query: drop table dest_j1 query: CREATE TABLE dest_j1(key STRING, value STRING) STORED AS TEXTFILE query: EXPLAIN INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(z) */ subq.key1, z.value FROM (SELECT /*+ MAPJOIN(x) */ x.key as key1, x.value as value1, y.key as key2, y.value as value2 FROM src1 x JOIN src y ON (x.key = y.key)) subq JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11) ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF src1 x) (TOK_TABREF src y) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL y) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST x))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key) key1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) value) value1) (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key) key2) (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) value) value2)))) subq) (TOK_TABREF srcpart z) (and (and (= (. (TOK_TABLE_OR_COL subq) key1) (. (TOK_TABLE_OR_COL z) key)) (= (. (TOK_TABLE_OR_COL z) ds) '2008-04-08')) (= (. (TOK_TABLE_OR_COL z) hr) 11)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_j1)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST z))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq) key1)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL z) value))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 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: subq:y TableScan alias: y Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} 1 keys: 0 1 outputColumnNames: _col0 Position of Big Table: 1 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Local Work: Map Reduce Local Work Alias -> Map Local Tables: subq:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: subq:x TableScan alias: x Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} 1 keys: 0 1 outputColumnNames: _col0 Position of Big Table: 1 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/868000036/10002 Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col0} 1 {value} keys: 0 1 outputColumnNames: _col0, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col5 type: string outputColumnNames: _col0, _col5 Select Operator expressions: expr: _col0 type: string expr: _col5 type: string outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 1 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: dest_j1 Local Work: Map Reduce Local Work Alias -> Map Local Tables: z Fetch Operator limit: -1 Alias -> Map Local Operator Tree: z TableScan alias: z Filter Operator predicate: expr: ((ds = '2008-04-08') and (UDFToDouble(hr) = UDFToDouble(11))) type: boolean Filter Operator predicate: expr: (ds = '2008-04-08') type: boolean Filter Operator predicate: expr: (UDFToDouble(hr) = UDFToDouble(11)) type: boolean Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col0} 1 {value} keys: 0 1 outputColumnNames: _col0, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col5 type: string outputColumnNames: _col0, _col5 Select Operator expressions: expr: _col0 type: string expr: _col5 type: string outputColumnNames: _col0, _col1 File Output Operator compressed: false GlobalTableId: 1 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: dest_j1 Stage: Stage-5 Conditional Operator list of dependent Tasks: Move Operator files: hdfs directory: true destination: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/207829460/10000 Map Reduce Alias -> Map Operator Tree: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/868000036/10003 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 Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 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: dest_j1 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: dest_j1 query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(z) */ subq.key1, z.value FROM (SELECT /*+ MAPJOIN(x) */ x.key as key1, x.value as value1, y.key as key2, y.value as value2 FROM src1 x JOIN src y ON (x.key = y.key)) subq JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11) Input: default/src1 Input: default/src Input: default/srcpart/ds=2008-04-08/hr=11 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/380670394/10000 128 val_128 128 val_128 128 val_128 128 val_128 128 val_128 128 val_128 128 val_128 128 val_128 128 val_128 146 val_146 146 val_146 146 val_146 146 val_146 150 val_150 213 val_213 213 val_213 213 val_213 213 val_213 224 val_224 224 val_224 224 val_224 224 val_224 238 val_238 238 val_238 238 val_238 238 val_238 255 val_255 255 val_255 255 val_255 255 val_255 273 val_273 273 val_273 273 val_273 273 val_273 273 val_273 273 val_273 273 val_273 273 val_273 273 val_273 278 val_278 278 val_278 278 val_278 278 val_278 311 val_311 311 val_311 311 val_311 311 val_311 311 val_311 311 val_311 311 val_311 311 val_311 311 val_311 369 val_369 369 val_369 369 val_369 369 val_369 369 val_369 369 val_369 369 val_369 369 val_369 369 val_369 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 401 val_401 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 406 val_406 66 val_66 98 val_98 98 val_98 98 val_98 98 val_98 query: drop table dest_j1