query: drop table dest_j1 query: CREATE TABLE dest_j1(key STRING, value STRING, val2 INT) STORED AS TEXTFILE query: EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x) */ x.key, x.value, subq1.cnt FROM ( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key UNION ALL SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key ) subq1 JOIN src1 x ON (x.key = subq1.key) ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF src x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (< (. (TOK_TABLE_OR_COL x) key) 20)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) (TOK_QUERY (TOK_FROM (TOK_TABREF src x1)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x1) key) key) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_WHERE (> (. (TOK_TABLE_OR_COL x1) key) 100)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x1) key))))) subq1) (TOK_TABREF src1 x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_j1)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST x))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) cnt))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1, Stage-6 Stage-5 depends on stages: Stage-2 Stage-0 depends on stages: Stage-5 Stage-6 is a root stage Stage-2 depends on stages: Stage-1, Stage-6 Stage-5 depends on stages: Stage-2 Stage-0 depends on stages: Stage-5 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery1:subq1-subquery1:x TableScan alias: x Filter Operator isSamplingPred: false predicate: expr: (UDFToDouble(key) < UDFToDouble(20)) type: boolean Filter Operator isSamplingPred: false predicate: expr: (UDFToDouble(key) < UDFToDouble(20)) type: boolean Select Operator expressions: expr: key type: string outputColumnNames: key Group By Operator aggregations: expr: count(1) keys: expr: key type: string mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: -1 value expressions: expr: _col1 type: bigint Needs Tagging: false Path -> Alias: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/src Path -> Partition: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/src Partition input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name src columns.types string:string serialization.ddl struct src { string key, string value} serialization.format 1 columns key,value bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/src serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: src Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) keys: expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10002 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10002 Union Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} keys: 0 1 outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col1 type: bigint expr: _col2 type: string expr: _col3 type: string outputColumnNames: _col1, _col2, _col3 Select Operator expressions: expr: _col2 type: string expr: _col3 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: UDFToInteger(_col2) type: int outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name dest_j1 columns.types string:string:int serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 columns key,value,val2 bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/dest_j1 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10004 Union Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} keys: 0 1 outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col1 type: bigint expr: _col2 type: string expr: _col3 type: string outputColumnNames: _col1, _col2, _col3 Select Operator expressions: expr: _col2 type: string expr: _col3 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: UDFToInteger(_col2) type: int outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name dest_j1 columns.types string:string:int serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 columns key,value,val2 bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/dest_j1 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 Local Work: Map Reduce Local Work Alias -> Map Local Tables: x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: x TableScan alias: x Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} keys: 0 1 outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col1 type: bigint expr: _col2 type: string expr: _col3 type: string outputColumnNames: _col1, _col2, _col3 Select Operator expressions: expr: _col2 type: string expr: _col3 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1, _col2 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: UDFToInteger(_col2) type: int outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name dest_j1 columns.types string:string:int serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 columns key,value,val2 bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/dest_j1 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 Needs Tagging: false Path -> Alias: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10002 file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10004 Path -> Partition: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10002 Partition input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10004 Partition input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ Stage: Stage-5 Conditional Operator list of dependent Tasks: Move Operator files: hdfs directory: true source: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 destination: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1251033308/10000 Map Reduce Alias -> Map Operator Tree: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 Reduce Output Operator sort order: Map-reduce partition columns: expr: rand() type: double tag: -1 value expressions: expr: key type: string expr: value type: string expr: val2 type: int Needs Tagging: false Path -> Alias: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 Path -> Partition: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10003 Partition input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name dest_j1 columns.types string:string:int serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 columns key,value,val2 bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/dest_j1 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1251033308/10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name dest_j1 columns.types string:string:int serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 columns key,value,val2 bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/dest_j1 file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 Stage: Stage-0 Move Operator tables: replace: true source: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1251033308/10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name dest_j1 columns.types string:string:int serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 columns key,value,val2 bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/dest_j1 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: dest_j1 tmp directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1251033308/10001 Stage: Stage-6 Map Reduce Alias -> Map Operator Tree: null-subquery2:subq1-subquery2:x1 TableScan alias: x1 Filter Operator isSamplingPred: false predicate: expr: (UDFToDouble(key) > UDFToDouble(100)) type: boolean Filter Operator isSamplingPred: false predicate: expr: (UDFToDouble(key) > UDFToDouble(100)) type: boolean Select Operator expressions: expr: key type: string outputColumnNames: key Group By Operator aggregations: expr: count(1) keys: expr: key type: string mode: hash outputColumnNames: _col0, _col1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: -1 value expressions: expr: _col1 type: bigint Needs Tagging: false Path -> Alias: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/src Path -> Partition: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/src Partition input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: name src columns.types string:string serialization.ddl struct src { string key, string value} serialization.format 1 columns key,value bucket_count -1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/test/data/warehouse/src serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: src Reduce Operator Tree: Group By Operator aggregations: expr: count(VALUE._col0) keys: expr: KEY._col0 type: string mode: mergepartial outputColumnNames: _col0, _col1 Select Operator expressions: expr: _col0 type: string expr: _col1 type: bigint outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 0 directory: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1727048194/10004 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat properties: columns _col0,_col1 columns.types string,bigint escape.delim \ query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(x) */ x.key, x.value, subq1.cnt FROM ( SELECT x.key as key, count(1) as cnt from src x where x.key < 20 group by x.key UNION ALL SELECT x1.key as key, count(1) as cnt from src x1 where x1.key > 100 group by x1.key ) subq1 JOIN src1 x ON (x.key = subq1.key) Input: default/src Input: default/src1 Output: default/dest_j1 query: select * from dest_j1 x order by x.key Input: default/dest_j1 Output: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/1156663841/10000 128 3 146 val_146 2 150 val_150 1 213 val_213 2 224 2 238 val_238 2 255 val_255 2 273 val_273 3 278 val_278 2 311 val_311 3 369 3 401 val_401 5 406 val_406 4 query: drop table dest_j1