query: drop TABLE dest_j1 query: CREATE TABLE dest_j1(key STRING, cnt INT) query: EXPLAIN INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(subq1) */ subq1.key, count(1) as cnt FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) group by subq1.key ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF src1 x)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL x) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL x) key)))) subq1) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF src y)) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL y) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL y) key)))) subq2) (= (. (TOK_TABLE_OR_COL subq1) key) (. (TOK_TABLE_OR_COL subq2) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB dest_j1)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST subq1))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) key)) (TOK_SELEXPR (TOK_FUNCTION count 1) cnt)) (TOK_GROUPBY (. (TOK_TABLE_OR_COL subq1) key)))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1, Stage-4 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 Stage-4 is a root stage Stage-2 depends on stages: Stage-1, Stage-4 Stage-3 depends on stages: Stage-2 Stage-0 depends on stages: Stage-3 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: subq2:y TableScan alias: y 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 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 outputColumnNames: _col0 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/733202123/10002 Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col0} 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: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/733202123/10004 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/733202123/10004 Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col0} 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-3 Map Reduce Alias -> Map Operator Tree: file:/data/users/athusoo/commits/hive_trunk_ws1/build/ql/tmp/733202123/10003 Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Select Operator expressions: expr: _col0 type: string outputColumnNames: _col0 Group By Operator aggregations: expr: count(1) keys: expr: _col0 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 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 Select Operator expressions: expr: _col0 type: string expr: UDFToInteger(_col1) type: int 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-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 Stage: Stage-4 Map Reduce Alias -> Map Operator Tree: subq1:x TableScan alias: x 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 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 outputColumnNames: _col0 File Output Operator compressed: false GlobalTableId: 0 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat query: INSERT OVERWRITE TABLE dest_j1 SELECT /*+ MAPJOIN(subq1) */ subq1.key, count(1) as cnt FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key) group by 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/2103472034/10000 128 1 146 1 150 1 213 1 224 1 238 1 255 1 273 1 278 1 311 1 369 1 401 1 406 1 66 1 98 1 query: drop TABLE dest_j1