| PREHOOK: query: create table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') |
| PREHOOK: type: CREATETABLE |
| PREHOOK: Output: database:default |
| PREHOOK: Output: default@acid_dtt |
| POSTHOOK: query: create table acid_dtt(a int, b varchar(128)) clustered by (a) into 2 buckets stored as orc TBLPROPERTIES ('transactional'='true') |
| POSTHOOK: type: CREATETABLE |
| POSTHOOK: Output: database:default |
| POSTHOOK: Output: default@acid_dtt |
| PREHOOK: query: desc formatted acid_dtt |
| PREHOOK: type: DESCTABLE |
| PREHOOK: Input: default@acid_dtt |
| POSTHOOK: query: desc formatted acid_dtt |
| POSTHOOK: type: DESCTABLE |
| POSTHOOK: Input: default@acid_dtt |
| # col_name data_type comment |
| a int |
| b varchar(128) |
| |
| # Detailed Table Information |
| Database: default |
| #### A masked pattern was here #### |
| Retention: 0 |
| #### A masked pattern was here #### |
| Table Type: MANAGED_TABLE |
| Table Parameters: |
| COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"}} |
| bucketing_version 2 |
| numFiles 0 |
| numRows 0 |
| rawDataSize 0 |
| totalSize 0 |
| transactional true |
| transactional_properties default |
| #### A masked pattern was here #### |
| |
| # Storage Information |
| SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| Compressed: No |
| Num Buckets: 2 |
| Bucket Columns: [a] |
| Sort Columns: [] |
| PREHOOK: query: explain insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@alltypesorc |
| PREHOOK: Output: default@acid_dtt |
| POSTHOOK: query: explain insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@alltypesorc |
| POSTHOOK: Output: default@acid_dtt |
| STAGE DEPENDENCIES: |
| Stage-1 is a root stage |
| Stage-2 depends on stages: Stage-1 |
| Stage-0 depends on stages: Stage-2 |
| Stage-3 depends on stages: Stage-0 |
| |
| STAGE PLANS: |
| Stage: Stage-1 |
| Tez |
| #### A masked pattern was here #### |
| Edges: |
| Reducer 2 <- Map 1 (SIMPLE_EDGE) |
| Reducer 3 <- Reducer 2 (SIMPLE_EDGE) |
| Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) |
| #### A masked pattern was here #### |
| Vertices: |
| Map 1 |
| Map Operator Tree: |
| TableScan |
| alias: alltypesorc |
| filterExpr: cint is not null (type: boolean) |
| Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE |
| Filter Operator |
| predicate: cint is not null (type: boolean) |
| Statistics: Num rows: 9173 Data size: 671202 Basic stats: COMPLETE Column stats: COMPLETE |
| Top N Key Operator |
| sort order: + |
| keys: cint (type: int) |
| null sort order: z |
| Statistics: Num rows: 9173 Data size: 671202 Basic stats: COMPLETE Column stats: COMPLETE |
| top n: 10 |
| Select Operator |
| expressions: cint (type: int), CAST( cstring1 AS varchar(128)) (type: varchar(128)) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 9173 Data size: 977184 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: z |
| sort order: + |
| Statistics: Num rows: 9173 Data size: 977184 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: varchar(128)) |
| Execution mode: vectorized, llap |
| LLAP IO: all inputs |
| Reducer 2 |
| Execution mode: vectorized, llap |
| Reduce Operator Tree: |
| Select Operator |
| expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(128)) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 9173 Data size: 977184 Basic stats: COMPLETE Column stats: COMPLETE |
| Limit |
| Number of rows: 10 |
| Statistics: Num rows: 10 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| key expressions: _col0 (type: int) |
| null sort order: a |
| sort order: + |
| Map-reduce partition columns: _col0 (type: int) |
| Statistics: Num rows: 10 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col1 (type: varchar(128)) |
| Reducer 3 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Select Operator |
| expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: varchar(128)) |
| outputColumnNames: _col0, _col1 |
| Statistics: Num rows: 10 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 10 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| name: default.acid_dtt |
| Write Type: INSERT |
| Select Operator |
| expressions: _col0 (type: int), _col1 (type: varchar(128)) |
| outputColumnNames: a, b |
| Statistics: Num rows: 10 Data size: 1296 Basic stats: COMPLETE Column stats: COMPLETE |
| Group By Operator |
| aggregations: min(a), max(a), count(1), count(a), compute_bit_vector(a, 'hll'), max(length(b)), avg(COALESCE(length(b),0)), count(b), compute_bit_vector(b, 'hll') |
| minReductionHashAggr: 0.9 |
| mode: hash |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 |
| Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE |
| Reduce Output Operator |
| null sort order: |
| sort order: |
| Statistics: Num rows: 1 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE |
| value expressions: _col0 (type: int), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: binary), _col5 (type: int), _col6 (type: struct<count:bigint,sum:double,input:int>), _col7 (type: bigint), _col8 (type: binary) |
| Reducer 4 |
| Execution mode: llap |
| Reduce Operator Tree: |
| Group By Operator |
| aggregations: min(VALUE._col0), max(VALUE._col1), count(VALUE._col2), count(VALUE._col3), compute_bit_vector(VALUE._col4), max(VALUE._col5), avg(VALUE._col6), count(VALUE._col7), compute_bit_vector(VALUE._col8) |
| mode: mergepartial |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 |
| Statistics: Num rows: 1 Data size: 332 Basic stats: COMPLETE Column stats: COMPLETE |
| Select Operator |
| expressions: 'LONG' (type: string), UDFToLong(_col0) (type: bigint), UDFToLong(_col1) (type: bigint), (_col2 - _col3) (type: bigint), COALESCE(ndv_compute_bit_vector(_col4),0) (type: bigint), _col4 (type: binary), 'STRING' (type: string), UDFToLong(COALESCE(_col5,0)) (type: bigint), COALESCE(_col6,0) (type: double), (_col2 - _col7) (type: bigint), COALESCE(ndv_compute_bit_vector(_col8),0) (type: bigint), _col8 (type: binary) |
| outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 |
| Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE |
| File Output Operator |
| compressed: false |
| Statistics: Num rows: 1 Data size: 530 Basic stats: COMPLETE Column stats: COMPLETE |
| table: |
| input format: org.apache.hadoop.mapred.SequenceFileInputFormat |
| output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat |
| serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe |
| |
| Stage: Stage-2 |
| Dependency Collection |
| |
| Stage: Stage-0 |
| Move Operator |
| tables: |
| replace: false |
| table: |
| input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| serde: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| name: default.acid_dtt |
| Write Type: INSERT |
| |
| Stage: Stage-3 |
| Stats Work |
| Basic Stats Work: |
| Column Stats Desc: |
| Columns: a, b |
| Column Types: int, varchar(128) |
| Table: default.acid_dtt |
| |
| PREHOOK: query: insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10 |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@alltypesorc |
| PREHOOK: Output: default@acid_dtt |
| POSTHOOK: query: insert into table acid_dtt select cint, cast(cstring1 as varchar(128)) from alltypesorc where cint is not null order by cint limit 10 |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@alltypesorc |
| POSTHOOK: Output: default@acid_dtt |
| POSTHOOK: Lineage: acid_dtt.a SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] |
| POSTHOOK: Lineage: acid_dtt.b EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] |
| PREHOOK: query: desc formatted acid_dtt |
| PREHOOK: type: DESCTABLE |
| PREHOOK: Input: default@acid_dtt |
| POSTHOOK: query: desc formatted acid_dtt |
| POSTHOOK: type: DESCTABLE |
| POSTHOOK: Input: default@acid_dtt |
| # col_name data_type comment |
| a int |
| b varchar(128) |
| |
| # Detailed Table Information |
| Database: default |
| #### A masked pattern was here #### |
| Retention: 0 |
| #### A masked pattern was here #### |
| Table Type: MANAGED_TABLE |
| Table Parameters: |
| COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\",\"COLUMN_STATS\":{\"a\":\"true\",\"b\":\"true\"}} |
| bucketing_version 2 |
| numFiles 2 |
| numRows 10 |
| rawDataSize 0 |
| totalSize 1884 |
| transactional true |
| transactional_properties default |
| #### A masked pattern was here #### |
| |
| # Storage Information |
| SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| Compressed: No |
| Num Buckets: 2 |
| Bucket Columns: [a] |
| Sort Columns: [] |
| PREHOOK: query: delete from acid_dtt where b = '0ruyd6Y50JpdGRf6HqD' or b = '2uLyD28144vklju213J1mr' |
| PREHOOK: type: QUERY |
| PREHOOK: Input: default@acid_dtt |
| PREHOOK: Output: default@acid_dtt |
| POSTHOOK: query: delete from acid_dtt where b = '0ruyd6Y50JpdGRf6HqD' or b = '2uLyD28144vklju213J1mr' |
| POSTHOOK: type: QUERY |
| POSTHOOK: Input: default@acid_dtt |
| POSTHOOK: Output: default@acid_dtt |
| PREHOOK: query: desc formatted acid_dtt |
| PREHOOK: type: DESCTABLE |
| PREHOOK: Input: default@acid_dtt |
| POSTHOOK: query: desc formatted acid_dtt |
| POSTHOOK: type: DESCTABLE |
| POSTHOOK: Input: default@acid_dtt |
| # col_name data_type comment |
| a int |
| b varchar(128) |
| |
| # Detailed Table Information |
| Database: default |
| #### A masked pattern was here #### |
| Retention: 0 |
| #### A masked pattern was here #### |
| Table Type: MANAGED_TABLE |
| Table Parameters: |
| COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} |
| bucketing_version 2 |
| numFiles 3 |
| numRows 8 |
| rawDataSize 0 |
| totalSize 2596 |
| transactional true |
| transactional_properties default |
| #### A masked pattern was here #### |
| |
| # Storage Information |
| SerDe Library: org.apache.hadoop.hive.ql.io.orc.OrcSerde |
| InputFormat: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat |
| OutputFormat: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat |
| Compressed: No |
| Num Buckets: 2 |
| Bucket Columns: [a] |
| Sort Columns: [] |