You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by pr...@apache.org on 2017/05/10 06:08:43 UTC
[4/6] hive git commit: Revert "HIVE-16330 : Improve plans for scalar
subquery with aggregates (Vineet Garg via Ashutosh Chauhan)"
http://git-wip-us.apache.org/repos/asf/hive/blob/cde41e9e/ql/src/test/results/clientpositive/llap/subquery_select.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out
index e96067f..8eaec9e 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out
@@ -1447,8 +1447,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1472,6 +1473,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: p
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 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 5
+ Map Operator Tree:
+ TableScan
+ alias: p
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: p_type is not null (type: boolean)
@@ -1496,18 +1517,20 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col0 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col1, _col4, _col5
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (0) ELSE (_col2) END (type: bigint)
+ expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (0) ELSE (_col4) END (type: bigint)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1516,6 +1539,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 448 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: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -1585,8 +1634,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1610,6 +1660,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: p
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 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 5
+ Map Operator Tree:
+ TableScan
+ alias: p
Statistics: Num rows: 26 Data size: 5850 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: p_type is not null (type: boolean)
@@ -1634,18 +1704,20 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col0 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 26 Data size: 4992 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col1, _col4, _col5
+ Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END (type: string)
+ expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 4888 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 4888 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1654,6 +1726,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 448 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: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: max(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -1710,7 +1808,8 @@ POSTHOOK: Input: default@part
7 NULL
12 NULL
23 NULL
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain SELECT p_size, (SELECT max(p_size) FROM part)
FROM part
PREHOOK: type: QUERY
@@ -1726,8 +1825,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1745,7 +1846,27 @@ STAGE PLANS:
value expressions: _col0 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 3
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
Map Operator Tree:
TableScan
alias: part
@@ -1770,20 +1891,62 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col0, _col1
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: int)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 26 Data size: 208 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 4
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 208 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:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ 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: (sq_count_check(_col0) <= 1) (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 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1802,7 +1965,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: SELECT p_size, (SELECT max(p_size) FROM part)
FROM part
PREHOOK: type: QUERY
@@ -1839,7 +2003,8 @@ POSTHOOK: Input: default@part
2 46
46 46
23 46
-Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 5' is a cross product
PREHOOK: query: explain
select *
from src b
@@ -1867,10 +2032,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Reducer 4 (SIMPLE_EDGE)
- Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1907,7 +2074,27 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(key)
+ 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)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 9
Map Operator Tree:
TableScan
alias: src
@@ -1927,6 +2114,18 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Reducer 10
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: string)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1950,14 +2149,29 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col1
+ Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 83 Data size: 7553 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: string)
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col1, _col2
+ outputColumnNames: _col1, _col3
Statistics: Num rows: 83 Data size: 22825 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- keys: _col2 (type: string), _col1 (type: string)
+ keys: _col3 (type: string), _col1 (type: string)
mode: hash
outputColumnNames: _col0, _col1
Statistics: Num rows: 36 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
@@ -1966,7 +2180,7 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 36 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 5
+ Reducer 6
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1979,18 +2193,29 @@ STAGE PLANS:
sort order: ++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
Statistics: Num rows: 36 Data size: 9900 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 7
+ Reducer 8
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: max(VALUE._col0)
+ aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: string)
+ 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: (sq_count_check(_col0) <= 1) (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
Stage: Stage-0
Fetch Operator
@@ -1998,7 +2223,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[48][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[49][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 5' is a cross product
PREHOOK: query: select *
from src b
where b.key in
@@ -2049,8 +2275,9 @@ STAGE PLANS:
#### A masked pattern was here ####
Edges:
Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
- Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2092,16 +2319,36 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: sc
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: max(key)
keys: value (type: string)
mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE
+ outputColumnNames: _col0
+ Statistics: Num rows: 214 Data size: 19474 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: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 7
+ Map Operator Tree:
+ TableScan
+ alias: sc
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: max(key)
+ keys: value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 214 Data size: 58850 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: string)
sort order: +
@@ -2134,13 +2381,15 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col1 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col1, _col2, _col3
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col1, _col4, _col5
Statistics: Num rows: 83 Data size: 23157 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END (type: string), _col1 (type: string)
+ expressions: CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END (type: string), _col1 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 83 Data size: 22825 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
@@ -2157,6 +2406,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 214 Data size: 19474 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 214 Data size: 21186 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 71 Data size: 7029 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: 71 Data size: 7029 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 8
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: max(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -2416,7 +2691,8 @@ POSTHOOK: query: CREATE TABLE tempty(i int)
POSTHOOK: type: CREATETABLE
POSTHOOK: Output: database:default
POSTHOOK: Output: default@tempty
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain select p_size, (select count(*) from tempty) from part
PREHOOK: type: QUERY
POSTHOOK: query: explain select p_size, (select count(*) from tempty) from part
@@ -2430,8 +2706,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2449,7 +2727,27 @@ STAGE PLANS:
value expressions: _col0 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 3
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: tempty
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: i (type: int)
+ outputColumnNames: i
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Group By Operator
+ aggregations: count(i)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
Map Operator Tree:
TableScan
alias: tempty
@@ -2472,20 +2770,62 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
- Statistics: Num rows: 26 Data size: 312 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 4
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 26 Data size: 572 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 572 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 572 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col0) <= 1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -2504,7 +2844,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select p_size, (select count(*) from tempty) from part
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -2541,7 +2882,8 @@ POSTHOOK: Input: default@tempty
2 0
46 0
23 0
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain select p_size, (select max(i) from tempty) from part
PREHOOK: type: QUERY
POSTHOOK: query: explain select p_size, (select max(i) from tempty) from part
@@ -2555,8 +2897,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2574,7 +2918,27 @@ STAGE PLANS:
value expressions: _col0 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 3
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: tempty
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: i (type: int)
+ outputColumnNames: i
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Group By Operator
+ aggregations: count(i)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
Map Operator Tree:
TableScan
alias: tempty
@@ -2599,20 +2963,62 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0
+ Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 338 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 234 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 26 Data size: 234 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- Reducer 4
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 26 Data size: 468 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col2 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 26 Data size: 468 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 26 Data size: 468 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: complete
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col0) <= 1) (type: boolean)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -2631,7 +3037,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[13][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[31][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select p_size, (select max(i) from tempty) from part
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -2699,8 +3106,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2724,6 +3132,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: p
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 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 5
+ Map Operator Tree:
+ TableScan
+ alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: p_type is not null (type: boolean)
@@ -2748,18 +3176,20 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col0 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 26 Data size: 312 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col1, _col4, _col5
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: int), (1 + CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: int)
+ expressions: _col1 (type: int), (1 + CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END) (type: int)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2768,6 +3198,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 448 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: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: max(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -2841,8 +3297,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2866,6 +3323,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: p
+ Statistics: Num rows: 26 Data size: 2704 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 26 Data size: 2704 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 5
+ Map Operator Tree:
+ TableScan
+ alias: p
Statistics: Num rows: 26 Data size: 2808 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: p_type is not null (type: boolean)
@@ -2890,18 +3367,20 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col0 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col1, _col4, _col5
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: int), CASE WHEN (_col3 is null) THEN (false) ELSE (_col2 is null) END (type: boolean)
+ expressions: _col1 (type: int), CASE WHEN (_col5 is null) THEN (false) ELSE (_col4 is null) END (type: boolean)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -2910,6 +3389,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 4 Data size: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 448 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: 448 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -3634,9 +4139,11 @@ POSTHOOK: Input: default@part
6 false
18 false
45 false
-Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[51][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[52][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 11' is a cross product
+Warning: Shuffle Join MERGEJOIN[85][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[86][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[88][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product
+Warning: Shuffle Join MERGEJOIN[89][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product
PREHOOK: query: explain select p_size, (p_size IN
(select (select max(p_size) from part) as sb from part order by sb limit 1)) = true
from part
@@ -3654,15 +4161,19 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE), Reducer 14 (CUSTOM_SIMPLE_EDGE)
- Reducer 12 <- Reducer 11 (SIMPLE_EDGE)
- Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE)
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 12 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
- Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
- Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
+ Reducer 14 <- Map 13 (CUSTOM_SIMPLE_EDGE), Reducer 18 (CUSTOM_SIMPLE_EDGE)
+ Reducer 15 <- Reducer 14 (CUSTOM_SIMPLE_EDGE), Reducer 20 (CUSTOM_SIMPLE_EDGE)
+ Reducer 16 <- Reducer 15 (SIMPLE_EDGE)
+ Reducer 18 <- Map 17 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
+ Reducer 20 <- Map 19 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 16 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE)
+ Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE), Reducer 10 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+ Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3680,7 +4191,27 @@ STAGE PLANS:
value expressions: _col0 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 10
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_size (type: int)
+ outputColumnNames: p_size
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: max(p_size)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 13
Map Operator Tree:
TableScan
alias: part
@@ -3692,7 +4223,27 @@ STAGE PLANS:
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 13
+ Map 17
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 19
Map Operator Tree:
TableScan
alias: part
@@ -3724,27 +4275,75 @@ STAGE PLANS:
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 8
+ Map 9
Map Operator Tree:
TableScan
alias: part
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: p_size (type: int)
- outputColumnNames: p_size
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
- aggregations: max(p_size)
+ aggregations: count(p_partkey)
mode: hash
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Reducer 11
+ Reducer 10
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ 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: (sq_count_check(_col0) <= 1) (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 12
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
+ Reducer 14
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 15
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
@@ -3753,10 +4352,10 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col1
+ outputColumnNames: _col2
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: int)
+ expressions: _col2 (type: int)
outputColumnNames: _col0
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
@@ -3764,7 +4363,7 @@ STAGE PLANS:
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
TopN Hash Memory Usage: 0.1
- Reducer 12
+ Reducer 16
Execution mode: llap
Reduce Operator Tree:
Select Operator
@@ -3784,18 +4383,29 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: boolean)
- Reducer 14
+ Reducer 18
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: max(VALUE._col0)
+ aggregations: count(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int)
+ 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: (sq_count_check(_col0) <= 1) (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
Execution mode: llap
Reduce Operator Tree:
@@ -3813,6 +4423,18 @@ STAGE PLANS:
Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 26 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col1 (type: bigint), _col2 (type: bigint)
+ Reducer 20
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -3840,21 +4462,34 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col1
+ outputColumnNames: _col2
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: _col1 (type: int)
+ expressions: _col2 (type: int)
outputColumnNames: _col0
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col0 (type: int)
sort order: +
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
- Reducer 6
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Select Operator
@@ -3873,7 +4508,7 @@ STAGE PLANS:
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
+ Reducer 8
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3885,18 +4520,6 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: bigint), _col1 (type: bigint)
- Reducer 9
- Execution mode: llap
- Reduce Operator Tree:
- Group By Operator
- aggregations: max(VALUE._col0)
- mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int)
Stage: Stage-0
Fetch Operator
@@ -3904,9 +4527,11 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[50][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
-Warning: Shuffle Join MERGEJOIN[51][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[52][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 11' is a cross product
+Warning: Shuffle Join MERGEJOIN[85][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[86][tables = [$hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[87][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[88][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 14' is a cross product
+Warning: Shuffle Join MERGEJOIN[89][tables = [$hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 15' is a cross product
PREHOOK: query: select p_size, (p_size IN
(select (select max(p_size) from part) as sb from part order by sb limit 1)) = true
from part
@@ -3945,9 +4570,12 @@ POSTHOOK: Input: default@part
42 false
45 false
46 true
-Warning: Shuffle Join MERGEJOIN[37][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[38][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
-Warning: Shuffle Join MERGEJOIN[39][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[94][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[95][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[96][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[97][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product
+Warning: Shuffle Join MERGEJOIN[98][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5]] in Stage 'Reducer 6' is a cross product
+Warning: Shuffle Join MERGEJOIN[99][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4, $hdt$_5, $hdt$_6]] in Stage 'Reducer 7' is a cross product
PREHOOK: query: explain select case when (select count(*)
from part
where p_size between 1 and 20) > 409437
@@ -3979,12 +4607,18 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 8 (CUSTOM_SIMPLE_EDGE)
- Reducer 4 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
- Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 8 <- Map 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
+ Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE)
+ Reducer 15 <- Map 14 (CUSTOM_SIMPLE_EDGE)
+ Reducer 17 <- Map 16 (CUSTOM_SIMPLE_EDGE)
+ Reducer 19 <- Map 18 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 15 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Reducer 17 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Reducer 19 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -3999,7 +4633,7 @@ STAGE PLANS:
Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 5
+ Map 10
Map Operator Tree:
TableScan
alias: part
@@ -4020,7 +4654,26 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 12
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_partkey BETWEEN 1 AND 20 (type: boolean)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 14
Map Operator Tree:
TableScan
alias: part
@@ -4039,7 +4692,26 @@ STAGE PLANS:
value expressions: _col0 (type: struct<count:bigint,sum:double,input:int>)
Execution mode: llap
LLAP IO: no inputs
- Map 9
+ Map 16
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_partkey BETWEEN 10000 AND 20000 (type: boolean)
+ Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 18
Map Operator Tree:
TableScan
alias: part
@@ -4062,7 +4734,100 @@ STAGE PLANS:
value expressions: _col0 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Reducer 10
+ Map 8
+ Map Operator Tree:
+ TableScan
+ alias: part
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_size BETWEEN 1 AND 20 (type: boolean)
+ Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
+ Statistics: Num rows: 8 Data size: 64 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 11
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ 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 13
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ 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: (sq_count_check(_col0) <= 1) (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 15
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ mode: mergepartial
+ 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: double)
+ Reducer 17
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ 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: (sq_count_check(_col0) <= 1) (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 19
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -4079,16 +4844,14 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Outer Join0 to 1
+ Inner Join 0 to 1
keys:
0
1
- outputColumnNames: _col1
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
@@ -4098,13 +4861,58 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col1, _col2
+ outputColumnNames: _col2
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col2
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint)
+ Reducer 5
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col2, _col4
Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col1 (type: bigint), _col2 (type: double)
- Reducer 4
+ value expressions: _col2 (type: bigint), _col4 (type: double)
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col2, _col4
+ Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 416 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: bigint), _col4 (type: double)
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
@@ -4113,10 +4921,10 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col1, _col2, _col3
+ outputColumnNames: _col2, _col4, _col6
Statistics: Num rows: 26 Data size: 520 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- expressions: CASE WHEN ((_col1 > 409437)) THEN (_col2) ELSE (_col3) END (type: double)
+ expressions: CASE WHEN ((_col2 > 409437)) THEN (_col4) ELSE (_col6) END (type: double)
outputColumnNames: _col0
Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
@@ -4126,7 +4934,7 @@ STAGE PLANS:
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 6
+ Reducer 9
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -4134,22 +4942,21 @@ STAGE PLANS:
mode: mergepartial
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 8
- Execution mode: llap
- Reduce Op
<TRUNCATED>