You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by br...@apache.org on 2015/02/11 18:48:41 UTC
svn commit: r1659014 [17/25] - in /hive/branches/parquet: ./
beeline/src/java/org/apache/hive/beeline/ beeline/src/main/resources/
beeline/src/test/org/apache/hive/beeline/ bin/
common/src/java/org/apache/hadoop/hive/conf/ data/conf/ data/conf/spark/ d...
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby11.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby11.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby11.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby11.q.out Wed Feb 11 17:48:36 2015
@@ -43,29 +43,44 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: key (type: string)
- sort order: +
- Map-reduce partition columns: key (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: value (type: string), substr(value, 5) (type: string)
- Reducer 3
+ Reduce Output Operator
+ key expressions: value (type: string), key (type: string)
+ sort order: ++
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: substr(value, 5) (type: string), key (type: string)
+ sort order: ++
+ Map-reduce partition columns: substr(value, 5) (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0), count(VALUE._col1)
+ aggregations: count(KEY._col1:0._col0), count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -80,12 +95,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0), count(VALUE._col1)
+ aggregations: count(KEY._col1:0._col0), count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -100,38 +115,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(KEY._col0), count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint), _col2 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(KEY._col0), count(DISTINCT KEY._col0)
- keys: VALUE._col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint), _col2 (type: bigint)
Stage: Stage-0
Move Operator
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8.q.out Wed Feb 11 17:48:36 2015
@@ -39,29 +39,44 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string)
- Reducer 3
+ Reduce Output Operator
+ key expressions: key (type: string), substr(value, 5) (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), substr(value, 5) (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -76,12 +91,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -96,38 +111,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
Stage: Stage-0
Move Operator
@@ -828,29 +811,44 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string)
- Reducer 3
+ Reduce Output Operator
+ key expressions: key (type: string), substr(value, 5) (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: string), substr(value, 5) (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -865,12 +863,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -885,38 +883,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
Stage: Stage-0
Move Operator
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map.q.out Wed Feb 11 17:48:36 2015
@@ -39,10 +39,7 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 31)
- Reducer 6 <- Map 1 (SORT, 31)
- Reducer 3 <- Reducer 5 (GROUP, 31)
- Reducer 4 <- Reducer 6 (GROUP, 31)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 31)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -50,84 +47,55 @@ STAGE PLANS:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string)
- Reducer 3
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: final
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1
- Reducer 4
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: final
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest2
- Reducer 5
+ Reduce Output Operator
+ key expressions: key (type: string), substr(value, 5) (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Forward
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
+ aggregations: count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
+ aggregations: count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest2
Stage: Stage-0
Move Operator
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map_skew.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map_skew.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map_skew.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_map_skew.q.out Wed Feb 11 17:48:36 2015
@@ -39,29 +39,56 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 31)
- Reducer 6 <- Map 1 (SORT, 31)
- Reducer 3 <- Reducer 5 (GROUP, 31)
- Reducer 4 <- Reducer 6 (GROUP, 31)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 31)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 31)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string)
- Reducer 3
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -76,12 +103,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: complete
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -96,38 +123,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
Stage: Stage-0
Move Operator
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_noskew.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_noskew.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_noskew.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby8_noskew.q.out Wed Feb 11 17:48:36 2015
@@ -39,10 +39,7 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 31)
- Reducer 6 <- Map 1 (SORT, 31)
- Reducer 3 <- Reducer 5 (GROUP, 31)
- Reducer 4 <- Reducer 6 (GROUP, 31)
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 31)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -50,84 +47,55 @@ STAGE PLANS:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string)
- Reducer 3
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: final
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1
- Reducer 4
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: final
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest2
- Reducer 5
+ Reduce Output Operator
+ key expressions: key (type: string), substr(value, 5) (type: string)
+ sort order: ++
+ Map-reduce partition columns: key (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Forward
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
+ aggregations: count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest1
Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
+ aggregations: count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: UDFToInteger(_col0) (type: int), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest2
Stage: Stage-0
Move Operator
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby9.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby9.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby9.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby9.q.out Wed Feb 11 17:48:36 2015
@@ -39,29 +39,56 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Reducer 3
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), value (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -76,12 +103,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -96,38 +123,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string), VALUE._col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: bigint)
Stage: Stage-0
Move Operator
@@ -829,29 +824,56 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Reducer 3
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string), key (type: string)
+ outputColumnNames: value, key
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: value (type: string), key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -866,12 +888,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -886,38 +908,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col1 (type: string), VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: bigint)
Stage: Stage-0
Move Operator
@@ -1619,29 +1609,56 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Reducer 3
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), value (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -1656,12 +1673,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -1676,38 +1693,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string), VALUE._col1 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: bigint)
Stage: Stage-0
Move Operator
@@ -3196,29 +3181,56 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
+ Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
+ Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 1
+ Map 4
Map Operator Tree:
TableScan
alias: src
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: substr(value, 5) (type: string)
- sort order: +
- Map-reduce partition columns: substr(value, 5) (type: string)
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), value (type: string)
- Reducer 3
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string), key (type: string)
+ outputColumnNames: value, key
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT substr(value, 5))
+ keys: value (type: string), key (type: string), substr(value, 5) (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col1:0._col0)
keys: KEY._col0 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -3233,12 +3245,12 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest1
- Reducer 4
+ Reducer 3
Reduce Operator Tree:
Group By Operator
- aggregations: count(VALUE._col0)
+ aggregations: count(DISTINCT KEY._col2:0._col0)
keys: KEY._col0 (type: string), KEY._col1 (type: string)
- mode: final
+ mode: mergepartial
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
@@ -3253,38 +3265,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col1 (type: string), VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string)
- sort order: ++
- Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col2 (type: bigint)
Stage: Stage-0
Move Operator
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_multi_insert_common_distinct.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_multi_insert_common_distinct.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_multi_insert_common_distinct.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_multi_insert_common_distinct.q.out Wed Feb 11 17:48:36 2015
@@ -39,191 +39,6 @@ STAGE PLANS:
Stage: Stage-2
Spark
Edges:
- Reducer 5 <- Map 1 (SORT, 2)
- Reducer 6 <- Map 1 (SORT, 2)
- Reducer 3 <- Reducer 5 (GROUP, 2)
- Reducer 4 <- Reducer 6 (GROUP, 2)
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: src
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: value (type: string)
- sort order: +
- Map-reduce partition columns: value (type: string)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: key (type: string), (key + key) (type: double)
- Reducer 3
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: string)
- mode: final
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1
- Reducer 4
- Reduce Operator Tree:
- Group By Operator
- aggregations: count(VALUE._col0)
- keys: KEY._col0 (type: double)
- mode: final
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest2
- Reducer 5
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col0 (type: string)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
- Reducer 6
- Reduce Operator Tree:
- Forward
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Group By Operator
- aggregations: count(DISTINCT KEY._col0)
- keys: VALUE._col1 (type: double)
- mode: hash
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: double)
- sort order: +
- Map-reduce partition columns: _col0 (type: double)
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col1 (type: bigint)
-
- Stage: Stage-0
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest1
-
- Stage: Stage-3
- Stats-Aggr Operator
-
- Stage: Stage-1
- Move Operator
- tables:
- replace: true
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest2
-
- Stage: Stage-4
- Stats-Aggr Operator
-
-PREHOOK: query: from src
-insert overwrite table dest1 select key, count(distinct value) group by key
-insert overwrite table dest2 select key+key, count(distinct value) group by key+key
-PREHOOK: type: QUERY
-PREHOOK: Input: default@src
-PREHOOK: Output: default@dest1
-PREHOOK: Output: default@dest2
-POSTHOOK: query: from src
-insert overwrite table dest1 select key, count(distinct value) group by key
-insert overwrite table dest2 select key+key, count(distinct value) group by key+key
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@src
-POSTHOOK: Output: default@dest1
-POSTHOOK: Output: default@dest2
-POSTHOOK: Lineage: dest1.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest1.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest2.cnt EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
-PREHOOK: query: select * from dest1 where key < 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest1
-#### A masked pattern was here ####
-POSTHOOK: query: select * from dest1 where key < 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest1
-#### A masked pattern was here ####
-0 1
-2 1
-4 1
-5 1
-8 1
-9 1
-PREHOOK: query: select * from dest2 where key < 20 order by key limit 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@dest2
-#### A masked pattern was here ####
-POSTHOOK: query: select * from dest2 where key < 20 order by key limit 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@dest2
-#### A masked pattern was here ####
-0 1
-10 1
-16 1
-18 1
-4 1
-8 1
-PREHOOK: query: -- no need to spray by distinct key first
-explain
-from src
-insert overwrite table dest1 select key, count(distinct value) group by key
-insert overwrite table dest2 select key+key, count(distinct value) group by key+key
-PREHOOK: type: QUERY
-POSTHOOK: query: -- no need to spray by distinct key first
-explain
-from src
-insert overwrite table dest1 select key, count(distinct value) group by key
-insert overwrite table dest2 select key+key, count(distinct value) group by key+key
-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-1 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-2
- Spark
- Edges:
Reducer 2 <- Map 4 (GROUP PARTITION-LEVEL SORT, 2)
Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_1_23.q.out Wed Feb 11 17:48:36 2015
@@ -1888,7 +1888,7 @@ ABSTRACT SYNTAX TREE:
TOK_QUERY
TOK_FROM
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
@@ -2241,7 +2241,7 @@ ABSTRACT SYNTAX TREE:
TOK_QUERY
TOK_FROM
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/groupby_sort_skew_1_23.q.out Wed Feb 11 17:48:36 2015
@@ -1960,7 +1960,7 @@ ABSTRACT SYNTAX TREE:
TOK_QUERY
TOK_FROM
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
@@ -2313,7 +2313,7 @@ ABSTRACT SYNTAX TREE:
TOK_QUERY
TOK_FROM
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/join34.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/join34.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/join34.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/join34.q.out Wed Feb 11 17:48:36 2015
@@ -40,7 +40,7 @@ TOK_QUERY
TOK_FROM
TOK_JOIN
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/join35.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/join35.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/join35.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/join35.q.out Wed Feb 11 17:48:36 2015
@@ -40,7 +40,7 @@ TOK_QUERY
TOK_FROM
TOK_JOIN
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/load_dyn_part14.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/load_dyn_part14.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/load_dyn_part14.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/load_dyn_part14.q.out Wed Feb 11 17:48:36 2015
@@ -36,21 +36,21 @@ value string
PREHOOK: query: explain
insert overwrite table nzhang_part14 partition(value)
select key, value from (
- select 'k1' as key, cast(null as string) as value from src limit 2
+ select * from (select 'k1' as key, cast(null as string) as value from src limit 2)a
union all
- select 'k2' as key, '' as value from src limit 2
+ select * from (select 'k2' as key, '' as value from src limit 2)b
union all
- select 'k3' as key, ' ' as value from src limit 2
+ select * from (select 'k3' as key, ' ' as value from src limit 2)c
) T
PREHOOK: type: QUERY
POSTHOOK: query: explain
insert overwrite table nzhang_part14 partition(value)
select key, value from (
- select 'k1' as key, cast(null as string) as value from src limit 2
+ select * from (select 'k1' as key, cast(null as string) as value from src limit 2)a
union all
- select 'k2' as key, '' as value from src limit 2
+ select * from (select 'k2' as key, '' as value from src limit 2)b
union all
- select 'k3' as key, ' ' as value from src limit 2
+ select * from (select 'k3' as key, ' ' as value from src limit 2)c
) T
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
@@ -175,22 +175,22 @@ STAGE PLANS:
PREHOOK: query: insert overwrite table nzhang_part14 partition(value)
select key, value from (
- select 'k1' as key, cast(null as string) as value from src limit 2
+ select * from (select 'k1' as key, cast(null as string) as value from src limit 2)a
union all
- select 'k2' as key, '' as value from src limit 2
+ select * from (select 'k2' as key, '' as value from src limit 2)b
union all
- select 'k3' as key, ' ' as value from src limit 2
+ select * from (select 'k3' as key, ' ' as value from src limit 2)c
) T
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Output: default@nzhang_part14
POSTHOOK: query: insert overwrite table nzhang_part14 partition(value)
select key, value from (
- select 'k1' as key, cast(null as string) as value from src limit 2
+ select * from (select 'k1' as key, cast(null as string) as value from src limit 2)a
union all
- select 'k2' as key, '' as value from src limit 2
+ select * from (select 'k2' as key, '' as value from src limit 2)b
union all
- select 'k3' as key, ' ' as value from src limit 2
+ select * from (select 'k3' as key, ' ' as value from src limit 2)c
) T
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out Wed Feb 11 17:48:36 2015
@@ -350,7 +350,7 @@ POSTHOOK: query: select count(*), sum(1)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@stats_tbl
#### A masked pattern was here ####
-9999 9999 1999.8 9999 9999 9999 9999 9999
+9999 9999 1999.8000000000002 9999 9999 9999 9999 9999
PREHOOK: query: explain
select min(i), max(i), min(b), max(b), min(f), max(f), min(d), max(d) from stats_tbl
PREHOOK: type: QUERY
@@ -375,7 +375,7 @@ POSTHOOK: query: select min(i), max(i),
POSTHOOK: type: QUERY
POSTHOOK: Input: default@stats_tbl
#### A masked pattern was here ####
-65536 65791 4294967296 4294967551 0.009999999776482582 99.9800033569336 0.01 50.0
+65536 65791 4294967296 4294967551 0.01 99.98 0.01 50.0
PREHOOK: query: explain
select count(*), sum(1), sum(0.2), count(1), count(s), count(bo), count(bin), count(si) from stats_tbl_part
PREHOOK: type: QUERY
@@ -400,7 +400,7 @@ POSTHOOK: query: select count(*), sum(1)
POSTHOOK: type: QUERY
POSTHOOK: Input: default@stats_tbl_part
#### A masked pattern was here ####
-9489 9489 1897.8 9489 9489 9489 9489 9489
+9489 9489 1897.8000000000002 9489 9489 9489 9489 9489
PREHOOK: query: explain
select min(i), max(i), min(b), max(b), min(f), max(f), min(d), max(d) from stats_tbl_part
PREHOOK: type: QUERY
@@ -425,7 +425,7 @@ POSTHOOK: query: select min(i), max(i),
POSTHOOK: type: QUERY
POSTHOOK: Input: default@stats_tbl_part
#### A masked pattern was here ####
-65536 65791 4294967296 4294967551 0.009999999776482582 99.9800033569336 0.01 50.0
+65536 65791 4294967296 4294967551 0.01 99.98 0.01 50.0
PREHOOK: query: explain select count(ts) from stats_tbl_part
PREHOOK: type: QUERY
POSTHOOK: query: explain select count(ts) from stats_tbl_part
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries_with_filters.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries_with_filters.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries_with_filters.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/metadata_only_queries_with_filters.q.out Wed Feb 11 17:48:36 2015
@@ -166,7 +166,7 @@ POSTHOOK: query: select count(*), count(
POSTHOOK: type: QUERY
POSTHOOK: Input: default@stats_tbl_part
#### A masked pattern was here ####
-2322 2322 2322 2322 2322 2322 2322 65791 4294967296 99.9800033569336 0.03
+2322 2322 2322 2322 2322 2322 2322 65791 4294967296 99.98 0.03
PREHOOK: query: explain
select count(*), count(1), sum(1), sum(2), count(s), count(bo), count(bin), count(si), max(i), min(b), max(f), min(d) from stats_tbl_part where dt > 2010
PREHOOK: type: QUERY
@@ -191,7 +191,7 @@ POSTHOOK: query: select count(*), count(
POSTHOOK: type: QUERY
POSTHOOK: Input: default@stats_tbl_part
#### A masked pattern was here ####
-2219 2219 2219 4438 2219 2219 2219 2219 65791 4294967296 99.95999908447266 0.04
+2219 2219 2219 4438 2219 2219 2219 2219 65791 4294967296 99.96 0.04
PREHOOK: query: select count(*) from stats_tbl_part
PREHOOK: type: QUERY
PREHOOK: Input: default@stats_tbl_part
Modified: hive/branches/parquet/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out
URL: http://svn.apache.org/viewvc/hive/branches/parquet/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out?rev=1659014&r1=1659013&r2=1659014&view=diff
==============================================================================
--- hive/branches/parquet/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out (original)
+++ hive/branches/parquet/ql/src/test/results/clientpositive/spark/optimize_nullscan.q.out Wed Feb 11 17:48:36 2015
@@ -595,7 +595,7 @@ ABSTRACT SYNTAX TREE:
TOK_QUERY
TOK_FROM
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF
@@ -1443,7 +1443,7 @@ ABSTRACT SYNTAX TREE:
TOK_QUERY
TOK_FROM
TOK_SUBQUERY
- TOK_UNION
+ TOK_UNIONALL
TOK_QUERY
TOK_FROM
TOK_TABREF