http://git-wip-us.apache.org/repos/asf/hive/blob/4ea77ecb/ql/src/test/results/clientpositive/auto_sortmerge_join_13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_13.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_13.q.out deleted file mode 100644 index ac143dd..0000000 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_13.q.out +++ /dev/null @@ -1,775 +0,0 @@ -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: insert overwrite table tbl1 select * from src where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl1 -POSTHOOK: query: insert overwrite table tbl1 select * from src where key < 10 -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 where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl2 -POSTHOOK: query: insert overwrite table tbl2 select * from src where key < 10 -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: CREATE TABLE dest1(k1 int, k2 int) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest1 -POSTHOOK: query: CREATE TABLE dest1(k1 int, k2 int) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest1 -PREHOOK: query: CREATE TABLE dest2(k1 string, k2 string) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest2 -POSTHOOK: query: CREATE TABLE dest2(k1 string, k2 string) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest2 -PREHOOK: query: explain -from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -PREHOOK: type: QUERY -POSTHOOK: query: explain -from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-5 - Stage-1 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-1, Stage-5 - Stage-5 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Select Operator - expressions: _col0 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: k1, k2 - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll') - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - sort order: - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: k1, k2 - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll') - mode: hash - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, k2 - Column Types: int, int - Table: default.dest1 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-4 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, k2 - Column Types: string, string - Table: default.dest2 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -PREHOOK: Output: default@dest1 -PREHOOK: Output: default@dest2 -POSTHOOK: query: from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -POSTHOOK: Output: default@dest1 -POSTHOOK: Output: default@dest2 -POSTHOOK: Lineage: dest1.k1 SIMPLE [(tbl1)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest1.k2 SIMPLE [(tbl2)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest2.k1 SIMPLE [(tbl1)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: dest2.k2 SIMPLE [(tbl2)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select * from dest1 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1 -#### A masked pattern was here #### -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -2 2 -4 4 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -8 8 -9 9 -PREHOOK: query: select * from dest2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest2 -#### A masked pattern was here #### -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_2 val_2 -val_4 val_4 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_8 val_8 -val_9 val_9 -PREHOOK: query: explain -from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -PREHOOK: type: QUERY -POSTHOOK: query: explain -from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-5 - Stage-1 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-1, Stage-5 - Stage-5 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Select Operator - expressions: _col0 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: k1, k2 - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll') - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - sort order: - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: k1, k2 - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll') - mode: hash - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, k2 - Column Types: int, int - Table: default.dest1 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-4 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, k2 - Column Types: string, string - Table: default.dest2 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -PREHOOK: Output: default@dest1 -PREHOOK: Output: default@dest2 -POSTHOOK: query: from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -POSTHOOK: Output: default@dest1 -POSTHOOK: Output: default@dest2 -POSTHOOK: Lineage: dest1.k1 SIMPLE [(tbl1)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest1.k2 SIMPLE [(tbl2)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest2.k1 SIMPLE [(tbl1)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: dest2.k2 SIMPLE [(tbl2)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select * from dest1 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1 -#### A masked pattern was here #### -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -2 2 -4 4 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -8 8 -9 9 -PREHOOK: query: select * from dest2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest2 -#### A masked pattern was here #### -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_2 val_2 -val_4 val_4 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_8 val_8 -val_9 val_9 -PREHOOK: query: explain -from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -PREHOOK: type: QUERY -POSTHOOK: query: explain -from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-2 is a root stage - Stage-0 depends on stages: Stage-2 - Stage-3 depends on stages: Stage-0, Stage-5 - Stage-1 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-1, Stage-5 - Stage-5 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-2 - Map Reduce - 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col3 - Select Operator - expressions: _col0 (type: int), _col2 (type: int) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - Select Operator - expressions: _col0 (type: int), _col1 (type: int) - outputColumnNames: k1, k2 - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll') - mode: hash - outputColumnNames: _col0, _col1 - Reduce Output Operator - sort order: - value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) - Select Operator - expressions: _col1 (type: string), _col3 (type: string) - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: k1, k2 - Group By Operator - aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll') - mode: hash - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest1 - - Stage: Stage-3 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, k2 - Column Types: int, int - Table: default.dest1 - - Stage: Stage-1 - Move Operator - tables: - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest2 - - Stage: Stage-4 - Stats Work - Basic Stats Work: - Column Stats Desc: - Columns: k1, k2 - Column Types: string, string - Table: default.dest2 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - Reduce Output Operator - sort order: - value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) - Reduce Operator Tree: - Group By Operator - aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) - mode: mergepartial - outputColumnNames: _col0, _col1 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - -PREHOOK: query: from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -PREHOOK: Output: default@dest1 -PREHOOK: Output: default@dest2 -POSTHOOK: query: from ( - SELECT a.key key1, a.value value1, b.key key2, b.value value2 - FROM tbl1 a JOIN tbl2 b - ON a.key = b.key ) subq -INSERT OVERWRITE TABLE dest1 select key1, key2 -INSERT OVERWRITE TABLE dest2 select value1, value2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -POSTHOOK: Output: default@dest1 -POSTHOOK: Output: default@dest2 -POSTHOOK: Lineage: dest1.k1 SIMPLE [(tbl1)a.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest1.k2 SIMPLE [(tbl2)b.FieldSchema(name:key, type:int, comment:null), ] -POSTHOOK: Lineage: dest2.k1 SIMPLE [(tbl1)a.FieldSchema(name:value, type:string, comment:null), ] -POSTHOOK: Lineage: dest2.k2 SIMPLE [(tbl2)b.FieldSchema(name:value, type:string, comment:null), ] -PREHOOK: query: select * from dest1 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest1 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest1 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest1 -#### A masked pattern was here #### -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -0 0 -2 2 -4 4 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -5 5 -8 8 -9 9 -PREHOOK: query: select * from dest2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest2 -#### A masked pattern was here #### -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_0 val_0 -val_2 val_2 -val_4 val_4 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_5 val_5 -val_8 val_8 -val_9 val_9
http://git-wip-us.apache.org/repos/asf/hive/blob/4ea77ecb/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out deleted file mode 100644 index f12bf98..0000000 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_14.q.out +++ /dev/null @@ -1,298 +0,0 @@ -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: insert overwrite table tbl1 select * from src where key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl1 -POSTHOOK: query: insert overwrite table tbl1 select * from src where key < 20 -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 where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl2 -POSTHOOK: query: insert overwrite table tbl2 select * from src where key < 10 -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: explain -select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key -PREHOOK: type: QUERY -POSTHOOK: query: explain -select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-4 is a root stage , consists of Stage-5, Stage-1 - Stage-5 has a backup stage: Stage-1 - Stage-3 depends on stages: Stage-5 - Stage-1 - Stage-0 depends on stages: Stage-3, Stage-1 - -STAGE PLANS: - Stage: Stage-4 - Conditional Operator - - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -32 -PREHOOK: query: insert overwrite table tbl2 select * from src where key < 200 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl2 -POSTHOOK: query: insert overwrite table tbl2 select * from src where key < 200 -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: explain -select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key -PREHOOK: type: QUERY -POSTHOOK: query: explain -select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-4 is a root stage , consists of Stage-5, Stage-1 - Stage-5 has a backup stage: Stage-1 - Stage-3 depends on stages: Stage-5 - Stage-1 - Stage-0 depends on stages: Stage-3, Stage-1 - -STAGE PLANS: - Stage: Stage-4 - Conditional Operator - - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key -PREHOOK: type: QUERY -PREHOOK: Input: default@tbl1 -PREHOOK: Input: default@tbl2 -#### A masked pattern was here #### -POSTHOOK: query: select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@tbl1 -POSTHOOK: Input: default@tbl2 -#### A masked pattern was here #### -207 http://git-wip-us.apache.org/repos/asf/hive/blob/4ea77ecb/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out deleted file mode 100644 index 827708c..0000000 --- a/ql/src/test/results/clientpositive/auto_sortmerge_join_15.q.out +++ /dev/null @@ -1,266 +0,0 @@ -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: insert overwrite table tbl1 select * from src where key < 20 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl1 -POSTHOOK: query: insert overwrite table tbl1 select * from src where key < 20 -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 where key < 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@src -PREHOOK: Output: default@tbl2 -POSTHOOK: query: insert overwrite table tbl2 select * from src where key < 10 -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: explain -select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key -PREHOOK: type: QUERY -POSTHOOK: query: explain -select count(*) FROM tbl1 a LEFT OUTER JOIN tbl2 b ON a.key = b.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-4 is a root stage , consists of Stage-5, Stage-1 - Stage-5 has a backup stage: Stage-1 - Stage-3 depends on stages: Stage-5 - Stage-1 - Stage-0 depends on stages: Stage-3, Stage-1 - -STAGE PLANS: - Stage: Stage-4 - Conditional Operator - - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:b - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:b - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: a - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: explain -select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key -PREHOOK: type: QUERY -POSTHOOK: query: explain -select count(*) FROM tbl1 a RIGHT OUTER JOIN tbl2 b ON a.key = b.key -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-4 is a root stage , consists of Stage-5, Stage-1 - Stage-5 has a backup stage: Stage-1 - Stage-3 depends on stages: Stage-5 - Stage-1 - Stage-0 depends on stages: Stage-3, Stage-1 - -STAGE PLANS: - Stage: Stage-4 - Conditional Operator - - Stage: Stage-5 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:a - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:a - TableScan - alias: a - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - - Stage: Stage-3 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Local Work: - Map Reduce Local Work - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE - Sorted Merge Bucket Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Reduce Output Operator - sort order: - value expressions: _col0 (type: bigint) - Reduce Operator Tree: - Group By Operator - aggregations: count(VALUE._col0) - mode: mergepartial - outputColumnNames: _col0 - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink -
