You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by mm...@apache.org on 2017/02/03 20:03:31 UTC
[06/51] [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/vectorized_dynamic_partition_pruning.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
index 203ded8..96cfd65 100644
--- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
+++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out
@@ -34,10 +34,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
11
12
-PREHOOK: query: EXPLAIN create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds
+PREHOOK: query: EXPLAIN VECTORIZATION create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds
PREHOOK: type: CREATETABLE_AS_SELECT
-POSTHOOK: query: EXPLAIN create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds
+POSTHOOK: query: EXPLAIN VECTORIZATION create table srcpart_date as select ds as ds, ds as `date` from srcpart group by ds
POSTHOOK: type: CREATETABLE_AS_SELECT
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+
STAGE DEPENDENCIES:
Stage-1 is a root stage
Stage-2 depends on stages: Stage-1
@@ -74,8 +78,19 @@ STAGE PLANS:
Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
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
keys: KEY._col0 (type: string)
@@ -198,10 +213,14 @@ POSTHOOK: Output: database:default
POSTHOOK: Output: default@srcpart_double_hour
POSTHOOK: Lineage: srcpart_double_hour.hour SIMPLE [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
POSTHOOK: Lineage: srcpart_double_hour.hr EXPRESSION [(srcpart)srcpart.FieldSchema(name:hr, type:string, comment:null), ]
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
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
@@ -232,6 +251,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -267,6 +290,14 @@ STAGE PLANS:
Target Vertex: Map 1
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
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -288,6 +319,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -327,10 +365,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_date
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
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
@@ -361,6 +403,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -381,6 +427,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
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: llap
Reduce Operator Tree:
@@ -402,6 +456,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -454,12 +515,16 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11
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
@@ -491,6 +556,10 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 5
Map Operator Tree:
TableScan
@@ -526,6 +595,14 @@ STAGE PLANS:
Target Vertex: Map 1
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 6
Map Operator Tree:
TableScan
@@ -561,6 +638,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -598,6 +683,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 4
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)
@@ -641,12 +733,16 @@ POSTHOOK: Input: default@srcpart_date
POSTHOOK: Input: default@srcpart_hour
#### A masked pattern was here ####
500
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11
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
@@ -679,6 +775,10 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 5
Map Operator Tree:
TableScan
@@ -699,6 +799,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
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 6
Map Operator Tree:
TableScan
@@ -719,6 +827,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -756,6 +872,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 4
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)
@@ -810,10 +933,14 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
#### A masked pattern was here ####
500
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
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
@@ -843,6 +970,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -893,6 +1024,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -914,6 +1053,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -953,10 +1099,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_date_hour
#### A masked pattern was here ####
500
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date_hour on (srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr) where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11
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
@@ -987,6 +1137,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1007,6 +1161,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1028,6 +1190,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1078,10 +1247,14 @@ POSTHOOK: Input: default@srcpart
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
#### A masked pattern was here ####
500
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
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
@@ -1112,6 +1285,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1147,6 +1324,14 @@ STAGE PLANS:
Target Vertex: Map 1
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
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1168,6 +1353,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1207,10 +1399,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_date
#### A masked pattern was here ####
0
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = 'I DONT EXIST'
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
@@ -1241,6 +1437,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1261,6 +1461,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
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: llap
Reduce Operator Tree:
@@ -1282,6 +1490,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1330,10 +1545,14 @@ POSTHOOK: type: QUERY
POSTHOOK: Input: default@srcpart
#### A masked pattern was here ####
0
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
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
@@ -1364,6 +1583,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1399,6 +1622,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1420,6 +1651,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1459,10 +1697,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_double_hour
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
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
@@ -1493,6 +1735,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1528,6 +1774,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1549,6 +1803,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1588,10 +1849,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_double_hour
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr = cast(srcpart_double_hour.hr/2 as int)) where srcpart_double_hour.hour = 11
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
@@ -1622,6 +1887,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1642,6 +1911,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1663,6 +1940,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1702,10 +1986,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_double_hour
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (srcpart.hr*2 = srcpart_double_hour.hr) where srcpart_double_hour.hour = 11
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
@@ -1736,6 +2024,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1756,6 +2048,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1777,6 +2077,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1829,10 +2136,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_double_hour on (cast(srcpart.hr*2 as string) = cast(srcpart_double_hour.hr as string)) where srcpart_double_hour.hour = 11
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
@@ -1863,6 +2174,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -1898,6 +2213,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -1919,6 +2242,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -1972,10 +2302,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
#### A masked pattern was here ####
1000
Warning: Shuffle Join MERGEJOIN[22][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08'
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
@@ -2003,6 +2337,10 @@ STAGE PLANS:
Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -2023,6 +2361,10 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2044,6 +2386,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -2059,6 +2408,13 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
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
keys: KEY._col0 (type: string)
@@ -2105,10 +2461,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
#### A masked pattern was here ####
1000
Warning: Shuffle Join MERGEJOIN[16][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product
-PREHOOK: query: EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where (srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11) and (srcpart.ds = srcpart_date_hour.ds or srcpart.hr = srcpart_date_hour.hr)
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
@@ -2137,6 +2497,10 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -2156,6 +2520,14 @@ STAGE PLANS:
value expressions: _col0 (type: string), _col2 (type: string)
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2183,6 +2555,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -2223,10 +2602,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_date_hour
#### A masked pattern was here ####
1500
-PREHOOK: query: EXPLAIN select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart, srcpart_date_hour where srcpart_date_hour.`date` = '2008-04-08' and srcpart_date_hour.hour = 11 and srcpart.ds = srcpart_date_hour.ds and srcpart.hr = srcpart_date_hour.hr
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
@@ -2256,6 +2639,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 736000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -2306,6 +2693,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2327,6 +2722,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -2366,10 +2768,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
POSTHOOK: Input: default@srcpart_date_hour
#### A masked pattern was here ####
500
-PREHOOK: query: EXPLAIN select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart left join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
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
@@ -2400,6 +2806,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -2435,6 +2845,14 @@ STAGE PLANS:
Target Vertex: Map 1
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
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2456,6 +2874,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -2476,10 +2901,14 @@ STAGE PLANS:
Processor Tree:
ListSink
-PREHOOK: query: EXPLAIN select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart_date left join srcpart on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
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
@@ -2528,6 +2957,14 @@ STAGE PLANS:
Target Vertex: Map 4
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 4
Map Operator Tree:
TableScan
@@ -2544,6 +2981,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2565,6 +3006,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -2585,10 +3033,14 @@ STAGE PLANS:
Processor Tree:
ListSink
-PREHOOK: query: EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart full outer join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
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
@@ -2618,6 +3070,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -2653,6 +3109,14 @@ STAGE PLANS:
Target Vertex: Map 1
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
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2674,6 +3138,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -2694,12 +3165,16 @@ STAGE PLANS:
Processor Tree:
ListSink
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 and srcpart.hr = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11 and srcpart.hr = 11
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
@@ -2731,6 +3206,10 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 5
Map Operator Tree:
TableScan
@@ -2766,6 +3245,14 @@ STAGE PLANS:
Target Vertex: Map 1
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 6
Map Operator Tree:
TableScan
@@ -2801,6 +3288,14 @@ STAGE PLANS:
Target Vertex: Map 1
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -2838,6 +3333,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 4
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)
@@ -2877,12 +3379,16 @@ POSTHOOK: Input: default@srcpart_date
POSTHOOK: Input: default@srcpart_hour
#### A masked pattern was here ####
500
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart.hr = 13
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart.hr = 13
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
@@ -2920,6 +3426,12 @@ STAGE PLANS:
value expressions: _col1 (type: string)
Execution mode: vectorized, llap
LLAP IO: unknown
+ Map Vectorization:
+ enabled: true
+ groupByVectorOutput: true
+ allNative: true
+ usesVectorUDFAdaptor: true
+ vectorized: true
Map 6
Map Operator Tree:
TableScan
@@ -2940,6 +3452,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 188 Basic stats: COMPLETE Column stats: NONE
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 7
Map Operator Tree:
TableScan
@@ -2960,6 +3480,14 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 172 Basic stats: COMPLETE Column stats: NONE
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: true
+ vectorized: true
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -3010,6 +3538,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 4
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)
@@ -3025,6 +3560,13 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
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: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=1)
@@ -3057,10 +3599,14 @@ POSTHOOK: Input: default@srcpart_date
POSTHOOK: Input: default@srcpart_hour
#### A masked pattern was here ####
0
-PREHOOK: query: EXPLAIN select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
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
@@ -3094,6 +3640,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -3114,6 +3664,10 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 8
Map Operator Tree:
TableScan
@@ -3134,6 +3688,10 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -3155,6 +3713,13 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Reducer 3
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)
@@ -3170,6 +3735,13 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
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: max(VALUE._col0)
@@ -3191,6 +3763,13 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 7
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
keys: KEY._col0 (type: string)
@@ -3219,6 +3798,13 @@ STAGE PLANS:
Target Vertex: Map 1
Reducer 9
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: min(VALUE._col0)
@@ -3264,10 +3850,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
2000
-PREHOOK: query: EXPLAIN select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
+PREHOOK: query: EXPLAIN VECTORIZATION select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
+POSTHOOK: query: EXPLAIN VECTORIZATION select distinct(ds) from srcpart where srcpart.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
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
@@ -3301,6 +3891,10 @@ STAGE PLANS:
Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 4
Map Operator Tree:
TableScan
@@ -3321,6 +3915,10 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 8
Map Operator Tree:
TableScan
@@ -3341,6 +3939,10 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Reducer 2
Execution mode: llap
Reduce Operator Tree:
@@ -3364,6 +3966,13 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 3
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
keys: KEY._col0 (type: string)
@@ -3379,6 +3988,13 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 5
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: max(VALUE._col0)
@@ -3400,6 +4016,13 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 7
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
keys: KEY._col0 (type: string)
@@ -3428,6 +4051,13 @@ STAGE PLANS:
Target Vertex: Map 1
Reducer 9
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: min(VALUE._col0)
@@ -3474,10 +4104,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
#### A masked pattern was here ####
2008-04-08
2008-04-09
-PREHOOK: query: EXPLAIN select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
+PREHOOK: query: EXPLAIN VECTORIZATION select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
+POSTHOOK: query: EXPLAIN VECTORIZATION select ds from (select distinct(ds) as ds from srcpart union all select distinct(ds) as ds from srcpart) s where s.ds in (select max(srcpart.ds) from srcpart union all select min(srcpart.ds) from srcpart)
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
@@ -3513,6 +4147,10 @@ STAGE PLANS:
Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 11
Map Operator Tree:
TableScan
@@ -3533,6 +4171,10 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 5
Map Operator Tree:
TableScan
@@ -3551,6 +4193,10 @@ STAGE PLANS:
Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 7
Map Operator Tree:
TableScan
@@ -3571,8 +4217,19 @@ STAGE PLANS:
value expressions: _col0 (type: string)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Reducer 10
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
keys: KEY._col0 (type: string)
@@ -3616,6 +4273,13 @@ STAGE PLANS:
Target Vertex: Map 5
Reducer 12
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: min(VALUE._col0)
@@ -3637,6 +4301,13 @@ STAGE PLANS:
Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: COMPLETE
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
keys: KEY._col0 (type: string)
@@ -3668,6 +4339,13 @@ STAGE PLANS:
serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
Reducer 6
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
keys: KEY._col0 (type: string)
@@ -3681,6 +4359,13 @@ STAGE PLANS:
Statistics: Num rows: 4 Data size: 736 Basic stats: COMPLETE Column stats: COMPLETE
Reducer 8
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: max(VALUE._col0)
@@ -3731,10 +4416,14 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12
2008-04-08
2008-04-09
2008-04-09
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) where srcpart_date.`date` = '2008-04-08'
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
@@ -3778,6 +4467,10 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
LLAP IO: no inputs
+ Map Vectorization:
+ enabled: false
+ enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
+ inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
Map 3
Map Operator Tree:
TableScan
@@ -3813,8 +4506,23 @@ STAGE PLANS:
Target Vertex: Map 1
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
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)
@@ -3867,12 +4575,16 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11
POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12
#### A masked pattern was here ####
1000
-PREHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+PREHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11
PREHOOK: type: QUERY
-POSTHOOK: query: EXPLAIN select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
+POSTHOOK: query: EXPLAIN VECTORIZATION select count(*) from srcpart join srcpart_date on (srcpart.ds = srcpart_date.ds) join srcpart_hour on (srcpart.hr = srcpart_hour.hr)
where srcpart_date.`date` = '2008-04-08' and srcpart_hour.hour = 11
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
@@ -3925,6 +4637,10 @@ STAGE PLANS:
value expressions: _col0 (type: bigint)
Execution mode: llap
<TRUNCATED>