PREHOOK: query: -- This test verifies that the sort merge join optimizer works when the tables are joined on columns with different names -- Create bucketed and sorted tables CREATE TABLE test_table1 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC) INTO 16 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table1 POSTHOOK: query: -- This test verifies that the sort merge join optimizer works when the tables are joined on columns with different names -- Create bucketed and sorted tables CREATE TABLE test_table1 (key INT, value STRING) CLUSTERED BY (key) SORTED BY (key ASC) INTO 16 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table1 PREHOOK: query: CREATE TABLE test_table2 (value INT, key STRING) CLUSTERED BY (value) SORTED BY (value ASC) INTO 16 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table2 POSTHOOK: query: CREATE TABLE test_table2 (value INT, key STRING) CLUSTERED BY (value) SORTED BY (value ASC) INTO 16 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table2 PREHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) CLUSTERED BY (key, value) SORTED BY (key ASC, value ASC) INTO 16 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table3 POSTHOOK: query: CREATE TABLE test_table3 (key INT, value STRING) CLUSTERED BY (key, value) SORTED BY (key ASC, value ASC) INTO 16 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table3 PREHOOK: query: CREATE TABLE test_table4 (key INT, value STRING) CLUSTERED BY (key, value) SORTED BY (value ASC, key ASC) INTO 16 BUCKETS PREHOOK: type: CREATETABLE PREHOOK: Output: database:default PREHOOK: Output: default@test_table4 POSTHOOK: query: CREATE TABLE test_table4 (key INT, value STRING) CLUSTERED BY (key, value) SORTED BY (value ASC, key ASC) INTO 16 BUCKETS POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@test_table4 PREHOOK: query: FROM src INSERT OVERWRITE TABLE test_table1 SELECT * INSERT OVERWRITE TABLE test_table2 SELECT * INSERT OVERWRITE TABLE test_table3 SELECT * INSERT OVERWRITE TABLE test_table4 SELECT * PREHOOK: type: QUERY PREHOOK: Input: default@src PREHOOK: Output: default@test_table1 PREHOOK: Output: default@test_table2 PREHOOK: Output: default@test_table3 PREHOOK: Output: default@test_table4 POSTHOOK: query: FROM src INSERT OVERWRITE TABLE test_table1 SELECT * INSERT OVERWRITE TABLE test_table2 SELECT * INSERT OVERWRITE TABLE test_table3 SELECT * INSERT OVERWRITE TABLE test_table4 SELECT * POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: default@test_table1 POSTHOOK: Output: default@test_table2 POSTHOOK: Output: default@test_table3 POSTHOOK: Output: default@test_table4 POSTHOOK: Lineage: test_table1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: test_table2.key SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: test_table2.value EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table3.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] POSTHOOK: Lineage: test_table4.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: test_table4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] PREHOOK: query: -- Join data from 2 tables on their respective sorted columns (one each, with different names) and -- verify sort merge join is used EXPLAIN EXTENDED SELECT /*+mapjoin(b)*/ * FROM test_table1 a JOIN test_table2 b ON a.key = b.value ORDER BY a.key LIMIT 10 PREHOOK: type: QUERY POSTHOOK: query: -- Join data from 2 tables on their respective sorted columns (one each, with different names) and -- verify sort merge join is used EXPLAIN EXTENDED SELECT /*+mapjoin(b)*/ * FROM test_table1 a JOIN test_table2 b ON a.key = b.value ORDER BY a.key LIMIT 10 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME test_table1 a TOK_TABREF TOK_TABNAME test_table2 b = . TOK_TABLE_OR_COL a key . TOK_TABLE_OR_COL b value TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_HINTLIST TOK_HINT TOK_MAPJOIN TOK_HINTARGLIST b TOK_SELEXPR TOK_ALLCOLREF TOK_ORDERBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL a key TOK_LIMIT 10 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: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 keys: 0 key (type: int) 1 value (type: int) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 BucketMapJoin: true Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Reduce Output Operator key expressions: _col0 (type: int) sort order: + tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) auto parallelism: false Path -> Alias: #### A masked pattern was here #### Path -> Partition: #### A masked pattern was here #### Partition base file name: test_table1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: COLUMN_STATS_ACCURATE true SORTBUCKETCOLSPREFIX TRUE bucket_count 16 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.test_table1 numFiles 16 numRows 500 rawDataSize 5312 serialization.ddl struct test_table1 { i32 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: COLUMN_STATS_ACCURATE true SORTBUCKETCOLSPREFIX TRUE bucket_count 16 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.test_table1 numFiles 16 numRows 500 rawDataSize 5312 serialization.ddl struct test_table1 { i32 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 name: default.test_table1 name: default.test_table1 Truncated Path -> Alias: /test_table1 [a] Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Limit Number of rows: 10 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 int:string: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: 10 Processor Tree: ListSink PREHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1 a JOIN test_table2 b ON a.key = b.value ORDER BY a.key LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@test_table1 PREHOOK: Input: default@test_table2 #### A masked pattern was here #### POSTHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table1 a JOIN test_table2 b ON a.key = b.value ORDER BY a.key LIMIT 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table1 POSTHOOK: Input: default@test_table2 #### A masked pattern was here #### 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 0 val_0 2 val_2 2 val_2 PREHOOK: query: -- Join data from 2 tables on their respective columns (two each, with the same names but sorted -- with different priorities) and verify sort merge join is not used EXPLAIN EXTENDED SELECT /*+mapjoin(b)*/ * FROM test_table3 a JOIN test_table4 b ON a.key = b.value ORDER BY a.key LIMIT 10 PREHOOK: type: QUERY POSTHOOK: query: -- Join data from 2 tables on their respective columns (two each, with the same names but sorted -- with different priorities) and verify sort merge join is not used EXPLAIN EXTENDED SELECT /*+mapjoin(b)*/ * FROM test_table3 a JOIN test_table4 b ON a.key = b.value ORDER BY a.key LIMIT 10 POSTHOOK: type: QUERY ABSTRACT SYNTAX TREE: TOK_QUERY TOK_FROM TOK_JOIN TOK_TABREF TOK_TABNAME test_table3 a TOK_TABREF TOK_TABNAME test_table4 b = . TOK_TABLE_OR_COL a key . TOK_TABLE_OR_COL b value TOK_INSERT TOK_DESTINATION TOK_DIR TOK_TMP_FILE TOK_SELECT TOK_HINTLIST TOK_HINT TOK_MAPJOIN TOK_HINTARGLIST b TOK_SELEXPR TOK_ALLCOLREF TOK_ORDERBY TOK_TABSORTCOLNAMEASC . TOK_TABLE_OR_COL a key TOK_LIMIT 10 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 Alias -> Map Local Operator Tree: b TableScan alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(value) is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 UDFToDouble(key) (type: double) 1 UDFToDouble(value) (type: double) Position of Big Table: 0 Stage: Stage-1 Map Reduce Map Operator Tree: TableScan alias: a Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: UDFToDouble(key) is not null (type: boolean) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 UDFToDouble(key) (type: double) 1 UDFToDouble(value) (type: double) outputColumnNames: _col0, _col1, _col5, _col6 Position of Big Table: 0 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col1 (type: string), _col2 (type: int), _col3 (type: string) 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: test_table3 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: COLUMN_STATS_ACCURATE true SORTBUCKETCOLSPREFIX TRUE bucket_count 16 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.test_table3 numFiles 16 numRows 500 rawDataSize 5312 serialization.ddl struct test_table3 { i32 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: COLUMN_STATS_ACCURATE true SORTBUCKETCOLSPREFIX TRUE bucket_count 16 bucket_field_name key columns key,value columns.comments columns.types int:string #### A masked pattern was here #### name default.test_table3 numFiles 16 numRows 500 rawDataSize 5312 serialization.ddl struct test_table3 { i32 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 name: default.test_table3 name: default.test_table3 Truncated Path -> Alias: /test_table3 [a] Needs Tagging: false Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 Statistics: Num rows: 10 Data size: 100 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,_col2,_col3 columns.types int:string: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: 10 Processor Tree: ListSink PREHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table3 a JOIN test_table4 b ON a.key = b.value ORDER BY a.key LIMIT 10 PREHOOK: type: QUERY PREHOOK: Input: default@test_table3 PREHOOK: Input: default@test_table4 #### A masked pattern was here #### POSTHOOK: query: SELECT /*+mapjoin(b)*/ * FROM test_table3 a JOIN test_table4 b ON a.key = b.value ORDER BY a.key LIMIT 10 POSTHOOK: type: QUERY POSTHOOK: Input: default@test_table3 POSTHOOK: Input: default@test_table4 #### A masked pattern was here ####