PREHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE dest_j1(key STRING, value STRING, val2 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@dest_j1 PREHOOK: 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) PREHOOK: type: QUERY POSTHOOK: 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) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME 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 (TOK_TABNAME 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 (TOK_TABNAME src1) x) (= (. (TOK_TABLE_OR_COL x) key) (. (TOK_TABLE_OR_COL subq1) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME 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-11 depends on stages: Stage-1, Stage-9 Stage-2 depends on stages: Stage-11 Stage-8 depends on stages: Stage-2 , consists of Stage-5, Stage-4, Stage-6 Stage-5 Stage-0 depends on stages: Stage-5, Stage-4, Stage-7 Stage-3 depends on stages: Stage-0 Stage-4 Stage-6 Stage-7 depends on stages: Stage-6 Stage-9 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: null-subquery1:subq1-subquery1:x TableScan alias: x GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key < 20.0) type: boolean 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 Needs Tagging: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src name: default.src 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 #### A masked pattern was here #### NumFilesPerFileSink: 1 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 \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Truncated Path -> Alias: /src [null-subquery1:subq1-subquery1:x] Stage: Stage-11 Map Reduce Local Work Alias -> Map Local Tables: x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: x TableScan alias: x GatherStats: false HashTable Sink Operator condition expressions: 0 {_col1} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[key]] Position of Big Table: 0 Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### TableScan GatherStats: false Union Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[key]] 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 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: true MultiFileSpray: false #### A masked pattern was here #### TableScan GatherStats: false Union Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {_col1} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[_col0]] 1 [Column[key]] 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 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: true MultiFileSpray: false Local Work: Map Reduce Local Work Needs Tagging: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10002 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 \ 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 \ #### A masked pattern was here #### Partition base file name: -mr-10004 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 \ 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 \ Truncated Path -> Alias: #### A masked pattern was here #### Stage: Stage-8 Conditional Operator Stage: Stage-5 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-0 Move Operator tables: replace: true #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 #### A masked pattern was here #### Stage: Stage-3 Stats-Aggr Operator #### A masked pattern was here #### Stage: Stage-4 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -ext-10003 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 name: default.dest_j1 Truncated Path -> Alias: #### A masked pattern was here #### Stage: Stage-6 Map Reduce Alias -> Map Operator Tree: #### A masked pattern was here #### File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -ext-10003 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value,val2 columns.types string:string:int #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, i32 val2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.dest_j1 name: default.dest_j1 Truncated Path -> Alias: #### A masked pattern was here #### Stage: Stage-7 Move Operator files: hdfs directory: true #### A masked pattern was here #### Stage: Stage-9 Map Reduce Alias -> Map Operator Tree: null-subquery2:subq1-subquery2:x1 TableScan alias: x1 GatherStats: false Filter Operator isSamplingPred: false predicate: expr: (key > 100.0) type: boolean 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 Needs Tagging: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: src input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct src { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src name: default.src 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 #### A masked pattern was here #### NumFilesPerFileSink: 1 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 \ TotalFiles: 1 GatherStats: false MultiFileSpray: false Truncated Path -> Alias: /src [null-subquery2:subq1-subquery2:x1] PREHOOK: 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) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Output: default@dest_j1 POSTHOOK: 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) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Output: default@dest_j1 POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.null, (src)x1.null, ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, 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.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)x.null, (src)x1.null, ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] 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