http://git-wip-us.apache.org/repos/asf/hive/blob/fb7a676b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
index a4d1447..9114283 100644
--- a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
+++ b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
@@ -47,7 +47,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: x
@@ -123,26 +123,48 @@ STAGE PLANS:
name: default.src1
Truncated Path -> Alias:
/src1 [$hdt$_2:x]
- Map 3
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL
SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
- alias: z
- filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
+ alias: y
+ filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: value is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
keys:
- 0 _col3 (type: string)
+ 0 _col0 (type: string)
1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
Position of Big Table: 0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col3 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col3 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic
stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string), _col2
(type: string)
+ auto parallelism: false
Execution mode: vectorized
Local Work:
Map Reduce Local Work
@@ -151,27 +173,23 @@ 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
+ bucketing_version 2
column.name.delimiter ,
columns key,value
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
@@ -181,6 +199,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -188,122 +207,70 @@ STAGE PLANS:
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 [$hdt$_0:z]
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /src [$hdt$_1:y]
+ Map 4
Map Operator Tree:
TableScan
- alias: y
- filterExpr: key is not null (type: boolean)
+ alias: z
+ filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
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: value is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2, _col3
- input vertices:
- 1 Map 2
- Position of Big Table: 0
- Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col3 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2, _col4
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col2 (type: string), _col4 (type:
string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 605 Data size: 6427 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}}
- bucket_count -1
- bucketing_version 2
- column.name.delimiter ,
- columns key,value,val2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.dest_j1_n21
- numFiles 0
- numRows 0
- rawDataSize 0
- serialization.ddl struct dest_j1_n21 {
string key, string value, string val2}
- serialization.format 1
- serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 0
-#### A masked pattern was here ####
- serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest_j1_n21
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Path -> Alias:
#### A masked pattern was here ####
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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
- bucketing_version 2
column.name.delimiter ,
columns key,value
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
@@ -313,7 +280,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -321,20 +287,66 @@ STAGE PLANS:
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 [$hdt$_1:y]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:z]
+ Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col4
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col2 (type: string), _col4 (type: string),
_col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 605 Data size: 6427 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}}
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value,val2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.dest_j1_n21
+ numFiles 0
+ numRows 0
+ rawDataSize 0
+ serialization.ddl struct dest_j1_n21 { string key,
string value, string val2}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 0
+#### A masked pattern was here ####
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest_j1_n21
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-0
Move Operator
@@ -678,26 +690,51 @@ STAGE PLANS:
name: default.src1
Truncated Path -> Alias:
/src1 [$hdt$_3:z]
- Map 4
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 4 <- Map 3 (PARTITION-LEVEL SORT, 2), Map 5 (PARTITION-LEVEL
SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 3
Map Operator Tree:
TableScan
- alias: w
- filterExpr: value is not null (type: boolean)
+ alias: y
+ filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: value is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
keys:
- 0 _col1 (type: string)
+ 0 _col0 (type: string)
1 _col0 (type: string)
- Position of Big Table: 0
+ 2 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3, _col5
+ input vertices:
+ 0 Map 1
+ 1 Map 2
+ Position of Big Table: 2
+ Statistics: Num rows: 1100 Data size: 11686 Basic
stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 1100 Data size: 11686 Basic
stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: string), _col3
(type: string), _col5 (type: string)
+ auto parallelism: false
Execution mode: vectorized
Local Work:
Map Reduce Local Work
@@ -753,92 +790,31 @@ STAGE PLANS:
name: default.src
name: default.src
Truncated Path -> Alias:
- /src [$hdt$_0:w]
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 3
+ /src [$hdt$_1:y]
+ Map 5
Map Operator Tree:
TableScan
- alias: y
- filterExpr: key is not null (type: boolean)
+ alias: w
+ filterExpr: value is not null (type: boolean)
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: value is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- 2 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3, _col5
- input vertices:
- 0 Map 1
- 1 Map 2
- Position of Big Table: 2
- Statistics: Num rows: 1100 Data size: 11686 Basic
stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col3, _col5
- input vertices:
- 1 Map 4
- Position of Big Table: 0
- Statistics: Num rows: 1210 Data size: 12854 Basic
stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type:
string), _col5 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1210 Data size: 12854 Basic
stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 1210 Data size: 12854
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
{"BASIC_STATS":"true"}
- bucket_count -1
- bucketing_version 2
- column.name.delimiter ,
- columns key,value,val2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.dest_j1_n21
- numFiles 1
- numRows 85
- rawDataSize 1600
- serialization.ddl struct dest_j1_n21 {
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_n21
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
@@ -891,7 +867,55 @@ STAGE PLANS:
name: default.src
name: default.src
Truncated Path -> Alias:
- /src [$hdt$_1:y]
+ /src [$hdt$_0:w]
+ Reducer 4
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col3, _col5
+ Statistics: Num rows: 1210 Data size: 12854 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string),
_col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1210 Data size: 12854 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 1210 Data size: 12854 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 {"BASIC_STATS":"true"}
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value,val2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.dest_j1_n21
+ numFiles 2
+ numRows 85
+ rawDataSize 1600
+ serialization.ddl struct dest_j1_n21 { 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_n21
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-0
Move Operator
@@ -911,7 +935,7 @@ STAGE PLANS:
columns.types string:string:string
#### A masked pattern was here ####
name default.dest_j1_n21
- numFiles 1
+ numFiles 2
numRows 85
rawDataSize 1600
serialization.ddl struct dest_j1_n21 { string key, string
value, string val2}
@@ -1074,7 +1098,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: x
@@ -1150,26 +1174,48 @@ STAGE PLANS:
name: default.src1
Truncated Path -> Alias:
/src1 [$hdt$_2:x]
- Map 3
+
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL
SORT, 2)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
Map Operator Tree:
TableScan
- alias: z
- filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
+ alias: y
+ filterExpr: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
- predicate: value is not null (type: boolean)
+ predicate: key is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
Select Operator
- expressions: value (type: string)
+ expressions: key (type: string)
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
keys:
- 0 _col2 (type: string)
+ 0 _col0 (type: string)
1 _col0 (type: string)
+ outputColumnNames: _col1, _col2
+ input vertices:
+ 1 Map 3
Position of Big Table: 0
+ Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic
stats: COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Execution mode: vectorized
Local Work:
Map Reduce Local Work
@@ -1178,27 +1224,23 @@ 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
+ bucketing_version 2
column.name.delimiter ,
columns key,value
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
@@ -1208,6 +1250,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1215,122 +1258,70 @@ STAGE PLANS:
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 [$hdt$_0:z]
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /src [$hdt$_1:y]
+ Map 4
Map Operator Tree:
TableScan
- alias: y
- filterExpr: key is not null (type: boolean)
+ alias: z
+ filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
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: value is not null (type: boolean)
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string)
+ expressions: value (type: string)
outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2
- input vertices:
- 1 Map 2
- Position of Big Table: 0
- Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2, _col3
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type:
string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 605 Data size: 6427 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}}
- bucket_count -1
- bucketing_version 2
- column.name.delimiter ,
- columns key,value,val2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.dest_j2_n1
- numFiles 0
- numRows 0
- rawDataSize 0
- serialization.ddl struct dest_j2_n1 {
string key, string value, string val2}
- serialization.format 1
- serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- totalSize 0
-#### A masked pattern was here ####
- serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.dest_j2_n1
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Path -> Alias:
#### A masked pattern was here ####
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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
- bucketing_version 2
column.name.delimiter ,
columns key,value
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
@@ -1340,7 +1331,6 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1348,20 +1338,66 @@ STAGE PLANS:
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 [$hdt$_1:y]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:z]
+ Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col3 (type: string),
_col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 605 Data size: 6427 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","val2":"true","value":"true"}}
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value,val2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.dest_j2_n1
+ numFiles 0
+ numRows 0
+ rawDataSize 0
+ serialization.ddl struct dest_j2_n1 { string key,
string value, string val2}
+ serialization.format 1
+ serialization.lib
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ totalSize 0
+#### A masked pattern was here ####
+ serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ name: default.dest_j2_n1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-0
Move Operator
@@ -1535,40 +1571,49 @@ WHERE `value` IS NOT NULL) AS `t2`
LEFT JOIN (SELECT `key`
FROM `default`.`src`) AS `t3` ON `t2`.`key` = `t3`.`key`) ON `t0`.`value` =
`t2`.`value`
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-1 depends on stages: Stage-3
+ Stage-1 is a root stage
Stage-0 depends on stages: Stage-1
Stage-2 depends on stages: Stage-0
STAGE PLANS:
- Stage: Stage-3
+ Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL
SORT, 2)
+ Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 2), Reducer 2
(PARTITION-LEVEL SORT, 2)
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 1
Map Operator Tree:
TableScan
- alias: y
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ alias: x
+ filterExpr: value is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
GatherStats: false
- Select Operator
- expressions: key (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
+ Filter Operator
+ isSamplingPred: false
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col1 (type: string)
+ auto parallelism: false
Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Path -> Alias:
#### A masked pattern was here ####
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:
@@ -1580,14 +1625,14 @@ 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
@@ -1602,69 +1647,61 @@ 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 [$hdt$_2:y]
- Map 3
+ /src1 [$hdt$_1:x]
+ Map 4
Map Operator Tree:
TableScan
- alias: z
- filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
+ alias: y
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
GatherStats: false
- Filter Operator
- isSamplingPred: false
- predicate: value is not null (type: boolean)
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- Position of Big Table: 0
+ tag: 1
+ auto parallelism: false
Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Path -> Alias:
#### A masked pattern was here ####
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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
+ bucketing_version 2
column.name.delimiter ,
columns key,value
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
@@ -1674,6 +1711,7 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
+ COLUMN_STATS_ACCURATE
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1681,132 +1719,79 @@ STAGE PLANS:
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 [$hdt$_0:z]
-
- Stage: Stage-1
- Spark
-#### A masked pattern was here ####
- Vertices:
- Map 1
+ /src [$hdt$_2:y]
+ Map 5
Map Operator Tree:
TableScan
- alias: x
- filterExpr: value is not null (type: boolean)
- Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
+ alias: z
+ filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
GatherStats: false
Filter Operator
isSamplingPred: false
predicate: value is not null (type: boolean)
- Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
Select Operator
- expressions: key (type: string), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 25 Data size: 191 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Left Outer Join 0 to 1
- keys:
- 0 _col0 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1
- input vertices:
- 1 Map 2
- Position of Big Table: 0
- Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col0, _col1, _col3
- input vertices:
- 1 Map 3
- Position of Big Table: 0
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: string), _col3 (type:
string), _col1 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- GlobalTableId: 1
-#### A masked pattern was here ####
- NumFilesPerFileSink: 1
- Statistics: Num rows: 605 Data size: 6427 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
{"BASIC_STATS":"true"}
- bucket_count -1
- bucketing_version 2
- column.name.delimiter ,
- columns key,value,val2
- columns.comments
- columns.types string:string:string
-#### A masked pattern was here ####
- name default.dest_j2_n1
- numFiles 1
- numRows 85
- rawDataSize 1600
- serialization.ddl struct dest_j2_n1 {
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_j2_n1
- TotalFiles: 1
- GatherStats: true
- MultiFileSpray: false
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ tag: 1
+ auto parallelism: false
Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Path -> Alias:
#### A masked pattern was here ####
Path -> Partition:
#### A masked pattern was here ####
Partition
- base file name: src1
+ 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
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
- bucketing_version 2
column.name.delimiter ,
columns key,value
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
+ name default.srcpart
numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { string key, string value}
+ numRows 500
+ partition_columns ds/hr
+ partition_columns.types string:string
+ rawDataSize 5312
+ serialization.ddl struct srcpart { 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
input format: org.apache.hadoop.mapred.TextInputFormat
output format:
org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
properties:
- COLUMN_STATS_ACCURATE
{"BASIC_STATS":"true","COLUMN_STATS":{"key":"true","value":"true"}}
bucket_count -1
bucketing_version 2
column.name.delimiter ,
@@ -1814,20 +1799,86 @@ STAGE PLANS:
columns.comments 'default','default'
columns.types string:string
#### A masked pattern was here ####
- name default.src1
- numFiles 1
- numRows 25
- rawDataSize 191
- serialization.ddl struct src1 { 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 216
#### A masked pattern was here ####
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
- name: default.src1
- name: default.src1
+ name: default.srcpart
+ name: default.srcpart
Truncated Path -> Alias:
- /src1 [$hdt$_1:x]
+ /srcpart/ds=2008-04-08/hr=11 [$hdt$_0:z]
+ Reducer 2
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Left Outer Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ null sort order: a
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
+ tag: 0
+ value expressions: _col0 (type: string)
+ auto parallelism: false
+ Reducer 3
+ Needs Tagging: true
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col3 (type: string),
_col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ GlobalTableId: 1
+#### A masked pattern was here ####
+ NumFilesPerFileSink: 1
+ Statistics: Num rows: 605 Data size: 6427 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 {"BASIC_STATS":"true"}
+ bucket_count -1
+ bucketing_version 2
+ column.name.delimiter ,
+ columns key,value,val2
+ columns.comments
+ columns.types string:string:string
+#### A masked pattern was here ####
+ name default.dest_j2_n1
+ numFiles 2
+ numRows 85
+ rawDataSize 1600
+ serialization.ddl struct dest_j2_n1 { 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_j2_n1
+ TotalFiles: 1
+ GatherStats: true
+ MultiFileSpray: false
Stage: Stage-0
Move Operator
@@ -1847,7 +1898,7 @@ STAGE PLANS:
columns.types string:string:string
#### A masked pattern was here ####
name default.dest_j2_n1
- numFiles 1
+ numFiles 2
numRows 85
rawDataSize 1600
serialization.ddl struct dest_j2_n1 { string key, string
value, string val2}
@@ -2014,7 +2065,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: x
@@ -2034,29 +2085,11 @@ STAGE PLANS:
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Map 3
- Map Operator Tree:
- TableScan
- alias: x
- filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col2 (type: string)
- 1 _col0 (type: string)
- Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL
SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2080,33 +2113,58 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col1, _col2
input vertices:
- 1 Map 2
+ 1 Map 3
Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2, _col3
- input vertices:
- 1 Map 3
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type:
string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 605 Data size: 6427 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.dest_j2_n1
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic
stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Execution mode: vectorized
Local Work:
Map Reduce Local Work
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: x
+ filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ 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
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col3 (type: string),
_col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 605 Data size: 6427 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.dest_j2_n1
Stage: Stage-0
Move Operator
@@ -2261,7 +2319,7 @@ STAGE PLANS:
Spark
#### A masked pattern was here ####
Vertices:
- Map 2
+ Map 3
Map Operator Tree:
TableScan
alias: x
@@ -2281,29 +2339,11 @@ STAGE PLANS:
Execution mode: vectorized
Local Work:
Map Reduce Local Work
- Map 3
- Map Operator Tree:
- TableScan
- alias: y
- filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Filter Operator
- predicate: value is not null (type: boolean)
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Select Operator
- expressions: value (type: string)
- outputColumnNames: _col0
- Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col2 (type: string)
- 1 _col0 (type: string)
- Execution mode: vectorized
- Local Work:
- Map Reduce Local Work
Stage: Stage-1
Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL
SORT, 2)
#### A masked pattern was here ####
Vertices:
Map 1
@@ -2327,33 +2367,58 @@ STAGE PLANS:
1 _col0 (type: string)
outputColumnNames: _col1, _col2
input vertices:
- 1 Map 2
+ 1 Map 3
Statistics: Num rows: 550 Data size: 5843 Basic stats:
COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col2 (type: string)
- 1 _col0 (type: string)
- outputColumnNames: _col1, _col2, _col3
- input vertices:
- 1 Map 3
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col1 (type: string), _col3 (type:
string), _col2 (type: string)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 605 Data size: 6427 Basic
stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 605 Data size: 6427 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.dest_j2_n1
+ Reduce Output Operator
+ key expressions: _col2 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col2 (type: string)
+ Statistics: Num rows: 550 Data size: 5843 Basic
stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
Execution mode: vectorized
Local Work:
Map Reduce Local Work
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: y
+ filterExpr: ((ds = '2008-04-08') and (11.0D = 11.0D) and
value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ 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
+ Execution mode: vectorized
+ Reducer 2
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1, _col2, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string), _col3 (type: string),
_col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats:
COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 605 Data size: 6427 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.dest_j2_n1
Stage: Stage-0
Move Operator