PREHOOK: query: -- SORT_QUERY_RESULTS CREATE TABLE dest_j1(key STRING, value STRING, val2 STRING) 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 STRING) 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, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) 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, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_JOIN TOK_TABREF TOK_TABNAME src1 x TOK_TABREF TOK_TABNAME src y = . TOK_TABLE_OR_COL x key . TOK_TABLE_OR_COL y key TOK_TABREF TOK_TABNAME srcpart z and and = . TOK_TABLE_OR_COL x value . TOK_TABLE_OR_COL z value = . TOK_TABLE_OR_COL z ds '2008-04-08' = . TOK_TABLE_OR_COL z hr 11 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 z value TOK_SELEXPR . TOK_TABLE_OR_COL y value STAGE DEPENDENCIES: Stage-7 is a root stage Stage-5 depends on stages: Stage-7 Stage-0 depends on stages: Stage-5 Stage-2 depends on stages: Stage-0 STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: $hdt$_0:z Fetch Operator limit: -1 Partition Description: Partition base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 hr 11 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.srcpart numFiles 1 numRows 500 partition_columns ds/hr partition_columns.types string:string rawDataSize 5312 serialization.ddl struct srcpart { 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.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.srcpart partition_columns ds/hr partition_columns.types string:string serialization.ddl struct srcpart { string key, string value} 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.srcpart name: default.srcpart $hdt$_1:$hdt$_2:x Fetch Operator limit: -1 Alias -> Map Local Operator Tree: $hdt$_0:z TableScan alias: z Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: ((11.0 = 11.0) and value is not null) (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) 1 _col3 (type: string) Position of Big Table: 1 $hdt$_1:$hdt$_2:x TableScan alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 7 Data size: 53 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-5 Map Reduce Map Operator Tree: TableScan alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 250 Data size: 2656 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) 1 _col3 (type: string) outputColumnNames: _col0, _col4, _col5 Position of Big Table: 1 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col5 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 302 Data size: 3213 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:string #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string 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: 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 #### 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 #### A masked pattern was here #### Partition base file name: hr=11 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 hr 11 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.srcpart numFiles 1 numRows 500 partition_columns ds/hr partition_columns.types string:string rawDataSize 5312 serialization.ddl struct srcpart { 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.comments 'default','default' columns.types string:string #### A masked pattern was here #### name default.srcpart partition_columns ds/hr partition_columns.types string:string serialization.ddl struct srcpart { string key, string value} 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.srcpart name: default.srcpart Truncated Path -> Alias: /src [$hdt$_1:$hdt$_1:y] 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:string #### A masked pattern was here #### name default.dest_j1 serialization.ddl struct dest_j1 { string key, string value, string 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-2 Stats-Aggr Operator #### A masked pattern was here #### PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Input: default@src1 PREHOOK: Input: default@srcpart PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 PREHOOK: Output: default@dest_j1 POSTHOOK: query: INSERT OVERWRITE TABLE dest_j1 SELECT x.key, z.value, y.value FROM src1 x JOIN src y ON (x.key = y.key) JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11) POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Input: default@src1 POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 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)y.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.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 #### 146 val_146 val_146 146 val_146 val_146 146 val_146 val_146 146 val_146 val_146 150 val_150 val_150 213 val_213 val_213 213 val_213 val_213 213 val_213 val_213 213 val_213 val_213 238 val_238 val_238 238 val_238 val_238 238 val_238 val_238 238 val_238 val_238 255 val_255 val_255 255 val_255 val_255 255 val_255 val_255 255 val_255 val_255 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 273 val_273 val_273 278 val_278 val_278 278 val_278 val_278 278 val_278 val_278 278 val_278 val_278 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 311 val_311 val_311 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 401 val_401 val_401 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 406 val_406 val_406 66 val_66 val_66 98 val_98 val_98 98 val_98 val_98 98 val_98 val_98 98 val_98 val_98