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 00:00:32 UTC
[34/51] [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/insert_into2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into2.q.out b/ql/src/test/results/clientpositive/insert_into2.q.out
index 90b409c..efffd53 100644
--- a/ql/src/test/results/clientpositive/insert_into2.q.out
+++ b/ql/src/test/results/clientpositive/insert_into2.q.out
@@ -21,7 +21,8 @@ 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
@@ -38,7 +39,6 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -60,6 +60,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 100 Data size: 1000 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
@@ -76,6 +92,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into2
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 50 Data size: 500 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 INTO TABLE insert_into2 PARTITION (ds='1') SELECT * FROM src order by key limit 100
PREHOOK: type: QUERY
@@ -171,7 +220,8 @@ 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
@@ -188,7 +238,6 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -210,6 +259,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '2' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 100 Data size: 1000 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
@@ -226,6 +291,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into2
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 100 Data size: 1000 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 50 Data size: 500 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 insert_into2 PARTITION (ds='2')
SELECT * FROM src order by key LIMIT 100
@@ -290,7 +388,8 @@ 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
@@ -307,7 +406,6 @@ STAGE PLANS:
key expressions: _col0 (type: string)
sort order: +
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -329,6 +427,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into2
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '2' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 50 Data size: 500 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
@@ -345,6 +459,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into2
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 50 Data size: 500 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 25 Data size: 250 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 25 Data size: 250 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 25 Data size: 250 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 insert_into2 PARTITION (ds='2')
SELECT * FROM src order by key LIMIT 50
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/insert_into3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into3.q.out b/ql/src/test/results/clientpositive/insert_into3.q.out
index 4bda7d9..77fca86 100644
--- a/ql/src/test/results/clientpositive/insert_into3.q.out
+++ b/ql/src/test/results/clientpositive/insert_into3.q.out
@@ -31,10 +31,12 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0
+ Stage-3 depends on stages: Stage-0, Stage-4, Stage-7
Stage-4 depends on stages: Stage-2
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
+ Stage-6 depends on stages: Stage-1, Stage-4, Stage-7
+ Stage-5 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-5
+ Stage-7 depends on stages: Stage-5
STAGE PLANS:
Stage: Stage-2
@@ -51,7 +53,6 @@ STAGE PLANS:
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
@@ -82,6 +83,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into3a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 50 Data size: 500 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
@@ -96,16 +112,49 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3a
Stage: Stage-4
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
+
+ Stage: Stage-6
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3b
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
key expressions: _col0 (type: string), _col1 (type: string)
sort order: ++
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
Reduce Operator Tree:
Select Operator
expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
@@ -126,6 +175,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into3b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 100 Data size: 1000 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-1
Move Operator
@@ -137,9 +201,27 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into3b
- Stage: Stage-5
- Stats Work
- Basic Stats Work:
+ Stage: Stage-7
+ 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 INSERT INTO TABLE insert_into3a SELECT * ORDER BY key, value LIMIT 50
INSERT INTO TABLE insert_into3b SELECT * ORDER BY key, value LIMIT 100
@@ -192,10 +274,12 @@ POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-2 is a root stage
Stage-0 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-0
+ Stage-3 depends on stages: Stage-0, Stage-4, Stage-7
Stage-4 depends on stages: Stage-2
- Stage-1 depends on stages: Stage-4
- Stage-5 depends on stages: Stage-1
+ Stage-6 depends on stages: Stage-1, Stage-4, Stage-7
+ Stage-5 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-5
+ Stage-7 depends on stages: Stage-5
STAGE PLANS:
Stage: Stage-2
@@ -214,7 +298,6 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Select Operator
expressions: key (type: string), value (type: string)
@@ -249,6 +332,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into3a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 100 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
@@ -263,6 +361,10 @@ STAGE PLANS:
Stage: Stage-3
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3a
Stage: Stage-4
Map Reduce
@@ -270,8 +372,37 @@ STAGE PLANS:
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
+
+ Stage: Stage-6
+ Stats Work
+ Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into3b
+
+ Stage: Stage-5
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -293,6 +424,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into3b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 100 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-1
Move Operator
@@ -304,9 +450,27 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into3b
- Stage: Stage-5
- Stats Work
- Basic Stats Work:
+ Stage: Stage-7
+ 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 INSERT OVERWRITE TABLE insert_into3a SELECT * LIMIT 10
INSERT INTO TABLE insert_into3b SELECT * LIMIT 10
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/insert_into4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into4.q.out b/ql/src/test/results/clientpositive/insert_into4.q.out
index 931ae3d..927d087 100644
--- a/ql/src/test/results/clientpositive/insert_into4.q.out
+++ b/ql/src/test/results/clientpositive/insert_into4.q.out
@@ -29,7 +29,8 @@ 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
@@ -48,7 +49,6 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -70,6 +70,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into4a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 100 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
@@ -84,6 +99,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into4a
+
+ 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: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
PREHOOK: type: QUERY
@@ -115,7 +156,8 @@ 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
@@ -134,7 +176,6 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -156,6 +197,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into4a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 100 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
@@ -170,6 +226,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into4a
+
+ 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: INSERT INTO TABLE insert_into4a SELECT * FROM src LIMIT 10
PREHOOK: type: QUERY
@@ -227,6 +309,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into4b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 20 Data size: 208 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
+ 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
Stage: Stage-7
Conditional Operator
@@ -250,6 +358,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into4b
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/insert_into5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into5.q.out b/ql/src/test/results/clientpositive/insert_into5.q.out
index 5e52e49..66dd502 100644
--- a/ql/src/test/results/clientpositive/insert_into5.q.out
+++ b/ql/src/test/results/clientpositive/insert_into5.q.out
@@ -29,7 +29,8 @@ 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
@@ -48,7 +49,6 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
- TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: int), _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -66,6 +66,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into5a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 910 Basic stats: COMPLETE Column stats: COMPLETE
+ 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: COMPLETE
+ 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
@@ -80,6 +95,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5a
+
+ 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: COMPLETE
+ 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: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 880 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
PREHOOK: query: INSERT INTO TABLE insert_into5a SELECT 1, 'one' FROM src LIMIT 10
PREHOOK: type: QUERY
@@ -137,6 +178,32 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into5a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 10 Data size: 50 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
+ 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
Stage: Stage-7
Conditional Operator
@@ -160,6 +227,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5a
Stage: Stage-3
Map Reduce
@@ -249,6 +320,40 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into5b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 20 Data size: 100 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: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 50 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-7
Conditional Operator
@@ -274,6 +379,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5b
Stage: Stage-3
Map Reduce
@@ -365,6 +474,40 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into5b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 20 Data size: 100 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: 20 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 10 Data size: 50 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 10 Data size: 50 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-7
Conditional Operator
@@ -390,6 +533,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into5b
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/insert_into6.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insert_into6.q.out b/ql/src/test/results/clientpositive/insert_into6.q.out
index 964e259..c0fc7bd 100644
--- a/ql/src/test/results/clientpositive/insert_into6.q.out
+++ b/ql/src/test/results/clientpositive/insert_into6.q.out
@@ -31,7 +31,8 @@ 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
@@ -50,7 +51,6 @@ STAGE PLANS:
Reduce Output Operator
sort order:
Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
- TopN Hash Memory Usage: 0.1
value expressions: _col0 (type: string), _col1 (type: string)
Reduce Operator Tree:
Select Operator
@@ -72,6 +72,22 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into6a
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), '1' (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 150 Data size: 1500 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
@@ -88,6 +104,39 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into6a
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 150 Data size: 1500 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 75 Data size: 750 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 75 Data size: 750 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 75 Data size: 750 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 INTO TABLE insert_into6a PARTITION (ds='1') SELECT * FROM src LIMIT 150
PREHOOK: type: QUERY
@@ -161,6 +210,40 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.insert_into6b
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: key, value, ds
+ Statistics: Num rows: 250 Data size: 2680 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll')
+ keys: ds (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 250 Data size: 2680 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: 2680 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: struct<columntype:string,min:bigint,max: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)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 125 Data size: 1340 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: struct<columntype:string,min:bigint,max:bigint,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col2 (type: struct<columntype:string,maxlength:bigint,avglength:double,countnulls:bigint,numdistinctvalues:bigint,ndvbitvector:binary>), _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 125 Data size: 1340 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 125 Data size: 1340 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-7
Conditional Operator
@@ -186,6 +269,10 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: key, value
+ Column Types: int, string
+ Table: default.insert_into6b
Stage: Stage-3
Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out b/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out
index 4c020fd..ed97f83 100644
--- a/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out
+++ b/ql/src/test/results/clientpositive/insertoverwrite_bucket.q.out
@@ -99,7 +99,8 @@ 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
@@ -130,6 +131,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.temp1
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string)
+ outputColumnNames: change, num
+ Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(change, 'hll'), compute_stats(num, '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
Stage: Stage-0
Move Operator
@@ -144,6 +160,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: change, num
+ Column Types: string, string
+ Table: default.temp1
+
+ 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: CREATE TABLE temp2
(
@@ -178,7 +220,8 @@ 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
@@ -210,6 +253,21 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.temp2
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ outputColumnNames: create_ts, change, num
+ Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(create_ts, 'hll'), compute_stats(change, 'hll'), compute_stats(num, 'hll')
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
Stage: Stage-0
Move Operator
@@ -224,6 +282,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: create_ts, change, num
+ Column Types: string, string, string
+ Table: default.temp2
+
+ Stage: Stage-3
+ Map Reduce
+ Map Operator Tree:
+ TableScan
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL 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>)
+ 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: PARTIAL Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 1320 Basic stats: PARTIAL 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: select * from bucketoutput1 a join bucketoutput2 b on (a.data=b.data)
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join14.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join14.q.out b/ql/src/test/results/clientpositive/join14.q.out
index 10b4e1f..cb456e2 100644
--- a/ql/src/test/results/clientpositive/join14.q.out
+++ b/ql/src/test/results/clientpositive/join14.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
@@ -75,6 +76,21 @@ 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: c1, c2
+ Statistics: Num rows: 366 Data size: 3890 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(c1, 'hll'), compute_stats(c2, '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
@@ -89,6 +105,32 @@ STAGE PLANS:
Stage: Stage-2
Stats Work
Basic Stats Work:
+ Column Stats Desc:
+ Columns: c1, c2
+ 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 JOIN srcpart ON src.key = srcpart.key AND srcpart.ds = '2008-04-08' and src.key > 100
INSERT OVERWRITE TABLE dest1 SELECT src.key, srcpart.value
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join17.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join17.q.out b/ql/src/test/results/clientpositive/join17.q.out
index 6c3e5fe..e6aac08 100644
--- a/ql/src/test/results/clientpositive/join17.q.out
+++ b/ql/src/test/results/clientpositive/join17.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
@@ -162,6 +163,33 @@ STAGE PLANS:
TotalFiles: 1
GatherStats: true
MultiFileSpray: false
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string)
+ outputColumnNames: key1, value1, key2, value2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: compute_stats(key1, 'hll'), compute_stats(value1, 'hll'), compute_stats(key2, 'hll'), compute_stats(value2, '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
+ 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,_col3
+ columns.types struct<columntype:string,min:bigint,max: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>,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
Stage: Stage-0
Move Operator
@@ -195,6 +223,80 @@ STAGE PLANS:
Stats Work
Basic Stats Work:
#### A masked pattern was here ####
+ Column Stats Desc:
+ Columns: key1, value1, key2, value2
+ Column Types: int, string, int, string
+ Table: default.dest1
+ 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: 1728 Basic stats: COMPLETE Column stats: NONE
+ tag: -1
+ 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>)
+ 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,_col3
+ columns.types struct<columntype:string,min:bigint,max: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>,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,_col3
+ columns.types struct<columntype:string,min:bigint,max: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>,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), 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
+ GlobalTableId: 0
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1 Data size: 1760 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,_col3
+ columns.types struct<columntype:string,min:bigint,max:bigint,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>: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: FROM src src1 JOIN src src2 ON (src1.key = src2.key)
INSERT OVERWRITE TABLE dest1 SELECT src1.*, src2.*
http://git-wip-us.apache.org/repos/asf/hive/blob/3bbc24d2/ql/src/test/results/clientpositive/join25.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join25.q.out b/ql/src/test/results/clientpositive/join25.q.out
index 8ed420b..30a62ce 100644
--- a/ql/src/test/results/clientpositive/join25.q.out
+++ b/ql/src/test/results/clientpositive/join25.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/join26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/join26.q.out b/ql/src/test/results/clientpositive/join26.q.out
index 134aa52..870a735 100644
--- a/ql/src/test/results/clientpositive/join26.q.out
+++ b/ql/src/test/results/clientpositive/join26.q.out
@@ -19,13 +19,14 @@ FROM src1 x JOIN src y ON (x.key = y.key)
JOIN srcpart z ON (x.key = z.key and z.ds='2008-04-08' and z.hr=11)
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:y
@@ -74,7 +75,7 @@ STAGE PLANS:
2 _col0 (type: string)
Position of Big Table: 2
- Stage: Stage-5
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -136,6 +137,33 @@ 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: 1100 Data size: 11686 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:
@@ -316,6 +344,80 @@ 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 /*+ MAPJOIN(x,y) */ x.key, z.value, y.value