[34/51] [partial] hive git commit: HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out b/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out index bc37741..b51bed6 100644 --- a/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_auto_smb_mapjoin_14.q.out @@ -38,47 +38,113 @@ POSTHOOK: Input: default@src POSTHOOK: Output: default@tbl2 POSTHOOK: Lineage: tbl2.key EXPRESSION [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: tbl2.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select count(*) from ( select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key ) subq1 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select count(*) from ( select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key ) subq1 POSTHOOK: type: QUERY -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] -Vertex dependency in root stage -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator -limit:-1 -Stage-1 - Reducer 2 vectorized, llap - File Output Operator [FS_22] -Group By Operator [GBY_21] (rows=1 width=8) - Output:["_col0"],aggregations:["count(VALUE._col0)"] -<-Map 1 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_11] -Group By Operator [GBY_10] (rows=1 width=8) - Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_19] (rows=11 width=93) -Conds:SEL_2._col0=SEL_5._col0(Inner) - <-Select Operator [SEL_5] (rows=10 width=93) - Output:["_col0"] - Filter Operator [FIL_18] (rows=10 width=93) -predicate:key is not null -TableScan [TS_3] (rows=10 width=93) - default@tbl2,b,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Select Operator [SEL_2] (rows=10 width=93) - Output:["_col0"] - Filter Operator [FIL_17] (rows=10 width=93) -predicate:key is not null -TableScan [TS_0] (rows=10 width=93) - default@tbl1,a,Tbl:COMPLETE,Col:NONE,Output:["key"] +STAGE PLANS: + Stage: Stage-1 +Tez + A masked pattern was here + Edges: +Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) + A masked pattern was here + Vertices: +Map 1 +Map Operator Tree: +TableScan + alias: b + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Filter Operator +predicate: key is not null (type: boolean) +Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE +Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE +Map Operator Tree: +TableScan + alias: a + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Filter Operator +predicate: key is not null (type: boolean) +Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE +Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 10 Data size: 930 Basic stats: COMPLETE Column stats: NONE + Merge Join Operator +condition map: + Inner Join 0 to 1 +keys: + 0 _col0 (type: int) + 1 _col0 (type: int) +Statistics: Num rows: 11 Data size: 1023 Basic stats: COMPLETE Column stats: NONE +Group By Operator + aggregations: count() + Group By Vectorization: + vectorOutput: false + native: false + projectedOutputColumns: null +
[34/51] [partial] hive git commit: HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)
http://git-wip-us.apache.org/repos/asf/hive/blob/f923db0b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
--
diff --git
a/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
index 6b59497..739d0e1 100644
--- a/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_between_columns.q.out
@@ -69,13 +69,17 @@ POSTHOOK: Lineage: tint.cint SIMPLE
[(tint_txt)tint_txt.FieldSchema(name:cint, t
POSTHOOK: Lineage: tint.rnum SIMPLE [(tint_txt)tint_txt.FieldSchema(name:rnum,
type:int, comment:null), ]
tint_txt.rnum tint_txt.cint
Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Map 1' is a cross product
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization expression
select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint
between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col
from tint , tsint
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization expression
select tint.rnum, tsint.rnum, tint.cint, tsint.csint, (case when (tint.cint
between tsint.csint and tsint.csint) then "Ok" else "NoOk" end) as between_col
from tint , tsint
POSTHOOK: type: QUERY
Explain
+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
@@ -93,9 +97,16 @@ STAGE PLANS:
TableScan
alias: tint
Statistics: Num rows: 5 Data size: 36 Basic stats: COMPLETE
Column stats: NONE
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1]
Select Operator
expressions: rnum (type: int), cint (type: int)
outputColumnNames: _col0, _col1
+Select Vectorization:
+className: VectorSelectOperator
+native: true
+projectedOutputColumns: [0, 1]
Statistics: Num rows: 5 Data size: 36 Basic stats:
COMPLETE Column stats: NONE
Map Join Operator
condition map:
@@ -103,6 +114,11 @@ STAGE PLANS:
keys:
0
1
+ Map Join Vectorization:
+ className: VectorMapJoinOperator
+ native: false
+ 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, When Fast Hash Table, then requires no Hybrid
Hash Join IS true, Small table vectorizes IS true
+ nativeConditionsNotMet: Not empty key IS false
outputColumnNames: _col0, _col1, _col2, _col3
input vertices:
1 Map 2
@@ -110,9 +126,17 @@ STAGE PLANS:
Select Operator
expressions: _col0 (type: int), _col2 (type: int),
_col1 (type: int), _col3 (type: smallint), CASE WHEN (_col1 BETWEEN _col3 AND
_col3) THEN ('Ok') ELSE ('NoOk') END (type: string)
outputColumnNames: _col0, _col1, _col2, _col3, _col4
+Select Vectorization:
+className: VectorSelectOperator
+native: true
+projectedOutputColumns: [0, 2, 1, 3, 5]
+selectExpressions: VectorUDFAdaptor(CASE WHEN
(_col1 BETWEEN _col3 AND _col3) THEN ('Ok') ELSE ('NoOk') END)(children:
VectorUDFAdaptor(_col1 BETWEEN _col3 AND _col3) -> 4:Long) -> 5:String
Statistics: Num rows: 25 Data size: 385 Basic stats:
COMPLETE Column stats: NONE
File Output Operator
compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
Statistics: Num rows: 25 Data size: 385 Basic stats:
COMPLETE Column stats: NONE
table:
input format:
org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -120,21 +144,49 @@ STAGE PLANS:
serde:
org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Execution mode: vectorized, llap
LLAP IO: all inputs
+Map Vectorization:
+enabled: true
+enabledConditionsMet:
