http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out index f5f5f91..3ba8a65 100644 --- a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_6.q.out @@ -79,25 +79,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -105,14 +106,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -122,16 +123,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: +- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -141,15 +142,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -169,6 +206,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, a.key2, concat(a.value, b.value) @@ -266,25 +307,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -292,14 +334,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -309,16 +351,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: +- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -328,15 +370,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -356,6 +434,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT subq1.key, subq1.key2, subq1.value from @@ -453,25 +535,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -479,14 +562,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -496,16 +579,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: +- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -515,15 +598,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -543,6 +662,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') @@ -575,25 +698,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -601,14 +725,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -618,16 +742,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), _col0 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: +- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -637,15 +761,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -665,6 +825,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 PREHOOK: query: EXPLAIN INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') @@ -703,25 +867,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -729,14 +894,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -746,16 +911,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: +- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -765,15 +930,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -793,6 +994,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT subq2.key, subq2.key2, subq2.value from @@ -908,25 +1113,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -934,14 +1140,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -951,16 +1157,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: +- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -970,15 +1176,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -998,6 +1240,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT subq2.k2, subq2.k1, subq2.value from @@ -1123,25 +1369,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: ++ Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 10 Data size: 2011 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 1820 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -1149,14 +1396,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 16531 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (key is not null and key2 is not null) (type: boolean) - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), key2 (type: int), value (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 76 Data size: 14956 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 15372 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1166,16 +1413,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col6 input vertices: 0 Map 1 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2618 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), concat(_col2, _col6) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: int) sort order: -- Map-reduce partition columns: _col0 (type: int), _col1 (type: int) - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: string) Execution mode: llap LLAP IO: no inputs @@ -1185,15 +1432,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 83 Data size: 16451 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14 Data size: 2688 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table4 + Select Operator + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: string), '1' (type: string) + outputColumnNames: key, key2, value, ds + Statistics: Num rows: 14 Data size: 3878 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(key2, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 1373 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 1405 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 1405 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 @@ -1213,4 +1496,8 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, key2, value + Column Types: int, int, string + Table: default.test_table4
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out index 7b38056..0af21e0 100644 --- a/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out +++ b/ql/src/test/results/clientpositive/llap/bucketsortoptimize_insert_7.q.out @@ -79,25 +79,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: a - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 712 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -105,14 +106,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 84 Data size: 15964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 358 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -122,16 +123,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col4 input vertices: 0 Map 1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), concat(_col1, _col4) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -141,15 +142,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 2 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 965 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 @@ -169,6 +206,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, concat(a.value, b.value) @@ -263,25 +304,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: test_table1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -289,14 +331,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table2 - Statistics: Num rows: 84 Data size: 15964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -306,16 +348,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 366 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -325,15 +367,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 376 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 2 Data size: 546 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 965 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 @@ -353,6 +431,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, concat(a.value, b.value) @@ -453,25 +535,26 @@ STAGE PLANS: Edges: Map 2 <- Map 1 (BROADCAST_EDGE) Reducer 3 <- Map 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan alias: test_table1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and (key < 8)) (type: boolean) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 10 Data size: 1950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 186 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -479,14 +562,14 @@ STAGE PLANS: Map Operator Tree: TableScan alias: test_table2 - Statistics: Num rows: 84 Data size: 15964 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 84 Data size: 7896 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (((key = 0) or (key = 5)) and (key < 8)) (type: boolean) - Statistics: Num rows: 10 Data size: 1900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 1900 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -496,16 +579,16 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 183 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), concat(_col1, _col3) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: llap LLAP IO: no inputs @@ -515,15 +598,51 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 11 Data size: 2145 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE 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.test_table3 + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string) + outputColumnNames: key, value, ds + Statistics: Num rows: 1 Data size: 273 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 949 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) + Reducer 4 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 965 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 965 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 @@ -543,6 +662,10 @@ STAGE PLANS: Stage: Stage-3 Stats Work Basic Stats Work: + Column Stats Desc: + Columns: key, value + Column Types: int, string + Table: default.test_table3 PREHOOK: query: INSERT OVERWRITE TABLE test_table3 PARTITION (ds = '1') SELECT a.key, concat(a.value, b.value)