Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out?rev=1634671&view=auto ============================================================================== --- hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out (added) +++ hive/branches/spark/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out Mon Oct 27 19:56:58 2014 @@ -0,0 +1,740 @@ +PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin +PREHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tab_part +POSTHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tab_part +PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@srcbucket_mapjoin_part +PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin +POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +PREHOOK: type: LOAD +#### A masked pattern was here #### +PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') +POSTHOOK: type: LOAD +#### A masked pattern was here #### +POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin_part +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin_part +PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +PREHOOK: Output: default@tab_part@ds=2008-04-08 +[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 tab_part partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin_part +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin_part +POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 +POSTHOOK: Output: default@tab_part@ds=2008-04-08 +POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tab +POSTHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tab +PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: Output: default@tab@ds=2008-04-08 +[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 tab partition (ds='2008-04-08') +select key,value from srcbucket_mapjoin +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +POSTHOOK: Output: default@tab@ds=2008-04-08 +POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.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 4 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Map 3 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + 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: string) + sort order: + + Map-reduce partition columns: value (type: string) + Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int) + Map 3 + 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: 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 {VALUE._col0} + outputColumnNames: _col0, _col12 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col12 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 878 Data size: 3517 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 878 Data size: 3517 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 4 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} {VALUE._col0} + 1 + outputColumnNames: _col0, _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 + value expressions: _col0 (type: int) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +PREHOOK: type: CREATETABLE +PREHOOK: Output: database:default +PREHOOK: Output: default@tab1 +POSTHOOK: query: CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE +POSTHOOK: type: CREATETABLE +POSTHOOK: Output: database:default +POSTHOOK: Output: default@tab1 +PREHOOK: query: insert overwrite table tab1 +select key,value from srcbucket_mapjoin +PREHOOK: type: QUERY +PREHOOK: Input: default@srcbucket_mapjoin +PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +PREHOOK: Output: default@tab1 +[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 tab1 +select key,value from srcbucket_mapjoin +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcbucket_mapjoin +POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08 +POSTHOOK: Output: default@tab1 +POSTHOOK: Lineage: tab1.key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ] +POSTHOOK: Lineage: tab1.value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ] +PREHOOK: query: explain +select a.key, a.value, b.value +from tab1 a join src b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, a.value, b.value +from tab1 a join src b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 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 + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 14 Data size: 1456 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: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + value expressions: key (type: int), value (type: string) + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {VALUE._col0} {VALUE._col1} + 1 {VALUE._col1} + outputColumnNames: _col0, _col1, _col6 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 275 Data size: 2921 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: explain +select a.key, b.key from (select key from tab_part where key > 1) a join (select key from tab_part where key > 2) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, b.key from (select key from tab_part where key > 1) a join (select key from tab_part where key > 2) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tab_part + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key > 1) and key is not null) (type: boolean) + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 242 Data size: 968 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: 242 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Map 3 + Map Operator Tree: + TableScan + alias: tab_part + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((key > 2) and key is not null) (type: boolean) + Statistics: Num rows: 242 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 242 Data size: 968 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: 242 Data size: 968 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1 + Statistics: Num rows: 266 Data size: 1064 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 266 Data size: 1064 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 266 Data size: 1064 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: explain +select a.key, b.key from (select key from tab_part where key > 1) a left outer join (select key from tab_part where key > 2) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, b.key from (select key from tab_part where key > 1) a left outer join (select key from tab_part where key > 2) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tab_part + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key > 1) (type: boolean) + Statistics: Num rows: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 484 Data size: 1936 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: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Map 3 + Map Operator Tree: + TableScan + alias: tab_part + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key > 2) (type: boolean) + Statistics: Num rows: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 484 Data size: 1936 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: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Left Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1 + Statistics: Num rows: 532 Data size: 2129 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 532 Data size: 2129 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 532 Data size: 2129 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: explain +select a.key, b.key from (select key from tab_part where key > 1) a right outer join (select key from tab_part where key > 2) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, b.key from (select key from tab_part where key > 1) a right outer join (select key from tab_part where key > 2) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Spark + Edges: + Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 3 (GROUP PARTITION-LEVEL SORT, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: tab_part + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key > 1) (type: boolean) + Statistics: Num rows: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 484 Data size: 1936 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: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Map 3 + Map Operator Tree: + TableScan + alias: tab_part + Statistics: Num rows: 1453 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key > 2) (type: boolean) + Statistics: Num rows: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 484 Data size: 1936 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: 484 Data size: 1936 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Right Outer Join0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1 + Statistics: Num rows: 532 Data size: 2129 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 532 Data size: 2129 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 532 Data size: 2129 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: explain select a.key, b.key from (select distinct key from tab) a join tab b on b.key = a.key +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.key, b.key from (select distinct key from tab) a join tab b on b.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), Reducer 4 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Map 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 702 Data size: 2808 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 351 Data size: 1404 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: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Map 3 + Map Operator Tree: + TableScan + alias: tab + Statistics: Num rows: 702 Data size: 2808 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: int) + outputColumnNames: key + Statistics: Num rows: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: key (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 351 Data size: 1404 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: 351 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Reducer 2 + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + condition expressions: + 0 {KEY.reducesinkkey0} + 1 {KEY.reducesinkkey0} + outputColumnNames: _col0, _col1 + Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int), _col1 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 386 Data size: 1544 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 386 Data size: 1544 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 4 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 175 Data size: 700 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 175 Data size: 700 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: 175 Data size: 700 Basic stats: COMPLETE Column stats: NONE + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: explain select a.value, b.value from (select distinct value from tab) a join tab b on b.key = a.value +PREHOOK: type: QUERY +POSTHOOK: query: explain select a.value, b.value from (select distinct value from tab) a join tab b on b.key = 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 4 (GROUP PARTITION-LEVEL SORT, 1) + Reducer 4 <- Map 3 (GROUP, 1) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(key) is not null (type: boolean) + Statistics: Num rows: 14 Data size: 1456 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: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE + value expressions: value (type: string) + Map 3 + Map Operator Tree: + TableScan + alias: tab + Statistics: Num rows: 28 Data size: 2808 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: UDFToDouble(value) is not null (type: boolean) + Statistics: Num rows: 14 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: value (type: string) + outputColumnNames: value + Statistics: Num rows: 14 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: value (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 14 Data size: 1404 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 14 Data size: 1404 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 {VALUE._col1} + outputColumnNames: _col0, _col2 + Statistics: Num rows: 15 Data size: 1601 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 15 Data size: 1601 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 15 Data size: 1601 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 4 + Reduce Operator Tree: + Group By Operator + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 7 Data size: 702 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink +
