PREHOOK: query: -- small 1 part, 4 bucket & big 2 part, 2 bucket CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_small POSTHOOK: query: -- small 1 part, 4 bucket & big 2 part, 2 bucket CREATE TABLE bucket_small (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_small PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_small POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small POSTHOOK: Output: default@bucket_small@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_small@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_small@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_small@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE bucket_small partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_small@ds=2008-04-08 PREHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@bucket_big POSTHOOK: query: CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@bucket_big PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_big POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big POSTHOOK: Output: default@bucket_big@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_big@ds=2008-04-08 POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-08') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-08 PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_big POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big POSTHOOK: Output: default@bucket_big@ds=2008-04-09 PREHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') PREHOOK: type: LOAD #### A masked pattern was here #### PREHOOK: Output: default@bucket_big@ds=2008-04-09 POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE bucket_big partition(ds='2008-04-09') POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_big@ds=2008-04-09 PREHOOK: query: explain extended select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME bucket_small a TOK_TABREF TOK_TABNAME bucket_big b = . TOK_TABLE_OR_COL a key . TOK_TABLE_OR_COL b key TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_HINTLIST TOK_HINT TOK_MAPJOIN TOK_HINTARGLIST a TOK_SELEXPR TOK_FUNCTIONSTAR count 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: a 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 properties: COLUMN_STATS_ACCURATE true bucket_count 4 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_small numFiles 4 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 serialization.ddl struct bucket_small { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE bucket_count 4 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_small partition_columns ds partition_columns.types string serialization.ddl struct bucket_small { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_small name: default.bucket_small Alias -> Map Local Operator Tree: a TableScan alias: a Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 Bucket Mapjoin Context: Alias Bucket Base File Name Mapping: a {ds=2008-04-08/srcsortbucket1outof4.txt=[ds=2008-04-08/srcsortbucket1outof4.txt, ds=2008-04-08/srcsortbucket3outof4.txt], ds=2008-04-08/srcsortbucket2outof4.txt=[ds=2008-04-08/srcsortbucket2outof4.txt, ds=2008-04-08/srcsortbucket4outof4.txt], ds=2008-04-09/srcsortbucket1outof4.txt=[ds=2008-04-08/srcsortbucket1outof4.txt, ds=2008-04-08/srcsortbucket3outof4.txt], ds=2008-04-09/srcsortbucket2outof4.txt=[ds=2008-04-08/srcsortbucket2outof4.txt, ds=2008-04-08/srcsortbucket4outof4.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: b Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: bigint) 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: 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: COLUMN_STATS_ACCURATE true bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big numFiles 2 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 serialization.ddl struct bucket_big { string 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big partition_columns ds partition_columns.types string serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big name: default.bucket_big #### A masked pattern was here #### Partition base file name: ds=2008-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-09 properties: COLUMN_STATS_ACCURATE true bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big numFiles 2 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 serialization.ddl struct bucket_big { string 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big partition_columns ds partition_columns.types string serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: /bucket_big/ds=2008-04-08 [b] /bucket_big/ds=2008-04-09 [b] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 8 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: 8 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 columns.types bigint 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(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big PREHOOK: Input: default@bucket_big@ds=2008-04-08 PREHOOK: Input: default@bucket_big@ds=2008-04-09 PREHOOK: Input: default@bucket_small PREHOOK: Input: default@bucket_small@ds=2008-04-08 #### A masked pattern was here #### POSTHOOK: query: select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key POSTHOOK: type: QUERY POSTHOOK: Input: default@bucket_big POSTHOOK: Input: default@bucket_big@ds=2008-04-08 POSTHOOK: Input: default@bucket_big@ds=2008-04-09 POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 #### A masked pattern was here #### 928 PREHOOK: query: explain extended select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME bucket_small a TOK_TABREF TOK_TABNAME bucket_big b = . TOK_TABLE_OR_COL a key . TOK_TABLE_OR_COL b key TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_HINTLIST TOK_HINT TOK_MAPJOIN TOK_HINTARGLIST a TOK_SELEXPR TOK_FUNCTIONSTAR count STAGE DEPENDENCIES: Stage-1 is a root stage Stage-0 depends on stages: Stage-1 STAGE PLANS: Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: b Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: string) 1 key (type: string) Position of Big Table: 1 BucketMapJoin: true Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 Reduce Output Operator sort order: tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### 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: COLUMN_STATS_ACCURATE true bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big numFiles 2 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 serialization.ddl struct bucket_big { string 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big partition_columns ds partition_columns.types string serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big name: default.bucket_big #### A masked pattern was here #### Partition base file name: ds=2008-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: ds 2008-04-09 properties: COLUMN_STATS_ACCURATE true bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big numFiles 2 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 serialization.ddl struct bucket_big { string 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: SORTBUCKETCOLSPREFIX TRUE bucket_count 2 bucket_field_name key columns key,value columns.comments columns.types string:string #### A masked pattern was here #### name default.bucket_big partition_columns ds partition_columns.types string serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.bucket_big name: default.bucket_big Truncated Path -> Alias: /bucket_big/ds=2008-04-08 [b] /bucket_big/ds=2008-04-09 [b] Needs Tagging: false Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 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 columns.types bigint 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(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big PREHOOK: Input: default@bucket_big@ds=2008-04-08 PREHOOK: Input: default@bucket_big@ds=2008-04-09 PREHOOK: Input: default@bucket_small PREHOOK: Input: default@bucket_small@ds=2008-04-08 #### A masked pattern was here #### POSTHOOK: query: select /* + MAPJOIN(a) */ count(*) FROM bucket_small a JOIN bucket_big b ON a.key = b.key POSTHOOK: type: QUERY POSTHOOK: Input: default@bucket_big POSTHOOK: Input: default@bucket_big@ds=2008-04-08 POSTHOOK: Input: default@bucket_big@ds=2008-04-09 POSTHOOK: Input: default@bucket_small POSTHOOK: Input: default@bucket_small@ds=2008-04-08 #### A masked pattern was here #### 928