http://git-wip-us.apache.org/repos/asf/hive/blob/6f5c1135/ql/src/test/results/clientpositive/join32_lessSize.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/join32_lessSize.q.out b/ql/src/test/results/clientpositive/join32_lessSize.q.out deleted file mode 100644 index f9f3506..0000000 --- a/ql/src/test/results/clientpositive/join32_lessSize.q.out +++ /dev/null @@ -1,2651 +0,0 @@ -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: CREATE TABLE dest_j2(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@dest_j2 -POSTHOOK: query: CREATE TABLE dest_j2(key STRING, value STRING, val2 STRING) STORED AS TEXTFILE -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@dest_j2 -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 -STAGE DEPENDENCIES: - Stage-9 is a root stage - Stage-7 depends on stages: Stage-9 - Stage-8 depends on stages: Stage-7 - Stage-6 depends on stages: Stage-8 - Stage-0 depends on stages: Stage-6 - Stage-3 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-9 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_2:x - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - Position of Big Table: 0 - - Stage: Stage-7 - Map Reduce - Map Operator Tree: - TableScan - alias: z - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 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,_col3 - columns.types string,string - 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 - Local Work: - Map Reduce Local Work - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:z] - - Stage: Stage-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:y - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:y - 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col3 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 - Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest_j1 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### 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-10002 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col3 - columns.types string,string - 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,_col3 - columns.types string,string - 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: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: -#### 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j1 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest_j1 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### 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 #### - -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 SIMPLE [(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 -PREHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest_j1 -SELECT x.key, z.value, y.value -FROM src w JOIN src1 x ON (x.value = w.value) -JOIN src y ON (x.key = y.key) -JOIN src1 z ON (x.key = z.key) -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest_j1 -SELECT x.key, z.value, y.value -FROM src w JOIN src1 x ON (x.value = w.value) -JOIN src y ON (x.key = y.key) -JOIN src1 z ON (x.key = z.key) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-13 is a root stage - Stage-10 depends on stages: Stage-13 - Stage-12 depends on stages: Stage-10 - Stage-9 depends on stages: Stage-12 - Stage-11 depends on stages: Stage-9 - Stage-8 depends on stages: Stage-11 - Stage-0 depends on stages: Stage-8 - Stage-4 depends on stages: Stage-0 - -STAGE PLANS: - Stage: Stage-13 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_2:x - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_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: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 1 - - Stage: Stage-10 - Map Reduce - Map Operator Tree: - TableScan - alias: z - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 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: _col0, _col1, _col3 - Position of Big Table: 1 - Statistics: Num rows: 27 Data size: 210 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,_col3 - columns.types string,string,string - 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 - Local Work: - Map Reduce Local Work - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: -#### 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: - /src1 [$hdt$_3:z] - - Stage: Stage-12 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:w - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:w - TableScan - alias: w - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Position of Big Table: 0 - - Stage: Stage-9 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3 - Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 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,_col3 - columns.types string,string - 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 - 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-10002 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1,_col3 - columns.types string,string,string - 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,_col3 - columns.types string,string,string - 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: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: -#### A masked pattern was here #### - - Stage: Stage-11 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_0:y - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_0:y - 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 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-8 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 - Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j1 - numFiles 1 - numRows 85 - rawDataSize 1600 - serialization.ddl struct dest_j1 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 1685 -#### 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-10003 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col3 - columns.types string,string - 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,_col3 - columns.types string,string - 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: src - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - properties: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: -#### 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j1 - numFiles 1 - numRows 85 - rawDataSize 1600 - serialization.ddl struct dest_j1 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 1685 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j1 - - Stage: Stage-4 - Stats-Aggr Operator -#### A masked pattern was here #### - -PREHOOK: query: INSERT OVERWRITE TABLE dest_j1 -SELECT x.key, z.value, y.value -FROM src w JOIN src1 x ON (x.value = w.value) -JOIN src y ON (x.key = y.key) -JOIN src1 z ON (x.key = z.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, z.value, y.value -FROM src w JOIN src1 x ON (x.value = w.value) -JOIN src y ON (x.key = y.key) -JOIN src1 z ON (x.key = z.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 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j1.value SIMPLE [(src1)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 -PREHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-7 depends on stages: Stage-6 - 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-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:$hdt$_2:x - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_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: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 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 - 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 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 - Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 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,string - 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 - 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: - /src [$hdt$_1:$hdt$_1:y] - - 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 - 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: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - Position of Big Table: 1 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3, _col4 - Position of Big Table: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest_j2 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 - 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-10002 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - 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,string - 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: 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: -#### 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j2 - numFiles 0 - numRows 0 - rawDataSize 0 - serialization.ddl struct dest_j2 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 0 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 - - Stage: Stage-2 - Stats-Aggr Operator -#### A masked pattern was here #### - -PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.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_j2 -POSTHOOK: query: INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.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_j2 -POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from dest_j2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest_j2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest_j2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest_j2 -#### 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 -PREHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN EXTENDED -INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.value = z.value and z.ds='2008-04-08' and z.hr=11) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-7 depends on stages: Stage-6 - 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-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:$hdt$_1:y - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_1:y - TableScan - alias: y - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Position of Big Table: 1 - - Stage: Stage-6 - Map Reduce - Map Operator Tree: - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col1, _col2 - Position of Big Table: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: string), _col2 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 550 Data size: 5843 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,string - 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 - 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: - /src1 [$hdt$_1:$hdt$_2:x] - - 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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 - 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: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - Position of Big Table: 1 - - Stage: Stage-5 - Map Reduce - Map Operator Tree: - TableScan - GatherStats: false - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3, _col4 - Position of Big Table: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 1 -#### A masked pattern was here #### - NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j2 - numFiles 1 - numRows 85 - rawDataSize 1600 - serialization.ddl struct dest_j2 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 1685 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 - 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-10002 - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - columns _col0,_col1 - columns.types string,string - 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,string - 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: 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 {"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"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: -#### 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: - COLUMN_STATS_ACCURATE {"BASIC_STATS":"true"} - bucket_count -1 - columns key,value,val2 - columns.comments - columns.types string:string:string -#### A masked pattern was here #### - name default.dest_j2 - numFiles 1 - numRows 85 - rawDataSize 1600 - serialization.ddl struct dest_j2 { string key, string value, string val2} - serialization.format 1 - serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 1685 -#### A masked pattern was here #### - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.dest_j2 - - Stage: Stage-2 - Stats-Aggr Operator -#### A masked pattern was here #### - -PREHOOK: query: INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.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_j2 -POSTHOOK: query: INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, z.value, res.value -FROM (select x.key, x.value from src1 x LEFT OUTER JOIN src y ON (x.key = y.key)) res -JOIN srcpart z ON (res.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_j2 -POSTHOOK: Lineage: dest_j2.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.val2 SIMPLE [(src1)x.FieldSchema(name:value, type:string, comment:default), ] -POSTHOOK: Lineage: dest_j2.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: select * from dest_j2 -PREHOOK: type: QUERY -PREHOOK: Input: default@dest_j2 -#### A masked pattern was here #### -POSTHOOK: query: select * from dest_j2 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@dest_j2 -#### A masked pattern was here #### - val_165 val_165 - val_165 val_165 - val_193 val_193 - val_193 val_193 - val_193 val_193 - val_265 val_265 - val_265 val_265 - val_27 val_27 - val_409 val_409 - val_409 val_409 - val_409 val_409 - val_484 val_484 -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 -PREHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, x.value, res.value -FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res -JOIN srcpart x ON (res.value = x.value and x.ds='2008-04-08' and x.hr=11) -PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN -INSERT OVERWRITE TABLE dest_j2 -SELECT res.key, x.value, res.value -FROM (select x.key, x.value from src1 x JOIN src y ON (x.key = y.key)) res -JOIN srcpart x ON (res.value = x.value and x.ds='2008-04-08' and x.hr=11) -POSTHOOK: type: QUERY -STAGE DEPENDENCIES: - Stage-8 is a root stage - Stage-6 depends on stages: Stage-8 - Stage-7 depends on stages: Stage-6 - 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-8 - Map Reduce Local Work - Alias -> Map Local Tables: - $hdt$_1:$hdt$_2:x - Fetch Operator - limit: -1 - Alias -> Map Local Operator Tree: - $hdt$_1:$hdt$_2:x - TableScan - alias: x - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - - Stage: Stage-6 - Map Reduce - Map Operator Tree: -
<TRUNCATED>
