You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2015/11/20 23:32:47 UTC
[20/51] [partial] hive git commit: HIVE-12017: Do not disable CBO by
default when number of joins in a query is equal or less than 1 (Jesus
Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/multiMapJoin2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/multiMapJoin2.q.out b/ql/src/test/results/clientpositive/multiMapJoin2.q.out
index 46b717f..dee81c2 100644
--- a/ql/src/test/results/clientpositive/multiMapJoin2.q.out
+++ b/ql/src/test/results/clientpositive/multiMapJoin2.q.out
@@ -2079,21 +2079,25 @@ STAGE PLANS:
Stage: Stage-5
Map Reduce Local Work
Alias -> Map Local Tables:
- y
+ $hdt$_1:y
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- y
+ $hdt$_1:y
TableScan
alias: y
Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 key (type: string)
- 1 key (type: string)
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
Stage: Stage-2
Map Reduce
@@ -2104,22 +2108,26 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 63 Data size: 635 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- Statistics: Num rows: 69 Data size: 698 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count()
- mode: hash
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- sort order:
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 63 Data size: 635 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ Statistics: Num rows: 69 Data size: 698 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: bigint)
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
Local Work:
Map Reduce Local Work
Reduce Operator Tree:
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/multi_join_union.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/multi_join_union.q.out b/ql/src/test/results/clientpositive/multi_join_union.q.out
index 466f34b..76c837f 100644
--- a/ql/src/test/results/clientpositive/multi_join_union.q.out
+++ b/ql/src/test/results/clientpositive/multi_join_union.q.out
@@ -53,36 +53,40 @@ src12 b ON (a.key = b.key) JOIN
(SELECT * FROM (SELECT * FROM src13 UNION ALL SELECT * FROM src14)a )c ON c.value = b.value
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-7 is a root stage
- Stage-5 depends on stages: Stage-7
- Stage-0 depends on stages: Stage-5
+ Stage-8 is a root stage
+ Stage-6 depends on stages: Stage-8
+ Stage-0 depends on stages: Stage-6
STAGE PLANS:
- Stage: Stage-7
+ Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
- a
+ $hdt$_0:a
Fetch Operator
limit: -1
- c-subquery1:a-subquery1:src13
+ $hdt$_2-subquery1:$hdt$_2-subquery1:src13
Fetch Operator
limit: -1
- c-subquery2:a-subquery2:src14
+ $hdt$_2-subquery2:$hdt$_2-subquery2:src14
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- a
+ $hdt$_0:a
TableScan
alias: a
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 key (type: string)
- 1 key (type: string)
- c-subquery1:a-subquery1:src13
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ $hdt$_2-subquery1:$hdt$_2-subquery1:src13
TableScan
alias: src13
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -97,9 +101,9 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
- 0 _col6 (type: string)
+ 0 _col3 (type: string)
1 _col1 (type: string)
- c-subquery2:a-subquery2:src14
+ $hdt$_2-subquery2:$hdt$_2-subquery2:src14
TableScan
alias: src14
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -114,10 +118,10 @@ STAGE PLANS:
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
HashTable Sink Operator
keys:
- 0 _col6 (type: string)
+ 0 _col3 (type: string)
1 _col1 (type: string)
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -126,24 +130,24 @@ STAGE PLANS:
Filter Operator
predicate: (key is not null and value is not null) (type: boolean)
Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: string)
- 1 key (type: string)
- outputColumnNames: _col0, _col1, _col5, _col6
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col6 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/orc_llap.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/orc_llap.q.out b/ql/src/test/results/clientpositive/orc_llap.q.out
index 79c6281..d0b07a0 100644
--- a/ql/src/test/results/clientpositive/orc_llap.q.out
+++ b/ql/src/test/results/clientpositive/orc_llap.q.out
@@ -550,52 +550,60 @@ STAGE PLANS:
Stage: Stage-4
Map Reduce Local Work
Alias -> Map Local Tables:
- o1
+ $hdt$_0:o1
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- o1
+ $hdt$_0:o1
TableScan
alias: o1
- filterExpr: (csmallint is not null and cbigint is not null) (type: boolean)
+ filterExpr: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint is not null and cbigint is not null) (type: boolean)
+ predicate: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 30720 Data size: 7269985 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 csmallint (type: smallint)
- 1 csmallint (type: smallint)
+ Select Operator
+ expressions: csmallint (type: smallint), cstring1 (type: string)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 30720 Data size: 7269985 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: smallint)
+ 1 _col0 (type: smallint)
Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
- alias: o2
- filterExpr: (csmallint is not null and cbigint is not null) (type: boolean)
+ alias: o1
+ filterExpr: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 122880 Data size: 29079940 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint is not null and cbigint is not null) (type: boolean)
+ predicate: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 30720 Data size: 7269985 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 csmallint (type: smallint)
- 1 csmallint (type: smallint)
- outputColumnNames: _col6, _col22
- Statistics: Num rows: 33792 Data size: 7996983 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col6 (type: string), _col22 (type: string)
- outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: csmallint (type: smallint), cstring2 (type: string)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 30720 Data size: 7269985 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: smallint)
+ 1 _col0 (type: smallint)
+ outputColumnNames: _col2, _col5
Statistics: Num rows: 33792 Data size: 7996983 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Select Operator
+ expressions: _col2 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 33792 Data size: 7996983 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 33792 Data size: 7996983 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Execution mode: vectorized
LLAP IO: all inputs
Local Work:
@@ -983,52 +991,60 @@ STAGE PLANS:
Stage: Stage-4
Map Reduce Local Work
Alias -> Map Local Tables:
- o1
+ $hdt$_0:o1
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- o1
+ $hdt$_0:o1
TableScan
alias: o1
- filterExpr: (csmallint is not null and cbigint is not null) (type: boolean)
+ filterExpr: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 14226 Data size: 1593339 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint is not null and cbigint is not null) (type: boolean)
+ predicate: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 3557 Data size: 398390 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 csmallint (type: smallint)
- 1 csmallint (type: smallint)
+ Select Operator
+ expressions: csmallint (type: smallint), cstring1 (type: string)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 3557 Data size: 398390 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: smallint)
+ 1 _col0 (type: smallint)
Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
- alias: o2
- filterExpr: (csmallint is not null and cbigint is not null) (type: boolean)
+ alias: o1
+ filterExpr: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 14226 Data size: 1593339 Basic stats: COMPLETE Column stats: NONE
Filter Operator
- predicate: (csmallint is not null and cbigint is not null) (type: boolean)
+ predicate: (cbigint is not null and csmallint is not null) (type: boolean)
Statistics: Num rows: 3557 Data size: 398390 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 csmallint (type: smallint)
- 1 csmallint (type: smallint)
- outputColumnNames: _col6, _col22
- Statistics: Num rows: 3912 Data size: 438229 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col6 (type: string), _col22 (type: string)
- outputColumnNames: _col0, _col1
+ Select Operator
+ expressions: csmallint (type: smallint), cstring2 (type: string)
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 3557 Data size: 398390 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: smallint)
+ 1 _col0 (type: smallint)
+ outputColumnNames: _col2, _col5
Statistics: Num rows: 3912 Data size: 438229 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Select Operator
+ expressions: _col2 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 3912 Data size: 438229 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3912 Data size: 438229 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Execution mode: vectorized
LLAP IO: all inputs
Local Work:
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/parallel_join1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/parallel_join1.q.out b/ql/src/test/results/clientpositive/parallel_join1.q.out
index 9ce2646..761c85e 100644
--- a/ql/src/test/results/clientpositive/parallel_join1.q.out
+++ b/ql/src/test/results/clientpositive/parallel_join1.q.out
@@ -34,15 +34,14 @@ STAGE PLANS:
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: string)
TableScan
alias: src1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -50,14 +49,15 @@ STAGE PLANS:
predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
@@ -65,10 +65,10 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col1, _col2
+ outputColumnNames: _col0, _col2
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: UDFToInteger(_col2) (type: int), _col1 (type: string)
+ expressions: UDFToInteger(_col0) (type: int), _col2 (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
File Output Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/parquet_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/parquet_join.q.out b/ql/src/test/results/clientpositive/parquet_join.q.out
index f880d1d..a9629dc 100644
--- a/ql/src/test/results/clientpositive/parquet_join.q.out
+++ b/ql/src/test/results/clientpositive/parquet_join.q.out
@@ -82,34 +82,42 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 2 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: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
TableScan
alias: p2
Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), myvalue (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- value expressions: myvalue (type: string)
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col7
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col7 (type: string)
+ expressions: _col2 (type: string)
outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -163,21 +171,25 @@ STAGE PLANS:
Stage: Stage-4
Map Reduce Local Work
Alias -> Map Local Tables:
- p1
+ $hdt$_0:p1
Fetch Operator
limit: -1
Alias -> Map Local Operator Tree:
- p1
+ $hdt$_0:p1
TableScan
alias: p1
Statistics: Num rows: 2 Data size: 4 Basic stats: COMPLETE Column stats: NONE
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
- HashTable Sink Operator
- keys:
- 0 key (type: int)
- 1 key (type: int)
+ Select Operator
+ expressions: key (type: int)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ HashTable Sink Operator
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
Stage: Stage-3
Map Reduce
@@ -188,25 +200,29 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col7
- Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col7 (type: string)
- outputColumnNames: _col0
+ Select Operator
+ expressions: key (type: int), myvalue (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col2
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
+ Select Operator
+ expressions: _col2 (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 2 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Local Work:
Map Reduce Local Work
@@ -287,22 +303,26 @@ STAGE PLANS:
Filter Operator
predicate: key is not null (type: boolean)
Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
- Sorted Merge Bucket Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col1, _col7
- Select Operator
- expressions: _col1 (type: string), _col7 (type: string)
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Select Operator
+ expressions: key (type: int), value2 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE
+ Sorted Merge Bucket Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col1, _col3
+ Select Operator
+ expressions: _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/pcr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out
index 7ba9f87..82dc31e 100644
--- a/ql/src/test/results/clientpositive/pcr.q.out
+++ b/ql/src/test/results/clientpositive/pcr.q.out
@@ -2712,30 +2712,38 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -2785,38 +2793,34 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds=2000-04-08 [t1, t2]
+ /pcr_t1/ds=2000-04-08 [$hdt$_0:t1, $hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col6, _col7
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4
Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col3,_col4
- columns.types int,string,int,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -3010,30 +3014,38 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -3128,39 +3140,35 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds=2000-04-08 [t1]
- /pcr_t1/ds=2000-04-09 [t2]
+ /pcr_t1/ds=2000-04-08 [$hdt$_0:t1]
+ /pcr_t1/ds=2000-04-09 [$hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col6, _col7
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4
Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col3,_col4
- columns.types int,string,int,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/pointlookup2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/pointlookup2.q.out b/ql/src/test/results/clientpositive/pointlookup2.q.out
index d677327..b6270b3 100644
--- a/ql/src/test/results/clientpositive/pointlookup2.q.out
+++ b/ql/src/test/results/clientpositive/pointlookup2.q.out
@@ -388,30 +388,38 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -461,38 +469,34 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds=2000-04-08 [t1, t2]
+ /pcr_t1/ds=2000-04-08 [$hdt$_0:t1, $hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col6, _col7
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4
Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col3,_col4
- columns.types int,string,int,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -646,30 +650,38 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -764,39 +776,35 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds=2000-04-08 [t1]
- /pcr_t1/ds=2000-04-09 [t2]
+ /pcr_t1/ds=2000-04-08 [$hdt$_0:t1]
+ /pcr_t1/ds=2000-04-09 [$hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col6, _col7
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4
Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col6 (type: int), _col7 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4
- Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col3,_col4
- columns.types int,string,int,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4
+ columns.types int,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -870,7 +878,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[4][tables = [t1, t2]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain extended
select *
from pcr_t1 t1 join pcr_t2 t2
@@ -962,22 +970,38 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: key (type: int), value (type: string), ds (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean)
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ auto parallelism: false
TableScan
alias: t2
Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- sort order:
+ Filter Operator
+ isSamplingPred: false
+ predicate: (key) IN (1, 2) (type: boolean)
Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: ds (type: string), key (type: int), value (type: string)
- auto parallelism: false
+ Select Operator
+ expressions: ds (type: string), key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -1116,9 +1140,9 @@ STAGE PLANS:
name: default.pcr_t2
name: default.pcr_t2
Truncated Path -> Alias:
- /pcr_t1/ds=2000-04-08 [t1]
- /pcr_t1/ds=2000-04-09 [t1]
- /pcr_t2 [t2]
+ /pcr_t1/ds=2000-04-08 [$hdt$_0:t1]
+ /pcr_t1/ds=2000-04-09 [$hdt$_0:t1]
+ /pcr_t2 [$hdt$_1:t2]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
@@ -1127,33 +1151,29 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col8
- Statistics: Num rows: 44 Data size: 352 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: (struct(_col7,_col2)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
- Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4,_col5
- columns.types int,string,string,string,int,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ predicate: (struct(_col4,_col2)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -1163,7 +1183,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
auto parallelism: false
@@ -1197,13 +1217,13 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1227,7 +1247,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[4][tables = [t1, t2]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain extended
select *
from pcr_t1 t1 join pcr_t2 t2
@@ -1319,22 +1339,38 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: key (type: int), value (type: string), ds (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (key) IN (1, 2) (type: boolean)
+ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string), ds (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ auto parallelism: false
TableScan
alias: t2
Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- sort order:
+ Filter Operator
+ isSamplingPred: false
+ predicate: (ds) IN ('2000-04-08', '2000-04-09') (type: boolean)
Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: ds (type: string), key (type: int), value (type: string)
- auto parallelism: false
+ Select Operator
+ expressions: ds (type: string), key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 18 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -1518,10 +1554,10 @@ STAGE PLANS:
name: default.pcr_t2
name: default.pcr_t2
Truncated Path -> Alias:
- /pcr_t1/ds=2000-04-08 [t1]
- /pcr_t1/ds=2000-04-09 [t1]
- /pcr_t1/ds=2000-04-10 [t1]
- /pcr_t2 [t2]
+ /pcr_t1/ds=2000-04-08 [$hdt$_0:t1]
+ /pcr_t1/ds=2000-04-09 [$hdt$_0:t1]
+ /pcr_t1/ds=2000-04-10 [$hdt$_0:t1]
+ /pcr_t2 [$hdt$_1:t2]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
@@ -1530,33 +1566,29 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col6, _col7, _col8
- Statistics: Num rows: 66 Data size: 528 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: (struct(_col0,_col6)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col6 (type: string), _col7 (type: int), _col8 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4,_col5
- columns.types int,string,string,string,int,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ predicate: (struct(_col0,_col3)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5
+ columns.types int,string,string,string,int,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -1566,7 +1598,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
sort order: +++
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col2 (type: string), _col4 (type: int), _col5 (type: string)
auto parallelism: false
@@ -1600,13 +1632,13 @@ STAGE PLANS:
Select Operator
expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/7dab21ac/ql/src/test/results/clientpositive/pointlookup3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/pointlookup3.q.out b/ql/src/test/results/clientpositive/pointlookup3.q.out
index 4cb3cba..a37e079 100644
--- a/ql/src/test/results/clientpositive/pointlookup3.q.out
+++ b/ql/src/test/results/clientpositive/pointlookup3.q.out
@@ -543,30 +543,38 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string), ds2 (type: string)
+ outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string), ds2 (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string), _col3 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string), ds1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string), ds1 (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string), _col2 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -617,38 +625,34 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [t1, t2]
+ /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1, $hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col3, _col7, _col8, _col9
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6
Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6
- Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col3,_col4,_col5,_col6
- columns.types int,string,string,int,string,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4,_col5,_col6
+ columns.types int,string,string,int,string,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -802,30 +806,38 @@ STAGE PLANS:
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string), ds2 (type: string)
+ outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: value (type: string), ds2 (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string), _col3 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: key is not null (type: boolean)
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: int)
- sort order: +
- Map-reduce partition columns: key (type: int)
+ Select Operator
+ expressions: key (type: int), value (type: string), ds2 (type: string)
+ outputColumnNames: _col0, _col1, _col3
Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: value (type: string), ds2 (type: string)
- auto parallelism: false
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 10 Data size: 80 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col1 (type: string), _col3 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -922,39 +934,35 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [t1]
- /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [t2]
+ /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1]
+ /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 key (type: int)
- 1 key (type: int)
- outputColumnNames: _col0, _col1, _col3, _col7, _col8, _col10
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7
Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col7 (type: int), _col8 (type: string), _col10 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col7
- Statistics: Num rows: 11 Data size: 88 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col3,_col4,_col5,_col7
- columns.types int,string,string,int,string,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col3,_col4,_col5,_col7
+ columns.types int,string,string,int,string,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -1028,7 +1036,7 @@ STAGE PLANS:
Processor Tree:
ListSink
-Warning: Shuffle Join JOIN[4][tables = [t1, t2]] in Stage 'Stage-1:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[9][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product
PREHOOK: query: explain extended
select *
from pcr_t1 t1 join pcr_t1 t2
@@ -1120,22 +1128,38 @@ STAGE PLANS:
alias: t1
Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 40 Data size: 320 Basic stats: COMPLETE Column stats: NONE
- tag: 0
- value expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (ds1) IN ('2000-04-08', '2000-04-09') (type: boolean)
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ auto parallelism: false
TableScan
- alias: t2
+ alias: t1
Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
- Reduce Output Operator
- sort order:
- Statistics: Num rows: 60 Data size: 480 Basic stats: COMPLETE Column stats: NONE
- tag: 1
- value expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string)
- auto parallelism: false
+ Filter Operator
+ isSamplingPred: false
+ predicate: (key) IN (1, 2) (type: boolean)
+ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string), ds1 (type: string), ds2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 30 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ tag: 1
+ value expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ auto parallelism: false
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -1278,9 +1302,9 @@ STAGE PLANS:
name: default.pcr_t1
name: default.pcr_t1
Truncated Path -> Alias:
- /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [t1, t2]
- /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [t1, t2]
- /pcr_t1/ds1=2000-04-10/ds2=2001-04-10 [t2]
+ /pcr_t1/ds1=2000-04-08/ds2=2001-04-08 [$hdt$_0:t1, $hdt$_1:t1]
+ /pcr_t1/ds1=2000-04-09/ds2=2001-04-09 [$hdt$_0:t1, $hdt$_1:t1]
+ /pcr_t1/ds1=2000-04-10/ds2=2001-04-10 [$hdt$_1:t1]
Needs Tagging: true
Reduce Operator Tree:
Join Operator
@@ -1289,33 +1313,29 @@ STAGE PLANS:
keys:
0
1
- outputColumnNames: _col0, _col1, _col2, _col3, _col7, _col8, _col9, _col10
- Statistics: Num rows: 66 Data size: 528 Basic stats: COMPLETE Column stats: NONE
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
Filter Operator
isSamplingPred: false
- predicate: (struct(_col7,_col2)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col7 (type: int), _col8 (type: string), _col9 (type: string), _col10 (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 0
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- properties:
- columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7
- columns.types int,string,string,string,int,string,string,string
- escape.delim \
- serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- TotalFiles: 1
- GatherStats: false
- MultiFileSpray: false
+ predicate: (struct(_col4,_col2)) IN (const struct(1,'2000-04-08'), const struct(2,'2000-04-09')) (type: boolean)
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2,_col3,_col4,_col5,_col6,_col7
+ columns.types int,string,string,string,int,string,string,string
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
Stage: Stage-2
Map Reduce
@@ -1325,7 +1345,7 @@ STAGE PLANS:
Reduce Output Operator
key expressions: _col4 (type: int), _col5 (type: string), _col2 (type: string)
sort order: +++
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
tag: -1
value expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string), _col6 (type: string), _col7 (type: string)
auto parallelism: false
@@ -1359,13 +1379,13 @@ STAGE PLANS:
Select Operator
expressions: VALUE._col0 (type: int), VALUE._col1 (type: string), KEY.reducesinkkey2 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), VALUE._col3 (type: string), VALUE._col4 (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
GlobalTableId: 0
#### A masked pattern was here ####
NumFilesPerFileSink: 1
- Statistics: Num rows: 33 Data size: 264 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 16 Data size: 128 Basic stats: COMPLETE Column stats: NONE
#### A masked pattern was here ####
table:
input format: org.apache.hadoop.mapred.TextInputFormat