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 2017/12/12 00:00:31 UTC
[33/51] [partial] hive git commit: HIVE-13567 : Enable auto-gather
column stats by default (Zoltan Haindrich,
Pengcheng Xiong via Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join27.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join27.q.out b/ql/src/test/results/clientpositive/join27.q.out
index 2e78d2a..a8f4ff4 100644
--- a/ql/src/test/results/clientpositive/join27.q.out
+++ b/ql/src/test/results/clientpositive/join27.q.out
@@ -17,13 +17,14 @@ SELECT /*+ MAPJOIN(x) */ x.key, x.value, y.value
FROM src1 x JOIN src y ON (x.value = y.value)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-4 depends on stages: Stage-5
- Stage-0 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-0
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-0 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-5
STAGE PLANS:
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:x
@@ -46,7 +47,7 @@ STAGE PLANS:
0 _col1 (type: string)
1 _col0 (type: string)
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -79,6 +80,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 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
Local Work:
Map Reduce Local Work
@@ -95,6 +111,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: int, string, string
+ Table: default.dest_j1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT /*+ MAPJOIN(x) */ x.key, x.value, y.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join28.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join28.q.out b/ql/src/test/results/clientpositive/join28.q.out
index c4b122f..3b29191 100644
--- a/ql/src/test/results/clientpositive/join28.q.out
+++ b/ql/src/test/results/clientpositive/join28.q.out
@@ -23,13 +23,14 @@ FROM
JOIN srcpart z ON (subq.key1 = z.key and z.ds='2008-04-08' and z.hr=11)
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-2 depends on stages: Stage-0
+ Stage-8 is a root stage
+ Stage-6 depends on stages: Stage-8
+ Stage-0 depends on stages: Stage-6
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-6
STAGE PLANS:
- Stage: Stage-7
+ Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:z
@@ -70,7 +71,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -115,6 +116,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 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
Local Work:
Map Reduce Local Work
@@ -131,6 +147,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: string, string
+ Table: default.dest_j1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT subq.key1, z.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join29.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join29.q.out b/ql/src/test/results/clientpositive/join29.q.out
index d394eda..02521dd 100644
--- a/ql/src/test/results/clientpositive/join29.q.out
+++ b/ql/src/test/results/clientpositive/join29.q.out
@@ -20,15 +20,16 @@ FROM (select x.key, count(1) as cnt from src1 x group by x.key) subq1 JOIN
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1, Stage-4 , consists of Stage-8, Stage-9, Stage-2
- Stage-8 has a backup stage: Stage-2
- Stage-5 depends on stages: Stage-8
- Stage-0 depends on stages: Stage-2, Stage-5, Stage-6
- Stage-3 depends on stages: Stage-0
+ Stage-8 depends on stages: Stage-1, Stage-5 , consists of Stage-9, Stage-10, Stage-2
Stage-9 has a backup stage: Stage-2
Stage-6 depends on stages: Stage-9
+ Stage-0 depends on stages: Stage-2, Stage-6, Stage-7
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-4 depends on stages: Stage-2, Stage-6, Stage-7
+ Stage-10 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-10
Stage-2
- Stage-4 is a root stage
+ Stage-5 is a root stage
STAGE PLANS:
Stage: Stage-1
@@ -66,10 +67,10 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-7
+ Stage: Stage-8
Conditional Operator
- Stage: Stage-8
+ Stage: Stage-9
Map Reduce Local Work
Alias -> Map Local Tables:
$INTNAME1
@@ -83,7 +84,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -107,6 +108,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int)
+ outputColumnNames: key, cnt1, cnt2
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(cnt1, 'hll'), compute_stats(cnt2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1288 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
Local Work:
Map Reduce Local Work
@@ -123,8 +139,34 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, cnt1, cnt2
+ Column Types: string, int, int
+ Table: default.dest_j1
- Stage: Stage-9
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1288 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-10
Map Reduce Local Work
Alias -> Map Local Tables:
$INTNAME
@@ -138,7 +180,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce
Map Operator Tree:
TableScan
@@ -162,6 +204,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int)
+ outputColumnNames: key, cnt1, cnt2
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(cnt1, 'hll'), compute_stats(cnt2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1288 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
Local Work:
Map Reduce Local Work
@@ -203,8 +260,23 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int), _col2 (type: int)
+ outputColumnNames: key, cnt1, cnt2
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(cnt1, 'hll'), compute_stats(cnt2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1288 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-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join3.q.out b/ql/src/test/results/clientpositive/join3.q.out
index 8c4cfe2..87fb057 100644
--- a/ql/src/test/results/clientpositive/join3.q.out
+++ b/ql/src/test/results/clientpositive/join3.q.out
@@ -17,7 +17,8 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -92,6 +93,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 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-0
Move Operator
@@ -106,6 +122,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.dest1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key = src3.key)
INSERT OVERWRITE TABLE dest1 SELECT src1.key, src3.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join30.q.out b/ql/src/test/results/clientpositive/join30.q.out
index cdd5445..d29ef1b 100644
--- a/ql/src/test/results/clientpositive/join30.q.out
+++ b/ql/src/test/results/clientpositive/join30.q.out
@@ -15,13 +15,14 @@ INSERT OVERWRITE TABLE dest_j1
SELECT /*+ MAPJOIN(x) */ x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-6 is a root stage
- Stage-2 depends on stages: Stage-6
+ Stage-7 is a root stage
+ Stage-2 depends on stages: Stage-7
Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-4 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:x
@@ -98,6 +99,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int)
+ outputColumnNames: key, cnt
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 848 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-0
Move Operator
@@ -112,6 +128,32 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, cnt
+ Column Types: int, int
+ Table: default.dest_j1
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 848 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT /*+ MAPJOIN(x) */ x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join31.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join31.q.out b/ql/src/test/results/clientpositive/join31.q.out
index 7b0cbdc..abcb32f 100644
--- a/ql/src/test/results/clientpositive/join31.q.out
+++ b/ql/src/test/results/clientpositive/join31.q.out
@@ -22,10 +22,11 @@ group by subq1.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-7
+ Stage-8 depends on stages: Stage-1
+ Stage-3 depends on stages: Stage-8
Stage-0 depends on stages: Stage-3
- Stage-4 depends on stages: Stage-0
+ Stage-4 depends on stages: Stage-0, Stage-5
+ Stage-5 depends on stages: Stage-3
STAGE PLANS:
Stage: Stage-1
@@ -60,7 +61,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-7
+ Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_1:y
@@ -133,6 +134,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: int)
+ outputColumnNames: key, cnt
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(cnt, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 864 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-0
Move Operator
@@ -147,6 +163,32 @@ STAGE PLANS:
Stage: Stage-4
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, cnt
+ Column Types: string, int
+ Table: default.dest_j1
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 864 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT subq1.key, count(1) as cnt
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join32.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join32.q.out b/ql/src/test/results/clientpositive/join32.q.out
index 30a5ba9..47c88b8 100644
--- a/ql/src/test/results/clientpositive/join32.q.out
+++ b/ql/src/test/results/clientpositive/join32.q.out
@@ -19,13 +19,14 @@ FROM src1 x JOIN src y ON (x.key = y.key)
JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-8 is a root stage
- Stage-6 depends on stages: Stage-8
- Stage-0 depends on stages: Stage-6
- Stage-3 depends on stages: Stage-0
+ Stage-9 is a root stage
+ Stage-7 depends on stages: Stage-9
+ Stage-0 depends on stages: Stage-7
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-4 depends on stages: Stage-7
STAGE PLANS:
- Stage: Stage-8
+ Stage: Stage-9
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:z
@@ -120,7 +121,7 @@ STAGE PLANS:
1 _col0 (type: string)
Position of Big Table: 0
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce
Map Operator Tree:
TableScan
@@ -189,6 +190,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 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:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ 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
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -369,6 +397,80 @@ STAGE PLANS:
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: string, string, string
+ Table: default.dest_j1
+ Is Table Level Stats: true
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT x.key, z.value, y.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join33.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join33.q.out b/ql/src/test/results/clientpositive/join33.q.out
index 30a5ba9..47c88b8 100644
--- a/ql/src/test/results/clientpositive/join33.q.out
+++ b/ql/src/test/results/clientpositive/join33.q.out
@@ -19,13 +19,14 @@ FROM src1 x JOIN src y ON (x.key = y.key)
JOIN srcpart z ON (x.value = z.value and z.ds='2008-04-08' and z.hr=11)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-8 is a root stage
- Stage-6 depends on stages: Stage-8
- Stage-0 depends on stages: Stage-6
- Stage-3 depends on stages: Stage-0
+ Stage-9 is a root stage
+ Stage-7 depends on stages: Stage-9
+ Stage-0 depends on stages: Stage-7
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-4 depends on stages: Stage-7
STAGE PLANS:
- Stage: Stage-8
+ Stage: Stage-9
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:z
@@ -120,7 +121,7 @@ STAGE PLANS:
1 _col0 (type: string)
Position of Big Table: 0
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce
Map Operator Tree:
TableScan
@@ -189,6 +190,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 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:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ 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
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -369,6 +397,80 @@ STAGE PLANS:
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: string, string, string
+ Table: default.dest_j1
+ Is Table Level Stats: true
+
+ Stage: Stage-4
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT x.key, z.value, y.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join34.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join34.q.out b/ql/src/test/results/clientpositive/join34.q.out
index 072a20b..7675ad9 100644
--- a/ql/src/test/results/clientpositive/join34.q.out
+++ b/ql/src/test/results/clientpositive/join34.q.out
@@ -27,13 +27,14 @@ FROM
JOIN src1 x ON (x.key = subq1.key)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-6 is a root stage
- Stage-5 depends on stages: Stage-6
- Stage-0 depends on stages: Stage-5
- Stage-2 depends on stages: Stage-0
+ Stage-7 is a root stage
+ Stage-6 depends on stages: Stage-7
+ Stage-0 depends on stages: Stage-6
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-6
STAGE PLANS:
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_1:x
@@ -59,7 +60,7 @@ STAGE PLANS:
1 _col0 (type: string)
Position of Big Table: 0
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -121,6 +122,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 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:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ 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
TableScan
alias: x1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
@@ -180,6 +208,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 365 Data size: 3878 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 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:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ 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
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -312,6 +367,80 @@ STAGE PLANS:
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: string, string, string
+ Table: default.dest_j1
+ Is Table Level Stats: true
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ GatherStats: false
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10002
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT x.key, x.value, subq1.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join35.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join35.q.out b/ql/src/test/results/clientpositive/join35.q.out
index f8fd438..4590ef9 100644
--- a/ql/src/test/results/clientpositive/join35.q.out
+++ b/ql/src/test/results/clientpositive/join35.q.out
@@ -28,11 +28,12 @@ JOIN src1 x ON (x.key = subq1.key)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1, Stage-4
- Stage-6 depends on stages: Stage-7
- Stage-0 depends on stages: Stage-6
- Stage-3 depends on stages: Stage-0
- Stage-4 is a root stage
+ Stage-8 depends on stages: Stage-1, Stage-5
+ Stage-7 depends on stages: Stage-8
+ Stage-0 depends on stages: Stage-7
+ Stage-3 depends on stages: Stage-0, Stage-4
+ Stage-4 depends on stages: Stage-7
+ Stage-5 is a root stage
STAGE PLANS:
Stage: Stage-1
@@ -139,7 +140,7 @@ STAGE PLANS:
GatherStats: false
MultiFileSpray: false
- Stage: Stage-7
+ Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_1:x
@@ -165,7 +166,7 @@ STAGE PLANS:
1 _col0 (type: string)
Position of Big Table: 0
- Stage: Stage-6
+ Stage: Stage-7
Map Reduce
Map Operator Tree:
TableScan
@@ -217,6 +218,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 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:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>
+ 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
TableScan
GatherStats: false
Union
@@ -266,6 +294,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: int)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 182 Data size: 1938 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 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:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>
+ 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
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -295,7 +350,7 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
#### A masked pattern was here ####
Partition
- base file name: -mr-10003
+ base file name: -mr-10004
input format: org.apache.hadoop.mapred.SequenceFileInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
properties:
@@ -396,11 +451,85 @@ STAGE PLANS:
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: string, string, int
+ Table: default.dest_j1
+ Is Table Level Stats: true
Stage: Stage-4
Map Reduce
Map Operator Tree:
TableScan
+ GatherStats: false
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ auto parallelism: false
+ Path -> Alias:
+#### A masked pattern was here ####
+ Path -> Partition:
+#### A masked pattern was here ####
+ Partition
+ base file name: -mr-10003
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ column.name.delimiter ,
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>,struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>
+ escape.delim \
+ serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ Truncated Path -> Alias:
+#### A masked pattern was here ####
+ Needs Tagging: false
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ properties:
+ columns _col0,_col1,_col2
+ columns.types struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>:struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>
+ escape.delim \
+ hive.serialization.extend.additional.nesting.levels true
+ serialization.escape.crlf true
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ TotalFiles: 1
+ GatherStats: false
+ MultiFileSpray: false
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
alias: x1
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join36.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join36.q.out b/ql/src/test/results/clientpositive/join36.q.out
index 0fd4d91..40dbabb 100644
--- a/ql/src/test/results/clientpositive/join36.q.out
+++ b/ql/src/test/results/clientpositive/join36.q.out
@@ -57,13 +57,14 @@ SELECT /*+ MAPJOIN(x) */ x.key, x.cnt, y.cnt
FROM tmp1 x JOIN tmp2 y ON (x.key = y.key)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-4 depends on stages: Stage-5
- Stage-0 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-0
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-0 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-5
STAGE PLANS:
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:x
@@ -86,7 +87,7 @@ STAGE PLANS:
0 _col0 (type: int)
1 _col0 (type: int)
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -119,6 +120,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1272 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
Local Work:
Map Reduce Local Work
@@ -135,6 +151,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: int, int, int
+ Table: default.dest_j1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1272 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT /*+ MAPJOIN(x) */ x.key, x.cnt, y.cnt
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join37.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join37.q.out b/ql/src/test/results/clientpositive/join37.q.out
index c8bef83..4effb31 100644
--- a/ql/src/test/results/clientpositive/join37.q.out
+++ b/ql/src/test/results/clientpositive/join37.q.out
@@ -17,13 +17,14 @@ SELECT /*+ MAPJOIN(X) */ x.key, x.value, y.value
FROM src1 x JOIN src y ON (x.key = y.key)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-4 depends on stages: Stage-5
- Stage-0 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-0
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-0 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-5
STAGE PLANS:
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_0:x
@@ -46,7 +47,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -79,6 +80,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, val2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1304 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
Local Work:
Map Reduce Local Work
@@ -95,6 +111,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, val2
+ Column Types: int, string, string
+ Table: default.dest_j1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1304 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT /*+ MAPJOIN(X) */ x.key, x.value, y.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join39.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join39.q.out b/ql/src/test/results/clientpositive/join39.q.out
index 93ebdb8..80272a4 100644
--- a/ql/src/test/results/clientpositive/join39.q.out
+++ b/ql/src/test/results/clientpositive/join39.q.out
@@ -17,13 +17,14 @@ SELECT /*+ MAPJOIN(y) */ x.key, x.value, y.key, y.value
FROM src x left outer JOIN (select * from src where key <= 100) y ON (x.key = y.key)
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-5 is a root stage
- Stage-4 depends on stages: Stage-5
- Stage-0 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-0
+ Stage-6 is a root stage
+ Stage-5 depends on stages: Stage-6
+ Stage-0 depends on stages: Stage-5
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-5
STAGE PLANS:
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce Local Work
Alias -> Map Local Tables:
$hdt$_1:src
@@ -46,7 +47,7 @@ STAGE PLANS:
0 _col0 (type: string)
1 _col0 (type: string)
- Stage: Stage-4
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -72,6 +73,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest_j1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+ outputColumnNames: key, value, key1, val2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(key1, 'hll'), compute_stats(val2, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 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
Local Work:
Map Reduce Local Work
@@ -88,6 +104,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value, key1, val2
+ Column Types: string, string, string, string
+ Table: default.dest_j1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT OVERWRITE TABLE dest_j1
SELECT /*+ MAPJOIN(y) */ x.key, x.value, y.key, y.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join4.q.out b/ql/src/test/results/clientpositive/join4.q.out
index d4e83c4..95a4dbf 100644
--- a/ql/src/test/results/clientpositive/join4.q.out
+++ b/ql/src/test/results/clientpositive/join4.q.out
@@ -39,7 +39,8 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -98,6 +99,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string)
+ outputColumnNames: c1, c2, c3, c4
+ Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1728 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-0
Move Operator
@@ -112,6 +128,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: c1, c2, c3, c4
+ Column Types: int, string, int, string
+ Table: default.dest1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: FROM (
FROM
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join5.q.out b/ql/src/test/results/clientpositive/join5.q.out
index 8cfe402..7ce3b34 100644
--- a/ql/src/test/results/clientpositive/join5.q.out
+++ b/ql/src/test/results/clientpositive/join5.q.out
@@ -39,7 +39,8 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
- Stage-2 depends on stages: Stage-0
+ Stage-2 depends on stages: Stage-0, Stage-3
+ Stage-3 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -98,6 +99,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string)
+ outputColumnNames: c1, c2, c3, c4
+ Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(c1, 'hll'), compute_stats(c2, 'hll'), compute_stats(c3, 'hll'), compute_stats(c4, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1728 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-0
Move Operator
@@ -112,6 +128,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: c1, c2, c3, c4
+ Column Types: int, string, int, string
+ Table: default.dest1
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1728 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col1 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>), _col2 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,bitvector:binary>), _col3 (type: struct<columntype:string,maxlength:bigint,sumlength:bigint,count:bigint,countnulls:bigint,bitvector:binary>)
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: compute_stats(VALUE._col0), compute_stats(VALUE._col1), compute_stats(VALUE._col2), compute_stats(VALUE._col3)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1760 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: FROM (
FROM