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 06:08:44 UTC
[5/6] 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_scalar.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
index c8524df..b2b5458 100644
--- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
+++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out
@@ -75,7 +75,7 @@ POSTHOOK: Lineage: part_null.p_partkey EXPRESSION [(values__tmp__table__2)values
POSTHOOK: Lineage: part_null.p_retailprice EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col8, type:string, comment:), ]
POSTHOOK: Lineage: part_null.p_size EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col6, type:string, comment:), ]
POSTHOOK: Lineage: part_null.p_type SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ]
-Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where p_size > (select avg(p_size) from part_null)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size > (select avg(p_size) from part_null)
@@ -89,8 +89,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -114,6 +115,26 @@ STAGE PLANS:
alias: part_null
Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Select Operator
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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 5
+ Map Operator Tree:
+ TableScan
+ alias: part_null
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
expressions: p_size (type: int)
outputColumnNames: p_size
Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
@@ -134,21 +155,23 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
- Statistics: Num rows: 26 Data size: 18096 Basic stats: COMPLETE Column stats: NONE
+ 2
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
+ Statistics: Num rows: 26 Data size: 18304 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(_col5) > _col9) (type: boolean)
- Statistics: Num rows: 8 Data size: 5568 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(_col5) > _col10) (type: boolean)
+ Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 8 Data size: 5568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 8 Data size: 5568 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 8 Data size: 5632 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -157,6 +180,29 @@ STAGE PLANS:
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 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: avg(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
@@ -172,7 +218,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where p_size > (select avg(p_size) from part_null)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -652,7 +698,7 @@ POSTHOOK: Input: default@tnull
85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
-Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where (select max(p_name) from part_null) is not null
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where (select max(p_name) from part_null) is not null
@@ -666,8 +712,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -689,6 +736,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_null
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(p_partkey)
+ 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 5
+ Map Operator Tree:
+ TableScan
+ alias: part_null
Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: p_name (type: string)
@@ -711,14 +778,16 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
+ 2
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 26 Data size: 20904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 21112 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 20904 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 26 Data size: 21112 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -727,6 +796,29 @@ STAGE PLANS:
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 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: max(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
@@ -746,7 +838,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[15][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where (select max(p_name) from part_null) is not null
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -783,8 +875,10 @@ POSTHOOK: Input: default@part_null
85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
-Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[58][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[59][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product
PREHOOK: query: explain select * from part where p_size between (select min(p_size) from part) and (select avg(p_size) from part)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size between (select min(p_size) from part) and (select avg(p_size) from part)
@@ -798,10 +892,14 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- 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 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
+ Reducer 13 <- Map 12 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 5 <- Reducer 13 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -819,27 +917,27 @@ STAGE PLANS:
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 4
+ Map 10
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: min(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
- Map 6
+ Map 12
Map Operator Tree:
TableScan
alias: part
@@ -859,22 +957,127 @@ STAGE PLANS:
value expressions: _col0 (type: struct<count:bigint,sum:double,input:int>)
Execution mode: llap
LLAP IO: no inputs
+ Map 6
+ 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 8
+ 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: min(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
+ 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
+ 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 13
+ 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 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ 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
+ sort order:
+ 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), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
+ Reducer 3
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
sort order:
Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int)
- Reducer 3
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: int)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
+ Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col10 (type: int)
+ Reducer 5
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
@@ -883,10 +1086,10 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10, _col12
Statistics: Num rows: 26 Data size: 16406 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: UDFToDouble(_col5) BETWEEN UDFToDouble(_col9) AND _col10 (type: boolean)
+ predicate: UDFToDouble(_col5) BETWEEN UDFToDouble(_col10) AND _col12 (type: boolean)
Statistics: Num rows: 2 Data size: 1262 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -899,30 +1102,41 @@ 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 5
+ Reducer 7
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: min(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)
- Reducer 7
+ 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 9
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: avg(VALUE._col0)
+ aggregations: min(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 4 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)
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: int)
Stage: Stage-0
Fetch Operator
@@ -930,8 +1144,10 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[23][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-Warning: Shuffle Join MERGEJOIN[24][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[57][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[58][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[59][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product
PREHOOK: query: select * from part where p_size between (select min(p_size) from part) and (select avg(p_size) from part)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -1210,7 +1426,7 @@ Manufacturer#5 almond antique medium spring khaki 6
Manufacturer#5 almond antique sky peru orange 2
Manufacturer#5 almond aquamarine dodger light gainsboro 46
Manufacturer#5 almond azure blanched chiffon midnight 23
-Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part)
@@ -1224,8 +1440,9 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 4 (CUSTOM_SIMPLE_EDGE), Reducer 6 (CUSTOM_SIMPLE_EDGE)
Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1253,6 +1470,26 @@ STAGE PLANS:
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 5
+ 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: min(p_partkey)
mode: hash
outputColumnNames: _col0
@@ -1269,13 +1506,15 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ 2
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((_col0 * _col5) <> _col9) (type: boolean)
+ predicate: ((_col0 * _col5) <> _col10) (type: boolean)
Statistics: Num rows: 26 Data size: 16198 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
@@ -1292,6 +1531,29 @@ STAGE PLANS:
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 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: min(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
@@ -1307,7 +1569,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where (p_partkey*p_size) <> (select min(p_partkey) from part)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -1355,9 +1617,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1381,6 +1644,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part
+ Statistics: Num rows: 26 Data size: 3146 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: p_name is not null (type: boolean)
+ 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 6
+ Map Operator Tree:
+ TableScan
+ alias: part
Statistics: Num rows: 26 Data size: 3250 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: p_name is not null (type: boolean)
@@ -1405,16 +1688,18 @@ 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: 2 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: ((_col1 + 100) < CASE WHEN (_col3 is null) THEN (null) ELSE (_col2) END) (type: boolean)
- Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: ((_col1 + 100) < CASE WHEN (_col5 is null) THEN (null) ELSE (_col4) END) (type: boolean)
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
- Statistics: Num rows: 8 Data size: 96 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
aggregations: count()
mode: hash
@@ -1443,6 +1728,32 @@ 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: 1573 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: 1677 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 4 Data size: 516 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 4 Data size: 516 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: 516 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: max(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -1487,8 +1798,9 @@ 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
@@ -1512,6 +1824,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: part_null
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: p_type (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: part_null
Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: p_type is not null (type: boolean)
@@ -1536,21 +1868,23 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col4 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12
+ Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (UDFToDouble(_col5) > CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) (type: boolean)
- Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE
+ predicate: (UDFToDouble(_col5) > CASE WHEN (_col12 is null) THEN (null) ELSE (_col11) END) (type: boolean)
+ Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1559,6 +1893,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: avg(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -1592,7 +1952,8 @@ POSTHOOK: Input: default@part
POSTHOOK: Input: default@part_null
#### A masked pattern was here ####
192697 almond antique blue firebrick mint Manufacturer#5 Brand#52 MEDIUM BURNISHED TIN 31 LG DRUM 1789.69 ickly ir
-Warning: Shuffle Join MERGEJOIN[27][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: explain select * from part where p_size BETWEEN (select min(p_size) from part_null where part_null.p_type = part.p_type) AND (select max(p_size) from part_null)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size BETWEEN (select min(p_size) from part_null where part_null.p_type = part.p_type) AND (select max(p_size) from part_null)
@@ -1606,10 +1967,13 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
- Reducer 5 <- Map 4 (SIMPLE_EDGE)
- Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 10 <- Map 9 (CUSTOM_SIMPLE_EDGE)
+ Reducer 12 <- Map 11 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 10 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Reducer 12 (CUSTOM_SIMPLE_EDGE), Reducer 3 (CUSTOM_SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1629,7 +1993,47 @@ STAGE PLANS:
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 4
+ Map 11
+ Map Operator Tree:
+ TableScan
+ alias: part_null
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_size (type: int)
+ outputColumnNames: p_size
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: max(p_size)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: part_null
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: p_type (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 7
Map Operator Tree:
TableScan
alias: part_null
@@ -1651,67 +2055,145 @@ STAGE PLANS:
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 9
Map Operator Tree:
TableScan
alias: part_null
Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_size (type: int)
- outputColumnNames: p_size
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
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: NONE
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
+ 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
+ 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: 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 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: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col4 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12
+ Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col9 (type: int), _col10 (type: boolean)
+ Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: int), _col12 (type: boolean)
Reducer 3
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
+ Inner Join 0 to 1
+ keys:
+ 0
+ 1
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12
+ Statistics: Num rows: 57 Data size: 35919 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 57 Data size: 35919 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string), _col11 (type: int), _col12 (type: boolean)
+ Reducer 4
+ Execution mode: llap
+ Reduce Operator Tree:
+ Merge Join Operator
+ condition map:
Left Outer Join0 to 1
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col12
- Statistics: Num rows: 28 Data size: 17843 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12, _col15
+ Statistics: Num rows: 57 Data size: 36204 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col5 BETWEEN CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END AND _col12 (type: boolean)
- Statistics: Num rows: 3 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
+ predicate: _col5 BETWEEN CASE WHEN (_col12 is null) THEN (null) ELSE (_col11) END AND _col15 (type: boolean)
+ Statistics: Num rows: 6 Data size: 3810 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 3 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 3810 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 1911 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 3810 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
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Reducer 8
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -1730,18 +2212,6 @@ STAGE PLANS:
Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: boolean)
- Reducer 7
- 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: NONE
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: int)
Stage: Stage-0
Fetch Operator
@@ -1749,7 +2219,8 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[27][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[61][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 4' is a cross product
PREHOOK: query: select * from part where p_size BETWEEN (select min(p_size) from part_null where part_null.p_type = part.p_type) AND (select max(p_size) from part_null)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -1786,7 +2257,7 @@ POSTHOOK: Input: default@part_null
85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
-Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: explain select * from part where p_size >= (select min(p_size) from part_null where part_null.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null)
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_size >= (select min(p_size) from part_null where part_null.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null)
@@ -1800,10 +2271,12 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 11 <- Map 10 (CUSTOM_SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+ Reducer 3 <- Reducer 11 (CUSTOM_SIMPLE_EDGE), Reducer 2 (CUSTOM_SIMPLE_EDGE), Reducer 9 (CUSTOM_SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE)
- Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (CUSTOM_SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -1823,10 +2296,50 @@ STAGE PLANS:
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 10
+ Map Operator Tree:
+ TableScan
+ alias: part_null
+ Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: p_retailprice (type: double)
+ outputColumnNames: p_retailprice
+ Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: max(p_retailprice)
+ 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: double)
+ Execution mode: llap
+ LLAP IO: no inputs
Map 4
Map Operator Tree:
TableScan
alias: part_null
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: p_type is not null (type: boolean)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: p_type (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 32 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: part_null
Statistics: Num rows: 31 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: p_type is not null (type: boolean)
@@ -1845,47 +2358,61 @@ STAGE PLANS:
value expressions: _col1 (type: int)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 8
Map Operator Tree:
TableScan
alias: part_null
- Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: p_retailprice (type: double)
- outputColumnNames: p_retailprice
- Statistics: Num rows: 407 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
+ expressions: p_partkey (type: int)
+ outputColumnNames: p_partkey
+ Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: max(p_retailprice)
+ aggregations: count(p_partkey)
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: double)
+ value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
+ Reducer 11
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: max(VALUE._col0)
+ mode: mergepartial
+ 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: double)
Reducer 2
Execution mode: llap
Reduce Operator Tree:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col4 (type: string)
- 1 _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 28 Data size: 17703 Basic stats: COMPLETE Column stats: NONE
+ 1 _col0 (type: string)
+ 2 _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col11, _col12
+ Statistics: Num rows: 57 Data size: 35406 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col5 >= CASE WHEN (_col10 is null) THEN (null) ELSE (_col9) END) (type: boolean)
- Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col5 >= CASE WHEN (_col12 is null) THEN (null) ELSE (_col11) END) (type: boolean)
+ Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE
Reduce Output Operator
sort order:
- Statistics: Num rows: 9 Data size: 5690 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 19 Data size: 11802 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
Reducer 3
Execution mode: llap
@@ -1893,21 +2420,23 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12
- Statistics: Num rows: 9 Data size: 5771 Basic stats: COMPLETE Column stats: NONE
+ 2
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col15
+ Statistics: Num rows: 19 Data size: 12125 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (_col7 <= _col12) (type: boolean)
- Statistics: Num rows: 3 Data size: 1923 Basic stats: COMPLETE Column stats: NONE
+ predicate: (_col7 <= _col15) (type: boolean)
+ Statistics: Num rows: 6 Data size: 3828 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
- Statistics: Num rows: 3 Data size: 1923 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 3828 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 3 Data size: 1923 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 6 Data size: 3828 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1916,6 +2445,32 @@ STAGE PLANS:
Execution mode: llap
Reduce Operator Tree:
Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 16 Data size: 1628 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 8 Data size: 814 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (sq_count_check(_col1) <= 1) (type: boolean)
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 203 Basic stats: COMPLETE Column stats: NONE
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
aggregations: min(VALUE._col0)
keys: KEY._col0 (type: string)
mode: mergepartial
@@ -1931,18 +2486,29 @@ STAGE PLANS:
Map-reduce partition columns: _col2 (type: string)
Statistics: Num rows: 15 Data size: 1575 Basic stats: COMPLETE Column stats: NONE
value expressions: _col0 (type: int), _col1 (type: boolean)
- Reducer 7
+ Reducer 9
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: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
+ Select Operator
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: double)
+ 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
Stage: Stage-0
Fetch Operator
@@ -1950,7 +2516,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[29][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 3' is a cross product
+Warning: Shuffle Join MERGEJOIN[60][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 3' is a cross product
PREHOOK: query: select * from part where p_size >= (select min(p_size) from part_null where part_null.p_type = part.p_type) AND p_retailprice <= (select max(p_retailprice) from part_null)
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -1987,7 +2553,7 @@ POSTHOOK: Input: default@part_null
85768 almond antique chartreuse lavender yellow Manufacturer#1 Brand#12 LARGE BRUSHED STEEL 34 SM BAG 1753.76 refull
86428 almond aquamarine burnished black steel Manufacturer#1 Brand#12 STANDARD ANODIZED STEEL 28 WRAP BAG 1414.42 arefully
90681 almond antique chartreuse khaki white Manufacturer#3 Brand#31 MEDIUM BURNISHED TIN 17 SM CASE 1671.68 are slyly after the sl
-Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[46][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: explain select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340
PREHOOK: type: QUERY
POSTHOOK: query: explain select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340
@@ -2001,10 +2567,11 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE)
- Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE), Reducer 5 (CUSTOM_SIMPLE_EDGE), Reducer 7 (CUSTOM_SIMPLE_EDGE)
+ Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (CUSTOM_SIMPLE_EDGE)
- Reducer 7 <- Map 6 (SIMPLE_EDGE)
+ Reducer 7 <- Map 6 (CUSTOM_SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (SIMPLE_EDGE)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2029,6 +2596,26 @@ STAGE PLANS:
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
Statistics: Num rows: 26 Data size: 2392 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: p_brand (type: string)
@@ -2045,7 +2632,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 8
Map Operator Tree:
TableScan
alias: p
@@ -2071,13 +2658,15 @@ STAGE PLANS:
Merge Join Operator
condition map:
Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9
+ 2
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col10
Statistics: Num rows: 26 Data size: 20878 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (_col3 <> _col9) (type: boolean)
+ predicate: (_col3 <> _col10) (type: boolean)
Statistics: Num rows: 26 Data size: 20878 Basic stats: COMPLETE Column stats: COMPLETE
Reduce Output Operator
key expressions: _col4 (type: string), _col5 (type: int)
@@ -2107,6 +2696,29 @@ STAGE PLANS:
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
aggregations: min(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
@@ -2115,7 +2727,7 @@ STAGE PLANS:
sort order:
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
value expressions: _col0 (type: string)
- Reducer 7
+ Reducer 9
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -2139,7 +2751,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join MERGEJOIN[30][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
+Warning: Shuffle Join MERGEJOIN[46][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Reducer 2' is a cross product
PREHOOK: query: select * from part where p_brand <> (select min(p_brand) from part ) AND p_size IN (select (p_size) from part p where p.p_type = part.p_type ) AND p_size <> 340
PREHOOK: type: QUERY
PREHOOK: Input: default@part
@@ -2184,8 +2796,9 @@ 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
@@ -2209,6 +2822,26 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: p
+ Statistics: Num rows: 26 Data size: 208 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ((p_size = p_size) and (p_partkey = p_partkey)) (type: boolean)
+ Statistics: Num rows: 6 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: p_partkey (type: int), p_size (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: int)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
+ Statistics: Num rows: 3 Data size: 24 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: 3354 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
predicate: ((p_size = p_size) and (p_partkey = p_partkey)) (type: boolean)
@@ -2233,21 +2866,23 @@ STAGE PLANS:
Merge Join Operator
condition map:
Left Outer Join0 to 1
+ Left Outer Join0 to 2
keys:
0 _col0 (type: int), _col5 (type: int)
- 1 _col2 (type: int), _col3 (type: int)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10
- Statistics: Num rows: 26 Data size: 16406 Basic stats: COMPLETE Column stats: COMPLETE
+ 1 _col0 (type: int), _col1 (type: int)
+ 2 _col2 (type: int), _col3 (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col12, _col13
+ Statistics: Num rows: 1 Data size: 631 Basic stats: COMPLETE Column stats: COMPLETE
Filter Operator
- predicate: (UDFToLong(_col5) <> CASE WHEN (_col10 is null) THEN (0) ELSE (_col9) END) (type: boolean)
- Statistics: Num rows: 26 Data size: 16406 Basic stats: COMPLETE Column stats: COMPLETE
+ predicate: (UDFToLong(_col5) <> CASE WHEN (_col13 is null) THEN (0) ELSE (_col12) END) (type: boolean)
+ Statistics: Num rows: 1 Data size: 631 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: string), _col7 (type: double), _col8 (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
+ Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE
File Output Operator
compressed: false
- Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE
+ Statistics: Num rows: 1 Data size: 619 Basic stats: COMPLETE Column stats: COMPLETE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apa
<TRUNCATED>