http://git-wip-us.apache.org/repos/asf/hive/blob/1f258e96/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out b/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out
new file mode 100644
index 0000000..eac269c
--- /dev/null
+++ b/ql/src/test/results/clientpositive/llap/multiMapJoin1.q.out
@@ -0,0 +1,2145 @@
+PREHOOK: query: create table smallTbl1(key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@smallTbl1
+POSTHOOK: query: create table smallTbl1(key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@smallTbl1
+RUN: Stage-0:DDL
+PREHOOK: query: insert overwrite table smallTbl1 select * from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@smalltbl1
+POSTHOOK: query: insert overwrite table smallTbl1 select * from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@smalltbl1
+POSTHOOK: Lineage: smalltbl1.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: smalltbl1.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: create table smallTbl2(key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@smallTbl2
+POSTHOOK: query: create table smallTbl2(key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@smallTbl2
+RUN: Stage-0:DDL
+PREHOOK: query: insert overwrite table smallTbl2 select * from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@smalltbl2
+POSTHOOK: query: insert overwrite table smallTbl2 select * from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@smalltbl2
+POSTHOOK: Lineage: smalltbl2.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: smalltbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: create table smallTbl3(key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@smallTbl3
+POSTHOOK: query: create table smallTbl3(key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@smallTbl3
+RUN: Stage-0:DDL
+PREHOOK: query: insert overwrite table smallTbl3 select * from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@smalltbl3
+POSTHOOK: query: insert overwrite table smallTbl3 select * from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@smalltbl3
+POSTHOOK: Lineage: smalltbl3.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: smalltbl3.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: create table smallTbl4(key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@smallTbl4
+POSTHOOK: query: create table smallTbl4(key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@smallTbl4
+RUN: Stage-0:DDL
+PREHOOK: query: insert overwrite table smallTbl4 select * from src where key < 10
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@smalltbl4
+POSTHOOK: query: insert overwrite table smallTbl4 select * from src where key < 10
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@smalltbl4
+POSTHOOK: Lineage: smalltbl4.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: smalltbl4.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: create table bigTbl(key string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bigTbl
+POSTHOOK: query: create table bigTbl(key string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bigTbl
+RUN: Stage-0:DDL
+PREHOOK: query: insert overwrite table bigTbl
+select * from
+(
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+) subq
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@bigtbl
+POSTHOOK: query: insert overwrite table bigTbl
+select * from
+(
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+ union all
+ select * from src
+) subq
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@bigtbl
+POSTHOOK: Lineage: bigtbl.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: bigtbl.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: explain
+select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: bigtbl
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5500 Data size: 58432 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5500 Data size: 58432 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 6050 Data size: 64275 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bigtbl
+PREHOOK: Input: default@smalltbl1
+PREHOOK: Input: default@smalltbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Input: default@smalltbl1
+POSTHOOK: Input: default@smalltbl2
+#### A masked pattern was here ####
+RUN: Stage-1:MAPRED
+580
+PREHOOK: query: -- Now run a query with two-way join, which should be converted into a
+-- map-join followed by groupby - two MR jobs overall
+explain
+select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Now run a query with two-way join, which should be converted into a
+-- map-join followed by groupby - two MR jobs overall
+explain
+select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: bigtbl
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5500 Data size: 58432 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5500 Data size: 58432 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 6050 Data size: 64275 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: value (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ mode: mergepartial
+ outputColumnNames: _col0
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bigtbl
+PREHOOK: Input: default@smalltbl1
+PREHOOK: Input: default@smalltbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Input: default@smalltbl1
+POSTHOOK: Input: default@smalltbl2
+#### A masked pattern was here ####
+RUN: Stage-1:MAPRED
+580
+PREHOOK: query: -- Now run a query with two-way join, which should first be converted into a
+-- map-join followed by groupby and then finally into a single MR job.
+
+explain
+select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+group by smallTbl2.key
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Now run a query with two-way join, which should first be converted into a
+-- map-join followed by groupby and then finally into a single MR job.
+
+explain
+select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+group by smallTbl2.key
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: bigtbl
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 5000 Data size: 53120 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5500 Data size: 58432 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 5500 Data size: 58432 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col1
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 6050 Data size: 64275 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: count()
+ keys: _col1 (type: string)
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 6050 Data size: 64275 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: 6050 Data size: 64275 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: count(VALUE._col0)
+ keys: KEY._col0 (type: string)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 3025 Data size: 32137 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col1 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 3025 Data size: 32137 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 3025 Data size: 32137 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+group by smallTbl2.key
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bigtbl
+PREHOOK: Input: default@smalltbl1
+PREHOOK: Input: default@smalltbl2
+#### A masked pattern was here ####
+POSTHOOK: query: select count(*) FROM
+(select bigTbl.key as key, bigTbl.value as value1,
+ bigTbl.value as value2 FROM bigTbl JOIN smallTbl1
+ on (bigTbl.key = smallTbl1.key)
+) firstjoin
+JOIN
+smallTbl2 on (firstjoin.value1 = smallTbl2.value)
+group by smallTbl2.key
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Input: default@smalltbl1
+POSTHOOK: Input: default@smalltbl2
+#### A masked pattern was here ####
+RUN: Stage-1:MAPRED
+270
+10
+10
+270
+10
+10
+PREHOOK: query: drop table bigTbl
+PREHOOK: type: DROPTABLE
+PREHOOK: Input: default@bigtbl
+PREHOOK: Output: default@bigtbl
+POSTHOOK: query: drop table bigTbl
+POSTHOOK: type: DROPTABLE
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Output: default@bigtbl
+RUN: Stage-0:DDL
+PREHOOK: query: create table bigTbl(key1 string, key2 string, value string)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bigTbl
+POSTHOOK: query: create table bigTbl(key1 string, key2 string, value string)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bigTbl
+RUN: Stage-0:DDL
+PREHOOK: query: insert overwrite table bigTbl
+select * from
+(
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+) subq
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: default@bigtbl
+POSTHOOK: query: insert overwrite table bigTbl
+select * from
+(
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+ union all
+ select key as key1, key as key2, value from src
+) subq
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: default@bigtbl
+POSTHOOK: Lineage: bigtbl.key1 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: bigtbl.key2 EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ]
+POSTHOOK: Lineage: bigtbl.value EXPRESSION [(src)src.FieldSchema(name:value, type:string, comment:default), ]
+RUN: Stage-1:MAPRED
+RUN: Stage-2:DEPENDENCY_COLLECTION
+RUN: Stage-0:MOVE
+RUN: Stage-3:STATS
+PREHOOK: query: -- First disable noconditionaltask
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- First disable noconditionaltask
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE), Map 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: bigtbl
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean)
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key1 (type: string), key2 (type: string), value (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 6050 Data size: 87337 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 6050 Data size: 87337 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 6655 Data size: 96070 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col4 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 6655 Data size: 96070 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ input vertices:
+ 1 Map 6
+ Statistics: Num rows: 7320 Data size: 105677 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col5) (type: int), hash(_col6) (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 7320 Data size: 105677 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl3
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl4
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bigtbl
+PREHOOK: Input: default@smalltbl1
+PREHOOK: Input: default@smalltbl2
+PREHOOK: Input: default@smalltbl3
+PREHOOK: Input: default@smalltbl4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Input: default@smalltbl1
+POSTHOOK: Input: default@smalltbl2
+POSTHOOK: Input: default@smalltbl3
+POSTHOOK: Input: default@smalltbl4
+#### A masked pattern was here ####
+RUN: Stage-1:MAPRED
+247580 247580 247580 247580 247580 247580 548662743780 548662743780
+PREHOOK: query: -- Enable noconditionaltask and set the size of hive.auto.convert.join.noconditionaltask.size
+-- to 10000, which is large enough to fit all four small tables (smallTbl1 to smallTbl4).
+-- We will use a single MR job to evaluate this query.
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable noconditionaltask and set the size of hive.auto.convert.join.noconditionaltask.size
+-- to 10000, which is large enough to fit all four small tables (smallTbl1 to smallTbl4).
+-- We will use a single MR job to evaluate this query.
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE), Map 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: bigtbl
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean)
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key1 (type: string), key2 (type: string), value (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 6050 Data size: 87337 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 6050 Data size: 87337 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 6655 Data size: 96070 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col4 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 6655 Data size: 96070 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ input vertices:
+ 1 Map 6
+ Statistics: Num rows: 7320 Data size: 105677 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col5) (type: int), hash(_col6) (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 7320 Data size: 105677 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl3
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl4
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bigtbl
+PREHOOK: Input: default@smalltbl1
+PREHOOK: Input: default@smalltbl2
+PREHOOK: Input: default@smalltbl3
+PREHOOK: Input: default@smalltbl4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Input: default@smalltbl1
+POSTHOOK: Input: default@smalltbl2
+POSTHOOK: Input: default@smalltbl3
+POSTHOOK: Input: default@smalltbl4
+#### A masked pattern was here ####
+RUN: Stage-1:MAPRED
+247580 247580 247580 247580 247580 247580 548662743780 548662743780
+PREHOOK: query: -- Enable noconditionaltask and set the size of hive.auto.convert.join.noconditionaltask.size
+-- to 200, which is large enough to fit two small tables. We will have two jobs to evaluate this
+-- query. The first job is a Map-only job to evaluate join1 and join2.
+-- The second job will evaluate the rest of this query.
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable noconditionaltask and set the size of hive.auto.convert.join.noconditionaltask.size
+-- to 200, which is large enough to fit two small tables. We will have two jobs to evaluate this
+-- query. The first job is a Map-only job to evaluate join1 and join2.
+-- The second job will evaluate the rest of this query.
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE), Map 5 (BROADCAST_EDGE), Map 6 (BROADCAST_EDGE)
+ Reducer 2 <- Map 1 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: bigtbl
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key1 is not null and value is not null and key2 is not null) (type: boolean)
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key1 (type: string), key2 (type: string), value (type: string)
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 5000 Data size: 72180 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col3 (type: string), _col2 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 5500 Data size: 79398 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 6050 Data size: 87337 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col5 (type: string), _col3 (type: string), _col4 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Statistics: Num rows: 6050 Data size: 87337 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ input vertices:
+ 1 Map 5
+ Statistics: Num rows: 6655 Data size: 96070 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col6 (type: string), _col4 (type: string), _col5 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Statistics: Num rows: 6655 Data size: 96070 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: string)
+ 1 _col0 (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ input vertices:
+ 1 Map 6
+ Statistics: Num rows: 7320 Data size: 105677 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int), hash(_col4) (type: int), hash(_col7) (type: int), hash(_col5) (type: int), hash(_col6) (type: int)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 7320 Data size: 105677 Basic stats: COMPLETE Column stats: NONE
+ Group By Operator
+ aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3), sum(_col4), sum(_col5), sum(_col6), sum(_col7)
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ sort order:
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: bigint), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: bigint), _col6 (type: bigint), _col7 (type: bigint)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 4
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl2
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: value is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Reduce Output Operator
+ key expressions: _col1 (type: string)
+ sort order: +
+ Map-reduce partition columns: _col1 (type: string)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col0 (type: string)
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl3
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Map 6
+ Map Operator Tree:
+ TableScan
+ alias: smalltbl4
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: key is not null (type: boolean)
+ Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: string)
+ outputColumnNames: _col0
+ Statistics: Num rows: 10 Data size: 70 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+ Execution mode: llap
+ LLAP IO: no inputs
+ Reducer 2
+ Execution mode: llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), sum(VALUE._col1), sum(VALUE._col2), sum(VALUE._col3), sum(VALUE._col4), sum(VALUE._col5), sum(VALUE._col6), sum(VALUE._col7)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 1 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
+
+PREHOOK: query: SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bigtbl
+PREHOOK: Input: default@smalltbl1
+PREHOOK: Input: default@smalltbl2
+PREHOOK: Input: default@smalltbl3
+PREHOOK: Input: default@smalltbl4
+#### A masked pattern was here ####
+POSTHOOK: query: SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bigtbl
+POSTHOOK: Input: default@smalltbl1
+POSTHOOK: Input: default@smalltbl2
+POSTHOOK: Input: default@smalltbl3
+POSTHOOK: Input: default@smalltbl4
+#### A masked pattern was here ####
+RUN: Stage-1:MAPRED
+247580 247580 247580 247580 247580 247580 548662743780 548662743780
+PREHOOK: query: -- Enable noconditionaltask and but set the size of hive.auto.convert.join.noconditionaltask.size
+-- to 0. The plan will be the same as the one with a disabled nonconditionaltask.
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+PREHOOK: type: QUERY
+POSTHOOK: query: -- Enable noconditionaltask and but set the size of hive.auto.convert.join.noconditionaltask.size
+-- to 0. The plan will be the same as the one with a disabled nonconditionaltask.
+EXPLAIN
+SELECT SUM(HASH(join3.key1)),
+ SUM(HASH(join3.key2)),
+ SUM(HASH(join3.key3)),
+ SUM(HASH(join3.key4)),
+ SUM(HASH(join3.key5)),
+ SUM(HASH(smallTbl4.key)),
+ SUM(HASH(join3.value1)),
+ SUM(HASH(join3.value2))
+FROM (SELECT join2.key1 as key1,
+ join2.key2 as key2,
+ join2.key3 as key3,
+ join2.key4 as key4,
+ smallTbl3.key as key5,
+ join2.value1 as value1,
+ join2.value2 as value2
+ FROM (SELECT join1.key1 as key1,
+ join1.key2 as key2,
+ join1.key3 as key3,
+ smallTbl2.key as key4,
+ join1.value1 as value1,
+ join1.value2 as value2
+ FROM (SELECT bigTbl.key1 as key1,
+ bigTbl.key2 as key2,
+ smallTbl1.key as key3,
+ bigTbl.value as value1,
+ bigTbl.value as value2
+ FROM bigTbl
+ JOIN smallTbl1 ON (bigTbl.key1 = smallTbl1.key)) join1
+ JOIN smallTbl2 ON (join1.value1 = smallTbl2.value)) join2
+ JOIN smallTbl3 ON (join2.key2 = smallTbl3.key)) join3
+JOIN smallTbl4 ON (join3.key3 = smallTbl4.key)
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+ Sta
<TRUNCATED>
|