You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by he...@apache.org on 2010/10/26 20:28:25 UTC
svn commit: r1027672 [12/13] - in /hadoop/hive/trunk: ./
ql/src/gen-javabean/org/apache/hadoop/hive/ql/plan/api/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/exec/persistence/
ql/src/java/org/apache/hadoop/hive/ql/i...
Modified: hadoop/hive/trunk/ql/src/test/results/clientpositive/skewjoin.q.out
URL: http://svn.apache.org/viewvc/hadoop/hive/trunk/ql/src/test/results/clientpositive/skewjoin.q.out?rev=1027672&r1=1027671&r2=1027672&view=diff
==============================================================================
--- hadoop/hive/trunk/ql/src/test/results/clientpositive/skewjoin.q.out (original)
+++ hadoop/hive/trunk/ql/src/test/results/clientpositive/skewjoin.q.out Tue Oct 26 18:28:23 2010
@@ -56,8 +56,9 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-5 depends on stages: Stage-1 , consists of Stage-4
- Stage-4
+ Stage-5 depends on stages: Stage-1 , consists of Stage-6
+ Stage-6
+ Stage-4 depends on stages: Stage-6
Stage-0 depends on stages: Stage-1, Stage-4
Stage-2 depends on stages: Stage-0
@@ -130,6 +131,27 @@ STAGE PLANS:
Stage: Stage-5
Conditional Operator
+ Stage: Stage-6
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ 1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ 1
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {0_VALUE_0}
+ 1 {1_VALUE_0}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0]]
+ 1 [Column[joinkey0]]
+ outputColumnNames: _col0, _col5
+ Position of Big Table: 0
+
Stage: Stage-4
Map Reduce
Alias -> Map Operator Tree:
@@ -170,46 +192,6 @@ STAGE PLANS:
name: dest_j1
Local Work:
Map Reduce Local Work
- Alias -> Map Local Tables:
- 1
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- 1
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0 {0_VALUE_0}
- 1 {1_VALUE_0}
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0]]
- 1 [Column[joinkey0]]
- outputColumnNames: _col0, _col5
- Position of Big Table: 0
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col5
- type: string
- outputColumnNames: _col0, _col1
- Select Operator
- expressions:
- expr: UDFToInteger(_col0)
- type: int
- expr: _col1
- type: string
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 1
- 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: dest_j1
Stage: Stage-0
Move Operator
@@ -240,11 +222,11 @@ POSTHOOK: Lineage: dest_j1.value SIMPLE
PREHOOK: query: SELECT sum(hash(key)), sum(hash(value)) FROM dest_j1
PREHOOK: type: QUERY
PREHOOK: Input: default@dest_j1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-32-20_088_265990891413321286/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-04-50_849_4926018945681458170/-mr-10000
POSTHOOK: query: SELECT sum(hash(key)), sum(hash(value)) FROM dest_j1
POSTHOOK: type: QUERY
POSTHOOK: Input: default@dest_j1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-32-20_088_265990891413321286/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-04-50_849_4926018945681458170/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
278697 101852390308
@@ -394,7 +376,7 @@ PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
PREHOOK: Input: default@t3
PREHOOK: Input: default@t4
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-32-59_862_2469201922490952543/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-30_958_5269065287490367280/-mr-10000
POSTHOOK: query: SELECT /*+ STREAMTABLE(a) */ *
FROM T1 a JOIN T2 b ON a.key = b.key
JOIN T3 c ON b.key = c.key
@@ -404,7 +386,7 @@ POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
POSTHOOK: Input: default@t3
POSTHOOK: Input: default@t4
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-32-59_862_2469201922490952543/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-30_958_5269065287490367280/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
2 12 2 22 2 12 2 12
@@ -554,7 +536,7 @@ PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
PREHOOK: Input: default@t3
PREHOOK: Input: default@t4
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-33-05_555_320549944562504832/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-36_527_8632422920697698077/-mr-10000
POSTHOOK: query: SELECT /*+ STREAMTABLE(a,c) */ *
FROM T1 a JOIN T2 b ON a.key = b.key
JOIN T3 c ON b.key = c.key
@@ -564,7 +546,7 @@ POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
POSTHOOK: Input: default@t3
POSTHOOK: Input: default@t4
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-33-05_555_320549944562504832/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-36_527_8632422920697698077/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
2 12 2 22 2 12 2 12
@@ -654,7 +636,7 @@ STAGE PLANS:
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- file:/tmp/nzhang/hive_2010-09-14_17-33-11_763_3320930002757015267/-mr-10002
+ file:/tmp/liyintang/hive_2010-10-19_10-05-42_041_7344594961437099384/-mr-10002
Reduce Output Operator
sort order:
tag: -1
@@ -699,12 +681,12 @@ PREHOOK: query: FROM T1 a JOIN src c ON
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-33-11_947_4948549999809455027/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-42_198_1840888490716635874/-mr-10000
POSTHOOK: query: FROM T1 a JOIN src c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-33-11_947_4948549999809455027/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-42_198_1840888490716635874/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
198 6274 194
@@ -729,8 +711,9 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-5 depends on stages: Stage-1 , consists of Stage-4
- Stage-4
+ Stage-5 depends on stages: Stage-1 , consists of Stage-6
+ Stage-6
+ Stage-4 depends on stages: Stage-6
Stage-2 depends on stages: Stage-1, Stage-4
Stage-0 is a root stage
@@ -812,6 +795,27 @@ STAGE PLANS:
Stage: Stage-5
Conditional Operator
+ Stage: Stage-6
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ 1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ 1
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {1_VALUE_0} {1_VALUE_1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0]]
+ 1 [Column[joinkey0]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+
Stage: Stage-4
Map Reduce
Alias -> Map Operator Tree:
@@ -850,49 +854,11 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Local Work:
Map Reduce Local Work
- Alias -> Map Local Tables:
- 1
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- 1
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1 {1_VALUE_0} {1_VALUE_1}
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0]]
- 1 [Column[joinkey0]]
- outputColumnNames: _col2, _col3
- Position of Big Table: 0
- Select Operator
- expressions:
- expr: _col2
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col2, _col3
- Group By Operator
- aggregations:
- expr: sum(hash(_col2))
- expr: sum(hash(_col3))
- bucketGroup: false
- mode: hash
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- file:/tmp/nzhang/hive_2010-09-14_17-33-21_233_135416400611149220/-mr-10002
+ file:/tmp/liyintang/hive_2010-10-19_10-05-50_405_6110056714768738373/-mr-10002
Reduce Output Operator
sort order:
tag: -1
@@ -936,7 +902,7 @@ ON (x.key = Y.key)
SELECT sum(hash(Y.key)), sum(hash(Y.value))
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-33-21_509_6518293255572217703/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-50_724_433499985548447694/-mr-10000
POSTHOOK: query: FROM
(SELECT src.* FROM src) x
JOIN
@@ -945,7 +911,7 @@ ON (x.key = Y.key)
SELECT sum(hash(Y.key)), sum(hash(Y.value))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-33-21_509_6518293255572217703/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-05-50_724_433499985548447694/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
44481300 101852390308
@@ -970,8 +936,9 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-5 depends on stages: Stage-1 , consists of Stage-4
- Stage-4
+ Stage-5 depends on stages: Stage-1 , consists of Stage-6
+ Stage-6
+ Stage-4 depends on stages: Stage-6
Stage-2 depends on stages: Stage-1, Stage-4
Stage-0 is a root stage
@@ -1063,6 +1030,27 @@ STAGE PLANS:
Stage: Stage-5
Conditional Operator
+ Stage: Stage-6
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ 1
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ 1
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {1_VALUE_0} {1_VALUE_1}
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0], Column[joinkey1]]
+ 1 [Column[joinkey0], Column[joinkey1]]
+ outputColumnNames: _col2, _col3
+ Position of Big Table: 0
+
Stage: Stage-4
Map Reduce
Alias -> Map Operator Tree:
@@ -1101,49 +1089,11 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Local Work:
Map Reduce Local Work
- Alias -> Map Local Tables:
- 1
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- 1
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- condition expressions:
- 0
- 1 {1_VALUE_0} {1_VALUE_1}
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0], Column[joinkey1]]
- 1 [Column[joinkey0], Column[joinkey1]]
- outputColumnNames: _col2, _col3
- Position of Big Table: 0
- Select Operator
- expressions:
- expr: _col2
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col2, _col3
- Group By Operator
- aggregations:
- expr: sum(hash(_col2))
- expr: sum(hash(_col3))
- bucketGroup: false
- mode: hash
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- file:/tmp/nzhang/hive_2010-09-14_17-35-01_721_1099039694801681089/-mr-10002
+ file:/tmp/liyintang/hive_2010-10-19_10-06-47_474_6216702342566228377/-mr-10002
Reduce Output Operator
sort order:
tag: -1
@@ -1187,7 +1137,7 @@ ON (x.key = Y.key and substring(x.value,
SELECT sum(hash(Y.key)), sum(hash(Y.value))
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-35-02_103_1296780027454091580/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-06-47_800_6350809369258245956/-mr-10000
POSTHOOK: query: FROM
(SELECT src.* FROM src) x
JOIN
@@ -1196,7 +1146,7 @@ ON (x.key = Y.key and substring(x.value,
SELECT sum(hash(Y.key)), sum(hash(Y.value))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-35-02_103_1296780027454091580/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-06-47_800_6350809369258245956/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
NULL NULL
@@ -1229,10 +1179,12 @@ ABSTRACT SYNTAX TREE:
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-7 depends on stages: Stage-1 , consists of Stage-5, Stage-6
- Stage-5
+ Stage-7 depends on stages: Stage-1 , consists of Stage-8, Stage-9
+ Stage-8
+ Stage-5 depends on stages: Stage-8
Stage-2 depends on stages: Stage-1, Stage-5, Stage-6
- Stage-6
+ Stage-9
+ Stage-6 depends on stages: Stage-9
Stage-0 is a root stage
STAGE PLANS:
@@ -1349,6 +1301,49 @@ STAGE PLANS:
Stage: Stage-7
Conditional Operator
+ Stage: Stage-8
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ 1
+ Fetch Operator
+ limit: -1
+ 2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ 1
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {0_VALUE_0}
+ 1 {1_VALUE_0}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0]]
+ 1 [Column[joinkey0]]
+ 2 [Column[joinkey0]]
+ outputColumnNames: _col0, _col3
+ Position of Big Table: 0
+ 2
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {0_VALUE_0}
+ 1 {1_VALUE_0}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0]]
+ 1 [Column[joinkey0]]
+ 2 [Column[joinkey0]]
+ outputColumnNames: _col0, _col3
+ Position of Big Table: 0
+
Stage: Stage-5
Map Reduce
Alias -> Map Operator Tree:
@@ -1390,91 +1385,11 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Local Work:
Map Reduce Local Work
- Alias -> Map Local Tables:
- 1
- Fetch Operator
- limit: -1
- 2
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- 1
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {0_VALUE_0}
- 1 {1_VALUE_0}
- 2
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0]]
- 1 [Column[joinkey0]]
- 2 [Column[joinkey0]]
- outputColumnNames: _col0, _col3
- Position of Big Table: 0
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col0, _col3
- Group By Operator
- aggregations:
- expr: sum(hash(_col0))
- expr: sum(hash(_col3))
- bucketGroup: false
- mode: hash
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- 2
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {0_VALUE_0}
- 1 {1_VALUE_0}
- 2
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0]]
- 1 [Column[joinkey0]]
- 2 [Column[joinkey0]]
- outputColumnNames: _col0, _col3
- Position of Big Table: 0
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col0, _col3
- Group By Operator
- aggregations:
- expr: sum(hash(_col0))
- expr: sum(hash(_col3))
- bucketGroup: false
- mode: hash
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- file:/tmp/nzhang/hive_2010-09-14_17-36-00_558_8264505707294012856/-mr-10002
+ file:/tmp/liyintang/hive_2010-10-19_10-07-40_748_888888270570061665/-mr-10002
Reduce Output Operator
sort order:
tag: -1
@@ -1505,6 +1420,49 @@ STAGE PLANS:
input format: org.apache.hadoop.mapred.TextInputFormat
output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ 0
+ Fetch Operator
+ limit: -1
+ 2
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ 0
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {0_VALUE_0}
+ 1 {1_VALUE_0}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0]]
+ 1 [Column[joinkey0]]
+ 2 [Column[joinkey0]]
+ outputColumnNames: _col0, _col3
+ Position of Big Table: 1
+ 2
+ Common Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {0_VALUE_0}
+ 1 {1_VALUE_0}
+ 2
+ handleSkewJoin: false
+ keys:
+ 0 [Column[joinkey0]]
+ 1 [Column[joinkey0]]
+ 2 [Column[joinkey0]]
+ outputColumnNames: _col0, _col3
+ Position of Big Table: 1
+
Stage: Stage-6
Map Reduce
Alias -> Map Operator Tree:
@@ -1546,86 +1504,6 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Local Work:
Map Reduce Local Work
- Alias -> Map Local Tables:
- 0
- Fetch Operator
- limit: -1
- 2
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- 0
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {0_VALUE_0}
- 1 {1_VALUE_0}
- 2
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0]]
- 1 [Column[joinkey0]]
- 2 [Column[joinkey0]]
- outputColumnNames: _col0, _col3
- Position of Big Table: 1
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col0, _col3
- Group By Operator
- aggregations:
- expr: sum(hash(_col0))
- expr: sum(hash(_col3))
- bucketGroup: false
- mode: hash
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- 2
- Common Join Operator
- condition map:
- Inner Join 0 to 1
- Inner Join 0 to 2
- condition expressions:
- 0 {0_VALUE_0}
- 1 {1_VALUE_0}
- 2
- handleSkewJoin: false
- keys:
- 0 [Column[joinkey0]]
- 1 [Column[joinkey0]]
- 2 [Column[joinkey0]]
- outputColumnNames: _col0, _col3
- Position of Big Table: 1
- Select Operator
- expressions:
- expr: _col0
- type: string
- expr: _col3
- type: string
- outputColumnNames: _col0, _col3
- Group By Operator
- aggregations:
- expr: sum(hash(_col0))
- expr: sum(hash(_col3))
- bucketGroup: false
- mode: hash
- outputColumnNames: _col0, _col1
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Stage: Stage-0
Fetch Operator
@@ -1643,7 +1521,7 @@ JOIN
ON src1.c1 = src3.c5 AND src3.c5 < 80
PREHOOK: type: QUERY
PREHOOK: Input: default@src
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-36-01_143_2592368341555694197/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-07-41_326_108115999211054386/-mr-10000
POSTHOOK: query: SELECT sum(hash(src1.c1)), sum(hash(src2.c4))
FROM
(SELECT src.key as c1, src.value as c2 from src) src1
@@ -1655,7 +1533,7 @@ JOIN
ON src1.c1 = src3.c5 AND src3.c5 < 80
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-36-01_143_2592368341555694197/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-07-41_326_108115999211054386/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
293143 -136853010385
@@ -1671,11 +1549,35 @@ ABSTRACT SYNTAX TREE:
(TOK_QUERY (TOK_FROM (TOK_LEFTOUTERJOIN (TOK_TABREF T1 k) (TOK_TABREF T1 v) (= (+ (. (TOK_TABLE_OR_COL k) key) 1) (. (TOK_TABLE_OR_COL v) key)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_HINTLIST (TOK_HINT TOK_MAPJOIN (TOK_HINTARGLIST v))) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL k) key)))) (TOK_SELEXPR (TOK_FUNCTION sum (TOK_FUNCTION hash (. (TOK_TABLE_OR_COL v) val)))))))
STAGE DEPENDENCIES:
- Stage-1 is a root stage
+ Stage-4 is a root stage
+ Stage-1 depends on stages: Stage-4
Stage-2 depends on stages: Stage-1
Stage-0 is a root stage
STAGE PLANS:
+ Stage: Stage-4
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ v
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ v
+ TableScan
+ alias: v
+ Common Join Operator
+ condition map:
+ Left Outer Join0 to 1
+ condition expressions:
+ 0 {key}
+ 1 {val}
+ handleSkewJoin: false
+ keys:
+ 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key], Const int 1()]
+ 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
+ outputColumnNames: _col0, _col5
+ Position of Big Table: 0
+
Stage: Stage-1
Map Reduce
Alias -> Map Operator Tree:
@@ -1702,37 +1604,11 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Local Work:
Map Reduce Local Work
- Alias -> Map Local Tables:
- v
- Fetch Operator
- limit: -1
- Alias -> Map Local Operator Tree:
- v
- TableScan
- alias: v
- Common Join Operator
- condition map:
- Left Outer Join0 to 1
- condition expressions:
- 0 {key}
- 1 {val}
- handleSkewJoin: false
- keys:
- 0 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key], Const int 1()]
- 1 [class org.apache.hadoop.hive.ql.udf.generic.GenericUDFBridge(Column[key]()]
- outputColumnNames: _col0, _col5
- Position of Big Table: 0
- File Output Operator
- compressed: false
- GlobalTableId: 0
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
Stage: Stage-2
Map Reduce
Alias -> Map Operator Tree:
- file:/tmp/nzhang/hive_2010-09-14_17-37-07_971_7104147537843225861/-mr-10002
+ file:/tmp/liyintang/hive_2010-10-19_10-08-41_351_6278160534430301243/-mr-10002
Select Operator
expressions:
expr: _col0
@@ -1792,55 +1668,55 @@ STAGE PLANS:
PREHOOK: query: SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-08_099_6986157948200697425/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-08-41_490_8646731125667777254/-mr-10000
POSTHOOK: query: SELECT /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) FROM T1 k LEFT OUTER JOIN T1 v ON k.key+1=v.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-08_099_6986157948200697425/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-08-41_490_8646731125667777254/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
372 6320
PREHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-15_103_7565149712452268536/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-08-49_667_1957853727227558594/-mr-10000
POSTHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.val
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-15_103_7565149712452268536/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-08-49_667_1957853727227558594/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
NULL NULL
PREHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-21_720_2771757907682080403/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-08-57_949_3421678461487010281/-mr-10000
POSTHOOK: query: select /*+ mapjoin(k)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-21_720_2771757907682080403/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-08-57_949_3421678461487010281/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
429 12643
PREHOOK: query: select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-28_452_6093434418535192386/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-06_106_9105927732182868271/-mr-10000
POSTHOOK: query: select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-28_452_6093434418535192386/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-06_106_9105927732182868271/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
429 12643
PREHOOK: query: select count(1) from T1 a join T1 b on a.key = b.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-38_889_1047609014892238447/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-17_819_6956454420254919929/-mr-10000
POSTHOOK: query: select count(1) from T1 a join T1 b on a.key = b.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-38_889_1047609014892238447/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-17_819_6956454420254919929/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
8
@@ -1848,12 +1724,12 @@ PREHOOK: query: FROM T1 a LEFT OUTER JOI
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-49_221_8506210790545243082/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-29_643_1471344657735837027/-mr-10000
POSTHOOK: query: FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key SELECT sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-49_221_8506210790545243082/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-29_643_1471344657735837027/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
317 9462 50
@@ -1861,12 +1737,12 @@ PREHOOK: query: FROM T1 a RIGHT OUTER JO
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-56_340_6168859629052833187/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-37_719_1766810325799201220/-mr-10000
POSTHOOK: query: FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-37-56_340_6168859629052833187/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-37_719_1766810325799201220/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
51 1570 318
@@ -1874,12 +1750,12 @@ PREHOOK: query: FROM T1 a FULL OUTER JOI
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-03_577_4249269048370838540/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-45_768_5626269091454711692/-mr-10000
POSTHOOK: query: FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key SELECT /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key))
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-03_577_4249269048370838540/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-45_768_5626269091454711692/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
317 9462 318
@@ -1887,12 +1763,12 @@ PREHOOK: query: SELECT sum(hash(src1.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-10_756_6811760235799500968/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-53_877_4064218124982922608/-mr-10000
POSTHOOK: query: SELECT sum(hash(src1.key)), sum(hash(src1.val)), sum(hash(src2.key)) FROM T1 src1 LEFT OUTER JOIN T2 src2 ON src1.key+1 = src2.key RIGHT OUTER JOIN T2 src3 ON src2.key = src3.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-10_756_6811760235799500968/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-09-53_877_4064218124982922608/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
370 11003 377
@@ -1900,23 +1776,23 @@ PREHOOK: query: SELECT sum(hash(src1.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
PREHOOK: Input: default@t2
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-18_994_7191347978897240811/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-10-00_997_7881612208030962780/-mr-10000
POSTHOOK: query: SELECT sum(hash(src1.key)), sum(hash(src1.val)), sum(hash(src2.key)) FROM T1 src1 JOIN T2 src2 ON src1.key+1 = src2.key JOIN T2 src3 ON src2.key = src3.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
POSTHOOK: Input: default@t2
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-18_994_7191347978897240811/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-10-00_997_7881612208030962780/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
370 11003 377
PREHOOK: query: select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key
PREHOOK: type: QUERY
PREHOOK: Input: default@t1
-PREHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-35_614_8013112114265683326/-mr-10000
+PREHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-10-21_614_76890166910035533/-mr-10000
POSTHOOK: query: select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@t1
-POSTHOOK: Output: file:/tmp/nzhang/hive_2010-09-14_17-38-35_614_8013112114265683326/-mr-10000
+POSTHOOK: Output: file:/tmp/liyintang/hive_2010-10-19_10-10-21_614_76890166910035533/-mr-10000
POSTHOOK: Lineage: dest_j1.key EXPRESSION [(src)src1.FieldSchema(name:key, type:string, comment:default), ]
POSTHOOK: Lineage: dest_j1.value SIMPLE [(src)src2.FieldSchema(name:value, type:string, comment:default), ]
372 6320