PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_1 (key INT, value STRING) PARTITIONED BY (ds STRING, hr STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@srcbucket_mapjoin_part_1 POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_1 (key INT, value STRING) PARTITIONED BY (ds STRING, hr STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@srcbucket_mapjoin_part_1 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part_1 PARTITION (ds='2008-04-08', hr='0') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part_1 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part_1 PARTITION (ds='2008-04-08', hr='0') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part_1 POSTHOOK: Output: default@srcbucket_mapjoin_part_1@ds=2008-04-08/hr=0 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part_1 PARTITION (ds='2008-04-08', hr='0') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part_1@ds=2008-04-08/hr=0 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part_1 PARTITION (ds='2008-04-08', hr='0') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part_1@ds=2008-04-08/hr=0 PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key INT, value STRING) PARTITIONED BY (ds STRING, hr STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@srcbucket_mapjoin_part_2 POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part_2 (key INT, value STRING) PARTITIONED BY (ds STRING, hr STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@srcbucket_mapjoin_part_2 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part_2 PARTITION (ds='2008-04-08', hr='0') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part_2 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part_2 PARTITION (ds='2008-04-08', hr='0') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part_2 POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08/hr=0 PREHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part_2 PARTITION (ds='2008-04-08', hr='0') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08/hr=0 POSTHOOK: query: LOAD DATA LOCAL INPATH '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part_2 PARTITION (ds='2008-04-08', hr='0') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@srcbucket_mapjoin_part_2@ds=2008-04-08/hr=0 PREHOOK: query: -- Tests that bucket map join works with a table with more than one level of partitioning EXPLAIN EXTENDED SELECT /*+ MAPJOIN(b) */ a.key, b.value FROM srcbucket_mapjoin_part_1 a JOIN srcbucket_mapjoin_part_2 b ON a.key = b.key AND a.ds = '2008-04-08' AND b.ds = '2008-04-08' ORDER BY a.key, b.value LIMIT 1 PREHOOK: type: QUERY POSTHOOK: query: -- Tests that bucket map join works with a table with more than one level of partitioning EXPLAIN EXTENDED SELECT /*+ MAPJOIN(b) */ a.key, b.value FROM srcbucket_mapjoin_part_1 a JOIN srcbucket_mapjoin_part_2 b ON a.key = b.key AND a.ds = '2008-04-08' AND b.ds = '2008-04-08' ORDER BY a.key, b.value LIMIT 1 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME srcbucket_mapjoin_part_1 a TOK_TABREF TOK_TABNAME srcbucket_mapjoin_part_2 b AND AND = . TOK_TABLE_OR_COL a key . TOK_TABLE_OR_COL b key = . TOK_TABLE_OR_COL a ds '2008-04-08' = . TOK_TABLE_OR_COL b ds '2008-04-08' TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE 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 b value TOK_ORDERBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL a key TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL b value TOK_LIMIT 1 STAGE DEPENDENCIES: Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-3 Map Reduce Local Work Alias -> Map Local Tables: b Fetch Operator limit: -1 Partition Description: Partition input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 hr 0 properties: COLUMN_STATS_ACCURATE true bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.srcbucket_mapjoin_part_2 numFiles 2 numRows 0 partition_columns ds/hr partition_columns.types string:string rawDataSize 0 serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.srcbucket_mapjoin_part_2 partition_columns ds/hr partition_columns.types string:string serialization.ddl struct srcbucket_mapjoin_part_2 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcbucket_mapjoin_part_2 name: default.srcbucket_mapjoin_part_2 Alias -> Map Local Operator Tree: b TableScan alias: b Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: int) 1 key (type: int) Position of Big Table: 0 Bucket Mapjoin Context: Alias Bucket Base File Name Mapping: b {ds=2008-04-08/hr=0/srcbucket20.txt=[ds=2008-04-08/hr=0/srcbucket20.txt], ds=2008-04-08/hr=0/srcbucket21.txt=[ds=2008-04-08/hr=0/srcbucket21.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 Map Operator Tree: TableScan alias: a Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 key (type: int) outputColumnNames: _col0, _col8 Position of Big Table: 0 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: _col0 (type: int), _col8 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE tag: -1 auto parallelism: 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: hr=0 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-08 hr 0 properties: COLUMN_STATS_ACCURATE true bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.srcbucket_mapjoin_part_1 numFiles 2 numRows 0 partition_columns ds/hr partition_columns.types string:string rawDataSize 0 serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 2750 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.srcbucket_mapjoin_part_1 partition_columns ds/hr partition_columns.types string:string serialization.ddl struct srcbucket_mapjoin_part_1 { i32 key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcbucket_mapjoin_part_1 name: default.srcbucket_mapjoin_part_1 Truncated Path -> Alias: /srcbucket_mapjoin_part_1/ds=2008-04-08/hr=0 [a] Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: columns _col0,_col1 columns.types int:string escape.delim \ hive.serialization.extend.additional.nesting.levels true serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe TotalFiles: 1 GatherStats: false MultiFileSpray: false Stage: Stage-0 Fetch Operator limit: 1 Processor Tree: ListSink PREHOOK: query: SELECT /*+ MAPJOIN(b) */ a.key, b.value FROM srcbucket_mapjoin_part_1 a JOIN srcbucket_mapjoin_part_2 b ON a.key = b.key AND a.ds = '2008-04-08' AND b.ds = '2008-04-08' ORDER BY a.key, b.value LIMIT 1 PREHOOK: type: QUERY PREHOOK: Input: default@srcbucket_mapjoin_part_1 PREHOOK: Input: default@srcbucket_mapjoin_part_1@ds=2008-04-08/hr=0 PREHOOK: Input: default@srcbucket_mapjoin_part_2 PREHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08/hr=0 #### A masked pattern was here #### POSTHOOK: query: SELECT /*+ MAPJOIN(b) */ a.key, b.value FROM srcbucket_mapjoin_part_1 a JOIN srcbucket_mapjoin_part_2 b ON a.key = b.key AND a.ds = '2008-04-08' AND b.ds = '2008-04-08' ORDER BY a.key, b.value LIMIT 1 POSTHOOK: type: QUERY POSTHOOK: Input: default@srcbucket_mapjoin_part_1 POSTHOOK: Input: default@srcbucket_mapjoin_part_1@ds=2008-04-08/hr=0 POSTHOOK: Input: default@srcbucket_mapjoin_part_2 POSTHOOK: Input: default@srcbucket_mapjoin_part_2@ds=2008-04-08/hr=0 #### A masked pattern was here #### 0 val_0