You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by br...@apache.org on 2014/08/24 23:53:03 UTC
svn commit: r1620200 [1/4] - in /hive/branches/spark:
itests/src/test/resources/ ql/src/test/results/clientpositive/spark/
Author: brock
Date: Sun Aug 24 21:53:03 2014
New Revision: 1620200
URL: http://svn.apache.org/r1620200
Log:
HIVE-7792 - Enable tests on Spark branch (2) [Sparch Branch] (Venki Korukanti via Brock)
Added:
hive/branches/spark/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/load_dyn_part2.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/load_dyn_part3.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/mapreduce1.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/mapreduce2.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/merge1.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/merge2.q.out
hive/branches/spark/ql/src/test/results/clientpositive/spark/metadata_only_queries.q.out
Modified:
hive/branches/spark/itests/src/test/resources/testconfiguration.properties
Modified: hive/branches/spark/itests/src/test/resources/testconfiguration.properties
URL: http://svn.apache.org/viewvc/hive/branches/spark/itests/src/test/resources/testconfiguration.properties?rev=1620200&r1=1620199&r2=1620200&view=diff
==============================================================================
--- hive/branches/spark/itests/src/test/resources/testconfiguration.properties (original)
+++ hive/branches/spark/itests/src/test/resources/testconfiguration.properties Sun Aug 24 21:53:03 2014
@@ -365,6 +365,14 @@ spark.query.files=alter_merge_orc.q \
join27.q \
join_1to1.q \
join_casesensitive.q \
+ limit_pushdown.q \
+ load_dyn_part2.q.out \
+ load_dyn_part3.q.out \
+ mapreduce1.q \
+ mapreduce2.q \
+ merge1.q \
+ merge2.q \
+ metadata_only_queries.q \
order.q \
order2.q \
ptf_decimal.q \
Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out?rev=1620200&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/limit_pushdown.q.out Sun Aug 24 21:53:03 2014
@@ -0,0 +1,1381 @@
+PREHOOK: query: -- HIVE-3562 Some limit can be pushed down to map stage
+
+explain
+select key,value from src order by key limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: -- HIVE-3562 Some limit can be pushed down to map stage
+
+explain
+select key,value from src order by key limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 4000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 4000 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key,value from src order by key limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key,value from src order by key limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 val_0
+0 val_0
+0 val_0
+10 val_10
+100 val_100
+100 val_100
+103 val_103
+103 val_103
+104 val_104
+104 val_104
+105 val_105
+11 val_11
+111 val_111
+113 val_113
+113 val_113
+114 val_114
+116 val_116
+118 val_118
+118 val_118
+119 val_119
+PREHOOK: query: explain
+select key,value from src order by key desc limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select key,value from src order by key desc limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: -
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 4000 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 4000 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key,value from src order by key desc limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key,value from src order by key desc limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+98 val_98
+98 val_98
+97 val_97
+97 val_97
+96 val_96
+95 val_95
+95 val_95
+92 val_92
+90 val_90
+90 val_90
+90 val_90
+9 val_9
+87 val_87
+86 val_86
+85 val_85
+84 val_84
+84 val_84
+83 val_83
+83 val_83
+82 val_82
+PREHOOK: query: explain
+select value, sum(key + 1) as sum from src group by value limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select value, sum(key + 1) as sum from src group by value limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string), key (type: string)
+ outputColumnNames: value, key
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum((key + 1))
+ keys: value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col1 (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2805 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select value, sum(key + 1) as sum from src group by value limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select value, sum(key + 1) as sum from src group by value limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+val_131 132.0
+val_113 228.0
+val_103 208.0
+val_114 115.0
+val_0 3.0
+val_116 117.0
+val_118 238.0
+val_129 260.0
+val_119 360.0
+val_104 210.0
+val_126 127.0
+val_128 387.0
+val_105 106.0
+val_10 11.0
+val_11 12.0
+val_100 202.0
+val_125 252.0
+val_120 242.0
+val_111 112.0
+val_12 26.0
+PREHOOK: query: -- deduped RS
+explain
+select value,avg(key + 1) from src group by value order by value limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: -- deduped RS
+explain
+select value,avg(key + 1) from src group by value order by value limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string), key (type: string)
+ outputColumnNames: value, key
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: avg((key + 1))
+ keys: value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col1 (type: struct<count:bigint,sum:double,input:double>)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: avg(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2805 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select value,avg(key + 1) from src group by value order by value limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select value,avg(key + 1) from src group by value order by value limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+val_131 132.0
+val_113 114.0
+val_103 104.0
+val_114 115.0
+val_0 1.0
+val_116 117.0
+val_118 119.0
+val_129 130.0
+val_119 120.0
+val_104 105.0
+val_126 127.0
+val_128 129.0
+val_105 106.0
+val_10 11.0
+val_11 12.0
+val_100 101.0
+val_125 126.0
+val_120 121.0
+val_111 112.0
+val_12 13.0
+PREHOOK: query: -- distincts
+explain
+select distinct(cdouble) from alltypesorc limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: -- distincts
+explain
+select distinct(cdouble) from alltypesorc limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: alltypesorc
+ Statistics: Num rows: 47154 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: cdouble (type: double)
+ outputColumnNames: cdouble
+ Statistics: Num rows: 47154 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ keys: cdouble (type: double)
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 47154 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: double)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: double)
+ Statistics: Num rows: 47154 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ keys: KEY._col0 (type: double)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 23577 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: double)
+ outputColumnNames: _col0
+ Statistics: Num rows: 23577 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 160 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select distinct(cdouble) from alltypesorc limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+POSTHOOK: query: select distinct(cdouble) from alltypesorc limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+-16372.0
+-16339.0
+-16310.0
+-16311.0
+-16296.0
+-16307.0
+-16277.0
+-16305.0
+-16309.0
+-16300.0
+-16280.0
+-16373.0
+-16306.0
+-16369.0
+-16324.0
+NULL
+-16355.0
+-16379.0
+-16274.0
+-16269.0
+PREHOOK: query: explain
+select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: alltypesorc
+ Statistics: Num rows: 31436 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ctinyint (type: tinyint), cdouble (type: double)
+ outputColumnNames: ctinyint, cdouble
+ Statistics: Num rows: 31436 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT cdouble)
+ keys: ctinyint (type: tinyint), cdouble (type: double)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 31436 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: tinyint), _col1 (type: double)
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: tinyint)
+ Statistics: Num rows: 31436 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0)
+ keys: KEY._col0 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 15718 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: tinyint), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 15718 Data size: 188618 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 240 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 240 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+POSTHOOK: query: select ctinyint, count(distinct(cdouble)) from alltypesorc group by ctinyint limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+NULL 2932
+-64 24
+-63 19
+-62 27
+-61 25
+-60 27
+-59 31
+-58 23
+-57 35
+-56 36
+-55 29
+-54 26
+-53 22
+-52 33
+-51 21
+-50 30
+-49 26
+-48 29
+-47 22
+-46 24
+PREHOOK: query: -- multi distinct
+explain
+select ctinyint, count(distinct(cstring1)), count(distinct(cstring2)) from alltypesorc group by ctinyint limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: -- multi distinct
+explain
+select ctinyint, count(distinct(cstring1)), count(distinct(cstring2)) from alltypesorc group by ctinyint limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: alltypesorc
+ Statistics: Num rows: 1849 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string)
+ outputColumnNames: ctinyint, cstring1, cstring2
+ Statistics: Num rows: 1849 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(DISTINCT cstring1), count(DISTINCT cstring2)
+ keys: ctinyint (type: tinyint), cstring1 (type: string), cstring2 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4
+ Statistics: Num rows: 1849 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: tinyint), _col1 (type: string), _col2 (type: string)
+ sort order: +++
+ Map-reduce partition columns: _col0 (type: tinyint)
+ Statistics: Num rows: 1849 Data size: 377237 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(DISTINCT KEY._col1:0._col0), count(DISTINCT KEY._col1:1._col0)
+ keys: KEY._col0 (type: tinyint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 924 Data size: 188516 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: tinyint), _col1 (type: bigint), _col2 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 924 Data size: 188516 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 20 Data size: 4080 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 20 Data size: 4080 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select ctinyint, count(distinct(cstring1)), count(distinct(cstring2)) from alltypesorc group by ctinyint limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+POSTHOOK: query: select ctinyint, count(distinct(cstring1)), count(distinct(cstring2)) from alltypesorc group by ctinyint limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@alltypesorc
+#### A masked pattern was here ####
+NULL 3065 3
+-64 3 13
+-63 3 16
+-62 3 23
+-61 3 25
+-60 3 25
+-59 3 27
+-58 3 24
+-57 3 23
+-56 3 22
+-55 3 21
+-54 3 21
+-53 3 17
+-52 3 21
+-51 1012 1045
+-50 3 25
+-49 3 24
+-48 3 27
+-47 3 23
+-46 3 19
+PREHOOK: query: -- limit zero
+explain
+select key,value from src order by key limit 0
+PREHOOK: type: QUERY
+POSTHOOK: query: -- limit zero
+explain
+select key,value from src order by key limit 0
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-0
+ Fetch Operator
+ limit: 0
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key,value from src order by key limit 0
+PREHOOK: type: QUERY
+#### A masked pattern was here ####
+POSTHOOK: query: select key,value from src order by key limit 0
+POSTHOOK: type: QUERY
+#### A masked pattern was here ####
+PREHOOK: query: -- 2MR (applied to last RS)
+explain
+select value, sum(key) as sum from src group by value order by sum limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: -- 2MR (applied to last RS)
+explain
+select value, sum(key) as sum from src group by value order by sum limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+ Reducer 3 <- Reducer 2 (GROUP SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string), key (type: string)
+ outputColumnNames: value, key
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(key)
+ keys: value (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: double)
+ sort order: +
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col0 (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2805 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select value, sum(key) as sum from src group by value order by sum limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select value, sum(key) as sum from src group by value order by sum limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+val_0 0.0
+val_2 2.0
+val_4 4.0
+val_8 8.0
+val_9 9.0
+val_10 10.0
+val_11 11.0
+val_5 15.0
+val_17 17.0
+val_19 19.0
+val_20 20.0
+val_12 24.0
+val_27 27.0
+val_28 28.0
+val_30 30.0
+val_15 30.0
+val_33 33.0
+val_34 34.0
+val_18 36.0
+val_41 41.0
+PREHOOK: query: -- subqueries
+explain
+select * from
+(select key, count(1) from src group by key order by key limit 2) subq
+join
+(select key, count(1) from src group by key limit 3) subq2
+on subq.key=subq2.key limit 4
+PREHOOK: type: QUERY
+POSTHOOK: query: -- subqueries
+explain
+select * from
+(select key, count(1) from src group by key order by key limit 2) subq
+join
+(select key, count(1) from src group by key limit 3) subq2
+on subq.key=subq2.key limit 4
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+ Reducer 3 <- Reducer 2 (GROUP SORT), Reducer 6 (GROUP SORT)
+ Reducer 5 <- Map 4 (GROUP)
+ Reducer 6 <- Reducer 5 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col1 (type: bigint)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: key
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count(1)
+ keys: key (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col1 (type: bigint)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 2
+ Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 1 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Reducer 3
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {KEY.reducesinkkey0} {VALUE._col0}
+ 1 {KEY.reducesinkkey0} {VALUE._col0}
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 4
+ Statistics: Num rows: 2 Data size: 220 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 2 Data size: 220 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
+ Reducer 5
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 2906 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 3
+ Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: _col0 (type: string), _col1 (type: bigint)
+ Reducer 6
+ Reduce Operator Tree:
+ Select Operator
+ expressions: VALUE._col0 (type: string), VALUE._col1 (type: bigint)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 3
+ Statistics: Num rows: 3 Data size: 300 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: _col0 is not null (type: boolean)
+ Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: string)
+ Statistics: Num rows: 2 Data size: 200 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 4
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: -- map aggregation disabled
+explain
+select value, sum(key) as sum from src group by value limit 20
+PREHOOK: type: QUERY
+POSTHOOK: query: -- map aggregation disabled
+explain
+select value, sum(key) as sum from src group by value limit 20
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: value (type: string)
+ sort order: +
+ Map-reduce partition columns: value (type: string)
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 0.3
+ value expressions: key (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 20
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2805 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 20
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select value, sum(key) as sum from src group by value limit 20
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select value, sum(key) as sum from src group by value limit 20
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+val_15 15.0
+val_138 414.0
+val_131 131.0
+val_113 226.0
+val_129 258.0
+val_103 206.0
+val_114 114.0
+val_0 0.0
+val_118 236.0
+val_116 116.0
+val_174 174.0
+val_119 357.0
+val_104 208.0
+val_128 384.0
+val_105 105.0
+val_193 193.0
+val_10 10.0
+val_11 11.0
+val_100 200.0
+val_126 126.0
+PREHOOK: query: -- flush for order-by
+explain
+select key,value,value,value,value,value,value,value,value from src order by key limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: -- flush for order-by
+explain
+select key,value,value,value,value,value,value,value,value from src order by key limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP SORT)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: string)
+ sort order: +
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 2.0E-5
+ value expressions: _col1 (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string), VALUE._col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 29 Data size: 5812 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select key,value,value,value,value,value,value,value,value from src order by key limit 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select key,value,value,value,value,value,value,value,value from src order by key limit 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+0 val_0 val_0 val_0 val_0 val_0 val_0 val_0 val_0
+0 val_0 val_0 val_0 val_0 val_0 val_0 val_0 val_0
+0 val_0 val_0 val_0 val_0 val_0 val_0 val_0 val_0
+10 val_10 val_10 val_10 val_10 val_10 val_10 val_10 val_10
+100 val_100 val_100 val_100 val_100 val_100 val_100 val_100 val_100
+100 val_100 val_100 val_100 val_100 val_100 val_100 val_100 val_100
+103 val_103 val_103 val_103 val_103 val_103 val_103 val_103 val_103
+103 val_103 val_103 val_103 val_103 val_103 val_103 val_103 val_103
+104 val_104 val_104 val_104 val_104 val_104 val_104 val_104 val_104
+104 val_104 val_104 val_104 val_104 val_104 val_104 val_104 val_104
+105 val_105 val_105 val_105 val_105 val_105 val_105 val_105 val_105
+11 val_11 val_11 val_11 val_11 val_11 val_11 val_11 val_11
+111 val_111 val_111 val_111 val_111 val_111 val_111 val_111 val_111
+113 val_113 val_113 val_113 val_113 val_113 val_113 val_113 val_113
+113 val_113 val_113 val_113 val_113 val_113 val_113 val_113 val_113
+114 val_114 val_114 val_114 val_114 val_114 val_114 val_114 val_114
+116 val_116 val_116 val_116 val_116 val_116 val_116 val_116 val_116
+118 val_118 val_118 val_118 val_118 val_118 val_118 val_118 val_118
+118 val_118 val_118 val_118 val_118 val_118 val_118 val_118 val_118
+119 val_119 val_119 val_119 val_119 val_119 val_119 val_119 val_119
+119 val_119 val_119 val_119 val_119 val_119 val_119 val_119 val_119
+119 val_119 val_119 val_119 val_119 val_119 val_119 val_119 val_119
+12 val_12 val_12 val_12 val_12 val_12 val_12 val_12 val_12
+12 val_12 val_12 val_12 val_12 val_12 val_12 val_12 val_12
+120 val_120 val_120 val_120 val_120 val_120 val_120 val_120 val_120
+120 val_120 val_120 val_120 val_120 val_120 val_120 val_120 val_120
+125 val_125 val_125 val_125 val_125 val_125 val_125 val_125 val_125
+125 val_125 val_125 val_125 val_125 val_125 val_125 val_125 val_125
+126 val_126 val_126 val_126 val_126 val_126 val_126 val_126 val_126
+128 val_128 val_128 val_128 val_128 val_128 val_128 val_128 val_128
+128 val_128 val_128 val_128 val_128 val_128 val_128 val_128 val_128
+128 val_128 val_128 val_128 val_128 val_128 val_128 val_128 val_128
+129 val_129 val_129 val_129 val_129 val_129 val_129 val_129 val_129
+129 val_129 val_129 val_129 val_129 val_129 val_129 val_129 val_129
+131 val_131 val_131 val_131 val_131 val_131 val_131 val_131 val_131
+133 val_133 val_133 val_133 val_133 val_133 val_133 val_133 val_133
+134 val_134 val_134 val_134 val_134 val_134 val_134 val_134 val_134
+134 val_134 val_134 val_134 val_134 val_134 val_134 val_134 val_134
+136 val_136 val_136 val_136 val_136 val_136 val_136 val_136 val_136
+137 val_137 val_137 val_137 val_137 val_137 val_137 val_137 val_137
+137 val_137 val_137 val_137 val_137 val_137 val_137 val_137 val_137
+138 val_138 val_138 val_138 val_138 val_138 val_138 val_138 val_138
+138 val_138 val_138 val_138 val_138 val_138 val_138 val_138 val_138
+138 val_138 val_138 val_138 val_138 val_138 val_138 val_138 val_138
+138 val_138 val_138 val_138 val_138 val_138 val_138 val_138 val_138
+143 val_143 val_143 val_143 val_143 val_143 val_143 val_143 val_143
+145 val_145 val_145 val_145 val_145 val_145 val_145 val_145 val_145
+146 val_146 val_146 val_146 val_146 val_146 val_146 val_146 val_146
+146 val_146 val_146 val_146 val_146 val_146 val_146 val_146 val_146
+149 val_149 val_149 val_149 val_149 val_149 val_149 val_149 val_149
+149 val_149 val_149 val_149 val_149 val_149 val_149 val_149 val_149
+15 val_15 val_15 val_15 val_15 val_15 val_15 val_15 val_15
+15 val_15 val_15 val_15 val_15 val_15 val_15 val_15 val_15
+150 val_150 val_150 val_150 val_150 val_150 val_150 val_150 val_150
+152 val_152 val_152 val_152 val_152 val_152 val_152 val_152 val_152
+152 val_152 val_152 val_152 val_152 val_152 val_152 val_152 val_152
+153 val_153 val_153 val_153 val_153 val_153 val_153 val_153 val_153
+155 val_155 val_155 val_155 val_155 val_155 val_155 val_155 val_155
+156 val_156 val_156 val_156 val_156 val_156 val_156 val_156 val_156
+157 val_157 val_157 val_157 val_157 val_157 val_157 val_157 val_157
+158 val_158 val_158 val_158 val_158 val_158 val_158 val_158 val_158
+160 val_160 val_160 val_160 val_160 val_160 val_160 val_160 val_160
+162 val_162 val_162 val_162 val_162 val_162 val_162 val_162 val_162
+163 val_163 val_163 val_163 val_163 val_163 val_163 val_163 val_163
+164 val_164 val_164 val_164 val_164 val_164 val_164 val_164 val_164
+164 val_164 val_164 val_164 val_164 val_164 val_164 val_164 val_164
+165 val_165 val_165 val_165 val_165 val_165 val_165 val_165 val_165
+165 val_165 val_165 val_165 val_165 val_165 val_165 val_165 val_165
+166 val_166 val_166 val_166 val_166 val_166 val_166 val_166 val_166
+167 val_167 val_167 val_167 val_167 val_167 val_167 val_167 val_167
+167 val_167 val_167 val_167 val_167 val_167 val_167 val_167 val_167
+167 val_167 val_167 val_167 val_167 val_167 val_167 val_167 val_167
+168 val_168 val_168 val_168 val_168 val_168 val_168 val_168 val_168
+169 val_169 val_169 val_169 val_169 val_169 val_169 val_169 val_169
+169 val_169 val_169 val_169 val_169 val_169 val_169 val_169 val_169
+169 val_169 val_169 val_169 val_169 val_169 val_169 val_169 val_169
+169 val_169 val_169 val_169 val_169 val_169 val_169 val_169 val_169
+17 val_17 val_17 val_17 val_17 val_17 val_17 val_17 val_17
+170 val_170 val_170 val_170 val_170 val_170 val_170 val_170 val_170
+172 val_172 val_172 val_172 val_172 val_172 val_172 val_172 val_172
+172 val_172 val_172 val_172 val_172 val_172 val_172 val_172 val_172
+174 val_174 val_174 val_174 val_174 val_174 val_174 val_174 val_174
+174 val_174 val_174 val_174 val_174 val_174 val_174 val_174 val_174
+175 val_175 val_175 val_175 val_175 val_175 val_175 val_175 val_175
+175 val_175 val_175 val_175 val_175 val_175 val_175 val_175 val_175
+176 val_176 val_176 val_176 val_176 val_176 val_176 val_176 val_176
+176 val_176 val_176 val_176 val_176 val_176 val_176 val_176 val_176
+177 val_177 val_177 val_177 val_177 val_177 val_177 val_177 val_177
+178 val_178 val_178 val_178 val_178 val_178 val_178 val_178 val_178
+179 val_179 val_179 val_179 val_179 val_179 val_179 val_179 val_179
+179 val_179 val_179 val_179 val_179 val_179 val_179 val_179 val_179
+18 val_18 val_18 val_18 val_18 val_18 val_18 val_18 val_18
+18 val_18 val_18 val_18 val_18 val_18 val_18 val_18 val_18
+180 val_180 val_180 val_180 val_180 val_180 val_180 val_180 val_180
+181 val_181 val_181 val_181 val_181 val_181 val_181 val_181 val_181
+183 val_183 val_183 val_183 val_183 val_183 val_183 val_183 val_183
+186 val_186 val_186 val_186 val_186 val_186 val_186 val_186 val_186
+187 val_187 val_187 val_187 val_187 val_187 val_187 val_187 val_187
+187 val_187 val_187 val_187 val_187 val_187 val_187 val_187 val_187
+187 val_187 val_187 val_187 val_187 val_187 val_187 val_187 val_187
+PREHOOK: query: -- flush for group-by
+explain
+select sum(key) as sum from src group by concat(key,value,value,value,value,value,value,value,value,value) limit 100
+PREHOOK: type: QUERY
+POSTHOOK: query: -- flush for group-by
+explain
+select sum(key) as sum from src group by concat(key,value,value,value,value,value,value,value,value,value) limit 100
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Spark
+ Edges:
+ Reducer 2 <- Map 1 (GROUP)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: src
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: concat(key, value, value, value, value, value, value, value, value, value) (type: string)
+ sort order: +
+ Map-reduce partition columns: concat(key, value, value, value, value, value, value, value, value, value) (type: string)
+ Statistics: Num rows: 29 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+ TopN Hash Memory Usage: 2.0E-5
+ value expressions: key (type: string)
+ Reducer 2
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double)
+ outputColumnNames: _col0
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 14 Data size: 2805 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 14 Data size: 2805 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
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select sum(key) as sum from src group by concat(key,value,value,value,value,value,value,value,value,value) limit 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+#### A masked pattern was here ####
+POSTHOOK: query: select sum(key) as sum from src group by concat(key,value,value,value,value,value,value,value,value,value) limit 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+#### A masked pattern was here ####
+579.0
+126.0
+105.0
+143.0
+414.0
+178.0
+399.0
+406.0
+330.0
+202.0
+410.0
+282.0
+235.0
+131.0
+309.0
+304.0
+194.0
+327.0
+434.0
+242.0
+280.0
+344.0
+432.0
+222.0
+214.0
+19.0
+201.0
+17.0
+177.0
+624.0
+1150.0
+272.0
+250.0
+240.0
+170.0
+192.0
+160.0
+426.0
+384.0
+158.0
+145.0
+348.0
+501.0
+114.0
+226.0
+111.0
+418.0
+156.0
+394.0
+150.0
+180.0
+208.0
+183.0
+218.0
+390.0
+476.0
+316.0
+474.0
+357.0
+459.0
+442.0
+446.0
+466.0
+20.0
+458.0
+0.0
+181.0
+166.0
+30.0
+328.0
+10.0
+489.0
+469.0
+24.0
+417.0
+622.0
+292.0
+636.0
+554.0
+400.0
+278.0
+186.0
+157.0
+352.0
+358.0
+382.0
+552.0
+268.0
+348.0
+236.0
+258.0
+163.0
+136.0
+226.0
+228.0
+189.0
+206.0
+561.0
+438.0
+162.0