS[10] +-- a = TS[1]-MAPJOIN[11] +-- h = TS[2]-RS[7]-JOIN[8] +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 6 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 1479 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: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 6 + Map Operator Tree: + TableScan + alias: h + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 878 Data size: 3517 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 4 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src h on h.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + 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: 1599 Data size: 6397 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1599 Data size: 6397 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 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + 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: 1599 Data size: 6397 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1599 Data size: 6397 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 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl3 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl3 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE + Map 6 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 1479 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: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 878 Data size: 3517 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 4 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl4 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl4 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 6 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 1479 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: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 878 Data size: 3517 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 4 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a non-bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + 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: 1599 Data size: 6397 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1599 Data size: 6397 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 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@src +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@src +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on the same key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Reducer 2 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 4 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + 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: 1599 Data size: 6397 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 1599 Data size: 6397 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 + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl3 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl3 c on c.key = a.key +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl3 +#### A masked pattern was here #### +2654 +PREHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +POSTHOOK: query: -- A SMB join is being followed by a regular join on a bucketed table on a different key +explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Reducer 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 727 Data size: 2908 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: 727 Data size: 2908 Basic stats: COMPLETE Column stats: NONE + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: value is not null (type: boolean) + Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE + Map 6 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key is not null and value is not null) (type: boolean) + Statistics: Num rows: 14 Data size: 1479 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: 14 Data size: 1479 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} + 1 + outputColumnNames: _col1 + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 799 Data size: 3198 Basic stats: COMPLETE Column stats: NONE + Reducer 3 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 + 1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + Statistics: Num rows: 878 Data size: 3517 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 4 + Reduce Operator Tree: + Group By Operator + aggregations: count(VALUE._col0) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +PREHOOK: type: QUERY +PREHOOK: Input: default@tbl1 +PREHOOK: Input: default@tbl2 +PREHOOK: Input: default@tbl4 +#### A masked pattern was here #### +POSTHOOK: query: select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join tbl4 c on c.value = a.value +POSTHOOK: type: QUERY +POSTHOOK: Input: default@tbl1 +POSTHOOK: Input: default@tbl2 +POSTHOOK: Input: default@tbl4 +#### A masked pattern was here #### +2654
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out?rev=1634671&view=auto ============================================================================== Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out (added) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out Mon Oct 27 19:56:58 2014 differ Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out?rev=1634671&view=auto ============================================================================== Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out (added) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out Mon Oct 27 19:56:58 2014 differ
