PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@srcbucket_mapjoin PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@srcbucket_mapjoin_part PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin_part POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin_part POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08') POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@srcbucket_mapjoin_part_2 PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin_part_2 POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin_part_2 POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08 PREHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') PREHOOK: type: LOAD PREHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08 POSTHOOK: query: load data local inpath '../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part_2 partition(ds='2008-04-08') POSTHOOK: type: LOAD POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08 PREHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint) PREHOOK: type: CREATETABLE POSTHOOK: query: create table bucketmapjoin_hash_result_1 (key bigint , value1 bigint, value2 bigint) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@bucketmapjoin_hash_result_1 PREHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint) PREHOOK: type: CREATETABLE POSTHOOK: query: create table bucketmapjoin_hash_result_2 (key bigint , value1 bigint, value2 bigint) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@bucketmapjoin_hash_result_2 PREHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string) PREHOOK: type: CREATETABLE POSTHOOK: query: create table bucketmapjoin_tmp_result (key string , value1 string, value2 string) POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@bucketmapjoin_tmp_result PREHOOK: query: explain extended insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" PREHOOK: type: QUERY POSTHOOK: query: explain extended insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part_2) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part) b) (and (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL b) ds) "2008-04-08")) (= (. (TOK_TABLE_OR_COL a) ds) "2008-04-08")))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST b))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value))))) STAGE DEPENDENCIES: Stage-7 is a root stage Stage-1 depends on stages: Stage-7 Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3 Stage-2 depends on stages: Stage-0 Stage-3 STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: b TableScan alias: b GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {value} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] Position of Big Table: 0 Bucket Mapjoin Context: Alias Bucket Base File Name Mapping: b {srcbucket22.txt=[srcbucket20.txt, srcbucket22.txt], srcbucket23.txt=[srcbucket21.txt, srcbucket23.txt]} Alias Bucket File Name Mapping: b {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt, pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt, pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt]} Alias Bucket Output File Name Mapping: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt 0 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt 1 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: a TableScan alias: a GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {value} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] outputColumnNames: _col0, _col1, _col6 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col6 type: string outputColumnNames: _col0, _col1, _col6 Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col6 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-34-40_179_2078859592920140854/-ext-10002 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-34-40_179_2078859592920140854/-ext-10000/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1310373280 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result TotalFiles: 1 GatherStats: true MultiFileSpray: false Local Work: Map Reduce Local Work Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 [a] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 Partition base file name: ds=2008-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 properties: bucket_count 2 bucket_field_name key columns key,value columns.types int:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08 name default.srcbucket_mapjoin_part_2 partition_columns ds serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979174 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 2 bucket_field_name key columns key,value columns.types int:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2 name default.srcbucket_mapjoin_part_2 partition_columns ds serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979173 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcbucket_mapjoin_part_2 name: default.srcbucket_mapjoin_part_2 Stage: Stage-5 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000 Stage: Stage-0 Move Operator tables: replace: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979174 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10001 Stage: Stage-2 Stats-Aggr Operator Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000/ Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 File Output Operator compressed: false GlobalTableId: 0 directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10000 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979174 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-14_989_6212335898656818660/-ext-10002 Partition base file name: -ext-10002 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979174 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,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979174 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result name: default.bucketmapjoin_tmp_result PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 PREHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 POSTHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(1) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-21_973_1112542633479425376/-mr-10000 POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-21_973_1112542633479425376/-mr-10000 POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] 564 PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_1 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: default@bucketmapjoin_hash_result_1 POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_1 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: default@bucketmapjoin_hash_result_1 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 PREHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(b)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 POSTHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(1) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-35_394_5427265786129780250/-mr-10000 POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-35_394_5427265786129780250/-mr-10000 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] 564 PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: default@bucketmapjoin_hash_result_2 POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: default@bucketmapjoin_hash_result_2 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b on a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_hash_result_1 PREHOOK: Input: default@bucketmapjoin_hash_result_2 PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-42_543_1855526648690468691/-mr-10000 POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b on a.key = b.key POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_hash_result_1 POSTHOOK: Input: default@bucketmapjoin_hash_result_2 POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-42_543_1855526648690468691/-mr-10000 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] 0 0 0 PREHOOK: query: explain extended insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" PREHOOK: type: QUERY POSTHOOK: query: explain extended insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" POSTHOOK: type: QUERY POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part_2) a) (TOK_TABREF (TOK_TABNAME srcbucket_mapjoin_part) b) (and (and (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)) (= (. (TOK_TABLE_OR_COL b) ds) "2008-04-08")) (= (. (TOK_TABLE_OR_COL a) ds) "2008-04-08")))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB (TOK_TABNAME bucketmapjoin_tmp_result))) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST a))) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL a) value)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL b) value))))) STAGE DEPENDENCIES: Stage-7 is a root stage Stage-1 depends on stages: Stage-7 Stage-5 depends on stages: Stage-1 , consists of Stage-4, Stage-3 Stage-4 Stage-0 depends on stages: Stage-4, Stage-3 Stage-2 depends on stages: Stage-0 Stage-3 STAGE PLANS: Stage: Stage-7 Map Reduce Local Work Alias -> Map Local Tables: a Fetch Operator limit: -1 Alias -> Map Local Operator Tree: a TableScan alias: a GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {value} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] Position of Big Table: 1 Bucket Mapjoin Context: Alias Bucket Base File Name Mapping: a {srcbucket20.txt=[srcbucket22.txt], srcbucket21.txt=[srcbucket23.txt], srcbucket22.txt=[srcbucket22.txt], srcbucket23.txt=[srcbucket23.txt]} Alias Bucket File Name Mapping: a {pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket22.txt], pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt=[pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part_2/ds=2008-04-08/srcbucket23.txt]} Alias Bucket Output File Name Mapping: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket20.txt 0 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket21.txt 1 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket22.txt 2 pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08/srcbucket23.txt 3 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: b TableScan alias: b GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {value} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] outputColumnNames: _col0, _col1, _col6 Position of Big Table: 1 Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col6 type: string outputColumnNames: _col0, _col1, _col6 Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col6 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-35-06_760_1506759328569853293/-ext-10002 NumFilesPerFileSink: 1 Stats Publishing Key Prefix: pfile:/home/amarsri/workspace/hive/build/ql/scratchdir/hive_2011-07-11_01-35-06_760_1506759328569853293/-ext-10000/ table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/home/amarsri/workspace/hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result numFiles 1 numPartitions 0 numRows 564 rawDataSize 10503 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11067 transient_lastDdlTime 1310373297 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result TotalFiles: 1 GatherStats: true MultiFileSpray: false Local Work: Map Reduce Local Work Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 [b] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 Partition base file name: ds=2008-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 properties: bucket_count 4 bucket_field_name key columns key,value columns.types int:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part/ds=2008-04-08 name default.srcbucket_mapjoin_part partition_columns ds serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979173 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 4 bucket_field_name key columns key,value columns.types int:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/srcbucket_mapjoin_part name default.srcbucket_mapjoin_part partition_columns ds serialization.ddl struct srcbucket_mapjoin_part { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1306979170 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcbucket_mapjoin_part name: default.srcbucket_mapjoin_part Stage: Stage-5 Conditional Operator Stage: Stage-4 Move Operator files: hdfs directory: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 destination: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000 Stage: Stage-0 Move Operator tables: replace: true source: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result numFiles 1 numPartitions 0 numRows 564 rawDataSize 10503 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11067 transient_lastDdlTime 1306979195 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result tmp directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10001 Stage: Stage-2 Stats-Aggr Operator Stats Aggregation Key Prefix: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000/ Stage: Stage-3 Map Reduce Alias -> Map Operator Tree: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 File Output Operator compressed: false GlobalTableId: 0 directory: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10000 NumFilesPerFileSink: 1 table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result numFiles 1 numPartitions 0 numRows 564 rawDataSize 10503 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11067 transient_lastDdlTime 1306979195 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result TotalFiles: 1 GatherStats: false MultiFileSpray: false Needs Tagging: false Path -> Alias: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 [pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002] Path -> Partition: pfile:/data/users/tomasz/apache-hive/build/ql/scratchdir/hive_2011-06-01_18-46-45_810_5134529884228638664/-ext-10002 Partition base file name: -ext-10002 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count -1 columns key,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result numFiles 1 numPartitions 0 numRows 564 rawDataSize 10503 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11067 transient_lastDdlTime 1306979195 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,value1,value2 columns.types string:string:string file.inputformat org.apache.hadoop.mapred.TextInputFormat file.outputformat org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat location pfile:/data/users/tomasz/apache-hive/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name default.bucketmapjoin_tmp_result numFiles 1 numPartitions 0 numRows 564 rawDataSize 10503 serialization.ddl struct bucketmapjoin_tmp_result { string key, string value1, string value2} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 11067 transient_lastDdlTime 1306979195 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucketmapjoin_tmp_result name: default.bucketmapjoin_tmp_result PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 PREHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 POSTHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(1) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-53_065_1705515381902717823/-mr-10000 POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-46-53_065_1705515381902717823/-mr-10000 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] 564 PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: default@bucketmapjoin_hash_result_2 POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: default@bucketmapjoin_hash_result_2 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 PREHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: query: insert overwrite table bucketmapjoin_tmp_result select /*+mapjoin(a)*/ a.key, a.value, b.value from srcbucket_mapjoin_part_2 a join srcbucket_mapjoin_part b on a.key=b.key and b.ds="2008-04-08" and a.ds="2008-04-08" POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08 POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08 POSTHOOK: Output: default@bucketmapjoin_tmp_result POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select count(1) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-06_437_5981294860429171586/-mr-10000 POSTHOOK: query: select count(1) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-06_437_5981294860429171586/-mr-10000 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] 564 PREHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_tmp_result PREHOOK: Output: default@bucketmapjoin_hash_result_2 POSTHOOK: query: insert overwrite table bucketmapjoin_hash_result_2 select sum(hash(key)), sum(hash(value1)), sum(hash(value2)) from bucketmapjoin_tmp_result POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_tmp_result POSTHOOK: Output: default@bucketmapjoin_hash_result_2 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] PREHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b on a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucketmapjoin_hash_result_1 PREHOOK: Input: default@bucketmapjoin_hash_result_2 PREHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-13_897_2470225707695372264/-mr-10000 POSTHOOK: query: select a.key-b.key, a.value1-b.value1, a.value2-b.value2 from bucketmapjoin_hash_result_1 a left outer join bucketmapjoin_hash_result_2 b on a.key = b.key POSTHOOK: type: QUERY POSTHOOK: Input: default@bucketmapjoin_hash_result_1 POSTHOOK: Input: default@bucketmapjoin_hash_result_2 POSTHOOK: Output: file:/tmp/tomasz/hive_2011-06-01_18-47-13_897_2470225707695372264/-mr-10000 POSTHOOK: Lineage: bucketmapjoin_hash_result_1.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_1.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.key EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:key, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value1 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value1, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_hash_result_2.value2 EXPRESSION [(bucketmapjoin_tmp_result)bucketmapjoin_tmp_result.FieldSchema(name:value2, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.key SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:key, type:int, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value1 SIMPLE [(srcbucket_mapjoin_part_2)a.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] POSTHOOK: Lineage: bucketmapjoin_tmp_result.value2 SIMPLE [(srcbucket_mapjoin_part)b.FieldSchema(name:value, type:string, comment:null), ] 0 0 0