You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2016/12/16 18:28:24 UTC
[11/21] hive git commit: HIVE-15192 : Use Calcite to de-correlate and
plan subqueries (Vineet Garg via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/llap/subquery_shared_alias.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_shared_alias.q.out b/ql/src/test/results/clientpositive/llap/subquery_shared_alias.q.out
new file mode 100644
index 0000000..0507ab7
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/subquery_shared_alias.q.out
@@ -0,0 +1,23 @@
+PREHOOK: query: select *
+from src
+where src.key in (select key from src where key > '9')
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select *
+from src
+where src.key in (select key from src where key > '9')
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+90 val_90
+90 val_90
+90 val_90
+92 val_92
+95 val_95
+95 val_95
+96 val_96
+97 val_97
+97 val_97
+98 val_98
+98 val_98
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/llap/subquery_views.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_views.q.out b/ql/src/test/results/clientpositive/llap/subquery_views.q.out
index 4cd0485..cf963b2 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_views.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_views.q.out
@@ -111,8 +111,6 @@ where `b`.`key` not in
from `default`.`src` `a`
where `b`.`value` = `a`.`value` and `a`.`key` = `b`.`key` and `a`.`value` > 'val_11'
), tableType:VIRTUAL_VIEW, rewriteEnabled:false)
-Warning: Shuffle Join MERGEJOIN[67][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 9' is a cross product
PREHOOK: query: explain
select *
from cv2 where cv2.key in (select key from cv2 c where c.key < '11')
@@ -130,13 +128,28 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Map 13 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
- Reducer 12 <- Map 11 (SIMPLE_EDGE)
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
- Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
- Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
- Reducer 6 <- Map 5 (SIMPLE_EDGE)
- Reducer 9 <- Map 8 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE)
+ Reducer 11 <- Map 10 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+ Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
+ Reducer 13 <- Reducer 12 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE)
+ Reducer 15 <- Map 14 (SIMPLE_EDGE)
+ Reducer 17 <- Map 16 (SIMPLE_EDGE)
+ Reducer 19 <- Map 18 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+ Reducer 20 <- Reducer 19 (SIMPLE_EDGE), Reducer 30 (SIMPLE_EDGE)
+ Reducer 21 <- Reducer 20 (SIMPLE_EDGE)
+ Reducer 23 <- Map 22 (SIMPLE_EDGE), Reducer 26 (SIMPLE_EDGE)
+ Reducer 24 <- Reducer 23 (SIMPLE_EDGE)
+ Reducer 26 <- Map 25 (SIMPLE_EDGE)
+ Reducer 28 <- Map 27 (SIMPLE_EDGE), Reducer 32 (SIMPLE_EDGE)
+ Reducer 29 <- Reducer 28 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 30 <- Reducer 29 (SIMPLE_EDGE), Reducer 34 (SIMPLE_EDGE)
+ Reducer 32 <- Map 31 (SIMPLE_EDGE)
+ Reducer 34 <- Map 33 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 21 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+ Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -154,112 +167,340 @@ STAGE PLANS:
outputColumnNames: _col0, _col1
Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- sort order:
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 11
+ Map 10
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((value > 'val_11') and (key is null or value is null)) (type: boolean)
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (value > 'val_11') (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 29548 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: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 13
+ Map 14
Map Operator Tree:
TableScan
- alias: a
+ alias: b
+ properties:
+ insideView TRUE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: b
+ properties:
+ insideView TRUE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 205 Data size: 17835 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: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 18
+ Map Operator Tree:
+ TableScan
+ alias: b
+ properties:
+ insideView TRUE
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((value > 'val_11') and (key < '11')) (type: boolean)
- Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (key < '11') (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: key (type: string), value (type: string), key (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col2 (type: string), _col1 (type: string), _col0 (type: string)
- sort order: +++
- Map-reduce partition columns: _col2 (type: string), _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 5
+ Map 22
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((value > 'val_11') and (key is null or value is null)) (type: boolean)
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (value > 'val_11') (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: bigint)
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 29548 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: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 25
+ Map Operator Tree:
+ TableScan
+ alias: b
+ properties:
+ insideView TRUE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 27
Map Operator Tree:
TableScan
alias: a
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((value > 'val_11') and (key < '11')) (type: boolean)
- Statistics: Num rows: 55 Data size: 9790 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (value > 'val_11') (type: boolean)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: key (type: string), value (type: string), key (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col2 (type: string), _col1 (type: string), _col0 (type: string)
- sort order: +++
- Map-reduce partition columns: _col2 (type: string), _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 55 Data size: 14575 Basic stats: COMPLETE Column stats: COMPLETE
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 8
+ Map 31
+ Map Operator Tree:
+ TableScan
+ alias: b
+ properties:
+ insideView TRUE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 33
Map Operator Tree:
TableScan
alias: b
properties:
insideView TRUE
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 205 Data size: 17835 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: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: a
Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (key < '11') (type: boolean)
+ predicate: (value > 'val_11') (type: boolean)
Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- sort order:
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: b
+ properties:
+ insideView TRUE
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: key (type: string), value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 11
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), _col2 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 265 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: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 12
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 269 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: 269 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: boolean)
+ Reducer 13
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col4 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col4 (type: string), _col2 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col3 (type: boolean)
+ Reducer 15
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 17
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 205 Data size: 17835 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: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 19
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col4, _col5
+ Statistics: Num rows: 166 Data size: 32204 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 32204 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col4 (type: bigint), _col5 (type: bigint)
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col4, _col5
+ Statistics: Num rows: 166 Data size: 32204 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string)
+ Statistics: Num rows: 166 Data size: 32204 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col4 (type: bigint), _col5 (type: bigint)
+ Reducer 20
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
@@ -267,16 +508,16 @@ STAGE PLANS:
Left Outer Join0 to 1
keys:
0 _col0 (type: string), _col1 (type: string), _col0 (type: string)
- 1 _col2 (type: string), _col1 (type: string), _col0 (type: string)
- outputColumnNames: _col0, _col3
- Statistics: Num rows: 166 Data size: 28884 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col4 (type: string), _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col4, _col5, _col9
+ Statistics: Num rows: 166 Data size: 17762 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 174 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col9 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean)
+ Statistics: Num rows: 83 Data size: 8881 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 8881 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
@@ -287,38 +528,113 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 12
+ Reducer 21
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 2
+ Statistics: Num rows: 1 Data size: 87 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: 87 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 23
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string)
+ outputColumnNames: _col2, _col3, _col0
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(), count(_col0)
+ keys: _col2 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 194 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: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ Reducer 24
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), count(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 194 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: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ Reducer 26
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string)
- sort order: +++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 28
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), _col2 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 265 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: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 29
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 269 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: 269 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: boolean)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -327,36 +643,79 @@ STAGE PLANS:
Left Outer Join0 to 1
keys:
0 _col0 (type: string), _col1 (type: string), _col0 (type: string)
- 1 _col2 (type: string), _col1 (type: string), _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 166 Data size: 43990 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col4 (type: string), _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col4, _col5, _col9
+ Statistics: Num rows: 166 Data size: 32868 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col9 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean)
+ Statistics: Num rows: 83 Data size: 16434 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 14774 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: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: string)
+ Reducer 30
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col4 (type: string), _col2 (type: string), _col1 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col4 (type: string), _col2 (type: string), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 269 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col3 (type: boolean)
+ Reducer 32
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 44500 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 34
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 205 Data size: 17835 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: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 4
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 178 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 14774 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -364,35 +723,58 @@ STAGE PLANS:
Reducer 6
Execution mode: llap
Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string), _col1 (type: string)
+ 1 _col0 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col2, _col3
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: string), _col3 (type: string), _col0 (type: string)
+ outputColumnNames: _col2, _col3, _col0
+ Statistics: Num rows: 1 Data size: 265 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(), count(_col0)
+ keys: _col2 (type: string), _col3 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 194 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: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(VALUE._col0), count(VALUE._col1)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col0 = 0) (type: boolean)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 194 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: 1 Data size: 194 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col3 (type: bigint)
Reducer 9
Execution mode: llap
Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
outputColumnNames: _col0, _col1
- Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col0 (type: string)
- sort order: +++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col0 (type: string)
- Statistics: Num rows: 166 Data size: 29548 Basic stats: COMPLETE Column stats: COMPLETE
+ 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: 44500 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -400,8 +782,6 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[67][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[69][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 9' is a cross product
PREHOOK: query: select *
from cv2 where cv2.key in (select key from cv2 c where c.key < '11')
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out
index ff658d7..27f32db 100644
--- a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out
@@ -1,4 +1,4 @@
-Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Map 1' is a cross product
+Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Map 1' is a cross product
PREHOOK: query: -- HIVE-12738 -- We are checking if a MapJoin after a GroupBy will work properly.
explain
select *
@@ -18,57 +18,61 @@ POSTHOOK: type: QUERY
Plan optimized by CBO.
Vertex dependency in root stage
-Map 1 <- Map 5 (BROADCAST_EDGE), Reducer 4 (BROADCAST_EDGE)
+Map 1 <- Reducer 4 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
+Reducer 6 <- Map 5 (SIMPLE_EDGE)
Stage-0
Fetch Operator
limit:-1
Stage-1
Reducer 2 vectorized, llap
- File Output Operator [FS_36]
- Select Operator [SEL_35] (rows=1 width=178)
+ File Output Operator [FS_37]
+ Select Operator [SEL_36] (rows=250 width=178)
Output:["_col0","_col1"]
<-Map 1 [SIMPLE_EDGE] llap
- SHUFFLE [RS_21]
- Select Operator [SEL_20] (rows=1 width=178)
+ SHUFFLE [RS_23]
+ Select Operator [SEL_22] (rows=250 width=178)
Output:["_col0","_col1"]
- Filter Operator [FIL_19] (rows=1 width=265)
- predicate:_col3 is null
- Map Join Operator [MAPJOIN_28] (rows=1219 width=265)
- Conds:MAPJOIN_27._col0=RS_17._col0(Left Outer),Output:["_col0","_col1","_col3"]
- <-Map 5 [BROADCAST_EDGE] llap
- BROADCAST [RS_17]
+ Filter Operator [FIL_21] (rows=250 width=198)
+ predicate:(not CASE WHEN ((_col2 = 0)) THEN (false) WHEN (_col5 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col3 < _col2)) THEN (true) ELSE (false) END)
+ Map Join Operator [MAPJOIN_29] (rows=500 width=198)
+ Conds:MAPJOIN_28._col0=RS_35._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5"]
+ <-Reducer 6 [BROADCAST_EDGE] vectorized, llap
+ BROADCAST [RS_35]
PartitionCols:_col0
- Select Operator [SEL_12] (rows=500 width=87)
- Output:["_col0"]
- TableScan [TS_11] (rows=500 width=87)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
- <-Map Join Operator [MAPJOIN_27] (rows=500 width=178)
- Conds:(Inner),Output:["_col0","_col1"]
+ Group By Operator [GBY_34] (rows=205 width=91)
+ Output:["_col0","_col1"],keys:KEY._col0, KEY._col1
+ <-Map 5 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_12]
+ PartitionCols:_col0, _col1
+ Group By Operator [GBY_11] (rows=205 width=91)
+ Output:["_col0","_col1"],keys:_col0, true
+ Select Operator [SEL_9] (rows=500 width=87)
+ Output:["_col0"]
+ TableScan [TS_8] (rows=500 width=87)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ <-Map Join Operator [MAPJOIN_28] (rows=500 width=194)
+ Conds:(Inner),Output:["_col0","_col1","_col2","_col3"]
<-Reducer 4 [BROADCAST_EDGE] vectorized, llap
- BROADCAST [RS_34]
- Select Operator [SEL_33] (rows=1 width=8)
- Filter Operator [FIL_32] (rows=1 width=8)
- predicate:(_col0 = 0)
- Group By Operator [GBY_31] (rows=1 width=8)
- Output:["_col0"],aggregations:["count(VALUE._col0)"]
- <-Map 3 [SIMPLE_EDGE] llap
- SHUFFLE [RS_6]
- Group By Operator [GBY_5] (rows=1 width=8)
- Output:["_col0"],aggregations:["count()"]
- Select Operator [SEL_4] (rows=1 width=87)
- Filter Operator [FIL_25] (rows=1 width=87)
- predicate:key is null
- TableScan [TS_2] (rows=500 width=87)
- default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
+ BROADCAST [RS_33]
+ Group By Operator [GBY_32] (rows=1 width=16)
+ Output:["_col0","_col1"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"]
+ <-Map 3 [SIMPLE_EDGE] llap
+ SHUFFLE [RS_5]
+ Group By Operator [GBY_4] (rows=1 width=16)
+ Output:["_col0","_col1"],aggregations:["count()","count(key)"]
+ Select Operator [SEL_3] (rows=500 width=87)
+ Output:["key"]
+ TableScan [TS_2] (rows=500 width=87)
+ default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"]
<-Select Operator [SEL_1] (rows=500 width=178)
Output:["_col0","_col1"]
TableScan [TS_0] (rows=500 width=178)
default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"]
-Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Map 1' is a cross product
+Warning: Map Join MAPJOIN[28][bigTable=?] in task 'Map 1' is a cross product
PREHOOK: query: select *
from src
where not key in
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out
index a075662..22d1bbe 100644
--- a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out
@@ -31,54 +31,64 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 2 (BROADCAST_EDGE)
- Reducer 4 <- Map 1 (BROADCAST_EDGE), Map 3 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (BROADCAST_EDGE), Reducer 5 (BROADCAST_EDGE)
+ Reducer 5 <- Map 4 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: lineitem
+ Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: l_partkey (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 50 Data size: 200 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: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
alias: li
Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((l_linenumber = 1) and l_partkey is not null and l_orderkey is not null) (type: boolean)
+ predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean)
Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col1, _col2
- input vertices:
- 1 Map 2
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col2 (type: int)
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col2 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 2
+ Map 4
Map Operator Tree:
TableScan
alias: lineitem
Statistics: Num rows: 100 Data size: 9200 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((l_shipmode = 'AIR') and l_orderkey is not null) (type: boolean)
+ predicate: (l_shipmode = 'AIR') (type: boolean)
Statistics: Num rows: 14 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: l_orderkey (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 14 Data size: 56 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: l_orderkey
+ Statistics: Num rows: 14 Data size: 1288 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- keys: _col0 (type: int)
+ keys: l_orderkey (type: int)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
@@ -89,27 +99,7 @@ STAGE PLANS:
Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 3
- Map Operator Tree:
- TableScan
- alias: lineitem
- Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: l_partkey is not null (type: boolean)
- Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: l_partkey (type: int)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 50 Data size: 200 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: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
- Execution mode: llap
- LLAP IO: no inputs
- Reducer 4
+ Reducer 2
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
@@ -121,23 +111,46 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
- 0 _col1 (type: int)
- 1 _col0 (type: int)
- outputColumnNames: _col2, _col4
+ 0 _col0 (type: int)
+ 1 _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col3
input vertices:
- 0 Map 1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col4 (type: int), _col2 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 4 Data size: 32 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
+ 1 Map 3
+ Statistics: Num rows: 5 Data size: 60 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Reducer 5
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col3 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 5 Data size: 40 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 5
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 16 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: 4 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -192,65 +205,74 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Map 2 (BROADCAST_EDGE)
- Reducer 4 <- Map 1 (BROADCAST_EDGE), Map 3 (SIMPLE_EDGE)
+ Map 7 <- Reducer 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (BROADCAST_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 4 (BROADCAST_EDGE), Map 7 (SIMPLE_EDGE)
+ Reducer 9 <- Reducer 2 (BROADCAST_EDGE), Reducer 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
+ alias: lineitem
+ Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 400 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: l_partkey (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 50 Data size: 200 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: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
alias: li
Statistics: Num rows: 100 Data size: 1600 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((l_linenumber = 1) and l_partkey is not null and l_orderkey is not null) (type: boolean)
+ predicate: ((l_linenumber = 1) and l_partkey is not null) (type: boolean)
Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int)
- outputColumnNames: _col0, _col1, _col2
+ expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int), 1 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 _col0 (type: int), 1 (type: int)
- 1 _col0 (type: int), _col1 (type: int)
- outputColumnNames: _col1, _col2
- input vertices:
- 1 Map 2
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col1 (type: int)
- sort order: +
- Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 13 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col2 (type: int)
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 17 Data size: 272 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col2 (type: int), _col3 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 2
+ Map 4
Map Operator Tree:
TableScan
alias: lineitem
Statistics: Num rows: 100 Data size: 9600 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((l_shipmode = 'AIR') and (l_linenumber = 1) and l_orderkey is not null) (type: boolean)
+ predicate: (l_shipmode = 'AIR') (type: boolean)
Statistics: Num rows: 14 Data size: 1344 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: l_orderkey (type: int), 1 (type: int)
+ expressions: l_orderkey (type: int), l_linenumber (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 4 Data size: 32 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: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 14 Data size: 1330 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 3
+ Map 5
Map Operator Tree:
TableScan
alias: lineitem
@@ -270,7 +292,41 @@ STAGE PLANS:
Statistics: Num rows: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Reducer 4
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: li
+ Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: l_partkey is not null (type: boolean)
+ Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: l_partkey (type: int), l_linenumber (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 100 Data size: 800 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2
+ input vertices:
+ 0 Reducer 6
+ Statistics: Num rows: 34 Data size: 136 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col2 (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 12 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: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
Execution mode: vectorized, llap
Reduce Operator Tree:
Group By Operator
@@ -282,19 +338,84 @@ STAGE PLANS:
condition map:
Inner Join 0 to 1
keys:
+ 0 _col0 (type: int)
+ 1 _col1 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: int), _col4 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: int), _col4 (type: int)
+ Statistics: Num rows: 5 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col3 (type: int)
+ Reducer 6
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 50 Data size: 200 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: 50 Data size: 200 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 8
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
0 _col1 (type: int)
1 _col0 (type: int)
- outputColumnNames: _col2, _col4
+ outputColumnNames: _col0, _col3
input vertices:
- 0 Map 1
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col4 (type: int), _col2 (type: int)
+ 0 Map 4
+ Statistics: Num rows: 14 Data size: 112 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: int), _col3 (type: int)
+ mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 4 Data size: 32 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: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 9
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int), _col4 (type: int)
+ 1 _col0 (type: int), _col1 (type: int)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 0 Reducer 2
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col3 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 40 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat