PREHOOK: query: drop table bucketmapjoin_tmp_result PREHOOK: type: DROPTABLE POSTHOOK: query: drop table bucketmapjoin_tmp_result POSTHOOK: type: DROPTABLE PREHOOK: query: drop table srcbucket_mapjoin PREHOOK: type: DROPTABLE POSTHOOK: query: drop table srcbucket_mapjoin POSTHOOK: type: DROPTABLE PREHOOK: query: drop table srcbucket_mapjoin_part PREHOOK: type: DROPTABLE POSTHOOK: query: drop table srcbucket_mapjoin_part POSTHOOK: type: DROPTABLE 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 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 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 3 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 3 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 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@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 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 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: 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 a join srcbucket_mapjoin_part b on a.key=b.key where b.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 a join srcbucket_mapjoin_part b on a.key=b.key where b.ds="2008-04-08" POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF srcbucket_mapjoin a) (TOK_TABREF srcbucket_mapjoin_part b) (= (. (TOK_TABLE_OR_COL a) key) (. (TOK_TABLE_OR_COL b) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_TAB 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))) (TOK_WHERE (= (. (TOK_TABLE_OR_COL b) ds) "2008-04-08")))) STAGE DEPENDENCIES: Stage-1 is a root stage Stage-4 depends on stages: Stage-1 , consists of Stage-3, Stage-2 Stage-3 Stage-0 depends on stages: Stage-3, Stage-2 Stage-2 STAGE PLANS: Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: a TableScan alias: a Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {value} {ds} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] outputColumnNames: _col0, _col1, _col3, _col4 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col3 type: string expr: _col4 type: string outputColumnNames: _col0, _col1, _col3, _col4 Filter Operator isSamplingPred: false predicate: expr: (_col4 = '2008-04-08') type: boolean Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col3 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name 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 1282626634 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: bucketmapjoin_tmp_result TotalFiles: 1 MultiFileSpray: false Local Work: Map Reduce Local Work Alias -> Map Local Tables: b Fetch Operator limit: -1 Alias -> Map Local Operator Tree: b TableScan alias: b Filter Operator isSamplingPred: false predicate: expr: (ds = '2008-04-08') type: boolean Common Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {value} {ds} handleSkewJoin: false keys: 0 [Column[key]] 1 [Column[key]] outputColumnNames: _col0, _col1, _col3, _col4 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col3 type: string expr: _col4 type: string outputColumnNames: _col0, _col1, _col3, _col4 Filter Operator isSamplingPred: false predicate: expr: (_col4 = '2008-04-08') type: boolean Select Operator expressions: expr: _col0 type: int expr: _col1 type: string expr: _col3 type: string outputColumnNames: _col0, _col1, _col2 File Output Operator compressed: false GlobalTableId: 1 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name 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 1282626634 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: bucketmapjoin_tmp_result TotalFiles: 1 MultiFileSpray: false Needs Tagging: false Path -> Alias: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/srcbucket_mapjoin [a] Path -> Partition: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/srcbucket_mapjoin Partition base file name: srcbucket_mapjoin 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/srcbucket_mapjoin name srcbucket_mapjoin serialization.ddl struct srcbucket_mapjoin { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282626634 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/srcbucket_mapjoin name srcbucket_mapjoin serialization.ddl struct srcbucket_mapjoin { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe transient_lastDdlTime 1282626634 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: srcbucket_mapjoin name: srcbucket_mapjoin Stage: Stage-4 Conditional Operator Stage: Stage-3 Move Operator files: hdfs directory: true source: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002 destination: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10000 Stage: Stage-0 Move Operator tables: replace: true source: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10000 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name 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 1282626634 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: bucketmapjoin_tmp_result tmp directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10001 Stage: Stage-2 Map Reduce Alias -> Map Operator Tree: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002 Reduce Output Operator sort order: Map-reduce partition columns: expr: rand() type: double tag: -1 value expressions: expr: key type: string expr: value1 type: string expr: value2 type: string Needs Tagging: false Path -> Alias: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002 [file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002] Path -> Partition: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10002 Partition base file name: 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name 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 1282626634 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name 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 1282626634 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: bucketmapjoin_tmp_result name: bucketmapjoin_tmp_result Reduce Operator Tree: Extract File Output Operator compressed: false GlobalTableId: 0 directory: file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/scratchdir/hive_2010-08-23_22-10-34_771_8569982714280085704/10000 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 file:/data/users/nzhang/reviews/0.6/branch-0.6/build/ql/test/data/warehouse/bucketmapjoin_tmp_result name 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 1282626634 serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: bucketmapjoin_tmp_result TotalFiles: 1 MultiFileSpray: false PREHOOK: query: drop table bucketmapjoin_tmp_result PREHOOK: type: DROPTABLE POSTHOOK: query: drop table bucketmapjoin_tmp_result POSTHOOK: type: DROPTABLE POSTHOOK: Output: default@bucketmapjoin_tmp_result PREHOOK: query: drop table srcbucket_mapjoin PREHOOK: type: DROPTABLE POSTHOOK: query: drop table srcbucket_mapjoin POSTHOOK: type: DROPTABLE POSTHOOK: Output: default@srcbucket_mapjoin PREHOOK: query: drop table srcbucket_mapjoin_part PREHOOK: type: DROPTABLE POSTHOOK: query: drop table srcbucket_mapjoin_part POSTHOOK: type: DROPTABLE POSTHOOK: Output: default@srcbucket_mapjoin_part