http://git-wip-us.apache.org/repos/asf/hive/blob/62a3778e/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out index 7c54d4c..d23d81c 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join3.q.out @@ -8,6 +8,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc1a +POSTHOOK: Lineage: small_alltypesorc1a.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cstring1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1a.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: create table small_alltypesorc2a as select * from alltypesorc where cint is null and cstring1 is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@alltypesorc @@ -18,6 +30,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc2a +POSTHOOK: Lineage: small_alltypesorc2a.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cint SIMPLE [] +POSTHOOK: Lineage: small_alltypesorc2a.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cstring1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2a.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: create table small_alltypesorc3a as select * from alltypesorc where cint is not null and cstring1 is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@alltypesorc @@ -28,6 +52,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc3a +POSTHOOK: Lineage: small_alltypesorc3a.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.cint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.cstring1 SIMPLE [] +POSTHOOK: Lineage: small_alltypesorc3a.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3a.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: create table small_alltypesorc4a as select * from alltypesorc where cint is null and cstring1 is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 5 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@alltypesorc @@ -38,6 +74,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc4a +POSTHOOK: Lineage: small_alltypesorc4a.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.cint SIMPLE [] +POSTHOOK: Lineage: small_alltypesorc4a.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.cstring1 SIMPLE [] +POSTHOOK: Lineage: small_alltypesorc4a.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4a.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: select * from small_alltypesorc1a PREHOOK: type: QUERY PREHOOK: Input: default@small_alltypesorc1a @@ -120,6 +168,18 @@ POSTHOOK: Input: default@small_alltypesorc3a POSTHOOK: Input: default@small_alltypesorc4a POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc_a +POSTHOOK: Lineage: small_alltypesorc_a.cbigint EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cbigint, type:bigint, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cbigint, type:bigint, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cbigint, type:bigint, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cboolean1 EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cboolean1, type:boolean, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cboolean1, type:boolean, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cboolean1, type:boolean, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cboolean2 EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cboolean2, type:boolean, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cboolean2, type:boolean, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cboolean2, type:boolean, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cdouble EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cdouble, type:double, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cdouble, type:double, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cdouble, type:double, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cfloat EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cfloat, type:float, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cfloat, type:float, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cfloat, type:float, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cint EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cint, type:int, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cint, type:int, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cint, type:int, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.csmallint EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:csmallint, type:smallint, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:csmallint, type:smallint, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:csmallint, type:smallint, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cstring1 EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cstring1, type:string, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cstring1, type:string, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cstring1, type:string, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.cstring2 EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:cstring2, type:string, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:cstring2, type:string, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:cstring2, type:string, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctimestamp1 EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctimestamp2 EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_a.ctinyint EXPRESSION [(small_alltypesorc1a)small_alltypesorc1a.FieldSchema(name:ctinyint, type:tinyint, comment:null), (small_alltypesorc2a)small_alltypesorc2a.FieldSchema(name:ctinyint, type:tinyint, comment:null), (small_alltypesorc3a)small_alltypesorc3a.FieldSchema(name:ctinyint, type:tinyint, comment:null), (small_alltypesorc4a)small_alltypesorc4a.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: ANALYZE TABLE small_alltypesorc_a COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@small_alltypesorc_a @@ -189,6 +249,7 @@ STAGE DEPENDENCIES: 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) @@ -213,7 +274,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 22 Data size: 5024 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Map Join Operator condition map: Left Outer Join0 to 1 @@ -223,7 +283,6 @@ STAGE PLANS: input vertices: 1 Map 4 Statistics: Num rows: 24 Data size: 5526 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -234,10 +293,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -249,10 +309,11 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 4 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) @@ -264,8 +325,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -276,8 +338,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -332,6 +394,7 @@ STAGE DEPENDENCIES: 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) @@ -356,7 +419,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 22 Data size: 5024 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Map Join Operator condition map: Left Outer Join0 to 1 @@ -366,7 +428,6 @@ STAGE PLANS: input vertices: 1 Map 4 Statistics: Num rows: 24 Data size: 5526 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -377,10 +438,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring2 (type: string) @@ -392,10 +454,11 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 4 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cstring1 (type: string) @@ -407,8 +470,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -419,8 +483,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -475,6 +539,7 @@ STAGE DEPENDENCIES: 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) @@ -493,23 +558,21 @@ STAGE PLANS: condition map: Left Outer Join0 to 1 keys: - 0 _col3 (type: string), _col1 (type: bigint) - 1 _col1 (type: string), _col0 (type: bigint) + 0 _col1 (type: bigint), _col3 (type: string) + 1 _col0 (type: bigint), _col1 (type: string) outputColumnNames: _col0, _col2 input vertices: 1 Map 3 Statistics: Num rows: 22 Data size: 5024 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Map Join Operator condition map: Left Outer Join0 to 1 keys: - 0 _col2 (type: string), _col0 (type: int) - 1 _col1 (type: string), _col0 (type: int) + 0 _col0 (type: int), _col2 (type: string) + 1 _col0 (type: int), _col1 (type: string) input vertices: 1 Map 4 Statistics: Num rows: 24 Data size: 5526 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -520,38 +583,41 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cbigint (type: bigint), cstring2 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: bigint) + key expressions: _col0 (type: bigint), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: bigint) + Map-reduce partition columns: _col0 (type: bigint), _col1 (type: string) Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 4 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int), cstring1 (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string), _col0 (type: int) + key expressions: _col0 (type: int), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col1 (type: string), _col0 (type: int) + Map-reduce partition columns: _col0 (type: int), _col1 (type: string) Statistics: Num rows: 20 Data size: 4568 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -562,8 +628,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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
http://git-wip-us.apache.org/repos/asf/hive/blob/62a3778e/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out index 55f65ed..1bb0e30 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join4.q.out @@ -8,6 +8,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc1b +POSTHOOK: Lineage: small_alltypesorc1b.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cstring1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc1b.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: create table small_alltypesorc2b as select * from alltypesorc where cint is null and ctinyint is not null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 10 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@alltypesorc @@ -18,6 +30,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc2b +POSTHOOK: Lineage: small_alltypesorc2b.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cint SIMPLE [] +POSTHOOK: Lineage: small_alltypesorc2b.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cstring1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc2b.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: create table small_alltypesorc3b as select * from alltypesorc where cint is not null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 10 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@alltypesorc @@ -28,6 +52,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc3b +POSTHOOK: Lineage: small_alltypesorc3b.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cstring1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc3b.ctinyint SIMPLE [] PREHOOK: query: create table small_alltypesorc4b as select * from alltypesorc where cint is null and ctinyint is null order by ctinyint, csmallint, cint, cbigint, cfloat, cdouble, cstring1, cstring2, ctimestamp1, ctimestamp2, cboolean1, cboolean2 limit 10 PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@alltypesorc @@ -38,6 +74,18 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc4b +POSTHOOK: Lineage: small_alltypesorc4b.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cboolean1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cboolean2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cdouble SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cfloat SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cint SIMPLE [] +POSTHOOK: Lineage: small_alltypesorc4b.csmallint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cstring1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.cstring2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.ctimestamp1 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.ctimestamp2 SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc4b.ctinyint SIMPLE [] PREHOOK: query: select * from small_alltypesorc1b PREHOOK: type: QUERY PREHOOK: Input: default@small_alltypesorc1b @@ -130,6 +178,18 @@ POSTHOOK: Input: default@small_alltypesorc3b POSTHOOK: Input: default@small_alltypesorc4b POSTHOOK: Output: database:default POSTHOOK: Output: default@small_alltypesorc_b +POSTHOOK: Lineage: small_alltypesorc_b.cbigint EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cbigint, type:bigint, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cbigint, type:bigint, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cbigint, type:bigint, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cboolean1 EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cboolean1, type:boolean, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cboolean1, type:boolean, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cboolean1, type:boolean, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cboolean1, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cboolean2 EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cboolean2, type:boolean, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cboolean2, type:boolean, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cboolean2, type:boolean, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cboolean2, type:boolean, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cdouble EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cdouble, type:double, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cdouble, type:double, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cdouble, type:double, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cdouble, type:double, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cfloat EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cfloat, type:float, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cfloat, type:float, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cfloat, type:float, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cfloat, type:float, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cint EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cint, type:int, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cint, type:int, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cint, type:int, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.csmallint EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:csmallint, type:smallint, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:csmallint, type:smallint, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:csmallint, type:smallint, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:csmallint, type:smallint, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cstring1 EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cstring1, type:string, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cstring1, type:string, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cstring1, type:string, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cstring1, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.cstring2 EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:cstring2, type:string, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:cstring2, type:string, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:cstring2, type:string, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:cstring2, type:string, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.ctimestamp1 EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:ctimestamp1, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.ctimestamp2 EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:ctimestamp2, type:timestamp, comment:null), ] +POSTHOOK: Lineage: small_alltypesorc_b.ctinyint EXPRESSION [(small_alltypesorc1b)small_alltypesorc1b.FieldSchema(name:ctinyint, type:tinyint, comment:null), (small_alltypesorc2b)small_alltypesorc2b.FieldSchema(name:ctinyint, type:tinyint, comment:null), (small_alltypesorc3b)small_alltypesorc3b.FieldSchema(name:ctinyint, type:tinyint, comment:null), (small_alltypesorc4b)small_alltypesorc4b.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: ANALYZE TABLE small_alltypesorc_b COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@small_alltypesorc_b @@ -203,6 +263,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 2 (BROADCAST_EDGE) #### A masked pattern was here #### @@ -226,19 +287,19 @@ STAGE PLANS: input vertices: 1 Map 2 Statistics: Num rows: 33 Data size: 7521 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true File Output Operator compressed: false Statistics: Num rows: 33 Data size: 7521 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap + LLAP IO: all inputs Map 2 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) @@ -251,6 +312,7 @@ STAGE PLANS: Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Execution mode: vectorized, llap + LLAP IO: all inputs Stage: Stage-0 Fetch Operator @@ -345,6 +407,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 2 (BROADCAST_EDGE) #### A masked pattern was here #### @@ -368,19 +431,19 @@ STAGE PLANS: input vertices: 1 Map 2 Statistics: Num rows: 33 Data size: 7521 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true File Output Operator compressed: false Statistics: Num rows: 33 Data size: 7521 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Execution mode: vectorized, llap + LLAP IO: all inputs Map 2 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) @@ -392,6 +455,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Stage: Stage-0 Fetch Operator @@ -848,6 +912,7 @@ STAGE DEPENDENCIES: 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) @@ -872,7 +937,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 33 Data size: 7521 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Map Join Operator condition map: Left Outer Join0 to 1 @@ -882,7 +946,6 @@ STAGE PLANS: input vertices: 1 Map 4 Statistics: Num rows: 36 Data size: 8273 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -893,10 +956,11 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan - alias: c + alias: cd Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cint (type: int) @@ -908,10 +972,11 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 4 Map Operator Tree: TableScan - alias: c + alias: hd Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) @@ -923,8 +988,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 30 Data size: 6838 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -935,8 +1001,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 http://git-wip-us.apache.org/repos/asf/hive/blob/62a3778e/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out b/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out index 608a420..d5db31f 100644 --- a/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_outer_join5.q.out @@ -14,6 +14,8 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@sorted_mod_4 +POSTHOOK: Lineage: sorted_mod_4.cmodint EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: sorted_mod_4.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: ANALYZE TABLE sorted_mod_4 COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@sorted_mod_4 @@ -42,6 +44,8 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_table +POSTHOOK: Lineage: small_table.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_table.ctinyint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: ANALYZE TABLE small_table COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@small_table @@ -79,6 +83,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -102,7 +107,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -113,6 +117,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -128,8 +133,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -140,8 +146,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -190,6 +196,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -216,7 +223,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -227,6 +233,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -242,8 +249,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -254,8 +262,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -304,6 +312,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -330,7 +339,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -341,6 +349,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -356,8 +365,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -368,8 +378,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -418,6 +428,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -444,7 +455,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -455,6 +465,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -470,8 +481,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -482,8 +494,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -536,6 +548,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 4 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) @@ -556,18 +569,18 @@ STAGE PLANS: Left Outer Join0 to 1 keys: 0 UDFToLong(_col1) (type: bigint) - 1 (_col0 pmod UDFToLong(8)) (type: bigint) + 1 (_col0 pmod 8) (type: bigint) outputColumnNames: _col0 input vertices: 1 Map 4 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Reduce Output Operator key expressions: _col0 (type: tinyint) sort order: + Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 4 Map Operator Tree: TableScan @@ -578,15 +591,16 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (_col0 pmod UDFToLong(8)) (type: bigint) + key expressions: (_col0 pmod 8) (type: bigint) sort order: + - Map-reduce partition columns: (_col0 pmod UDFToLong(8)) (type: bigint) + Map-reduce partition columns: (_col0 pmod 8) (type: bigint) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 5 Map Operator Tree: TableScan - alias: s + alias: s2 Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) @@ -598,6 +612,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: tinyint) Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -618,7 +633,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -629,8 +644,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -676,6 +691,8 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@mod_8_mod_4 +POSTHOOK: Lineage: mod_8_mod_4.cmodint EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:cint, type:int, comment:null), ] +POSTHOOK: Lineage: mod_8_mod_4.cmodtinyint EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: ANALYZE TABLE mod_8_mod_4 COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@mod_8_mod_4 @@ -704,6 +721,8 @@ POSTHOOK: type: CREATETABLE_AS_SELECT POSTHOOK: Input: default@alltypesorc POSTHOOK: Output: database:default POSTHOOK: Output: default@small_table2 +POSTHOOK: Lineage: small_table2.cbigint SIMPLE [(alltypesorc)alltypesorc.FieldSchema(name:cbigint, type:bigint, comment:null), ] +POSTHOOK: Lineage: small_table2.cmodtinyint EXPRESSION [(alltypesorc)alltypesorc.FieldSchema(name:ctinyint, type:tinyint, comment:null), ] PREHOOK: query: ANALYZE TABLE small_table2 COMPUTE STATISTICS PREHOOK: type: QUERY PREHOOK: Input: default@small_table2 @@ -741,6 +760,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -764,7 +784,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -775,6 +794,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -790,8 +810,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -802,8 +823,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -852,6 +873,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -878,7 +900,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -889,6 +910,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -904,8 +926,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -916,8 +939,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -966,6 +989,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -992,7 +1016,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -1003,6 +1026,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -1018,8 +1042,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1030,8 +1055,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -1080,6 +1105,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 3 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE) @@ -1106,7 +1132,6 @@ STAGE PLANS: input vertices: 1 Map 3 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Group By Operator aggregations: count() mode: hash @@ -1117,6 +1142,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Execution mode: vectorized, llap + LLAP IO: all inputs Map 3 Map Operator Tree: TableScan @@ -1132,8 +1158,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1144,8 +1171,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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 @@ -1198,6 +1225,7 @@ STAGE DEPENDENCIES: STAGE PLANS: Stage: Stage-1 Tez +#### A masked pattern was here #### Edges: Map 1 <- Map 4 (BROADCAST_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) @@ -1218,18 +1246,18 @@ STAGE PLANS: Left Outer Join0 to 1 keys: 0 UDFToLong(_col1) (type: bigint) - 1 (_col0 pmod UDFToLong(8)) (type: bigint) + 1 (_col0 pmod 8) (type: bigint) outputColumnNames: _col0 input vertices: 1 Map 4 Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE - HybridGraceHashJoin: true Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 6663 Data size: 53310 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 4 Map Operator Tree: TableScan @@ -1240,15 +1268,16 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: (_col0 pmod UDFToLong(8)) (type: bigint) + key expressions: (_col0 pmod 8) (type: bigint) sort order: + - Map-reduce partition columns: (_col0 pmod UDFToLong(8)) (type: bigint) + Map-reduce partition columns: (_col0 pmod 8) (type: bigint) Statistics: Num rows: 100 Data size: 392 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Map 5 Map Operator Tree: TableScan - alias: s + alias: s2 Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: cmodtinyint (type: int) @@ -1260,6 +1289,7 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 6058 Data size: 48464 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap + LLAP IO: all inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1280,7 +1310,7 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint) Reducer 3 - Execution mode: vectorized, uber + Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator aggregations: count(VALUE._col0) @@ -1291,8 +1321,8 @@ STAGE PLANS: compressed: false Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE table: - input format: org.apache.hadoop.mapred.TextInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + 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
