You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by ha...@apache.org on 2016/12/16 18:28:30 UTC
[17/21] hive git commit: HIVE-15192 : Use Calcite to de-correlate and
plan subqueries (Vineet Garg via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/queries/clientpositive/subquery_notin_having.q
----------------------------------------------------------------------
diff --git a/ql/src/test/queries/clientpositive/subquery_notin_having.q b/ql/src/test/queries/clientpositive/subquery_notin_having.q
index 05148df..2cd0bec 100644
--- a/ql/src/test/queries/clientpositive/subquery_notin_having.q
+++ b/ql/src/test/queries/clientpositive/subquery_notin_having.q
@@ -56,3 +56,19 @@ having b.p_mfgr not in
having max(p_retailprice) - min(p_retailprice) > 600
)
;
+
+--nullability tests
+CREATE TABLE t1 (c1 INT, c2 CHAR(100));
+INSERT INTO t1 VALUES (null,null), (1,''), (2,'abcde'), (100,'abcdefghij');
+
+CREATE TABLE t2 (c1 INT);
+INSERT INTO t2 VALUES (null), (2), (100);
+
+explain SELECT c1 FROM t1 group by c1 having c1 NOT IN (SELECT c1 FROM t2);
+SELECT c1 FROM t1 group by c1 having c1 NOT IN (SELECT c1 FROM t2);
+
+explain SELECT c1 FROM t1 group by c1 having c1 NOT IN (SELECT c1 FROM t2 where t1.c1=t2.c1);
+SELECT c1 FROM t1 group by c1 having c1 NOT IN (SELECT c1 FROM t2 where t1.c1=t2.c1);
+
+DROP TABLE t1;
+DROP TABLE t2;
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_corr_from.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_corr_from.q.out b/ql/src/test/results/clientnegative/subquery_corr_from.q.out
new file mode 100644
index 0000000..663a8bb
--- /dev/null
+++ b/ql/src/test/results/clientnegative/subquery_corr_from.q.out
@@ -0,0 +1 @@
+FAILED: SemanticException [Error 10004]: Line 3:113 Invalid table alias or column reference 'po': (possible column names are: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment)
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_corr_grandparent.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_corr_grandparent.q.out b/ql/src/test/results/clientnegative/subquery_corr_grandparent.q.out
new file mode 100644
index 0000000..fb72270
--- /dev/null
+++ b/ql/src/test/results/clientnegative/subquery_corr_grandparent.q.out
@@ -0,0 +1 @@
+FAILED: SemanticException [Error 10249]: Line 4:53 Unsupported SubQuery Expression 'p_name': SubQuery expression refers to both Parent and SubQuery expressions and is not a valid join condition.
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_corr_select.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_corr_select.q.out b/ql/src/test/results/clientnegative/subquery_corr_select.q.out
new file mode 100644
index 0000000..1f3dbb7
--- /dev/null
+++ b/ql/src/test/results/clientnegative/subquery_corr_select.q.out
@@ -0,0 +1 @@
+FAILED: SemanticException [Error 10004]: Line 2:54 Invalid table alias or column reference 'po': (possible column names are: p_partkey, p_name, p_mfgr, p_brand, p_type, p_size, p_container, p_retailprice, p_comment)
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_in_groupby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_in_groupby.q.out b/ql/src/test/results/clientnegative/subquery_in_groupby.q.out
index 809bb0a..a546d49 100644
--- a/ql/src/test/results/clientnegative/subquery_in_groupby.q.out
+++ b/ql/src/test/results/clientnegative/subquery_in_groupby.q.out
@@ -1 +1 @@
-FAILED: SemanticException [Error 10249]: Line 5:37 Unsupported SubQuery Expression ''9'': Currently SubQuery expressions are only allowed as Where Clause predicates
+FAILED: SemanticException [Error 10249]: Unsupported SubQuery Expression Currently SubQuery expressions are only allowed as Where and Having Clause predicates
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_in_select.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_in_select.q.out b/ql/src/test/results/clientnegative/subquery_in_select.q.out
index 3d74132..a546d49 100644
--- a/ql/src/test/results/clientnegative/subquery_in_select.q.out
+++ b/ql/src/test/results/clientnegative/subquery_in_select.q.out
@@ -1 +1 @@
-FAILED: SemanticException [Error 10249]: Line 4:35 Unsupported SubQuery Expression ''9'': Currently SubQuery expressions are only allowed as Where Clause predicates
+FAILED: SemanticException [Error 10249]: Unsupported SubQuery Expression Currently SubQuery expressions are only allowed as Where and Having Clause predicates
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_nested_subquery.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_nested_subquery.q.out b/ql/src/test/results/clientnegative/subquery_nested_subquery.q.out
deleted file mode 100644
index 140b093..0000000
--- a/ql/src/test/results/clientnegative/subquery_nested_subquery.q.out
+++ /dev/null
@@ -1 +0,0 @@
-FAILED: SemanticException [Error 10249]: Line 3:53 Unsupported SubQuery Expression 'p_name': Nested SubQuery expressions are not supported.
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientnegative/subquery_restrictions.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientnegative/subquery_restrictions.q.out b/ql/src/test/results/clientnegative/subquery_restrictions.q.out
new file mode 100644
index 0000000..a546d49
--- /dev/null
+++ b/ql/src/test/results/clientnegative/subquery_restrictions.q.out
@@ -0,0 +1 @@
+FAILED: SemanticException [Error 10249]: Unsupported SubQuery Expression Currently SubQuery expressions are only allowed as Where and Having Clause predicates
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/constant_prop_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/constant_prop_3.q.out b/ql/src/test/results/clientpositive/constant_prop_3.q.out
index 58f1065..066ed07 100644
--- a/ql/src/test/results/clientpositive/constant_prop_3.q.out
+++ b/ql/src/test/results/clientpositive/constant_prop_3.q.out
@@ -88,7 +88,7 @@ POSTHOOK: query: analyze table supplier_hive compute statistics for columns
POSTHOOK: type: QUERY
POSTHOOK: Input: default@supplier_hive
#### A masked pattern was here ####
-Warning: Shuffle Join JOIN[23][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[26][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product
PREHOOK: query: explain select
p_brand,
p_type,
@@ -154,10 +154,11 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1, Stage-7
- Stage-3 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-2, Stage-8
Stage-4 depends on stages: Stage-3
Stage-5 depends on stages: Stage-4
Stage-7 is a root stage
+ Stage-8 is a root stage
Stage-0 depends on stages: Stage-5
STAGE PLANS:
@@ -223,7 +224,8 @@ STAGE PLANS:
TableScan
Reduce Output Operator
sort order:
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
Reduce Operator Tree:
Join Operator
condition map:
@@ -231,8 +233,8 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col1, _col3, _col4, _col5
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -248,23 +250,15 @@ STAGE PLANS:
key expressions: _col1 (type: int)
sort order: +
Map-reduce partition columns: _col1 (type: int)
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col3 (type: string), _col4 (type: string), _col5 (type: int)
+ Statistics: Num rows: 1 Data size: 17 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col3 (type: string), _col4 (type: string), _col5 (type: int), _col6 (type: bigint), _col7 (type: bigint)
TableScan
- alias: supplier_hive
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Filter Operator
- predicate: (s_comment like '%Customer%Complaints%') (type: boolean)
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Select Operator
- expressions: s_suppkey (type: int)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: int)
- sort order: +
- Map-reduce partition columns: _col0 (type: int)
- Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ value expressions: _col1 (type: boolean)
Reduce Operator Tree:
Join Operator
condition map:
@@ -272,21 +266,21 @@ STAGE PLANS:
keys:
0 _col1 (type: int)
1 _col0 (type: int)
- outputColumnNames: _col1, _col3, _col4, _col5, _col7
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col9
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: _col7 is null (type: boolean)
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ predicate: ((_col6 = 0) or (_col9 is null and _col1 is not null and (_col7 >= _col6))) (type: boolean)
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: _col3 (type: string), _col4 (type: string), _col5 (type: int), _col1 (type: int)
outputColumnNames: _col3, _col4, _col5, _col1
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: count(DISTINCT _col1)
keys: _col3 (type: string), _col4 (type: string), _col5 (type: int), _col1 (type: int)
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -302,14 +296,14 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int), _col3 (type: int)
sort order: ++++
Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: int)
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Group By Operator
aggregations: count(DISTINCT KEY._col3:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: int)
mode: mergepartial
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
table:
@@ -324,15 +318,15 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col3 (type: bigint), _col0 (type: string), _col1 (type: string), _col2 (type: int)
sort order: -+++
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: int), KEY.reducesinkkey0 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- Statistics: Num rows: 1 Data size: 9 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
table:
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -345,36 +339,69 @@ STAGE PLANS:
alias: supplier_hive
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Filter Operator
- predicate: ((s_comment like '%Customer%Complaints%') and s_suppkey is null) (type: boolean)
+ predicate: (s_comment like '%Customer%Complaints%') (type: boolean)
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Select Operator
+ expressions: s_suppkey (type: int)
+ outputColumnNames: s_suppkey
Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
Group By Operator
- aggregations: count()
+ aggregations: count(), count(s_suppkey)
mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 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)
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint)
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(VALUE._col0), count(VALUE._col1)
mode: mergepartial
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: (_col0 = 0) (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
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-8
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: supplier_hive
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Filter Operator
+ predicate: (s_comment like '%Customer%Complaints%') (type: boolean)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Select Operator
+ expressions: s_suppkey (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int), true (type: boolean)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int), _col1 (type: boolean)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: int), _col1 (type: boolean)
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: boolean)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/constprog_partitioner.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/constprog_partitioner.q.out b/ql/src/test/results/clientpositive/constprog_partitioner.q.out
index d1016ad..d4ccb8c 100644
--- a/ql/src/test/results/clientpositive/constprog_partitioner.q.out
+++ b/ql/src/test/results/clientpositive/constprog_partitioner.q.out
@@ -80,10 +80,114 @@ WHERE li.l_linenumber = 1 AND
li.l_orderkey IN (SELECT l_orderkey FROM lineitem WHERE l_shipmode = 'AIR' AND l_linenumber = li.l_linenumber)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-2 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
STAGE PLANS:
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: li
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: l_linenumber (type: int)
+ outputColumnNames: l_linenumber
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: l_linenumber (type: int)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-2
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ alias: lineitem
+ Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (l_shipmode = 'AIR') (type: boolean)
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: l_orderkey (type: int), l_linenumber (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int)
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col3
+ Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: _col0 (type: int), _col3 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ 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: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: int), KEY._col1 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 3239 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
Stage: Stage-1
Map Reduce
Map Operator Tree:
@@ -91,7 +195,7 @@ STAGE PLANS:
alias: li
Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: ((l_linenumber = 1) and l_orderkey is not null) (type: boolean)
+ predicate: (l_linenumber = 1) (type: boolean)
Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: l_orderkey (type: int), l_partkey (type: int), l_suppkey (type: int)
@@ -104,29 +208,15 @@ STAGE PLANS:
Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
value expressions: _col1 (type: int), _col2 (type: int)
TableScan
- alias: lineitem
- Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
- Filter Operator
- predicate: ((l_shipmode = 'AIR') and (l_linenumber = 1) and l_orderkey is not null) (type: boolean)
- Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: l_orderkey (type: int), 1 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- keys: _col0 (type: int), _col1 (type: int)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
- 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: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
+ 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: 27 Data size: 3239 Basic stats: COMPLETE Column stats: NONE
Reduce Operator Tree:
Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: int), 1 (type: int)
1 _col0 (type: int), _col1 (type: int)
http://git-wip-us.apache.org/repos/asf/hive/blob/382dc208/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
index f993cf0..d3acbcd 100644
--- a/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/llap/dynamic_partition_pruning.q.out
@@ -3297,17 +3297,17 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 6 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE), Union 6 (CONTAINS)
- Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 6 (CONTAINS)
+ Reducer 7 <- Union 6 (SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 6 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
@@ -3340,7 +3340,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 8
Map Operator Tree:
TableScan
alias: srcpart
@@ -3365,7 +3365,7 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -3402,35 +3402,45 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
+ Dynamic Partitioning Event Operator
+ Target column: ds (string)
+ Target Input: srcpart
+ Partition key expr: ds
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Reducer 8
+ Target Vertex: Map 1
+ Reducer 9
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3438,34 +3448,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
Union 6
Vertex: Union 6
@@ -3505,17 +3497,17 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 6 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
Reducer 5 <- Map 4 (SIMPLE_EDGE), Union 6 (CONTAINS)
- Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 6 (CONTAINS)
+ Reducer 7 <- Union 6 (SIMPLE_EDGE)
+ Reducer 9 <- Map 8 (SIMPLE_EDGE), Union 6 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
@@ -3548,7 +3540,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 7
+ Map 8
Map Operator Tree:
TableScan
alias: srcpart
@@ -3573,7 +3565,7 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -3612,35 +3604,45 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 7
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
+ Dynamic Partitioning Event Operator
+ Target column: ds (string)
+ Target Input: srcpart
+ Partition key expr: ds
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Reducer 8
+ Target Vertex: Map 1
+ Reducer 9
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -3648,34 +3650,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
Union 6
Vertex: Union 6
@@ -3716,9 +3700,10 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 9 (CONTAINS)
+ Reducer 10 <- Union 9 (SIMPLE_EDGE)
+ Reducer 12 <- Map 11 (SIMPLE_EDGE), Union 9 (CONTAINS)
Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS)
- Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 9 (SIMPLE_EDGE)
+ Reducer 4 <- Reducer 10 (SIMPLE_EDGE), Union 3 (SIMPLE_EDGE)
Reducer 6 <- Map 5 (SIMPLE_EDGE), Union 3 (CONTAINS)
Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 9 (CONTAINS)
#### A masked pattern was here ####
@@ -3727,7 +3712,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: ds (type: string)
@@ -3741,7 +3725,7 @@ STAGE PLANS:
Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 10
+ Map 11
Map Operator Tree:
TableScan
alias: srcpart
@@ -3765,7 +3749,6 @@ STAGE PLANS:
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: ds (type: string)
@@ -3799,57 +3782,67 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Reducer 11
+ Reducer 10
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: min(VALUE._col0)
+ keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
+ Dynamic Partitioning Event Operator
+ Target column: ds (string)
+ Target Input: srcpart
+ Partition key expr: ds
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
+ Target Vertex: Map 1
+ Select Operator
+ expressions: _col0 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Dynamic Partitioning Event Operator
+ Target column: ds (string)
+ Target Input: srcpart
+ Partition key expr: ds
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 5
+ Target Vertex: Map 5
+ Reducer 12
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -3868,7 +3861,7 @@ STAGE PLANS:
Reduce Operator Tree:
Merge Join Operator
condition map:
- Left Semi Join 0 to 1
+ Inner Join 0 to 1
keys:
0 _col0 (type: string)
1 _col0 (type: string)
@@ -3902,49 +3895,16 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 5
Union 3
Vertex: Union 3
Union 9
@@ -5688,45 +5648,29 @@ STAGE PLANS:
Tez
#### A masked pattern was here ####
Edges:
- Map 1 <- Union 5 (BROADCAST_EDGE)
- Reducer 2 <- Map 1 (SIMPLE_EDGE)
- Reducer 4 <- Map 3 (SIMPLE_EDGE), Union 5 (CONTAINS)
- Reducer 7 <- Map 6 (SIMPLE_EDGE), Union 5 (CONTAINS)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE), Union 4 (CONTAINS)
+ Reducer 5 <- Map 1 (BROADCAST_EDGE), Union 4 (SIMPLE_EDGE)
+ Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
+ Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 4 (CONTAINS)
#### A masked pattern was here ####
Vertices:
Map 1
Map Operator Tree:
TableScan
alias: srcpart
- filterExpr: ds is not null (type: boolean)
Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE
Select Operator
expressions: ds (type: string)
outputColumnNames: _col0
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
- Map Join Operator
- condition map:
- Left Semi Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0
- input vertices:
- 1 Union 5
- Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 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: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
- Map 3
+ Map 2
Map Operator Tree:
TableScan
alias: srcpart
@@ -5746,7 +5690,7 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Map 6
+ Map 7
Map Operator Tree:
TableScan
alias: srcpart
@@ -5766,32 +5710,42 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
- Reducer 2
+ Reducer 3
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- keys: KEY._col0 (type: string)
+ aggregations: max(VALUE._col0)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- File Output Operator
- compressed: false
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 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
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 5
Execution mode: llap
Reduce Operator Tree:
Group By Operator
- aggregations: max(VALUE._col0)
+ keys: KEY._col0 (type: string)
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0
+ input vertices:
+ 0 Map 1
+ Statistics: Num rows: 1000 Data size: 184000 Basic stats: COMPLETE Column stats: COMPLETE
Group By Operator
keys: _col0 (type: string)
mode: hash
@@ -5802,22 +5756,22 @@ STAGE PLANS:
sort order: +
Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Reducer 7
+ Reducer 6
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 184 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 8
Execution mode: llap
Reduce Operator Tree:
Group By Operator
@@ -5825,36 +5779,18 @@ STAGE PLANS:
mode: mergepartial
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Filter Operator
- predicate: _col0 is not null (type: boolean)
+ Group By Operator
+ keys: _col0 (type: string)
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Reduce Output Operator
- key expressions: _col0 (type: string)
- sort order: +
- Map-reduce partition columns: _col0 (type: string)
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Select Operator
- expressions: _col0 (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Group By Operator
- keys: _col0 (type: string)
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Dynamic Partitioning Event Operator
- Target column: ds (string)
- Target Input: srcpart
- Partition key expr: ds
- Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
- Target Vertex: Map 1
- Union 5
- Vertex: Union 5
+ Union 4
+ Vertex: Union 4
Stage: Stage-0
Fetch Operator