PREHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest_j1(key STRING, value STRING, val2 INT) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@dest_j1 POSTHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest_j1(key STRING, value STRING, val2 INT) STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest_j1 PREHOOK: query: -- Since the inputs are small, it should be automatically converted to mapjoin EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT 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: -- Since the inputs are small, it should be automatically converted to mapjoin EXPLAIN EXTENDED INSERT OVERWRITE TABLE dest_j1 SELECT 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_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-7 depends on stages: Stage-1, Stage-4 Stage-6 depends on stages: Stage-7 Stage-0 depends on stages: Stage-6 Stage-3 depends on stages: Stage-0 Stage-4 is a root stage STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) < 20.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numRows 500 rawDataSize 5312 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numRows 500 rawDataSize 5312 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 Truncated Path -> Alias: /src [$hdt$_0-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:x] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE 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 \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: $hdt$_1:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $hdt$_1:x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (((UDFToDouble(key) < 20.0) or (UDFToDouble(key) > 100.0)) and key is not null) (type: boolean) Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 8 Data size: 61 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 Stage: Stage-6 Map Reduce Map Operator Tree: TableScan GatherStats: false Union Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col3 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE #### 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.comments 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 TableScan GatherStats: false Union Statistics: Num rows: 166 Data size: 1762 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 Position of Big Table: 0 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col2 (type: string), _col3 (type: string), UDFToInteger(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE #### 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.comments 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 Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: -mr-10001 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 \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe 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 \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### 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 \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe 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 \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe #### A masked pattern was here #### Partition base file name: src1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.src1 numFiles 1 numRows 25 rawDataSize 191 serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 216 #### 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.src1 numFiles 1 numRows 25 rawDataSize 191 serialization.ddl struct src1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 216 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.src1 name: default.src1 Truncated Path -> Alias: #### 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.comments 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 Stage: Stage-3 Stats-Aggr Operator #### A masked pattern was here #### Stage: Stage-4 Map Reduce Map Operator Tree: TableScan alias: x Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (UDFToDouble(key) > 100.0) (type: boolean) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: bigint) auto parallelism: 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numRows 500 rawDataSize 5312 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: COLUMN_STATS_ACCURATE true bucket_count -1 columns key,value columns.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.src numFiles 1 numRows 500 rawDataSize 5312 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 Truncated Path -> Alias: /src [$hdt$_0-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:x] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE 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 \ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT 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 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)x.null, ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: select * from dest_j1 PREHOOK: type: QUERY PREHOOK: Input: default@dest_j1 #### A masked pattern was here #### POSTHOOK: query: select * from dest_j1 POSTHOOK: type: QUERY POSTHOOK: Input: default@dest_j1 #### A masked pattern was here #### 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