You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by vi...@apache.org on 2014/03/28 07:11:08 UTC
svn commit: r1582623 [3/4] - in /hive/trunk:
common/src/java/org/apache/hadoop/hive/conf/ itests/qtest/
ql/src/java/org/apache/hadoop/hive/ql/exec/
ql/src/java/org/apache/hadoop/hive/ql/exec/tez/
ql/src/java/org/apache/hadoop/hive/ql/io/ ql/src/java/or...
Added: hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out?rev=1582623&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out Fri Mar 28 06:11:07 2014
@@ -0,0 +1,1127 @@
+PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@srcbucket_mapjoin
+PREHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE tab_part (key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab_part
+PREHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE srcbucket_mapjoin_part (key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@srcbucket_mapjoin_part
+PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin
+POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket20.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket21.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket22.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: query: load data local inpath '../../data/files/srcbucket23.txt' INTO TABLE srcbucket_mapjoin_part partition(ds='2008-04-08')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin_part
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin_part
+PREHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
+PREHOOK: Output: default@tab_part@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab_part partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin_part
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin_part
+POSTHOOK: Input: default@srcbucket_mapjoin_part@ds=2008-04-08
+POSTHOOK: Output: default@tab_part@ds=2008-04-08
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE tab(key int, value string) PARTITIONED BY(ds STRING) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: query: insert overwrite table tab partition (ds='2008-04-08')
+select key,value from srcbucket_mapjoin
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab@ds=2008-04-08
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Map 2 (CUSTOM_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col6
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int), value (type: string)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: -- one side is really bucketed. srcbucket_mapjoin is not really a bucketed table.
+-- In this case the sub-query is chosen as the big table.
+explain
+select a.k1, a.v1, b.value
+from (select sum(substr(srcbucket_mapjoin.value,5)) as v1, key as k1 from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab b on a.k1 = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- one side is really bucketed. srcbucket_mapjoin is not really a bucketed table.
+-- In this case the sub-query is chosen as the big table.
+explain
+select a.k1, a.v1, b.value
+from (select sum(substr(srcbucket_mapjoin.value,5)) as v1, key as k1 from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab b on a.k1 = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Reducer 3 (CUSTOM_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 266 Data size: 2822 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: srcbucket_mapjoin
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(value, 5))
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double), _col1 (type: int)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(tab.value,5)) as v1, key as k1 from tab_part join tab on tab_part.key = tab.key GROUP BY tab.key) a
+join tab b on a.k1 = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(tab.value,5)) as v1, key as k1 from tab_part join tab on tab_part.key = tab.key GROUP BY tab.key) a
+join tab b on a.k1 = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 2 <- Map 4 (CUSTOM_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE), Map 1 (CUSTOM_SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: tab_part
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1 {key} {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col5, _col6
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col5 (type: int), _col6 (type: string)
+ outputColumnNames: _col5, _col6
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(_col6, 5))
+ keys: _col5 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: tab
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int), value (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 302 Data size: 3213 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: -1
+
+PREHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(x.value,5)) as v1, x.key as k1 from tab x join tab y on x.key = y.key GROUP BY x.key) a
+join tab_part b on a.k1 = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.k1, a.v1, b.value
+from (select sum(substr(x.value,5)) as v1, x.key as k1 from tab x join tab y on x.key = y.key GROUP BY x.key) a
+join tab_part b on a.k1 = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Reducer 3 (CUSTOM_EDGE)
+ Map 2 <- Map 4 (CUSTOM_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col1 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(_col1, 5))
+ keys: _col0 (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: double), _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: int)
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: double), _col1 (type: int)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: -- multi-way join
+explain
+select a.key, a.value, b.value
+from tab_part a join tab b on a.key = b.key join tab c on a.key = c.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- multi-way join
+explain
+select a.key, a.value, b.value
+from tab_part a join tab b on a.key = b.key join tab c on a.key = c.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 3 <- Map 1 (CUSTOM_EDGE), Map 2 (CUSTOM_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ Inner Join 0 to 2
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ 2
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ 2 key (type: int)
+ outputColumnNames: _col0, _col1, _col6
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1100 Data size: 11686 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: -1
+
+PREHOOK: query: explain
+select a.key, a.value, c.value
+from (select x.key, x.value from tab_part x join tab y on x.key = y.key) a join tab c on a.key = c.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, c.value
+from (select x.key, x.value from tab_part x join tab y on x.key = y.key) a join tab c on a.key = c.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 2 <- Map 1 (CUSTOM_EDGE), Map 3 (CUSTOM_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: value (type: string)
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: x
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: y
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: -- in this case sub-query is the small table
+explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- in this case sub-query is the small table
+explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Reducer 3 (CUSTOM_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: srcbucket_mapjoin
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(substr(value, 5))
+ keys: key (type: int)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: double)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from (select key, sum(substr(srcbucket_mapjoin.value,5)) as value from srcbucket_mapjoin GROUP BY srcbucket_mapjoin.key) a
+join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Reducer 3 (CUSTOM_EDGE)
+ Reducer 3 <- Map 2 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0} {_col1}
+ 1 {value}
+ keys:
+ 0 _col0 (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col3
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: srcbucket_mapjoin
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: key, value
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
+ value expressions: substr(value, 5) (type: string)
+ Reducer 3
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: int)
+ mode: complete
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: double)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col0 (type: int)
+ sort order: +
+ Map-reduce partition columns: _col0 (type: int)
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: int), _col1 (type: double)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: -- join on non-bucketed column results in broadcast join.
+explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.value = b.value
+PREHOOK: type: QUERY
+POSTHOOK: query: -- join on non-bucketed column results in broadcast join.
+explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.value = b.value
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Map 2 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 value (type: string)
+ 1 value (type: string)
+ outputColumnNames: _col0, _col1, _col6
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 242 Data size: 2566 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: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int), value (type: string)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+POSTHOOK: query: CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@tab1
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: insert overwrite table tab1
+select key,value from srcbucket_mapjoin
+PREHOOK: type: QUERY
+PREHOOK: Input: default@srcbucket_mapjoin
+PREHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+PREHOOK: Output: default@tab1
+POSTHOOK: query: insert overwrite table tab1
+select key,value from srcbucket_mapjoin
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@srcbucket_mapjoin
+POSTHOOK: Input: default@srcbucket_mapjoin@ds=2008-04-08
+POSTHOOK: Output: default@tab1
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab1.key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab1.value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from tab1 a join tab_part b on a.key = b.key
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from tab1 a join tab_part b on a.key = b.key
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab1.key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab1.value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 1 <- Map 2 (CUSTOM_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1 {value}
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1, _col5
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 550 Data size: 5843 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
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int), value (type: string)
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+PREHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value
+PREHOOK: type: QUERY
+POSTHOOK: query: explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value
+POSTHOOK: type: QUERY
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab1.key SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab1.value SIMPLE [(srcbucket_mapjoin)srcbucket_mapjoin.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).key SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:key, type:int, comment:null), ]
+POSTHOOK: Lineage: tab_part PARTITION(ds=2008-04-08).value SIMPLE [(srcbucket_mapjoin_part)srcbucket_mapjoin_part.FieldSchema(name:value, type:string, comment:null), ]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+ Edges:
+ Map 3 <- Map 2 (CUSTOM_EDGE), Map 1 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: b
+ Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: key (type: int)
+ Map 2
+ Map Operator Tree:
+ TableScan
+ alias: c
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: key (type: int)
+ sort order: +
+ Map-reduce partition columns: key (type: int)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {key} {value}
+ 1
+ keys:
+ 0 key (type: int)
+ 1 key (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0 {_col0}
+ 1 {key}
+ keys:
+ 0 _col1 (type: string)
+ 1 value (type: string)
+ outputColumnNames: _col5, _col10
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col5 (type: int), _col10 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+