http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out b/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out index 18dca49..7e6e88b 100644 --- a/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_partitioned.q.out @@ -1916,7 +1916,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: oft - Statistics: Num rows: 12288 Data size: 13243096 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 12288 Data size: 1884148 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true vectorizationSchemaColumns: [0:csmallint:smallint, 1:cint:int, 2:cbigint:bigint, 3:cfloat:float, 4:cdouble:double, 5:cstring1:string, 6:cchar1:char(255), 7:cvchar1:varchar(255), 8:cboolean1:boolean, 9:cboolean2:boolean, 10:ctinyint:tinyint, 11:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] @@ -1939,7 +1939,7 @@ STAGE PLANS: outputColumnNames: _col1, _col6, _col7, _col10 input vertices: 1 Map 2 - Statistics: Num rows: 960 Data size: 240494 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 960 Data size: 4040 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col10 (type: tinyint), _col1 (type: int), _col6 (type: char(255)), _col7 (type: varchar(255)) outputColumnNames: _col0, _col1, _col2, _col3 @@ -1947,13 +1947,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [10, 1, 6, 7] - Statistics: Num rows: 960 Data size: 240494 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 960 Data size: 4040 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 960 Data size: 240494 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 960 Data size: 4040 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/llap_stats.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/llap_stats.q.out b/ql/src/test/results/clientpositive/llap/llap_stats.q.out index 89c0c57..5bba6b0 100644 --- a/ql/src/test/results/clientpositive/llap/llap_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_stats.q.out @@ -153,11 +153,11 @@ STAGE PLANS: Map Operator Tree: TableScan alias: llap_stats - Statistics: Num rows: 10 Data size: 196 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int) outputColumnNames: ctinyint, csmallint, cint - Statistics: Num rows: 10 Data size: 196 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 10 Data size: 120 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: compute_stats(ctinyint, 'hll'), compute_stats(csmallint, 'hll') keys: cint (type: int) http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/load_dyn_part5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/load_dyn_part5.q.out b/ql/src/test/results/clientpositive/llap/load_dyn_part5.q.out index 9255be7..9e0c053 100644 --- a/ql/src/test/results/clientpositive/llap/load_dyn_part5.q.out +++ b/ql/src/test/results/clientpositive/llap/load_dyn_part5.q.out @@ -41,6 +41,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -52,14 +53,50 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: key, value + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll') + keys: value (type: string) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 132750 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: 250 Data size: 132750 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) value expressions: _col0 (type: string) - Execution mode: vectorized, llap + Execution mode: llap LLAP IO: no inputs Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0) + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 132750 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 132750 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 132750 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 + Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/orc_merge10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge10.q.out b/ql/src/test/results/clientpositive/llap/orc_merge10.q.out index d943b40..c03d7b8 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge10.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge10.q.out @@ -65,6 +65,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -76,6 +77,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _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>) Reduce Output Operator key expressions: _col2 (type: int) sort order: + @@ -86,6 +103,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _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), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -172,6 +209,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -183,6 +221,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _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>) Reduce Output Operator key expressions: _col2 (type: int) sort order: + @@ -193,6 +247,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _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), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -324,6 +398,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -335,6 +410,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _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>) Reduce Output Operator key expressions: _col2 (type: int) sort order: + @@ -345,6 +436,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _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), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) outputColumnNames: _col0, _col1, _col2 http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/orc_merge2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge2.q.out b/ql/src/test/results/clientpositive/llap/orc_merge2.q.out index 7265292..ea6706c 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge2.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge2.q.out @@ -39,6 +39,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -50,6 +51,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 10) (type: int), (hash(value) pmod 10) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 500 Data size: 51500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string), CAST( _col3 AS STRING) (type: string) + outputColumnNames: key, value, one, two, three + Statistics: Num rows: 500 Data size: 274000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: one (type: string), two (type: string), three (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 500 Data size: 658500 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) + sort order: +++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string) + Statistics: Num rows: 500 Data size: 658500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Output Operator key expressions: _col2 (type: int), _col3 (type: int) sort order: ++ @@ -60,6 +77,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 500 Data size: 666500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col3 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string), _col1 (type: string), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 500 Data size: 666500 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 666500 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int), KEY._col3 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/orc_merge7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge7.q.out b/ql/src/test/results/clientpositive/llap/orc_merge7.q.out index 634f139..583ee96 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge7.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge7.q.out @@ -41,6 +41,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -52,6 +53,22 @@ STAGE PLANS: expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp), subtype (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp), _col5 (type: double) + outputColumnNames: userid, string1, subtype, decimal1, ts, st + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: st (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(38,0),max:decimal(38,0),countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Reduce Output Operator key expressions: _col5 (type: double) sort order: + @@ -62,6 +79,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(38,0),max:decimal(38,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: bigint), VALUE._col1 (type: string), VALUE._col2 (type: double), VALUE._col3 (type: decimal(38,0)), VALUE._col4 (type: timestamp), KEY._col5 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 @@ -237,6 +274,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -248,6 +286,22 @@ STAGE PLANS: expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp), subtype (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp), _col5 (type: double) + outputColumnNames: userid, string1, subtype, decimal1, ts, st + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: st (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(38,0),max:decimal(38,0),countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Reduce Output Operator key expressions: _col5 (type: double) sort order: + @@ -258,6 +312,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(38,0),max:decimal(38,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: bigint), VALUE._col1 (type: string), VALUE._col2 (type: double), VALUE._col3 (type: decimal(38,0)), VALUE._col4 (type: timestamp), KEY._col5 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out b/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out index a912216..3bd001a 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge_diff_fs.q.out @@ -65,6 +65,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -76,6 +77,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _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>) Reduce Output Operator key expressions: _col2 (type: int) sort order: + @@ -86,6 +103,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _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), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -172,6 +209,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -183,6 +221,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _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>) Reduce Output Operator key expressions: _col2 (type: int) sort order: + @@ -193,6 +247,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _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), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) outputColumnNames: _col0, _col1, _col2 @@ -324,6 +398,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -335,6 +410,22 @@ STAGE PLANS: expressions: UDFToInteger(key) (type: int), value (type: string), (hash(key) pmod 2) (type: int) outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 49500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: string), '1' (type: string), CAST( _col2 AS STRING) (type: string) + outputColumnNames: key, value, ds, part + Statistics: Num rows: 500 Data size: 182000 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') + keys: ds (type: string), part (type: string) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string) + sort order: ++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) + Statistics: Num rows: 250 Data size: 283250 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _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>) Reduce Output Operator key expressions: _col2 (type: int) sort order: + @@ -345,6 +436,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1) + keys: KEY._col0 (type: string), KEY._col1 (type: string) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _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), _col1 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 287250 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 287250 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY._col2 (type: int) outputColumnNames: _col0, _col1, _col2 http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out b/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out index ee13faf..708652b 100644 --- a/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out +++ b/ql/src/test/results/clientpositive/llap/orc_merge_incompat2.q.out @@ -41,6 +41,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -52,6 +53,22 @@ STAGE PLANS: expressions: userid (type: bigint), string1 (type: string), subtype (type: double), decimal1 (type: decimal(38,0)), ts (type: timestamp), subtype (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: bigint), _col1 (type: string), _col2 (type: double), _col3 (type: decimal(38,0)), _col4 (type: timestamp), _col5 (type: double) + outputColumnNames: userid, string1, subtype, decimal1, ts, st + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(userid, 'hll'), compute_stats(string1, 'hll'), compute_stats(subtype, 'hll'), compute_stats(decimal1, 'hll'), compute_stats(ts, 'hll') + keys: st (type: double) + mode: hash + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: double) + sort order: + + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,bitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(38,0),max:decimal(38,0),countnulls:bigint,bitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>) Reduce Output Operator key expressions: _col5 (type: double) sort order: + @@ -62,6 +79,26 @@ STAGE PLANS: Reducer 2 Execution mode: llap Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3), compute_stats(VALUE._col4) + keys: KEY._col0 (type: double) + mode: mergepartial + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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>), _col3 (type: struct<columntype:string,min:double,max:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col4 (type: struct<columntype:string,min:decimal(38,0),max:decimal(38,0),countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col5 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: double) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 352 Basic stats: COMPLETE Column stats: NONE + 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 + Reducer 3 + Execution mode: llap + Reduce Operator Tree: Select Operator expressions: VALUE._col0 (type: bigint), VALUE._col1 (type: string), VALUE._col2 (type: double), VALUE._col3 (type: decimal(38,0)), VALUE._col4 (type: timestamp), KEY._col5 (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/tez_dml.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/tez_dml.q.out b/ql/src/test/results/clientpositive/llap/tez_dml.q.out index a9b3172..ef30b30 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dml.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dml.q.out @@ -455,6 +455,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -466,14 +467,50 @@ STAGE PLANS: expressions: value (type: string), cnt (type: bigint) outputColumnNames: _col0, _col1 Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), UDFToInteger(_col1) (type: int) + outputColumnNames: c, d + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: compute_stats(c, 'hll') + keys: d (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>) Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) value expressions: _col0 (type: string) - Execution mode: vectorized, llap + Execution mode: llap LLAP IO: no inputs Reducer 2 + Execution mode: llap + Reduce Operator Tree: + Group By Operator + aggregations: compute_stats(VALUE._col0) + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 154 Data size: 28228 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col1 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 154 Data size: 28228 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 154 Data size: 28228 Basic stats: COMPLETE Column stats: NONE + 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 + Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator http://git-wip-us.apache.org/repos/asf/hive/blob/b650083f/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out index 28977d7..ca8232e 100644 --- a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out @@ -1316,7 +1316,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: web_sales - Statistics: Num rows: 2000 Data size: 3511604 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE TableScan Vectorization: native: true Select Operator @@ -1326,7 +1326,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [16] - Statistics: Num rows: 2000 Data size: 3511604 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 8000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator Group By Vectorization: className: VectorGroupByOperator @@ -1338,7 +1338,7 @@ STAGE PLANS: keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 3511604 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1347,7 +1347,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 2000 Data size: 3511604 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1379,7 +1379,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 1755802 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 170 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) Group By Vectorization: @@ -1391,14 +1391,14 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1420,13 +1420,13 @@ STAGE PLANS: projectedOutputColumnNums: [0] mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
