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 2014/05/30 19:37:15 UTC
svn commit: r1598678 [8/31] - in /hive/trunk:
cli/src/java/org/apache/hadoop/hive/cli/
common/src/java/org/apache/hadoop/hive/common/io/
itests/util/src/main/java/org/apache/hadoop/hive/ql/
ql/src/java/org/apache/hadoop/hive/ql/ ql/src/java/org/apache/...
Modified: hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out?rev=1598678&r1=1598677&r2=1598678&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/correlationoptimizer6.q.out Fri May 30 17:37:05 2014
@@ -1,4 +1,6 @@
-PREHOOK: query: -- When Correlation Optimizer is turned off, 6 MR jobs are needed.
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+-- When Correlation Optimizer is turned off, 6 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
-- The first job will evaluate subquery xx, subquery yy, and xx join yy.
EXPLAIN
@@ -7,9 +9,11 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
-POSTHOOK: query: -- When Correlation Optimizer is turned off, 6 MR jobs are needed.
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+-- When Correlation Optimizer is turned off, 6 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
-- The first job will evaluate subquery xx, subquery yy, and xx join yy.
EXPLAIN
@@ -18,16 +22,15 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-2, Stage-7
- Stage-4 depends on stages: Stage-3
- Stage-6 is a root stage
- Stage-7 depends on stages: Stage-6
- Stage-0 depends on stages: Stage-4
+ Stage-3 depends on stages: Stage-2, Stage-6
+ Stage-5 is a root stage
+ Stage-6 depends on stages: Stage-5
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
Stage: Stage-1
@@ -136,32 +139,13 @@ STAGE PLANS:
Statistics: Num rows: 34 Data size: 3459 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
- sort order: ++++
Statistics: Num rows: 34 Data size: 3459 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 34 Data size: 3459 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 34 Data size: 3459 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
+ 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
- Stage: Stage-6
+ Stage: Stage-5
Map Reduce
Map Operator Tree:
TableScan
@@ -207,7 +191,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-7
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -246,7 +230,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -256,7 +240,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -282,7 +266,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, xx.cnt, yy.key, yy.cnt
@@ -290,12 +274,11 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -378,10 +361,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Join Operator
condition map:
Inner Join 0 to 1
@@ -422,30 +406,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
- sort order: ++++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -458,7 +423,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -468,7 +433,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -495,7 +460,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: -- Enable hive.auto.convert.join.
EXPLAIN
@@ -504,16 +469,15 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-9 is a root stage
- Stage-2 depends on stages: Stage-9
- Stage-3 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-3
+ Stage-8 is a root stage
+ Stage-2 depends on stages: Stage-8
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
- Stage: Stage-9
+ Stage: Stage-8
Map Reduce Local Work
Alias -> Map Local Tables:
xx:x
@@ -640,10 +604,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
@@ -670,30 +635,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
- sort order: ++++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -706,7 +652,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -716,7 +662,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -744,7 +690,7 @@ SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 3 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -754,13 +700,12 @@ SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
- Stage-3 depends on stages: Stage-2
- Stage-0 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-2
STAGE PLANS:
Stage: Stage-1
@@ -837,30 +782,11 @@ STAGE PLANS:
Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-3
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 31 Data size: 3196 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 31 Data size: 3196 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
+ 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
Stage: Stage-0
Fetch Operator
@@ -872,7 +798,7 @@ PREHOOK: query: SELECT xx.key, yy.key, y
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -881,7 +807,7 @@ POSTHOOK: query: SELECT xx.key, yy.key,
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -906,19 +832,18 @@ SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -971,10 +896,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
@@ -1001,30 +927,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -1036,7 +943,7 @@ PREHOOK: query: SELECT xx.key, yy.key, y
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -1045,7 +952,7 @@ POSTHOOK: query: SELECT xx.key, yy.key,
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x GROUP BY x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -1073,7 +980,7 @@ SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -1083,14 +990,13 @@ SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-3 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-3
- Stage-0 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
Stage: Stage-1
@@ -1201,30 +1107,11 @@ STAGE PLANS:
Statistics: Num rows: 34 Data size: 3459 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
Statistics: Num rows: 34 Data size: 3459 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 34 Data size: 3459 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 34 Data size: 3459 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
+ 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
Stage: Stage-0
Fetch Operator
@@ -1236,7 +1123,7 @@ PREHOOK: query: SELECT xx.key, yy.key, y
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -1245,7 +1132,7 @@ POSTHOOK: query: SELECT xx.key, yy.key,
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -1270,19 +1157,18 @@ SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, yy.key, yy.cnt
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1333,10 +1219,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Join Operator
condition map:
Inner Join 0 to 1
@@ -1377,30 +1264,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -1412,7 +1280,7 @@ PREHOOK: query: SELECT xx.key, yy.key, y
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -1421,7 +1289,7 @@ POSTHOOK: query: SELECT xx.key, yy.key,
FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON xx.key=yy.key ORDER BY xx.key, yy.key, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -1449,7 +1317,7 @@ SELECT xx.key, xx.cnt, yy.key
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -1459,17 +1327,16 @@ SELECT xx.key, xx.cnt, yy.key
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-4 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-3
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
@@ -1515,7 +1382,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-4
+ Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
@@ -1577,30 +1444,11 @@ STAGE PLANS:
Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
- sort order: +++
Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 63 Data size: 6393 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
+ 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
Stage: Stage-0
Fetch Operator
@@ -1612,7 +1460,7 @@ PREHOOK: query: SELECT xx.key, xx.cnt, y
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -1621,7 +1469,7 @@ POSTHOOK: query: SELECT xx.key, xx.cnt,
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -1668,19 +1516,18 @@ SELECT xx.key, xx.cnt, yy.key
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, xx.cnt, yy.key
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -1755,10 +1602,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Mux Operator
Statistics: Num rows: 62 Data size: 6244 Basic stats: COMPLETE Column stats: NONE
Join Operator
@@ -1775,30 +1623,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
- sort order: +++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -1810,7 +1639,7 @@ PREHOOK: query: SELECT xx.key, xx.cnt, y
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -1819,7 +1648,7 @@ POSTHOOK: query: SELECT xx.key, xx.cnt,
FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN src yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -1870,8 +1699,7 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -1882,18 +1710,16 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-4 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-3
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
@@ -1939,7 +1765,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-4
+ Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
@@ -2011,30 +1837,11 @@ STAGE PLANS:
Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 127 Data size: 12786 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
+ 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
Stage: Stage-0
Fetch Operator
@@ -2047,8 +1854,7 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -2058,8 +1864,7 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -2110,8 +1915,7 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -2122,13 +1926,11 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -2189,10 +1991,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Join Operator
condition map:
Inner Join 0 to 1
@@ -2235,30 +2038,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -2271,8 +2055,7 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -2282,8 +2065,7 @@ FROM src1 xx
JOIN src zz ON xx.key=zz.key
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
-ON zz.key=yy.key
-ORDER BY xx.key, yy.key, yy.cnt
+ON zz.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -2334,7 +2116,7 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 4 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -2345,17 +2127,16 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-3 is a root stage
- Stage-4 depends on stages: Stage-3
- Stage-1 depends on stages: Stage-4
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-2 is a root stage
+ Stage-3 depends on stages: Stage-2
+ Stage-1 depends on stages: Stage-3
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
- Stage: Stage-3
+ Stage: Stage-2
Map Reduce
Map Operator Tree:
TableScan
@@ -2401,7 +2182,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-4
+ Stage: Stage-3
Map Reduce
Map Operator Tree:
TableScan
@@ -2473,30 +2254,11 @@ STAGE PLANS:
Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 127 Data size: 12786 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
+ 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
Stage: Stage-0
Fetch Operator
@@ -2509,7 +2271,7 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -2519,7 +2281,7 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -2567,7 +2329,7 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, yy.key, yy.cnt
@@ -2575,12 +2337,11 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -2641,10 +2402,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Join Operator
condition map:
Inner Join 0 to 1
@@ -2687,30 +2449,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- sort order: +++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -2723,7 +2466,7 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -2733,7 +2476,7 @@ FROM src1 xx
JOIN
(SELECT x.key as key, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key) yy
ON xx.key=yy.key JOIN src zz
-ON yy.key=zz.key ORDER BY xx.key, yy.key, yy.cnt
+ON yy.key=zz.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -2786,7 +2529,6 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
PREHOOK: type: QUERY
POSTHOOK: query: -- When Correlation Optimizer is turned off, 6 MR jobs are needed.
-- When Correlation Optimizer is turned on, 2 MR jobs are needed.
@@ -2799,16 +2541,14 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1, Stage-7
+ Stage-2 depends on stages: Stage-1, Stage-6
Stage-3 depends on stages: Stage-2
Stage-4 depends on stages: Stage-3
- Stage-5 depends on stages: Stage-4
- Stage-7 is a root stage
- Stage-0 depends on stages: Stage-5
+ Stage-6 is a root stage
+ Stage-0 depends on stages: Stage-4
STAGE PLANS:
Stage: Stage-1
@@ -2956,32 +2696,13 @@ STAGE PLANS:
Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
File Output Operator
compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-5
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: string)
- sort order: +++++
Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: string)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 31 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 31 Data size: 6393 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
+ 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
- Stage: Stage-7
+ Stage: Stage-6
Map Reduce
Map Operator Tree:
TableScan
@@ -3034,7 +2755,6 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -3046,7 +2766,6 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -3096,7 +2815,6 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
@@ -3106,12 +2824,10 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
+ Stage-0 depends on stages: Stage-1
STAGE PLANS:
Stage: Stage-1
@@ -3219,10 +2935,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Group By Operator
aggregations: count(VALUE._col0)
keys: KEY._col0 (type: string)
@@ -3275,10 +2992,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Mux Operator
Statistics: Num rows: 89 Data size: 11840 Basic stats: COMPLETE Column stats: NONE
Join Operator
@@ -3295,30 +3013,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: string)
- sort order: +++++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: string), _col4 (type: string)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -3333,7 +3032,6 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -3345,7 +3043,6 @@ FROM
JOIN (SELECT y.key as key, count(*) AS cnt FROM src1 y group by y.key) yy
ON (xx.key=yy.key) GROUP BY xx.key) tmp
JOIN src z ON tmp.key=z.key
-ORDER BY tmp.key, tmp.sum1, tmp.sum2, z.key, z.value
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -3673,7 +3370,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, xx.cnt, yy.key, yy.value, yy.cnt
@@ -3681,14 +3378,13 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
Stage-3 depends on stages: Stage-2
- Stage-4 depends on stages: Stage-3
- Stage-0 depends on stages: Stage-4
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
Stage: Stage-1
@@ -3835,10 +3531,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Mux Operator
Statistics: Num rows: 35 Data size: 3577 Basic stats: COMPLETE Column stats: NONE
Join Operator
@@ -3855,30 +3552,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint)
- sort order: +++++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -3891,7 +3569,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -3901,7 +3579,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1
@@ -3927,7 +3605,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
POSTHOOK: query: EXPLAIN
SELECT xx.key, xx.cnt, yy.key, yy.value, yy.cnt
@@ -3935,18 +3613,17 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
STAGE DEPENDENCIES:
- Stage-11 is a root stage
- Stage-2 depends on stages: Stage-11
- Stage-10 depends on stages: Stage-2
- Stage-3 depends on stages: Stage-10
- Stage-4 depends on stages: Stage-3
- Stage-0 depends on stages: Stage-4
+ Stage-10 is a root stage
+ Stage-2 depends on stages: Stage-10
+ Stage-9 depends on stages: Stage-2
+ Stage-3 depends on stages: Stage-9
+ Stage-0 depends on stages: Stage-3
STAGE PLANS:
- Stage: Stage-11
+ Stage: Stage-10
Map Reduce Local Work
Alias -> Map Local Tables:
yy:x
@@ -4018,7 +3695,7 @@ STAGE PLANS:
output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
- Stage: Stage-10
+ Stage: Stage-9
Map Reduce Local Work
Alias -> Map Local Tables:
xx:x
@@ -4108,10 +3785,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Mux Operator
Statistics: Num rows: 49 Data size: 5021 Basic stats: COMPLETE Column stats: NONE
Join Operator
@@ -4128,30 +3806,11 @@ STAGE PLANS:
Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
File Output Operator
compressed: false
+ Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-4
- Map Reduce
- Map Operator Tree:
- TableScan
- Reduce Output Operator
- key expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint)
- sort order: +++++
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- value expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string), _col4 (type: bigint)
- Reduce Operator Tree:
- Extract
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Stage: Stage-0
Fetch Operator
@@ -4164,7 +3823,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
PREHOOK: type: QUERY
PREHOOK: Input: default@src
PREHOOK: Input: default@src1
@@ -4174,7 +3833,7 @@ FROM
(SELECT x.key as key, count(1) as cnt FROM src1 x JOIN src1 y ON (x.key = y.key) group by x.key) xx
JOIN
(SELECT x.key as key, x.value as value, count(1) as cnt FROM src x JOIN src y ON (x.key = y.key) group by x.key, x.value) yy
-ON xx.key=yy.key ORDER BY xx.key, xx.cnt, yy.key, yy.value, yy.cnt
+ON xx.key=yy.key
POSTHOOK: type: QUERY
POSTHOOK: Input: default@src
POSTHOOK: Input: default@src1