http://git-wip-us.apache.org/repos/asf/hive/blob/975a49b6/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out b/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out deleted file mode 100644 index 9f12f5b..0000000 --- a/ql/src/test/results/clientpositive/tez/dynpart_sort_optimization.q.out +++ /dev/null @@ -1,3205 +0,0 @@ -PREHOOK: query: create table over1k( - t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) - row format delimited - fields terminated by '|' -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k -POSTHOOK: query: create table over1k( - t tinyint, - si smallint, - i int, - b bigint, - f float, - d double, - bo boolean, - s string, - ts timestamp, - dec decimal(4,2), - bin binary) - row format delimited - fields terminated by '|' -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k -PREHOOK: query: load data local inpath '../../data/files/over1k' into table over1k -PREHOOK: type: LOAD -#### A masked pattern was here #### -PREHOOK: Output: default@over1k -POSTHOOK: query: load data local inpath '../../data/files/over1k' into table over1k -POSTHOOK: type: LOAD -#### A masked pattern was here #### -POSTHOOK: Output: default@over1k -PREHOOK: query: create table over1k_part( - si smallint, - i int, - b bigint, - f float) - partitioned by (ds string, t tinyint) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k_part -POSTHOOK: query: create table over1k_part( - si smallint, - i int, - b bigint, - f float) - partitioned by (ds string, t tinyint) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k_part -PREHOOK: query: create table over1k_part_limit like over1k_part -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k_part_limit -POSTHOOK: query: create table over1k_part_limit like over1k_part -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k_part_limit -PREHOOK: query: create table over1k_part_buck( - si smallint, - i int, - b bigint, - f float) - partitioned by (t tinyint) - clustered by (si) into 4 buckets -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k_part_buck -POSTHOOK: query: create table over1k_part_buck( - si smallint, - i int, - b bigint, - f float) - partitioned by (t tinyint) - clustered by (si) into 4 buckets -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k_part_buck -PREHOOK: query: create table over1k_part_buck_sort( - si smallint, - i int, - b bigint, - f float) - partitioned by (t tinyint) - clustered by (si) - sorted by (f) into 4 buckets -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k_part_buck_sort -POSTHOOK: query: create table over1k_part_buck_sort( - si smallint, - i int, - b bigint, - f float) - partitioned by (t tinyint) - clustered by (si) - sorted by (f) into 4 buckets -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k_part_buck_sort -PREHOOK: query: -- map-only jobs converted to map-reduce job by hive.optimize.sort.dynamic.partition optimization -explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: -- map-only jobs converted to map-reduce job by hive.optimize.sort.dynamic.partition optimization -explain insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_limit - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_limit - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) - sort order: ++ - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) - sort order: +++ - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck_sort - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck_sort - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part@ds=foo -POSTHOOK: query: insert overwrite table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part@ds=foo/t=27 -POSTHOOK: Output: default@over1k_part@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part_limit@ds=foo -POSTHOOK: query: insert overwrite table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=27 -POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part_buck -POSTHOOK: query: insert overwrite table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part_buck@t=27 -POSTHOOK: Output: default@over1k_part_buck@t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part_buck_sort -POSTHOOK: query: insert overwrite table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part_buck_sort@t=27 -POSTHOOK: Output: default@over1k_part_buck_sort@t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: -- map-reduce jobs modified by hive.optimize.sort.dynamic.partition optimization -explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: -- map-reduce jobs modified by hive.optimize.sort.dynamic.partition optimization -explain insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_limit - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_limit - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint), '_bucket_number' (type: string) - sort order: ++ - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - t - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint), '_bucket_number' (type: string), _col3 (type: float) - sort order: +++ - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), KEY._col3 (type: float), KEY._col4 (type: tinyint), KEY.'_bucket_number' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck_sort - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - t - replace: false - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part_buck_sort - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part@ds=foo -POSTHOOK: query: insert into table over1k_part partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part@ds=foo/t=27 -POSTHOOK: Output: default@over1k_part@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part_limit@ds=foo -POSTHOOK: query: insert into table over1k_part_limit partition(ds="foo", t) select si,i,b,f,t from over1k where t is null or t=27 limit 10 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=27 -POSTHOOK: Output: default@over1k_part_limit@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_limit PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part_buck -POSTHOOK: query: insert into table over1k_part_buck partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part_buck@t=27 -POSTHOOK: Output: default@over1k_part_buck@t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part_buck_sort -POSTHOOK: query: insert into table over1k_part_buck_sort partition(t) select si,i,b,f,t from over1k where t is null or t=27 -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part_buck_sort@t=27 -POSTHOOK: Output: default@over1k_part_buck_sort@t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part_buck_sort PARTITION(t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: desc formatted over1k_part partition(ds="foo",t=27) -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part -POSTHOOK: query: desc formatted over1k_part partition(ds="foo",t=27) -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -ds string -t tinyint - -# Detailed Partition Information -Partition Value: [foo, 27] -Database: default -Table: over1k_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 2 - numRows 32 - rawDataSize 830 - totalSize 862 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part partition(ds="foo",t="__HIVE_DEFAULT_PARTITION__") -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part -POSTHOOK: query: desc formatted over1k_part partition(ds="foo",t="__HIVE_DEFAULT_PARTITION__") -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -ds string -t tinyint - -# Detailed Partition Information -Partition Value: [foo, __HIVE_DEFAULT_PARTITION__] -Database: default -Table: over1k_part -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 2 - numRows 6 - rawDataSize 156 - totalSize 162 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part_limit partition(ds="foo",t=27) -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part_limit -POSTHOOK: query: desc formatted over1k_part_limit partition(ds="foo",t=27) -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part_limit -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -ds string -t tinyint - -# Detailed Partition Information -Partition Value: [foo, 27] -Database: default -Table: over1k_part_limit -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 2 - numRows 14 - rawDataSize 362 - totalSize 376 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part_limit partition(ds="foo",t="__HIVE_DEFAULT_PARTITION__") -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part_limit -POSTHOOK: query: desc formatted over1k_part_limit partition(ds="foo",t="__HIVE_DEFAULT_PARTITION__") -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part_limit -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -ds string -t tinyint - -# Detailed Partition Information -Partition Value: [foo, __HIVE_DEFAULT_PARTITION__] -Database: default -Table: over1k_part_limit -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 2 - numRows 6 - rawDataSize 156 - totalSize 162 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part_buck partition(t=27) -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part_buck -POSTHOOK: query: desc formatted over1k_part_buck partition(t=27) -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part_buck -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -t tinyint - -# Detailed Partition Information -Partition Value: [27] -Database: default -Table: over1k_part_buck -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 8 - numRows 32 - rawDataSize 830 - totalSize 862 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: 4 -Bucket Columns: [si] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part_buck partition(t="__HIVE_DEFAULT_PARTITION__") -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part_buck -POSTHOOK: query: desc formatted over1k_part_buck partition(t="__HIVE_DEFAULT_PARTITION__") -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part_buck -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -t tinyint - -# Detailed Partition Information -Partition Value: [__HIVE_DEFAULT_PARTITION__] -Database: default -Table: over1k_part_buck -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 4 - numRows 6 - rawDataSize 156 - totalSize 162 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: 4 -Bucket Columns: [si] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part_buck_sort partition(t=27) -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part_buck_sort -POSTHOOK: query: desc formatted over1k_part_buck_sort partition(t=27) -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part_buck_sort -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -t tinyint - -# Detailed Partition Information -Partition Value: [27] -Database: default -Table: over1k_part_buck_sort -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 8 - numRows 32 - rawDataSize 830 - totalSize 862 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: 4 -Bucket Columns: [si] -Sort Columns: [Order(col:f, order:1)] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part_buck_sort partition(t="__HIVE_DEFAULT_PARTITION__") -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part_buck_sort -POSTHOOK: query: desc formatted over1k_part_buck_sort partition(t="__HIVE_DEFAULT_PARTITION__") -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part_buck_sort -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -t tinyint - -# Detailed Partition Information -Partition Value: [__HIVE_DEFAULT_PARTITION__] -Database: default -Table: over1k_part_buck_sort -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 4 - numRows 6 - rawDataSize 156 - totalSize 162 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: 4 -Bucket Columns: [si] -Sort Columns: [Order(col:f, order:1)] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: select count(*) from over1k_part -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k_part -PREHOOK: Input: default@over1k_part@ds=foo/t=27 -PREHOOK: Input: default@over1k_part@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from over1k_part -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k_part -POSTHOOK: Input: default@over1k_part@ds=foo/t=27 -POSTHOOK: Input: default@over1k_part@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -38 -PREHOOK: query: select count(*) from over1k_part_limit -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k_part_limit -PREHOOK: Input: default@over1k_part_limit@ds=foo/t=27 -PREHOOK: Input: default@over1k_part_limit@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from over1k_part_limit -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k_part_limit -POSTHOOK: Input: default@over1k_part_limit@ds=foo/t=27 -POSTHOOK: Input: default@over1k_part_limit@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -20 -PREHOOK: query: select count(*) from over1k_part_buck -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k_part_buck -PREHOOK: Input: default@over1k_part_buck@t=27 -PREHOOK: Input: default@over1k_part_buck@t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from over1k_part_buck -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k_part_buck -POSTHOOK: Input: default@over1k_part_buck@t=27 -POSTHOOK: Input: default@over1k_part_buck@t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -38 -PREHOOK: query: select count(*) from over1k_part_buck_sort -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k_part_buck_sort -PREHOOK: Input: default@over1k_part_buck_sort@t=27 -PREHOOK: Input: default@over1k_part_buck_sort@t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -POSTHOOK: query: select count(*) from over1k_part_buck_sort -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k_part_buck_sort -POSTHOOK: Input: default@over1k_part_buck_sort@t=27 -POSTHOOK: Input: default@over1k_part_buck_sort@t=__HIVE_DEFAULT_PARTITION__ -#### A masked pattern was here #### -38 -PREHOOK: query: -- tests for HIVE-6883 -create table over1k_part2( - si smallint, - i int, - b bigint, - f float) - partitioned by (ds string, t tinyint) -PREHOOK: type: CREATETABLE -PREHOOK: Output: database:default -PREHOOK: Output: default@over1k_part2 -POSTHOOK: query: -- tests for HIVE-6883 -create table over1k_part2( - si smallint, - i int, - b bigint, - f float) - partitioned by (ds string, t tinyint) -POSTHOOK: type: CREATETABLE -POSTHOOK: Output: database:default -POSTHOOK: Output: default@over1k_part2 -PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float), _col4 (type: tinyint) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col1 (type: bigint), VALUE._col2 (type: float), VALUE._col3 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: si (type: smallint), i (type: int), b (type: bigint), f (type: float), t (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint), _col1 (type: int) - sort order: ++ - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col2 (type: bigint), _col3 (type: float) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), KEY._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27 -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from (select * from over1k order by i limit 10) tmp where t is null or t=27 -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col2 (type: int) - sort order: + - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - TopN Hash Memory Usage: 0.1 - value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float) - Reducer 2 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (_col0 is null or (_col0 = 27)) (type: boolean) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: tinyint) - sort order: + - Map-reduce partition columns: _col4 (type: tinyint) - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: bigint), _col3 (type: float) - Reducer 3 - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: smallint), VALUE._col1 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), KEY._col4 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 240 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t -PREHOOK: type: QUERY -POSTHOOK: query: explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) - sort order: +++++ - Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator -explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t -PREHOOK: type: QUERY -POSTHOOK: query: -- tests for HIVE-8162, only partition column 't' should be in last RS operator -explain insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 group by si,i,b,f,t -POSTHOOK: type: QUERY -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) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: over1k - Statistics: Num rows: 4443 Data size: 106636 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (t is null or (t = 27)) (type: boolean) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: t (type: tinyint), si (type: smallint), i (type: int), b (type: bigint), f (type: float) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: tinyint), _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float) - sort order: +++++ - Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 4442 Data size: 106611 Basic stats: COMPLETE Column stats: NONE - Reducer 2 - Reduce Operator Tree: - Group By Operator - keys: KEY._col0 (type: tinyint), KEY._col1 (type: smallint), KEY._col2 (type: int), KEY._col3 (type: bigint), KEY._col4 (type: float) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: smallint), _col2 (type: int), _col3 (type: bigint), _col4 (type: float), _col0 (type: tinyint) - outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 2221 Data size: 53305 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-2 - Dependency Collection - - Stage: Stage-0 - Move Operator - tables: - partition: - ds foo - t - replace: true - table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.over1k_part2 - - Stage: Stage-3 - Stats-Aggr Operator - -PREHOOK: query: insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i -PREHOOK: type: QUERY -PREHOOK: Input: default@over1k -PREHOOK: Output: default@over1k_part2@ds=foo -POSTHOOK: query: insert overwrite table over1k_part2 partition(ds="foo",t) select si,i,b,f,t from over1k where t is null or t=27 order by i -POSTHOOK: type: QUERY -POSTHOOK: Input: default@over1k -POSTHOOK: Output: default@over1k_part2@ds=foo/t=27 -POSTHOOK: Output: default@over1k_part2@ds=foo/t=__HIVE_DEFAULT_PARTITION__ -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=27).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=27).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=27).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=27).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).b SIMPLE [(over1k)over1k.FieldSchema(name:b, type:bigint, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).f SIMPLE [(over1k)over1k.FieldSchema(name:f, type:float, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).i SIMPLE [(over1k)over1k.FieldSchema(name:i, type:int, comment:null), ] -POSTHOOK: Lineage: over1k_part2 PARTITION(ds=foo,t=__HIVE_DEFAULT_PARTITION__).si SIMPLE [(over1k)over1k.FieldSchema(name:si, type:smallint, comment:null), ] -PREHOOK: query: desc formatted over1k_part2 partition(ds="foo",t=27) -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part2 -POSTHOOK: query: desc formatted over1k_part2 partition(ds="foo",t=27) -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part2 -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -ds string -t tinyint - -# Detailed Partition Information -Partition Value: [foo, 27] -Database: default -Table: over1k_part2 -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_ACCURATE {\"BASIC_STATS\":\"true\"} - numFiles 1 - numRows 16 - rawDataSize 415 - totalSize 431 -#### A masked pattern was here #### - -# Storage Information -SerDe Library: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe -InputFormat: org.apache.hadoop.mapred.TextInputFormat -OutputFormat: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat -Compressed: No -Num Buckets: -1 -Bucket Columns: [] -Sort Columns: [] -Storage Desc Params: - serialization.format 1 -PREHOOK: query: desc formatted over1k_part2 partition(ds="foo",t="__HIVE_DEFAULT_PARTITION__") -PREHOOK: type: DESCTABLE -PREHOOK: Input: default@over1k_part2 -POSTHOOK: query: desc formatted over1k_part2 partition(ds="foo",t="__HIVE_DEFAULT_PARTITION__") -POSTHOOK: type: DESCTABLE -POSTHOOK: Input: default@over1k_part2 -# col_name data_type comment - -si smallint -i int -b bigint -f float - -# Partition Information -# col_name data_type comment - -ds string -t tinyint - -# Detailed Partition Information -Partition Value: [foo, __HIVE_DEFAULT_PARTITION__] -Database: default -Table: over1k_part2 -#### A masked pattern was here #### -Partition Parameters: - COLUMN_STATS_AC
<TRUNCATED>
