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 2015/04/20 07:56:46 UTC
svn commit: r1674737 [3/9] - in
/hive/branches/cbo/ql/src/test/results/clientpositive: ./ spark/ tez/
Modified: hive/branches/cbo/ql/src/test/results/clientpositive/ptf_streaming.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/ptf_streaming.q.out?rev=1674737&r1=1674736&r2=1674737&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/ptf_streaming.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/ptf_streaming.q.out Mon Apr 20 05:56:44 2015
@@ -97,28 +97,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col7
name: sum
window function: GenericUDAFSumDouble
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -313,7 +313,7 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: lag_window_0
arguments: _col5, 1, _col5
name: lag
window function: GenericUDAFLagEvaluator
@@ -321,7 +321,7 @@ STAGE PLANS:
isPivotResult: true
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), (_col5 - _wcol0) (type: int)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), (_col5 - lag_window_0) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -637,7 +637,7 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1, _col5
name: rank
window function: GenericUDAFRankEvaluator
@@ -645,7 +645,7 @@ STAGE PLANS:
isPivotResult: true
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -814,28 +814,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col7
name: sum
window function: GenericUDAFSumDouble
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1061,28 +1061,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col7
name: sum
window function: GenericUDAFSumDouble
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1310,28 +1310,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col7
name: sum
window function: GenericUDAFSumDouble
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1559,28 +1559,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col7
name: sum
window function: GenericUDAFSumDouble
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: double)
+ expressions: _col2 (type: string), _col1 (type: string), _col5 (type: int), rank_window_0 (type: int), dense_rank_window_1 (type: int), sum_window_2 (type: double)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -1785,33 +1785,33 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: count_window_2
arguments: _col1
name: count
window function: GenericUDAFCountEvaluator
window frame: PRECEDING(MAX)~
window function definition
- alias: _wcol3
+ alias: sum_window_3
arguments: _col7
name: sum
window function: GenericUDAFSumDouble
window frame: PRECEDING(MAX)~
window function definition
- alias: _wcol4
+ alias: lag_window_4
arguments: _col5, 1, _col5
name: lag
window function: GenericUDAFLagEvaluator
@@ -1819,7 +1819,7 @@ STAGE PLANS:
isPivotResult: true
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _wcol2 (type: bigint), _col7 (type: double), _wcol3 (type: double), _col5 (type: int), (_col5 - _wcol4) (type: int)
+ expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), count_window_2 (type: bigint), _col7 (type: double), sum_window_3 (type: double), _col5 (type: int), (_col5 - lag_window_4) (type: int)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -2074,28 +2074,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col2, _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col2, _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col5
name: sum
window function: GenericUDAFSumLong
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint)
+ expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -2364,28 +2364,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col5
name: sum
window function: GenericUDAFSumLong
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint)
+ expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -2628,28 +2628,28 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol1
+ alias: dense_rank_window_1
arguments: _col1
name: dense_rank
window function: GenericUDAFDenseRankEvaluator
window frame: PRECEDING(MAX)~FOLLOWING(MAX)
isPivotResult: true
window function definition
- alias: _wcol2
+ alias: sum_window_2
arguments: _col5
name: sum
window function: GenericUDAFSumLong
window frame: PRECEDING(MAX)~
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col2 (type: string), _col1 (type: string), _wcol0 (type: int), _wcol1 (type: int), _col5 (type: int), _wcol2 (type: bigint), _wcol2 (type: bigint)
+ expressions: _col2 (type: string), _col1 (type: string), rank_window_0 (type: int), dense_rank_window_1 (type: int), _col5 (type: int), sum_window_2 (type: bigint), sum_window_2 (type: bigint)
outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
File Output Operator
Modified: hive/branches/cbo/ql/src/test/results/clientpositive/quotedid_basic.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/quotedid_basic.q.out?rev=1674737&r1=1674736&r2=1674737&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/quotedid_basic.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/quotedid_basic.q.out Mon Apr 20 05:56:44 2015
@@ -211,7 +211,7 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
@@ -219,7 +219,7 @@ STAGE PLANS:
isPivotResult: true
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _wcol0 (type: int)
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
@@ -315,7 +315,7 @@ STAGE PLANS:
raw input shape:
window functions:
window function definition
- alias: _wcol0
+ alias: rank_window_0
arguments: _col1
name: rank
window function: GenericUDAFRankEvaluator
@@ -323,7 +323,7 @@ STAGE PLANS:
isPivotResult: true
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
Select Operator
- expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _wcol0 (type: int)
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), rank_window_0 (type: int)
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
Modified: hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32.q.out?rev=1674737&r1=1674736&r2=1674737&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32.q.out Mon Apr 20 05:56:44 2015
@@ -113,16 +113,16 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
+ alias: z
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
+ predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: value (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -136,9 +136,12 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -146,11 +149,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -160,26 +165,23 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [y]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Map 3
Map Operator Tree:
TableScan
@@ -188,7 +190,7 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
+ predicate: (key is not null and value is not null) (type: boolean)
Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -197,7 +199,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -258,24 +260,24 @@ STAGE PLANS:
Map 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
input vertices:
1 Map 3
Position of Big Table: 0
@@ -286,13 +288,13 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ outputColumnNames: _col0, _col4, _col5
input vertices:
0 Map 1
Position of Big Table: 1
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col5 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col5 (type: string), _col0 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -328,12 +330,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -341,13 +340,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -357,23 +354,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
+ /src [y]
Stage: Stage-0
Move Operator
@@ -422,8 +422,8 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
Modified: hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out?rev=1674737&r1=1674736&r2=1674737&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out Mon Apr 20 05:56:44 2015
@@ -121,16 +121,16 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
+ alias: z
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
+ predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: value (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -144,9 +144,12 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -154,11 +157,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -168,26 +173,23 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [y]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Map 3
Map Operator Tree:
TableScan
@@ -196,7 +198,7 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
+ predicate: (key is not null and value is not null) (type: boolean)
Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -205,7 +207,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -266,24 +268,24 @@ STAGE PLANS:
Map 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
input vertices:
1 Map 3
Position of Big Table: 0
@@ -294,13 +296,13 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ outputColumnNames: _col0, _col4, _col5
input vertices:
0 Map 1
Position of Big Table: 1
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col5 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col5 (type: string), _col0 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -336,12 +338,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -349,13 +348,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -365,23 +362,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
+ /src [y]
Stage: Stage-0
Move Operator
@@ -430,8 +430,8 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
@@ -613,35 +613,34 @@ TOK_QUERY
STAGE DEPENDENCIES:
- Stage-4 is a root stage
- Stage-3 depends on stages: Stage-4
+ Stage-3 is a root stage
Stage-1 depends on stages: Stage-3
Stage-0 depends on stages: Stage-1
Stage-2 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-4
+ Stage: Stage-3
Spark
#### A masked pattern was here ####
Vertices:
- Map 3
+ Map 1
Map Operator Tree:
TableScan
- alias: x
- Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+ alias: w
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col0 (type: string)
+ 1 _col1 (type: string)
Position of Big Table: 1
Local Work:
Map Reduce Local Work
@@ -650,7 +649,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src1
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -660,14 +659,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -680,44 +679,39 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.src
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 216
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src1
- name: default.src1
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /src1 [x]
-
- Stage: Stage-3
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /src [w]
+ Map 3
Map Operator Tree:
TableScan
- alias: w
- Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ alias: x
+ Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: (value is not null and key is not null) (type: boolean)
+ Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
1 _col1 (type: string)
- Position of Big Table: 1
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -725,7 +719,7 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: src1
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
@@ -735,14 +729,14 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
@@ -755,20 +749,20 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.src1
numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ numRows 25
+ rawDataSize 191
+ serialization.ddl struct src1 { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
+ totalSize 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.src1
+ name: default.src1
Truncated Path -> Alias:
- /src [w]
+ /src1 [x]
Map 4
Map Operator Tree:
TableScan
@@ -783,22 +777,11 @@ STAGE PLANS:
expressions: key (type: string), value (type: string)
outputColumnNames: _col0, _col1
Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
+ Spark HashTable Sink Operator
keys:
- 0 _col0 (type: string)
+ 0 _col1 (type: string)
1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- input vertices:
- 0 Map 3
- Position of Big Table: 1
- Statistics: Num rows: 14 Data size: 108 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- Position of Big Table: 0
+ Position of Big Table: 0
Local Work:
Map Reduce Local Work
Path -> Alias:
@@ -875,57 +858,68 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col1 (type: string)
- outputColumnNames: _col1, _col4
+ outputColumnNames: _col1
input vertices:
- 1 Map 4
+ 1 Map 3
Position of Big Table: 0
Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
- 0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col1, _col3, _col6
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col4
input vertices:
- 0 Map 1
- Position of Big Table: 1
+ 1 Map 4
+ Position of Big Table: 0
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col3 (type: string), _col6 (type: string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- properties:
- COLUMN_STATS_ACCURATE true
- bucket_count -1
- columns key,value,val2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.dest_j1
- numFiles 1
- numRows 85
- rawDataSize 1600
- serialization.ddl struct dest_j1 { string key, string value, string val2}
- serialization.format 1
- serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 1685
-#### A masked pattern was here ####
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest_j1
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col1, _col3, _col6
+ input vertices:
+ 0 Map 1
+ Position of Big Table: 1
+ Statistics: Num rows: 332 Data size: 3534 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col3 (type: string), _col6 (type: string), _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 332 Data size: 3534 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 332 Data size: 3534 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ properties:
+ COLUMN_STATS_ACCURATE true
+ bucket_count -1
+ columns key,value,val2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.dest_j1
+ numFiles 1
+ numRows 85
+ rawDataSize 1600
+ serialization.ddl struct dest_j1 { string key, string value, string val2}
+ serialization.format 1
+ serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 1685
+#### A masked pattern was here ####
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest_j1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Local Work:
Map Reduce Local Work
Path -> Alias:
Modified: hive/branches/cbo/ql/src/test/results/clientpositive/spark/join33.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/spark/join33.q.out?rev=1674737&r1=1674736&r2=1674737&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/spark/join33.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/spark/join33.q.out Mon Apr 20 05:56:44 2015
@@ -113,16 +113,16 @@ STAGE PLANS:
Map 1
Map Operator Tree:
TableScan
- alias: y
+ alias: z
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: key is not null (type: boolean)
+ predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
+ expressions: value (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Spark HashTable Sink Operator
keys:
@@ -136,9 +136,12 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src
+ base file name: hr=11
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ partition values:
+ ds 2008-04-08
+ hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -146,11 +149,13 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
+ name default.srcpart
numFiles 1
numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -160,26 +165,23 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src
- numFiles 1
- numRows 500
- rawDataSize 5312
- serialization.ddl struct src { string key, string value}
+ name default.srcpart
+ partition_columns ds/hr
+ partition_columns.types string:string
+ serialization.ddl struct srcpart { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src
- name: default.src
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src [y]
+ /srcpart/ds=2008-04-08/hr=11 [z]
Map 3
Map Operator Tree:
TableScan
@@ -188,7 +190,7 @@ STAGE PLANS:
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: (value is not null and key is not null) (type: boolean)
+ predicate: (key is not null and value is not null) (type: boolean)
Statistics: Num rows: 7 Data size: 53 Basic stats: COMPLETE Column stats: NONE
Select Operator
expressions: key (type: string), value (type: string)
@@ -197,7 +199,7 @@ STAGE PLANS:
Spark HashTable Sink Operator
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
+ 1 _col0 (type: string)
Position of Big Table: 0
Local Work:
Map Reduce Local Work
@@ -258,24 +260,24 @@ STAGE PLANS:
Map 2
Map Operator Tree:
TableScan
- alias: z
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: ((11.0 = 11.0) and value is not null) (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
Map Join Operator
condition map:
Inner Join 0 to 1
keys:
0 _col0 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
input vertices:
1 Map 3
Position of Big Table: 0
@@ -286,13 +288,13 @@ STAGE PLANS:
keys:
0 _col0 (type: string)
1 _col3 (type: string)
- outputColumnNames: _col1, _col2, _col5
+ outputColumnNames: _col0, _col4, _col5
input vertices:
0 Map 1
Position of Big Table: 1
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
Select Operator
- expressions: _col5 (type: string), _col2 (type: string), _col1 (type: string)
+ expressions: _col5 (type: string), _col0 (type: string), _col4 (type: string)
outputColumnNames: _col0, _col1, _col2
Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
File Output Operator
@@ -328,12 +330,9 @@ STAGE PLANS:
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: hr=11
+ base file name: src
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- partition values:
- ds 2008-04-08
- hr 11
properties:
COLUMN_STATS_ACCURATE true
bucket_count -1
@@ -341,13 +340,11 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
+ name default.src
numFiles 1
numRows 500
- partition_columns ds/hr
- partition_columns.types string:string
rawDataSize 5312
- serialization.ddl struct srcpart { string key, string value}
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
totalSize 5812
@@ -357,23 +354,26 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE true
bucket_count -1
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.srcpart
- partition_columns ds/hr
- partition_columns.types string:string
- serialization.ddl struct srcpart { string key, string value}
+ name default.src
+ numFiles 1
+ numRows 500
+ rawDataSize 5312
+ serialization.ddl struct src { string key, string value}
serialization.format 1
serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 5812
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.srcpart
- name: default.srcpart
+ name: default.src
+ name: default.src
Truncated Path -> Alias:
- /srcpart/ds=2008-04-08/hr=11 [z]
+ /src [y]
Stage: Stage-0
Move Operator
@@ -422,8 +422,8 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Output: default@dest_j1
POSTHOOK: Lineage: dest_j1.key SIMPLE [(src1)x.FieldSchema(name:key, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.val2 SIMPLE [(src)y.FieldSchema(name:value, type:string, comment:default), ]
-POSTHOOK: Lineage: dest_j1.value EXPRESSION [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.val2 EXPRESSION [(src)y.FieldSchema(name:value, type:string, comment:default), ]
+POSTHOOK: Lineage: dest_j1.value SIMPLE [(srcpart)z.FieldSchema(name:value, type:string, comment:default), ]
PREHOOK: query: select * from dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1