PREHOOK: query: drop table test1 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table test1 POSTHOOK: type: DROPTABLE PREHOOK: query: drop table test2 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table test2 POSTHOOK: type: DROPTABLE PREHOOK: query: drop table test3 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table test3 POSTHOOK: type: DROPTABLE PREHOOK: query: drop table test4 PREHOOK: type: DROPTABLE POSTHOOK: query: drop table test4 POSTHOOK: type: DROPTABLE PREHOOK: query: create table test1 (key string, value string) clustered by (key) sorted by (key) into 3 buckets PREHOOK: type: CREATETABLE POSTHOOK: query: create table test1 (key string, value string) clustered by (key) sorted by (key) into 3 buckets POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@test1 PREHOOK: query: create table test2 (key string, value string) clustered by (value) sorted by (value) into 3 buckets PREHOOK: type: CREATETABLE POSTHOOK: query: create table test2 (key string, value string) clustered by (value) sorted by (value) into 3 buckets POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@test2 PREHOOK: query: create table test3 (key string, value string) clustered by (key, value) sorted by (key, value) into 3 buckets PREHOOK: type: CREATETABLE POSTHOOK: query: create table test3 (key string, value string) clustered by (key, value) sorted by (key, value) into 3 buckets POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@test3 PREHOOK: query: create table test4 (key string, value string) clustered by (value, key) sorted by (value, key) into 3 buckets PREHOOK: type: CREATETABLE POSTHOOK: query: create table test4 (key string, value string) clustered by (value, key) sorted by (value, key) into 3 buckets POSTHOOK: type: CREATETABLE POSTHOOK: Output: default@test4 PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test1 PREHOOK: type: LOAD PREHOOK: Output: default@test1 POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test1 POSTHOOK: type: LOAD POSTHOOK: Output: default@test1 PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test1 PREHOOK: type: LOAD PREHOOK: Output: default@test1 POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test1 POSTHOOK: type: LOAD POSTHOOK: Output: default@test1 PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test1 PREHOOK: type: LOAD PREHOOK: Output: default@test1 POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test1 POSTHOOK: type: LOAD POSTHOOK: Output: default@test1 PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test2 PREHOOK: type: LOAD PREHOOK: Output: default@test2 POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test2 POSTHOOK: type: LOAD POSTHOOK: Output: default@test2 PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test2 PREHOOK: type: LOAD PREHOOK: Output: default@test2 POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test2 POSTHOOK: type: LOAD POSTHOOK: Output: default@test2 PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test2 PREHOOK: type: LOAD PREHOOK: Output: default@test2 POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test2 POSTHOOK: type: LOAD POSTHOOK: Output: default@test2 PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test3 PREHOOK: type: LOAD PREHOOK: Output: default@test3 POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test3 POSTHOOK: type: LOAD POSTHOOK: Output: default@test3 PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test3 PREHOOK: type: LOAD PREHOOK: Output: default@test3 POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test3 POSTHOOK: type: LOAD POSTHOOK: Output: default@test3 PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test3 PREHOOK: type: LOAD PREHOOK: Output: default@test3 POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test3 POSTHOOK: type: LOAD POSTHOOK: Output: default@test3 PREHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test4 PREHOOK: type: LOAD PREHOOK: Output: default@test4 POSTHOOK: query: load data local inpath '../data/files/srcbucket20.txt' INTO TABLE test4 POSTHOOK: type: LOAD POSTHOOK: Output: default@test4 PREHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test4 PREHOOK: type: LOAD PREHOOK: Output: default@test4 POSTHOOK: query: load data local inpath '../data/files/srcbucket21.txt' INTO TABLE test4 POSTHOOK: type: LOAD POSTHOOK: Output: default@test4 PREHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test4 PREHOOK: type: LOAD PREHOOK: Output: default@test4 POSTHOOK: query: load data local inpath '../data/files/srcbucket22.txt' INTO TABLE test4 POSTHOOK: type: LOAD POSTHOOK: Output: default@test4 PREHOOK: query: -- should be allowed explain extended select /* + MAPJOIN(R) */ * from test1 L join test1 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: -- should be allowed explain extended select /* + MAPJOIN(R) */ * from test1 L join test1 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test1) L) (TOK_TABREF (TOK_TABNAME test1) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Bucket Mapjoin Context: Alias Bucket Base File Name Mapping: r {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt], srcbucket22.txt=[srcbucket22.txt]} Alias Bucket File Name Mapping: #### A masked pattern was here #### Alias Bucket Output File Name Mapping: #### A masked pattern was here #### Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 BucketMapJoin: true Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 Truncated Path -> Alias: /test1 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test2 L join test2 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test2 L join test2 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test2) L) (TOK_TABREF (TOK_TABNAME test2) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Bucket Mapjoin Context: Alias Bucket Base File Name Mapping: r {srcbucket20.txt=[srcbucket20.txt], srcbucket21.txt=[srcbucket21.txt], srcbucket22.txt=[srcbucket22.txt]} Alias Bucket File Name Mapping: #### A masked pattern was here #### Alias Bucket Output File Name Mapping: #### A masked pattern was here #### Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 BucketMapJoin: true Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name value columns key,value columns.types string:string #### A masked pattern was here #### name default.test2 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test2 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name value columns key,value columns.types string:string #### A masked pattern was here #### name default.test2 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test2 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 Truncated Path -> Alias: /test2 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: -- should not apply bucket mapjoin explain extended select /* + MAPJOIN(R) */ * from test1 L join test1 R on L.key+L.key=R.key PREHOOK: type: QUERY POSTHOOK: query: -- should not apply bucket mapjoin explain extended select /* + MAPJOIN(R) */ * from test1 L join test1 R on L.key+L.key=R.key POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test1) L) (TOK_TABREF (TOK_TABNAME test1) R) (= (+ (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL L) key)) (. (TOK_TABLE_OR_COL R) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key], Column[key]()] 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key], Column[key]()] 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 Truncated Path -> Alias: /test1 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test1 L join test2 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test1 L join test2 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test1) L) (TOK_TABREF (TOK_TABNAME test2) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 Truncated Path -> Alias: /test1 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test1 L join test3 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test1 L join test3 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test1) L) (TOK_TABREF (TOK_TABNAME test3) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 Truncated Path -> Alias: /test1 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test1 L join test4 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test1 L join test4 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test1) L) (TOK_TABREF (TOK_TABNAME test4) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test1 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test1 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test1 name: default.test1 Truncated Path -> Alias: /test1 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test2 L join test3 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test2 L join test3 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test2) L) (TOK_TABREF (TOK_TABNAME test3) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name value columns key,value columns.types string:string #### A masked pattern was here #### name default.test2 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test2 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name value columns key,value columns.types string:string #### A masked pattern was here #### name default.test2 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test2 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 Truncated Path -> Alias: /test2 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test2 L join test4 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test2 L join test4 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test2) L) (TOK_TABREF (TOK_TABNAME test4) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test2 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name value columns key,value columns.types string:string #### A masked pattern was here #### name default.test2 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test2 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name value columns key,value columns.types string:string #### A masked pattern was here #### name default.test2 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test2 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test2 name: default.test2 Truncated Path -> Alias: /test2 [l] Stage: Stage-0 Fetch Operator limit: -1 PREHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test3 L join test4 R on L.key=R.key AND L.value=R.value PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(R) */ * from test3 L join test4 R on L.key=R.key AND L.value=R.value POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_TABREF (TOK_TABNAME test3) L) (TOK_TABREF (TOK_TABNAME test4) R) (AND (= (. (TOK_TABLE_OR_COL L) key) (. (TOK_TABLE_OR_COL R) key)) (= (. (TOK_TABLE_OR_COL L) value) (. (TOK_TABLE_OR_COL R) value))))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST R))) (TOK_SELEXPR TOK_ALLCOLREF)))) STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 is a root stage STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: r Fetch Operator limit: -1 Alias -> Map Local Operator Tree: r TableScan alias: r GatherStats: false HashTable Sink Operator condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] Position of Big Table: 0 Stage: Stage-1 Map Reduce Alias -> Map Operator Tree: l TableScan alias: l GatherStats: false Map Join Operator condition map: Inner Join 0 to 1 condition expressions: 0 {key} {value} 1 {key} {value} handleSkewJoin: false keys: 0 [Column[key], Column[value]] 1 [Column[key], Column[value]] outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 Select Operator expressions: expr: _col0 type: string expr: _col1 type: string expr: _col4 type: string expr: _col5 type: string outputColumnNames: _col0, _col1, _col2, _col3 File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1,_col2,_col3 columns.types string:string:string:string escape.delim \ hive.serialization.extend.nesting.levels true serialization.format 1 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: test3 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test3 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test3 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 3 bucket_field_name key columns key,value columns.types string:string #### A masked pattern was here #### name default.test3 numFiles 3 numPartitions 0 numRows 0 rawDataSize 0 serialization.ddl struct test3 { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 4200 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.test3 name: default.test3 Truncated Path -> Alias: /test3 [l] Stage: Stage-0 Fetch Operator limit: -1