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 18:28:25 UTC
[12/21] 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_notin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out
index 3da1acb..47a9d6b 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out
@@ -1,4 +1,4 @@
-Warning: Shuffle Join MERGEJOIN[26][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- non agg, non corr
explain
select *
@@ -27,8 +27,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -50,21 +51,19 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: s1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: false (type: boolean)
- Statistics: Num rows: 1 Data size: 4 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)
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (key > '2') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(), count(key)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -79,11 +78,16 @@ STAGE PLANS:
expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 166 Data size: 14442 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: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), true (type: boolean)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 69 Data size: 6279 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: boolean)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: boolean)
+ Statistics: Num rows: 69 Data size: 6279 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -95,14 +99,14 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 97000 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: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string), _col2 (type: bigint), _col3 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -112,18 +116,18 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 500 Data size: 132500 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col5
+ Statistics: Num rows: 500 Data size: 99000 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: (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) (type: boolean)
+ Statistics: Num rows: 250 Data size: 49500 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: 250 Data size: 44500 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: 250 Data size: 44500 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -132,18 +136,28 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(VALUE._col0), count(VALUE._col1)
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
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: boolean)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 69 Data size: 6279 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: 69 Data size: 6279 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: boolean)
Stage: Stage-0
Fetch Operator
@@ -151,7 +165,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[28][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select *
from src
where src.key not in ( select key from src s1 where s1.key > '2')
@@ -285,7 +299,6 @@ POSTHOOK: Input: default@src
199 val_199
199 val_199
2 val_2
-Warning: Shuffle Join MERGEJOIN[36][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- non agg, corr
explain
select p_mfgr, b.p_name, p_size
@@ -315,11 +328,18 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 11 <- Map 10 (SIMPLE_EDGE)
+ Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 16 (SIMPLE_EDGE)
+ Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
+ Reducer 14 <- Reducer 13 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE)
+ Reducer 16 <- Map 15 (SIMPLE_EDGE)
+ Reducer 18 <- Map 17 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
- Reducer 8 <- Map 7 (SIMPLE_EDGE)
+ Reducer 6 <- Reducer 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
@@ -332,12 +352,14 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ value expressions: _col0 (type: string), _col2 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 10
Map Operator Tree:
TableScan
alias: part
@@ -351,7 +373,41 @@ STAGE PLANS:
value expressions: p_name (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 15
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 17
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_name (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
Map Operator Tree:
TableScan
alias: part
@@ -365,49 +421,24 @@ STAGE PLANS:
value expressions: p_name (type: string)
Execution mode: llap
LLAP IO: no inputs
- Reducer 2
- Execution mode: llap
- Reduce Operator Tree:
- Merge Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 5798 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: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col2 (type: int)
- Reducer 3
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
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, _col2, _col4
- Statistics: Num rows: 26 Data size: 8944 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col4 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 344 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 223 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
+ LLAP IO: no inputs
+ Reducer 11
Execution mode: llap
Reduce Operator Tree:
Select Operator
@@ -436,36 +467,143 @@ STAGE PLANS:
isPivotResult: true
Statistics: Num rows: 26 Data size: 12766 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((rank_window_0 <= 2) and (_col1 is null or _col2 is null)) (type: boolean)
- Statistics: Num rows: 1 Data size: 491 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (rank_window_0 <= 2) (type: boolean)
+ Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 1 Data size: 491 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)
- Reducer 6
+ expressions: _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 8 Data size: 1752 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: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string)
+ Reducer 12
+ 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
+ Statistics: Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col1 (type: string), _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4 Data size: 876 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: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 13
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 4 Data size: 876 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 4 Data size: 892 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: 4 Data size: 892 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string), _col2 (type: boolean)
+ Reducer 14
+ 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
+ Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col3 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col3 (type: string), _col1 (type: string)
+ Statistics: Num rows: 2 Data size: 446 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: boolean)
+ Reducer 16
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 18
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1573 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: 13 Data size: 1573 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5
+ Statistics: Num rows: 26 Data size: 6214 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: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint)
+ Reducer 3
+ 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 _col3 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8
+ Statistics: Num rows: 26 Data size: 6318 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
+ predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean)
+ Statistics: Num rows: 13 Data size: 3159 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 8
+ expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 13 Data size: 2899 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: llap
Reduce Operator Tree:
Select Operator
@@ -497,14 +635,70 @@ STAGE PLANS:
predicate: (rank_window_0 <= 2) (type: boolean)
Statistics: Num rows: 8 Data size: 3928 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: string), _col2 (type: string)
+ expressions: _col2 (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 8 Data size: 1752 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)
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string)
+ Reducer 6
+ 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
+ Statistics: Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: string)
+ outputColumnNames: _col2, _col1
+ Statistics: Num rows: 8 Data size: 1752 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(), count(_col1)
+ keys: _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 228 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: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0), count(VALUE._col1)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 228 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: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 9
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -512,7 +706,6 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select p_mfgr, b.p_name, p_size
from part b
where b.p_name not in
@@ -551,7 +744,7 @@ Manufacturer#4 almond azure aquamarine papaya violet 12
Manufacturer#5 almond antique blue firebrick mint 31
Manufacturer#5 almond aquamarine dodger light gainsboro 46
Manufacturer#5 almond azure blanched chiffon midnight 23
-Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- agg, non corr
explain
select p_name, p_size
@@ -581,8 +774,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
+ Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
Reducer 8 <- Map 7 (SIMPLE_EDGE)
@@ -630,6 +824,20 @@ STAGE PLANS:
TopN Hash Memory Usage: 0.1
Execution mode: llap
LLAP IO: no inputs
+ Reducer 10
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: double), KEY._col1 (type: boolean)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: boolean)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -639,14 +847,14 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 26 Data size: 3666 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: UDFToDouble(_col1) (type: double)
sort order: +
Map-reduce partition columns: UDFToDouble(_col1) (type: double)
- Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: int)
+ Statistics: Num rows: 26 Data size: 3666 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: bigint), _col3 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -656,18 +864,18 @@ STAGE PLANS:
keys:
0 UDFToDouble(_col1) (type: double)
1 _col0 (type: double)
- outputColumnNames: _col0, _col1, _col3
- Statistics: Num rows: 26 Data size: 3458 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col5
+ Statistics: Num rows: 26 Data size: 3770 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: _col3 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 133 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (not CASE WHEN ((_col2 = 0)) THEN (false) WHEN (_col5 is not null) THEN (true) WHEN (_col1 is null) THEN (null) WHEN ((_col3 < _col2)) THEN (true) ELSE (false) END) (type: boolean)
+ Statistics: Num rows: 13 Data size: 1885 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: string), _col1 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 125 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 1625 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -724,24 +932,15 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is null (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
- Group By Operator
- aggregations: count()
- mode: complete
- 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
+ Group By Operator
+ aggregations: count(), count(_col0)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
Reducer 8
Execution mode: llap
Reduce Operator Tree:
@@ -794,11 +993,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: double), true (type: boolean)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: double), _col1 (type: boolean)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: double), _col1 (type: boolean)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Stage: Stage-0
Fetch Operator
@@ -806,7 +1010,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[51][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select p_name, p_size
from
part where part.p_size not in
@@ -853,7 +1057,6 @@ almond aquamarine sandy cyan gainsboro 18
almond aquamarine yellow dodger mint 7
almond azure aquamarine papaya violet 12
almond azure blanched chiffon midnight 23
-Warning: Shuffle Join MERGEJOIN[47][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- agg, corr
explain
select p_mfgr, p_name, p_size
@@ -881,11 +1084,17 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Reducer 9 (SIMPLE_EDGE)
+ Reducer 11 <- Map 10 (SIMPLE_EDGE)
+ Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 17 (SIMPLE_EDGE)
+ Reducer 13 <- Reducer 12 (SIMPLE_EDGE)
+ Reducer 14 <- Reducer 13 (SIMPLE_EDGE)
+ Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 19 (SIMPLE_EDGE)
+ Reducer 17 <- Map 16 (SIMPLE_EDGE)
+ Reducer 19 <- Map 18 (SIMPLE_EDGE)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 10 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 15 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+ Reducer 6 <- Reducer 5 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
Reducer 9 <- Map 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
@@ -900,12 +1109,14 @@ STAGE PLANS:
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- sort order:
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ value expressions: _col0 (type: string), _col2 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 10
Map Operator Tree:
TableScan
alias: part
@@ -918,7 +1129,41 @@ STAGE PLANS:
TopN Hash Memory Usage: 0.1
Execution mode: llap
LLAP IO: no inputs
- Map 8
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 18
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_size (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 52 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: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
Map Operator Tree:
TableScan
alias: part
@@ -931,7 +1176,92 @@ STAGE PLANS:
TopN Hash Memory Usage: 0.1
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 26 Data size: 2548 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_mfgr (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 11
+ Execution mode: llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)
+ outputColumnNames: _col2, _col5
+ Statistics: Num rows: 26 Data size: 9620 Basic stats: COMPLETE Column stats: COMPLETE
+ PTF Operator
+ Function definitions:
+ Input definition
+ input alias: ptf_0
+ output shape: _col2: string, _col5: int
+ type: WINDOWING
+ Windowing table definition
+ input alias: ptf_1
+ name: windowingtablefunction
+ order by: _col5 ASC NULLS FIRST
+ partition by: _col2
+ raw input shape:
+ window functions:
+ window function definition
+ alias: rank_window_0
+ arguments: _col5
+ name: rank
+ window function: GenericUDAFRankEvaluator
+ window frame: PRECEDING(MAX)~FOLLOWING(MAX)
+ isPivotResult: true
+ Statistics: Num rows: 26 Data size: 9620 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (rank_window_0 <= 2) (type: boolean)
+ Statistics: Num rows: 8 Data size: 2960 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: string), _col5 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 8 Data size: 816 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: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
+ Reducer 12
+ 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
+ Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: int)
+ outputColumnNames: _col2, _col1
+ Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col1)
+ keys: _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 204 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: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
+ Reducer 13
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -940,32 +1270,94 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col1 (type: int), _col0 (type: string)
+ Group By Operator
+ keys: _col1 (type: int), _col0 (type: string)
+ mode: hash
outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
- key expressions: _col1 (type: string), _col0 (type: int)
+ key expressions: _col0 (type: int), _col1 (type: string)
sort order: ++
- Map-reduce partition columns: _col1 (type: string), _col0 (type: int)
- Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 2
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 14
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), true (type: boolean)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 106 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: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string), _col2 (type: boolean)
+ Reducer 15
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0
- 1
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: string), _col3 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col1 (type: string), _col3 (type: int)
+ Statistics: Num rows: 1 Data size: 106 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: boolean)
+ Reducer 17
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 19
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 52 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: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5
+ Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col1 (type: string), _col2 (type: int)
sort order: ++
Map-reduce partition columns: _col1 (type: string), _col2 (type: int)
- Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string)
+ Statistics: Num rows: 26 Data size: 6214 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string), _col4 (type: bigint), _col5 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -974,19 +1366,19 @@ STAGE PLANS:
Left Outer Join0 to 1
keys:
0 _col1 (type: string), _col2 (type: int)
- 1 _col1 (type: string), _col0 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col4
- Statistics: Num rows: 26 Data size: 5902 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col1 (type: string), _col3 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8
+ Statistics: Num rows: 26 Data size: 6318 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: _col4 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 227 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col2 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean)
+ Statistics: Num rows: 13 Data size: 3159 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int)
outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 223 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 13 Data size: 2899 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1025,113 +1417,81 @@ STAGE PLANS:
Select Operator
expressions: _col2 (type: string), _col5 (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 8 Data size: 2960 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: min(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 204 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: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: int)
+ Statistics: Num rows: 8 Data size: 816 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: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
Reducer 6
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
+ Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col2 (type: string), _col1 (type: int)
+ outputColumnNames: _col2, _col1
+ Statistics: Num rows: 8 Data size: 816 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col1)
+ keys: _col2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 2 Data size: 204 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: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
Group By Operator
aggregations: min(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (_col1 is null or _col0 is null) (type: boolean)
- Statistics: Num rows: 1 Data size: 102 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- Statistics: Num rows: 1 Data size: 102 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)
- Reducer 7
+ Group By Operator
+ aggregations: count(), count(_col1)
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 2 Data size: 228 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: 2 Data size: 228 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 9
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 9
- Execution mode: llap
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)
- outputColumnNames: _col2, _col5
- Statistics: Num rows: 26 Data size: 9620 Basic stats: COMPLETE Column stats: COMPLETE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col2: string, _col5: int
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col5 ASC NULLS FIRST
- partition by: _col2
- raw input shape:
- window functions:
- window function definition
- alias: rank_window_0
- arguments: _col5
- name: rank
- window function: GenericUDAFRankEvaluator
- window frame: PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 26 Data size: 9620 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: (rank_window_0 <= 2) (type: boolean)
- Statistics: Num rows: 8 Data size: 2960 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col2 (type: string), _col5 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 8 Data size: 2960 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- aggregations: min(_col1)
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 2 Data size: 204 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: 2 Data size: 204 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: int)
-
- Stage: Stage-0
- Fetch Operator
+ Statistics: Num rows: 5 Data size: 490 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: 5 Data size: 490 Basic stats: COMPLETE Column stats: COMPLETE
+
+ Stage: Stage-0
+ Fetch Operator
limit: -1
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select p_mfgr, p_name, p_size
from part b where b.p_size not in
(select min(p_size)
@@ -1172,21 +1532,21 @@ Manufacturer#5 almond antique medium spring khaki 6
Manufacturer#5 almond azure blanched chiffon midnight 23
Manufacturer#5 almond antique blue firebrick mint 31
Manufacturer#5 almond aquamarine dodger light gainsboro 46
-Warning: Shuffle Join MERGEJOIN[32][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[35][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- non agg, non corr, Group By in Parent Query
-select li.l_partkey, count(*)
-from lineitem li
-where li.l_linenumber = 1 and
- li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR')
+select li.l_partkey, count(*)
+from lineitem li
+where li.l_linenumber = 1 and
+ li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR')
group by li.l_partkey
PREHOOK: type: QUERY
PREHOOK: Input: default@lineitem
#### A masked pattern was here ####
POSTHOOK: query: -- non agg, non corr, Group By in Parent Query
-select li.l_partkey, count(*)
-from lineitem li
-where li.l_linenumber = 1 and
- li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR')
+select li.l_partkey, count(*)
+from lineitem li
+where li.l_linenumber = 1 and
+ li.l_orderkey not in (select l_orderkey from lineitem where l_shipmode = 'AIR')
group by li.l_partkey
POSTHOOK: type: QUERY
POSTHOOK: Input: default@lineitem
@@ -1207,7 +1567,7 @@ POSTHOOK: Input: default@lineitem
139636 1
175839 1
182052 1
-Warning: Shuffle Join MERGEJOIN[28][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: -- alternate not in syntax
select *
from src
@@ -1371,7 +1731,7 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@t1_v
POSTHOOK: Output: database:default
POSTHOOK: Output: default@T2_v
-Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain
select *
from T1_v where T1_v.key not in (select T2_v.key from T2_v)
@@ -1390,8 +1750,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1422,19 +1783,21 @@ STAGE PLANS:
insideView TRUE
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (true) ELSE (key is null) END) (type: boolean)
- Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (key < '11') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: count()
+ aggregations: count(), count(_col0)
mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 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)
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
Map 6
@@ -1445,17 +1808,22 @@ STAGE PLANS:
insideView TRUE
Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((key < '11') and CASE WHEN ((key > '104')) THEN (null) ELSE ((key < '11')) END) (type: boolean)
- Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (key < '11') (type: boolean)
+ Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: CASE WHEN ((key > '104')) THEN (null) ELSE (key) END (type: string)
outputColumnNames: _col0
- Statistics: Num rows: 83 Data size: 15272 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: 83 Data size: 15272 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 166 Data size: 31208 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string), true (type: boolean)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 69 Data size: 12972 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: boolean)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: boolean)
+ Statistics: Num rows: 69 Data size: 12972 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
Reducer 2
@@ -1467,13 +1835,14 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0
- Statistics: Num rows: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 166 Data size: 17098 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: 166 Data size: 14442 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 166 Data size: 17098 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: bigint), _col2 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -1483,18 +1852,18 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col2
- Statistics: Num rows: 199 Data size: 53929 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0, _col1, _col2, _col4
+ Statistics: Num rows: 166 Data size: 17762 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: _col2 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 271 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (not CASE WHEN ((_col1 = 0)) THEN (false) WHEN (_col4 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col2 < _col1)) THEN (true) ELSE (false) 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: 7221 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 87 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 83 Data size: 7221 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1503,18 +1872,28 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(VALUE._col0), count(VALUE._col1)
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
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string), KEY._col1 (type: boolean)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 69 Data size: 12972 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: 69 Data size: 12972 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: boolean)
Stage: Stage-0
Fetch Operator
@@ -1522,7 +1901,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[33][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select *
from T1_v where T1_v.key not in (select T2_v.key from T2_v)
PREHOOK: type: QUERY
@@ -1537,3 +1916,7252 @@ POSTHOOK: Input: default@src
POSTHOOK: Input: default@t1_v
POSTHOOK: Input: default@t2_v
#### A masked pattern was here ####
+PREHOOK: query: --where has multiple conjuction
+explain select * from part where p_brand <> 'Brand#14' AND p_size NOT IN (select min(p_size) from part p where p.p_type = part.p_type group by p_type) AND p_size <> 340
+PREHOOK: type: QUERY
+POSTHOOK: query: --where has multiple conjuction
+explain select * from part where p_brand <> 'Brand#14' AND p_size NOT IN (select min(p_size) from part p where p.p_type = part.p_type group by p_type) AND p_size <> 340
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Reducer 10 <- Map 9 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE)
+ Reducer 11 <- Reducer 10 (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 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 13 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((p_brand <> 'Brand#14') and (p_size <> 340)) (type: boolean)
+ Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_partkey (type: int), p_name (type: string), p_mfgr (type: string), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col4 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col4 (type: string)
+ Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 14
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 5200 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((p_brand <> 'Brand#14') and (p_size <> 340)) (type: boolean)
+ Statistics: Num rows: 26 Data size: 5200 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_type (type: string)
+ outputColumnNames: p_type
+ Statistics: Num rows: 26 Data size: 5200 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_type (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((p_brand <> 'Brand#14') and (p_size <> 340)) (type: boolean)
+ Statistics: Num rows: 26 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_size (type: int)
+ outputColumnNames: p_size
+ Statistics: Num rows: 26 Data size: 2496 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_size (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 52 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: 13 Data size: 52 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: p
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_type (type: string), p_size (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 2808 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: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 5200 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((p_brand <> 'Brand#14') and (p_size <> 340)) (type: boolean)
+ Statistics: Num rows: 26 Data size: 5200 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_type (type: string)
+ outputColumnNames: p_type
+ Statistics: Num rows: 26 Data size: 5200 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_type (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1352 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: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 9
+ Map Operator Tree:
+ TableScan
+ alias: p
+ Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_type (type: string), p_size (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 2808 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: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 10
+ 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: _col0, _col1, _col2
+ Statistics: Num rows: 12 Data size: 2544 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col1)
+ keys: _col2 (type: string), _col0 (type: string)
+ mode: hash
+ outputColumnNames: _c
<TRUNCATED>