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 20:04:04 UTC
[39/51] [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/schema_evol_orc_vec_part.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
index 86c94f7..c6fc7b5 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part.q.out
@@ -53,25 +53,73 @@ POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).b SIMPLE [(valu
POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
POSTHOOK: Lineage: part_add_int_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,a,b from part_add_int_permute_select
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,a,b from part_add_int_permute_select
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=2 width=4)
- Output:["_col0","_col1","_col2","_col3"]
- TableScan [TS_0] (rows=2 width=101)
- default@part_add_int_permute_select,part_add_int_permute_select,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","a","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_add_int_permute_select
+ Statistics: Num rows: 2 Data size: 202 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 4, 1, 2]
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 4
+ includeColumns: [0, 1, 2]
+ dataColumns: insert_num:int, a:int, b:string, c:int
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,a,b from part_add_int_permute_select
PREHOOK: type: QUERY
@@ -158,25 +206,73 @@ POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).c EXPRES
POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).d SIMPLE [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col5, type:string, comment:), ]
POSTHOOK: Lineage: part_add_int_string_permute_select PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__4)values__tmp__table__4.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,a,b from part_add_int_string_permute_select
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,a,b from part_add_int_string_permute_select
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=2 width=4)
- Output:["_col0","_col1","_col2","_col3"]
- TableScan [TS_0] (rows=2 width=145)
- default@part_add_int_string_permute_select,part_add_int_string_permute_select,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","a","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_add_int_string_permute_select
+ Statistics: Num rows: 2 Data size: 290 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), a (type: int), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 5, 1, 2]
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 5
+ includeColumns: [0, 1, 2]
+ dataColumns: insert_num:int, a:int, b:string, c:int, d:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,a,b from part_add_int_string_permute_select
PREHOOK: type: QUERY
@@ -321,25 +417,73 @@ POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c2 SIMPLE [
POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).c3 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:double1, type:double, comment:null), ]
POSTHOOK: Lineage: part_change_string_group_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ]
insert_num double1 double1 double1 _c4
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,b from part_change_string_group_double
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,b from part_change_string_group_double
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=5 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- TableScan [TS_0] (rows=5 width=426)
- default@part_change_string_group_double,part_change_string_group_double,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","b"]
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_string_group_double
+ Statistics: Num rows: 5 Data size: 2130 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 5, 1, 2, 3, 4]
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 5
+ includeColumns: [0, 1, 2, 3, 4]
+ dataColumns: insert_num:int, c1:double, c2:double, c3:double, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_string_group_double
PREHOOK: type: QUERY
@@ -421,25 +565,73 @@ POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(
POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: part_change_date_group_string_group_date_timestamp PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"]
- TableScan [TS_0] (rows=6 width=586)
- default@part_change_date_group_string_group_date_timestamp,part_change_date_group_string_group_date_timestamp,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_date_group_string_group_date_timestamp
+ Statistics: Num rows: 6 Data size: 3521 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: char(50)), c3 (type: char(15)), c4 (type: varchar(50)), c5 (type: varchar(15)), c6 (type: string), c7 (type: char(50)), c8 (type: char(15)), c9 (type: varchar(50)), c10 (type: varchar(15)), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+ dataColumns: insert_num:int, c1:string, c2:char(50), c3:char(15), c4:varchar(50), c5:varchar(15), c6:string, c7:char(50), c8:char(15), c9:varchar(50), c10:varchar(15), b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_date_group_string_group_date_timestamp
PREHOOK: type: QUERY
@@ -590,25 +782,73 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_grou
POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: part_change_numeric_group_string_group_multi_ints_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22"]
- TableScan [TS_0] (rows=6 width=483)
- default@part_change_numeric_group_string_group_multi_ints_string_group,part_change_numeric_group_string_group_multi_ints_string_group,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","b"]
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_numeric_group_string_group_multi_ints_string_group
+ Statistics: Num rows: 6 Data size: 2903 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: string), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(50)), c8 (type: char(50)), c9 (type: char(5)), c10 (type: char(5)), c11 (type: char(5)), c12 (type: char(5)), c13 (type: varchar(50)), c14 (type: varchar(50)), c15 (type: varchar(50)), c16 (type: varchar(50)), c17 (type: varchar(5)), c18 (type: varchar(5)), c19 (type: varchar(5)), c20 (type: varchar(5)), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 22, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 22
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21]
+ dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:string, c5:char(50), c6:char(50), c7:char(50), c8:char(50), c9:char(5), c10:char(5), c11:char(5), c12:char(5), c13:varchar(50), c14:varchar(50), c15:varchar(50), c16:varchar(50), c17:varchar(5), c18:varchar(5), c19:varchar(5), c20:varchar(5), b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from part_change_numeric_group_string_group_multi_ints_string_group
PREHOOK: type: QUERY
@@ -749,25 +989,73 @@ POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group
POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: part_change_numeric_group_string_group_floating_string_group PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__7)values__tmp__table__7.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_numeric_group_string_group_floating_string_group
+ Statistics: Num rows: 6 Data size: 4540 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: string), c2 (type: string), c3 (type: string), c4 (type: char(50)), c5 (type: char(50)), c6 (type: char(50)), c7 (type: char(7)), c8 (type: char(7)), c9 (type: char(7)), c10 (type: varchar(50)), c11 (type: varchar(50)), c12 (type: varchar(50)), c13 (type: varchar(7)), c14 (type: varchar(7)), c15 (type: varchar(7)), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 17, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 17
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16]
+ dataColumns: insert_num:int, c1:string, c2:string, c3:string, c4:char(50), c5:char(50), c6:char(50), c7:char(7), c8:char(7), c9:char(7), c10:varchar(50), c11:varchar(50), c12:varchar(50), c13:varchar(7), c14:varchar(7), c15:varchar(7), b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17"]
- TableScan [TS_0] (rows=6 width=756)
- default@part_change_numeric_group_string_group_floating_string_group,part_change_numeric_group_string_group_floating_string_group,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","b"]
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from part_change_numeric_group_string_group_floating_string_group
PREHOOK: type: QUERY
@@ -894,25 +1182,73 @@ POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1
POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: part_change_string_group_string_group_string PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__8)values__tmp__table__8.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_string_group_string_group_string
+ Statistics: Num rows: 6 Data size: 6682 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: char(50)), c2 (type: char(9)), c3 (type: varchar(50)), c4 (type: char(9)), c5 (type: varchar(50)), c6 (type: varchar(9)), c7 (type: string), c8 (type: char(50)), c9 (type: char(9)), c10 (type: string), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 12, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 12
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
+ dataColumns: insert_num:int, c1:char(50), c2:char(9), c3:varchar(50), c4:char(9), c5:varchar(50), c6:varchar(9), c7:string, c8:char(50), c9:char(9), c10:string, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12"]
- TableScan [TS_0] (rows=6 width=1113)
- default@part_change_string_group_string_group_string,part_change_string_group_string_group_string,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","b"]
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,b from part_change_string_group_string_group_string
PREHOOK: type: QUERY
@@ -1067,25 +1403,73 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint P
POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).c9 EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_tinyint_to_bigint PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__9)values__tmp__table__9.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4 _col5 _col6 _col7 _col8 _col9 _col10 _col11 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20"]
- TableScan [TS_0] (rows=6 width=236)
- default@part_change_lower_to_higher_numeric_group_tinyint_to_bigint,part_change_lower_to_higher_numeric_group_tinyint_to_bigint,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_lower_to_higher_numeric_group_tinyint_to_bigint
+ Statistics: Num rows: 6 Data size: 1419 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: smallint), c2 (type: int), c3 (type: bigint), c4 (type: decimal(38,18)), c5 (type: float), c6 (type: double), c7 (type: int), c8 (type: bigint), c9 (type: decimal(38,18)), c10 (type: float), c11 (type: double), c12 (type: bigint), c13 (type: decimal(38,18)), c14 (type: float), c15 (type: double), c16 (type: decimal(38,18)), c17 (type: float), c18 (type: double), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 20, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 20
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19]
+ dataColumns: insert_num:int, c1:smallint, c2:int, c3:bigint, c4:decimal(38,18), c5:float, c6:double, c7:int, c8:bigint, c9:decimal(38,18), c10:float, c11:double, c12:bigint, c13:decimal(38,18), c14:float, c15:double, c16:decimal(38,18), c17:float, c18:double, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,b from part_change_lower_to_higher_numeric_group_tinyint_to_bigint
PREHOOK: type: QUERY
@@ -1182,25 +1566,73 @@ POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PA
POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).c3 EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
POSTHOOK: Lineage: part_change_lower_to_higher_numeric_group_decimal_to_float PARTITION(part=1).insert_num EXPRESSION [(values__tmp__table__10)values__tmp__table__10.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_lower_to_higher_numeric_group_decimal_to_float
+ Statistics: Num rows: 6 Data size: 1523 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: float), c2 (type: double), c3 (type: double), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 5, 1, 2, 3, 4]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 5
+ includeColumns: [0, 1, 2, 3, 4]
+ dataColumns: insert_num:int, c1:float, c2:double, c3:double, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5"]
- TableScan [TS_0] (rows=6 width=253)
- default@part_change_lower_to_higher_numeric_group_decimal_to_float,part_change_lower_to_higher_numeric_group_decimal_to_float,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","b"]
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,b from part_change_lower_to_higher_numeric_group_decimal_to_float
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
index 3da9284..d0cafaa 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_complex.q.out
@@ -131,25 +131,55 @@ POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).b SIMPL
POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).insert_num SIMPLE [(complex_struct1_c_txt)complex_struct1_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ]
POSTHOOK: Lineage: part_change_various_various_struct1 PARTITION(part=1).s1 SIMPLE [(complex_struct1_c_txt)complex_struct1_c_txt.FieldSchema(name:s1, type:struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>, comment:null), ]
complex_struct1_c_txt.insert_num complex_struct1_c_txt.s1 complex_struct1_c_txt.b
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,s1,b from part_change_various_various_struct1
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,s1,b from part_change_various_various_struct1
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 llap
- File Output Operator [FS_2]
- Select Operator [SEL_1] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3"]
- TableScan [TS_0] (rows=6 width=789)
- default@part_change_various_various_struct1,part_change_various_various_struct1,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","s1","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_various_various_struct1
+ Statistics: Num rows: 6 Data size: 4734 Basic stats: COMPLETE Column stats: PARTIAL
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), s1 (type: struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ notVectorizedReason: Select expression for SELECT operator: Data type struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string> of Column[s1] not supported
+ vectorized: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,s1,b from part_change_various_various_struct1
PREHOOK: type: QUERY
@@ -383,25 +413,55 @@ POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).b SIMPLE [
POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).insert_num SIMPLE [(complex_struct2_d_txt)complex_struct2_d_txt.FieldSchema(name:insert_num, type:int, comment:null), ]
POSTHOOK: Lineage: part_add_various_various_struct2 PARTITION(part=1).s2 SIMPLE [(complex_struct2_d_txt)complex_struct2_d_txt.FieldSchema(name:s2, type:struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>, comment:null), ]
complex_struct2_d_txt.insert_num complex_struct2_d_txt.b complex_struct2_d_txt.s2
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,b,s2 from part_add_various_various_struct2
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,b,s2 from part_add_various_various_struct2
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 llap
- File Output Operator [FS_2]
- Select Operator [SEL_1] (rows=8 width=4)
- Output:["_col0","_col1","_col2","_col3"]
- TableScan [TS_0] (rows=8 width=614)
- default@part_add_various_various_struct2,part_add_various_various_struct2,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","b","s2"]
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_add_various_various_struct2
+ Statistics: Num rows: 8 Data size: 4912 Basic stats: COMPLETE Column stats: PARTIAL
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), b (type: string), s2 (type: struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string>)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 8 Data size: 32 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ notVectorizedReason: Select expression for SELECT operator: Data type struct<c1:string,c2:string,c3:string,c4:string,c5:string,c6:string,c7:string,c8:string,c9:string,c10:string,c11:string,c12:string,c13:string> of Column[s2] not supported
+ vectorized: false
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,b,s2 from part_add_various_various_struct2
PREHOOK: type: QUERY
@@ -563,25 +623,55 @@ POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).b SIMPL
POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).insert_num SIMPLE [(complex_struct4_c_txt)complex_struct4_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ]
POSTHOOK: Lineage: part_add_to_various_various_struct4 PARTITION(part=1).s3 SIMPLE [(complex_struct4_c_txt)complex_struct4_c_txt.FieldSchema(name:s3, type:struct<c1:boolean,c2:tinyint,c3:smallint,c4:int,c5:bigint,c6:float,c7:double,c8:decimal(38,18),c9:char(25),c10:varchar(25),c11:timestamp,c12:date,c13:binary>, comment:null), ]
complex_struct4_c_txt.insert_num complex_struct4_c_txt.b complex_struct4_c_txt.s3
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,b,s3 from part_add_to_various_various_struct4
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,b,s3 from part_add_to_various_various_struct4
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_add_to_various_various_struct4
+ Statistics: Num rows: 4 Data size: 1172 Basic stats: COMPLETE Column stats: PARTIAL
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), b (type: string), s3 (type: struct<c1:boolean,c2:tinyint,c3:smallint,c4:int,c5:bigint,c6:float,c7:double,c8:decimal(38,18),c9:char(25),c10:varchar(25),c11:timestamp,c12:date,c13:binary>)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: llap
+ Map Vectorization:
+ enabled: true
+ enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+ inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+ notVectorizedReason: Select expression for SELECT operator: Data type struct<c1:boolean,c2:tinyint,c3:smallint,c4:int,c5:bigint,c6:float,c7:double,c8:decimal(38,18),c9:char(25),c10:varchar(25),c11:timestamp,c12:date,c13:binary> of Column[s3] not supported
+ vectorized: false
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 llap
- File Output Operator [FS_2]
- Select Operator [SEL_1] (rows=4 width=4)
- Output:["_col0","_col1","_col2","_col3"]
- TableScan [TS_0] (rows=4 width=293)
- default@part_add_to_various_various_struct4,part_add_to_various_various_struct4,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","b","s3"]
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,b,s3 from part_add_to_various_various_struct4
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
index f155b00..3a5232a 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_orc_vec_part_all_primitive.q.out
@@ -242,25 +242,73 @@ POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=
POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=1).c9 SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:boolean1, type:boolean, comment:null), ]
POSTHOOK: Lineage: part_change_various_various_boolean_to_bigint PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data)schema_evolution_data.FieldSchema(name:insert_num, type:int, comment:null), ]
insert_num boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 boolean1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 tinyint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 smallint1 int1 int1 int1 int1 int1 int1 int1 int1 int1 int1 int1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 bigint1 _c54
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=10 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35","_col36","_col37","_col38","_col39","_col40","_col41","_col42","_col43","_col44","_col45","_col46","_col47","_col48","_col49","_col50","_col51","_col52","_col53","_col54","_col55"]
- TableScan [TS_0] (rows=10 width=1168)
- default@part_change_various_various_boolean_to_bigint,part_change_various_various_boolean_to_bigint,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","c21","c22","c23","c24","c25","c26","c27","c28","c29","c30","c31","c32","c33","c34","c35","c36","c37","c38","c39","c40","c41","c42","c43","c44","c45","c46","c47","c48","c49","c50","c51","c52","c53","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_various_various_boolean_to_bigint
+ Statistics: Num rows: 10 Data size: 11688 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: boolean), c2 (type: boolean), c3 (type: boolean), c4 (type: boolean), c5 (type: boolean), c6 (type: boolean), c7 (type: boolean), c8 (type: boolean), c9 (type: boolean), c10 (type: tinyint), c11 (type: tinyint), c12 (type: tinyint), c13 (type: tinyint), c14 (type: tinyint), c15 (type: tinyint), c16 (type: tinyint), c17 (type: tinyint), c18 (type: tinyint), c19 (type: tinyint), c20 (type: tinyint), c21 (type: smallint), c22 (type: smallint), c23 (type: smallint), c24 (type: smallint), c25 (type: smallint), c26 (type: smallint), c27 (type: smallint), c28 (type: smallint), c29 (type: smallint), c30 (type: smallint), c31 (type: smallint), c32 (type: int), c33 (type: int), c34 (type: int), c35 (type: int), c36 (type: int), c37 (type: int), c38 (type: int), c39 (type: int), c40 (type: int), c41 (type: int), c42 (type: int), c43 (type: bigint), c44 (type: bigint), c45 (type: bigint), c46 (type: bigint), c4
7 (type: bigint), c48 (type: bigint), c49 (type: bigint), c50 (type: bigint), c51 (type: bigint), c52 (type: bigint), c53 (type: bigint), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35, _col36, _col37, _col38, _col39, _col40, _col41, _col42, _col43, _col44, _col45, _col46, _col47, _col48, _col49, _col50, _col51, _col52, _col53, _col54, _col55
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 55, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54]
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 10 Data size: 40 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 55
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54]
+ dataColumns: insert_num:int, c1:boolean, c2:boolean, c3:boolean, c4:boolean, c5:boolean, c6:boolean, c7:boolean, c8:boolean, c9:boolean, c10:tinyint, c11:tinyint, c12:tinyint, c13:tinyint, c14:tinyint, c15:tinyint, c16:tinyint, c17:tinyint, c18:tinyint, c19:tinyint, c20:tinyint, c21:smallint, c22:smallint, c23:smallint, c24:smallint, c25:smallint, c26:smallint, c27:smallint, c28:smallint, c29:smallint, c30:smallint, c31:smallint, c32:int, c33:int, c34:int, c35:int, c36:int, c37:int, c38:int, c39:int, c40:int, c41:int, c42:int, c43:bigint, c44:bigint, c45:bigint, c46:bigint, c47:bigint, c48:bigint, c49:bigint, c50:bigint, c51:bigint, c52:bigint, c53:bigint, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,c34,c35,c36,c37,c38,c39,c40,c41,c42,c43,c44,c45,c46,c47,c48,c49,c50,c51,c52,c53,b from part_change_various_various_boolean_to_bigint
PREHOOK: type: QUERY
@@ -443,25 +491,73 @@ POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=
POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=1).c9 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:decimal1, type:decimal(38,18), comment:null), ]
POSTHOOK: Lineage: part_change_various_various_decimal_to_double PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ]
insert_num decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 decimal1 float1 float1 float1 float1 float1 float1 float1 float1 float1 float1 float1 double1 double1 double1 double1 double1 double1 double1 double1 double1 double1 double1 _c34
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23","_col24","_col25","_col26","_col27","_col28","_col29","_col30","_col31","_col32","_col33","_col34","_col35"]
- TableScan [TS_0] (rows=6 width=1382)
- default@part_change_various_various_decimal_to_double,part_change_various_various_decimal_to_double,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","c21","c22","c23","c24","c25","c26","c27","c28","c29","c30","c31","c32","c33","b"]
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_various_various_decimal_to_double
+ Statistics: Num rows: 6 Data size: 8295 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: decimal(38,18)), c2 (type: decimal(38,18)), c3 (type: decimal(38,18)), c4 (type: decimal(38,18)), c5 (type: decimal(38,18)), c6 (type: decimal(38,18)), c7 (type: decimal(38,18)), c8 (type: decimal(38,18)), c9 (type: decimal(38,18)), c10 (type: decimal(38,18)), c11 (type: decimal(38,18)), c12 (type: float), c13 (type: float), c14 (type: float), c15 (type: float), c16 (type: float), c17 (type: float), c18 (type: float), c19 (type: float), c20 (type: float), c21 (type: float), c22 (type: float), c23 (type: double), c24 (type: double), c25 (type: double), c26 (type: double), c27 (type: double), c28 (type: double), c29 (type: double), c30 (type: double), c31 (type: double), c32 (type: double), c33 (type: double), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23, _col24, _col25, _col26, _col27, _col28, _col29, _col30, _col31, _col32, _col33, _col34, _col35
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 35, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 35
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34]
+ dataColumns: insert_num:int, c1:decimal(38,18), c2:decimal(38,18), c3:decimal(38,18), c4:decimal(38,18), c5:decimal(38,18), c6:decimal(38,18), c7:decimal(38,18), c8:decimal(38,18), c9:decimal(38,18), c10:decimal(38,18), c11:decimal(38,18), c12:float, c13:float, c14:float, c15:float, c16:float, c17:float, c18:float, c19:float, c20:float, c21:float, c22:float, c23:double, c24:double, c25:double, c26:double, c27:double, c28:double, c29:double, c30:double, c31:double, c32:double, c33:double, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,c21,c22,c23,c24,c25,c26,c27,c28,c29,c30,c31,c32,c33,b from part_change_various_various_decimal_to_double
PREHOOK: type: QUERY
@@ -566,25 +662,73 @@ POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).c8 SI
POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).c9 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:timestamp1, type:timestamp, comment:null), ]
POSTHOOK: Lineage: part_change_various_various_timestamp PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ]
insert_num timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 timestamp1 _c13
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+PLAN VECTORIZATION:
+ enabled: true
+ enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14"]
- TableScan [TS_0] (rows=6 width=494)
- default@part_change_various_various_timestamp,part_change_various_various_timestamp,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","b"]
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_various_various_timestamp
+ Statistics: Num rows: 6 Data size: 2965 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: timestamp), c2 (type: timestamp), c3 (type: timestamp), c4 (type: timestamp), c5 (type: timestamp), c6 (type: timestamp), c7 (type: timestamp), c8 (type: timestamp), c9 (type: timestamp), c10 (type: timestamp), c11 (type: timestamp), c12 (type: timestamp), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 14, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 14
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13]
+ dataColumns: insert_num:int, c1:timestamp, c2:timestamp, c3:timestamp, c4:timestamp, c5:timestamp, c6:timestamp, c7:timestamp, c8:timestamp, c9:timestamp, c10:timestamp, c11:timestamp, c12:timestamp, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,b from part_change_various_various_timestamp
PREHOOK: type: QUERY
@@ -673,25 +817,73 @@ POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).c3 SIMPLE
POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).c4 SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:date1, type:date, comment:null), ]
POSTHOOK: Lineage: part_change_various_various_date PARTITION(part=1).insert_num SIMPLE [(schema_evolution_data_2)schema_evolution_data_2.FieldSchema(name:insert_num, type:int, comment:null), ]
insert_num date1 date1 date1 date1 _c5
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_various_various_date
+ Statistics: Num rows: 6 Data size: 2444 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: date), c2 (type: date), c3 (type: date), c4 (type: date), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 6, 1, 2, 3, 4, 5]
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 6
+ includeColumns: [0, 1, 2, 3, 4, 5]
+ dataColumns: insert_num:int, c1:date, c2:date, c3:date, c4:date, b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=6 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6"]
- TableScan [TS_0] (rows=6 width=407)
- default@part_change_various_various_date,part_change_various_various_date,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","b"]
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date
PREHOOK: type: QUERY
@@ -861,25 +1053,73 @@ POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).c5 S
POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).c6 SIMPLE [(same_type1_c_txt)same_type1_c_txt.FieldSchema(name:c6, type:decimal(25,15), comment:null), ]
POSTHOOK: Lineage: part_change_same_type_different_params PARTITION(part=2).insert_num SIMPLE [(same_type1_c_txt)same_type1_c_txt.FieldSchema(name:insert_num, type:int, comment:null), ]
same_type1_c_txt.insert_num same_type1_c_txt.c1 same_type1_c_txt.c2 same_type1_c_txt.c3 same_type1_c_txt.c4 same_type1_c_txt.c5 same_type1_c_txt.c6 same_type1_c_txt.b
-PREHOOK: query: explain
+PREHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params
PREHOOK: type: QUERY
-POSTHOOK: query: explain
+POSTHOOK: query: explain vectorization detail
select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params
POSTHOOK: type: QUERY
Explain
-Plan optimized by CBO.
+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
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: part_change_same_type_different_params
+ Statistics: Num rows: 13 Data size: 8736 Basic stats: COMPLETE Column stats: PARTIAL
+ TableScan Vectorization:
+ native: true
+ projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8]
+ Select Operator
+ expressions: insert_num (type: int), part (type: int), c1 (type: char(8)), c2 (type: char(32)), c3 (type: varchar(15)), c4 (type: varchar(18)), c5 (type: decimal(10,2)), c6 (type: decimal(25,15)), b (type: string)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8
+ Select Vectorization:
+ className: VectorSelectOperator
+ native: true
+ projectedOutputColumns: [0, 8, 1, 2, 3, 4, 5, 6, 7]
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL
+ File Output Operator
+ compressed: false
+ File Sink Vectorization:
+ className: VectorFileSinkOperator
+ native: false
+ Statistics: Num rows: 13 Data size: 52 Basic stats: COMPLETE Column stats: PARTIAL
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Execution mode: vectorized, llap
+ 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
+ rowBatchContext:
+ dataColumnCount: 8
+ includeColumns: [0, 1, 2, 3, 4, 5, 6, 7]
+ dataColumns: insert_num:int, c1:char(8), c2:char(32), c3:varchar(15), c4:varchar(18), c5:decimal(10,2), c6:decimal(25,15), b:string
+ partitionColumnCount: 1
+ partitionColumns: part:int
-Stage-0
- Fetch Operator
- limit:-1
- Stage-1
- Map 1 vectorized, llap
- File Output Operator [FS_4]
- Select Operator [SEL_3] (rows=13 width=4)
- Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8"]
- TableScan [TS_0] (rows=13 width=672)
- default@part_change_same_type_different_params,part_change_same_type_different_params,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","c5","c6","b"]
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+ Processor Tree:
+ ListSink
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params
PREHOOK: type: QUERY