PREHOOK: query: CREATE TABLE dest_j1(key STRING, cnt1 INT, cnt2 INT) PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE dest_j1(key STRING, cnt1 INT, cnt2 INT) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@dest_j1 PREHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin EXPLAIN INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.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) PREHOOK: type: QUERY POSTHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin EXPLAIN INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.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) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME 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 (TOK_TABNAME 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 (TOK_TABNAME dest_j1))) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq1) cnt)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL subq2) cnt))))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-7 depends on stages: Stage-1, Stage-4 , consists of Stage-8, Stage-9, Stage-2 Stage-8 has a backup stage: Stage-2 Stage-5 depends on stages: Stage-8 Stage-0 depends on stages: Stage-2, Stage-5, Stage-6 Stage-3 depends on stages: Stage-0 Stage-9 has a backup stage: Stage-2 Stage-6 depends on stages: Stage-9 Stage-2 Stage-4 is a root stage 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) bucketGroup: false 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) bucketGroup: false 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 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat Stage: Stage-7 Conditional Operator Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: $INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $INTNAME HashTable Sink Operator condition expressions: 0 {_col0} {_col1} 1 {_col1} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[_col0]] Position of Big Table: 0 Stage: Stage-5 Map Reduce Alias -> Map Operator Tree: $INTNAME1 Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col0} {_col1} 1 {_col1} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[_col0]] outputColumnNames: _col0, _col1, _col3 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: UDFToInteger(_col1) type: int expr: UDFToInteger(_col3) type: int outputColumnNames: _col0, _col1, _col2 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: default.dest_j1 Local Work: Map Reduce Local Work 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.dest_j1 Stage: Stage-3 Stats-Aggr Operator Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: $INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $INTNAME1 HashTable Sink Operator condition expressions: 0 {_col0} {_col1} 1 {_col1} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[_col0]] Position of Big Table: 1 Stage: Stage-6 Map Reduce Alias -> Map Operator Tree: $INTNAME Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col0} {_col1} 1 {_col1} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[_col0]] outputColumnNames: _col0, _col1, _col3 Position of Big Table: 1 Select Operator expressions: expr: _col0 type: string expr: UDFToInteger(_col1) type: int expr: UDFToInteger(_col3) type: int outputColumnNames: _col0, _col1, _col2 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: default.dest_j1 Local Work: Map Reduce Local Work Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: $INTNAME 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 $INTNAME1 Reduce Output Operator key expressions: expr: _col0 type: string sort order: + Map-reduce partition columns: expr: _col0 type: string tag: 0 value expressions: expr: _col0 type: string expr: _col1 type: bigint Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {VALUE._col0} {VALUE._col1} 1 {VALUE._col1} handleSkewJoin: false outputColumnNames: _col0, _col1, _col3 Select Operator expressions: expr: _col0 type: string expr: UDFToInteger(_col1) type: int expr: UDFToInteger(_col3) type: int outputColumnNames: _col0, _col1, _col2 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: default.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) bucketGroup: false 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) bucketGroup: false 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 table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.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) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Output: default@dest_j1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT subq1.key, subq1.cnt, subq2.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) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.cnt1 EXPRESSION [(src1)x.null, ] POSTHOOK: Lineage: dest_j1.cnt2 EXPRESSION [(src)y.null, ] POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 x order by x.key PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 #### A masked pattern was here #### POSTHOOK: query: select * from dest_j1 x order by x.key POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_j1 #### A masked pattern was here #### POSTHOOK: Lineage: dest_j1.cnt1 EXPRESSION [(src1)x.null, ] POSTHOOK: Lineage: dest_j1.cnt2 EXPRESSION [(src)y.null, ] POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] 128 1 3 146 1 2 150 1 1 213 1 2 224 1 2 238 1 2 255 1 2 273 1 3 278 1 2 311 1 3 369 1 3 401 1 5 406 1 4 66 1 1 98 1 2