hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From ser...@apache.org
Subject [23/67] [abbrv] [partial] hive git commit: Revert "Revert "HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)""
Date Mon, 17 Oct 2016 20:42:15 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/16d28b34/ql/src/test/results/clientpositive/llap/vector_join_part_col_char.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_join_part_col_char.q.out b/ql/src/test/results/clientpositive/llap/vector_join_part_col_char.q.out
index 16603c7..c21da5f 100644
--- a/ql/src/test/results/clientpositive/llap/vector_join_part_col_char.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_join_part_col_char.q.out
@@ -97,9 +97,9 @@ POSTHOOK: type: SHOWPARTITIONS
 POSTHOOK: Input: default@char_tbl2
 gpa=3    
 gpa=3.5  
-PREHOOK: query: explain select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1
c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
+PREHOOK: query: explain vectorization select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa
from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
 PREHOOK: type: QUERY
-POSTHOOK: query: explain select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa from char_tbl1
c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
+POSTHOOK: query: explain vectorization select c1.name, c1.age, c1.gpa, c2.name, c2.age, c2.gpa
from char_tbl1 c1 join char_tbl2 c2 on (c1.gpa = c2.gpa)
 POSTHOOK: type: QUERY
 Plan optimized by CBO.
 

http://git-wip-us.apache.org/repos/asf/hive/blob/16d28b34/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out
index b9ffa34..25066be 100644
--- a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out
@@ -1,4 +1,4 @@
-PREHOOK: query: explain 
+PREHOOK: query: explain vectorization 
 select count(*) from (select c.ctinyint 
 from alltypesorc c
 left outer join alltypesorc cd
@@ -7,7 +7,7 @@ left outer join alltypesorc hd
   on hd.ctinyint = c.ctinyint
 ) t1
 PREHOOK: type: QUERY
-POSTHOOK: query: explain 
+POSTHOOK: query: explain vectorization 
 select count(*) from (select c.ctinyint 
 from alltypesorc c
 left outer join alltypesorc cd
@@ -16,6 +16,10 @@ left outer join alltypesorc hd
   on hd.ctinyint = c.ctinyint
 ) t1
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: true
+  enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -68,6 +72,14 @@ STAGE PLANS:
                             value expressions: _col0 (type: bigint)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -84,6 +96,14 @@ STAGE PLANS:
                       Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE
Column stats: COMPLETE
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 4 
             Map Operator Tree:
                 TableScan
@@ -100,8 +120,23 @@ STAGE PLANS:
                       Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE
Column stats: COMPLETE
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Reducer 2 
             Execution mode: vectorized, llap
+            Reduce Vectorization:
+                enabled: true
+                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine
tez IN [tez, spark] IS true
+                groupByVectorOutput: true
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)

http://git-wip-us.apache.org/repos/asf/hive/blob/16d28b34/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out b/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out
index 1163d24..fa35da7 100644
--- a/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out
@@ -80,12 +80,16 @@ POSTHOOK: Output: default@tjoin2
 POSTHOOK: Lineage: tjoin2.c1 SIMPLE [(tjoin2stage)tjoin2stage.FieldSchema(name:c1, type:int,
comment:null), ]
 POSTHOOK: Lineage: tjoin2.c2 SIMPLE [(tjoin2stage)tjoin2stage.FieldSchema(name:c2, type:char(2),
comment:null), ]
 POSTHOOK: Lineage: tjoin2.rnum SIMPLE [(tjoin2stage)tjoin2stage.FieldSchema(name:rnum, type:int,
comment:null), ]
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: false
+  enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -170,12 +174,16 @@ POSTHOOK: Input: default@tjoin2
 0	10	15	NULL
 1	20	25	NULL
 2	NULL	50	NULL
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: false
+  enabledConditionsNotMet: [hive.vectorized.execution.enabled IS false]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -260,12 +268,16 @@ POSTHOOK: Input: default@tjoin2
 0	10	15	NULL
 1	20	25	NULL
 2	NULL	50	NULL
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: true
+  enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -283,9 +295,16 @@ STAGE PLANS:
                 TableScan
                   alias: tjoin1
                   Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: rnum (type: int), c1 (type: int), c2 (type: int)
                     outputColumnNames: _col0, _col1, _col2
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0, 1, 2]
                     Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
                     Map Join Operator
                       condition map:
@@ -296,6 +315,11 @@ STAGE PLANS:
                       keys:
                         0 _col1 (type: int)
                         1 _col0 (type: int)
+                      Map Join Vectorization:
+                          className: VectorMapJoinOuterFilteredOperator
+                          native: false
+                          nativeConditionsMet: hive.execution.engine tez IN [tez, spark]
IS true, One MapJoin Condition IS true, No nullsafe IS true, Supports Key Types IS true, Not
empty key IS true, When Fast Hash Table, then requires no Hybrid Hash Join IS true, Small
table vectorizes IS true
+                          nativeConditionsNotMet: hive.vectorized.execution.mapjoin.native.enabled
IS false
                       outputColumnNames: _col0, _col1, _col2, _col4
                       input vertices:
                         1 Map 2
@@ -303,9 +327,16 @@ STAGE PLANS:
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int),
_col4 (type: char(2))
                         outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Vectorization:
+                            className: VectorSelectOperator
+                            native: true
+                            projectedOutputColumns: [0, 1, 2, 3]
                         Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                         File Output Operator
                           compressed: false
+                          File Sink Vectorization:
+                              className: VectorFileSinkOperator
+                              native: false
                           Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                           table:
                               input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -313,23 +344,50 @@ STAGE PLANS:
                               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 2 
             Map Operator Tree:
                 TableScan
                   alias: tjoin2
                   Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: c1 (type: int), c2 (type: char(2))
                     outputColumnNames: _col0, _col1
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [1, 2]
                     Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
+                      Reduce Sink Vectorization:
+                          className: VectorReduceSinkLongOperator
+                          native: true
+                          nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true,
No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe
for keys IS true, LazyBinarySerDe for values IS true
                       Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column
stats: NONE
                       value expressions: _col1 (type: char(2))
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
 
   Stage: Stage-0
     Fetch Operator
@@ -350,12 +408,16 @@ POSTHOOK: Input: default@tjoin2
 0	10	15	NULL
 1	20	25	NULL
 2	NULL	50	NULL
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: true
+  enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -373,9 +435,16 @@ STAGE PLANS:
                 TableScan
                   alias: tjoin1
                   Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: rnum (type: int), c1 (type: int), c2 (type: int)
                     outputColumnNames: _col0, _col1, _col2
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0, 1, 2]
                     Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
                     Map Join Operator
                       condition map:
@@ -386,6 +455,11 @@ STAGE PLANS:
                       keys:
                         0 _col1 (type: int)
                         1 _col0 (type: int)
+                      Map Join Vectorization:
+                          className: VectorMapJoinOuterFilteredOperator
+                          native: false
+                          nativeConditionsMet: hive.execution.engine tez IN [tez, spark]
IS true, One MapJoin Condition IS true, No nullsafe IS true, Supports Key Types IS true, Not
empty key IS true, When Fast Hash Table, then requires no Hybrid Hash Join IS true, Small
table vectorizes IS true
+                          nativeConditionsNotMet: hive.vectorized.execution.mapjoin.native.enabled
IS false
                       outputColumnNames: _col0, _col1, _col2, _col4
                       input vertices:
                         1 Map 2
@@ -393,9 +467,16 @@ STAGE PLANS:
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int),
_col4 (type: char(2))
                         outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Vectorization:
+                            className: VectorSelectOperator
+                            native: true
+                            projectedOutputColumns: [0, 1, 2, 3]
                         Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                         File Output Operator
                           compressed: false
+                          File Sink Vectorization:
+                              className: VectorFileSinkOperator
+                              native: false
                           Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                           table:
                               input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -403,23 +484,50 @@ STAGE PLANS:
                               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 2 
             Map Operator Tree:
                 TableScan
                   alias: tjoin2
                   Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: c1 (type: int), c2 (type: char(2))
                     outputColumnNames: _col0, _col1
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [1, 2]
                     Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
+                      Reduce Sink Vectorization:
+                          className: VectorReduceSinkLongOperator
+                          native: true
+                          nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true,
No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe
for keys IS true, LazyBinarySerDe for values IS true
                       Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column
stats: NONE
                       value expressions: _col1 (type: char(2))
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
 
   Stage: Stage-0
     Fetch Operator
@@ -440,12 +548,16 @@ POSTHOOK: Input: default@tjoin2
 0	10	15	NULL
 1	20	25	NULL
 2	NULL	50	NULL
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: true
+  enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -463,9 +575,16 @@ STAGE PLANS:
                 TableScan
                   alias: tjoin1
                   Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: rnum (type: int), c1 (type: int), c2 (type: int)
                     outputColumnNames: _col0, _col1, _col2
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0, 1, 2]
                     Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
                     Map Join Operator
                       condition map:
@@ -476,6 +595,10 @@ STAGE PLANS:
                       keys:
                         0 _col1 (type: int)
                         1 _col0 (type: int)
+                      Map Join Vectorization:
+                          className: VectorMapJoinOuterLongOperator
+                          native: true
+                          nativeConditionsMet: hive.vectorized.execution.mapjoin.native.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true,
No nullsafe IS true, Supports Key Types IS true, Not empty key IS true, When Fast Hash Table,
then requires no Hybrid Hash Join IS true, Small table vectorizes IS true
                       outputColumnNames: _col0, _col1, _col2, _col4
                       input vertices:
                         1 Map 2
@@ -483,9 +606,16 @@ STAGE PLANS:
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int),
_col4 (type: char(2))
                         outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Vectorization:
+                            className: VectorSelectOperator
+                            native: true
+                            projectedOutputColumns: [0, 1, 2, 3]
                         Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                         File Output Operator
                           compressed: false
+                          File Sink Vectorization:
+                              className: VectorFileSinkOperator
+                              native: false
                           Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                           table:
                               input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -493,23 +623,50 @@ STAGE PLANS:
                               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 2 
             Map Operator Tree:
                 TableScan
                   alias: tjoin2
                   Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: c1 (type: int), c2 (type: char(2))
                     outputColumnNames: _col0, _col1
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [1, 2]
                     Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
+                      Reduce Sink Vectorization:
+                          className: VectorReduceSinkLongOperator
+                          native: true
+                          nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true,
No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe
for keys IS true, LazyBinarySerDe for values IS true
                       Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column
stats: NONE
                       value expressions: _col1 (type: char(2))
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
 
   Stage: Stage-0
     Fetch Operator
@@ -530,12 +687,16 @@ POSTHOOK: Input: default@tjoin2
 0	10	15	NULL
 1	20	25	NULL
 2	NULL	50	NULL
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
 select tjoin1.rnum, tjoin1.c1, tjoin1.c2, tjoin2.c2 as c2j2 from tjoin1 left outer join tjoin2
on ( tjoin1.c1 = tjoin2.c1 and tjoin1.c2 > 15 )
 POSTHOOK: type: QUERY
+PLAN VECTORIZATION:
+  enabled: true
+  enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
@@ -553,9 +714,16 @@ STAGE PLANS:
                 TableScan
                   alias: tjoin1
                   Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: rnum (type: int), c1 (type: int), c2 (type: int)
                     outputColumnNames: _col0, _col1, _col2
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0, 1, 2]
                     Statistics: Num rows: 3 Data size: 32 Basic stats: COMPLETE Column stats:
NONE
                     Map Join Operator
                       condition map:
@@ -566,6 +734,10 @@ STAGE PLANS:
                       keys:
                         0 _col1 (type: int)
                         1 _col0 (type: int)
+                      Map Join Vectorization:
+                          className: VectorMapJoinOuterLongOperator
+                          native: true
+                          nativeConditionsMet: hive.vectorized.execution.mapjoin.native.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true,
No nullsafe IS true, Supports Key Types IS true, Not empty key IS true, When Fast Hash Table,
then requires no Hybrid Hash Join IS true, Small table vectorizes IS true
                       outputColumnNames: _col0, _col1, _col2, _col4
                       input vertices:
                         1 Map 2
@@ -573,9 +745,16 @@ STAGE PLANS:
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int),
_col4 (type: char(2))
                         outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Vectorization:
+                            className: VectorSelectOperator
+                            native: true
+                            projectedOutputColumns: [0, 1, 2, 3]
                         Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                         File Output Operator
                           compressed: false
+                          File Sink Vectorization:
+                              className: VectorFileSinkOperator
+                              native: false
                           Statistics: Num rows: 4 Data size: 409 Basic stats: COMPLETE Column
stats: NONE
                           table:
                               input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -583,23 +762,50 @@ STAGE PLANS:
                               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: false
+                usesVectorUDFAdaptor: false
+                vectorized: true
         Map 2 
             Map Operator Tree:
                 TableScan
                   alias: tjoin2
                   Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1, 2]
                   Select Operator
                     expressions: c1 (type: int), c2 (type: char(2))
                     outputColumnNames: _col0, _col1
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [1, 2]
                     Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column stats:
NONE
                     Reduce Output Operator
                       key expressions: _col0 (type: int)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: int)
+                      Reduce Sink Vectorization:
+                          className: VectorReduceSinkLongOperator
+                          native: true
+                          nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled
IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true,
No buckets IS true, No TopN IS true, Uniform Hash IS true, No DISTINCT columns IS true, BinarySortableSerDe
for keys IS true, LazyBinarySerDe for values IS true
                       Statistics: Num rows: 4 Data size: 372 Basic stats: COMPLETE Column
stats: NONE
                       value expressions: _col1 (type: char(2))
             Execution mode: vectorized, llap
             LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
 
   Stage: Stage-0
     Fetch Operator


Mime
View raw message