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 2016/10/17 20:36:07 UTC
[36/51] [partial] hive git commit: Revert "Revert "Revert
"HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline,
reviewed by Gopal Vijayaraghavan)"""
http://git-wip-us.apache.org/repos/asf/hive/blob/ad6ce078/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
index 964ce95..85116e7 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_part_all_primitive.q.out
@@ -282,73 +282,25 @@ 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 vectorization detail
+PREHOOK: query: explain
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 vectorization detail
+POSTHOOK: query: explain
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 VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+Plan optimized by CBO.
-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: 4759 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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
+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=475)
+ 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"]
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
@@ -545,73 +497,25 @@ 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 vectorization detail
+PREHOOK: query: explain
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 vectorization detail
+POSTHOOK: query: explain
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 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
+Plan optimized by CBO.
-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: 2563 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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
+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=427)
+ 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"]
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
@@ -724,73 +628,25 @@ 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 vectorization detail
+PREHOOK: query: explain
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 vectorization detail
+POSTHOOK: query: explain
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 VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+Plan optimized by CBO.
-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: 874 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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
+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=145)
+ 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"]
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
@@ -887,73 +743,25 @@ 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 vectorization detail
+PREHOOK: query: explain
select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-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: 376 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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
+Plan optimized by CBO.
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+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=62)
+ default@part_change_various_various_date,part_change_various_various_date,Tbl:COMPLETE,Col:PARTIAL,Output:["insert_num","c1","c2","c3","c4","b"]
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,b from part_change_various_various_date
PREHOOK: type: QUERY
@@ -1131,73 +939,25 @@ 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 vectorization detail
+PREHOOK: query: explain
select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-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: 1311 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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
+Plan optimized by CBO.
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+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=100)
+ 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"]
PREHOOK: query: select insert_num,part,c1,c2,c3,c4,c5,c6,b from part_change_same_type_different_params
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/ad6ce078/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table.q.out b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table.q.out
index 208ee4f..04f2891 100644
--- a/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table.q.out
+++ b/ql/src/test/results/clientpositive/llap/schema_evol_text_vecrow_table.q.out
@@ -87,72 +87,25 @@ POSTHOOK: Lineage: table_add_int_permute_select.b SIMPLE [(values__tmp__table__1
POSTHOOK: Lineage: table_add_int_permute_select.c EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
POSTHOOK: Lineage: table_add_int_permute_select.insert_num EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3
-PREHOOK: query: explain vectorization detail
+PREHOOK: query: explain
select insert_num,a,b from table_add_int_permute_select
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,a,b from table_add_int_permute_select
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+Plan optimized by CBO.
-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: table_add_int_permute_select
- Statistics: Num rows: 5 Data size: 101 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedOutputColumns: [0, 1, 2, 3]
- Select Operator
- expressions: insert_num (type: int), a (type: int), b (type: string)
- outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumns: [0, 1, 2]
- Statistics: Num rows: 5 Data size: 101 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 5 Data size: 101 Basic stats: COMPLETE Column stats: NONE
- 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 4
- includeColumns: [0, 1, 2]
- dataColumns: insert_num:int, a:int, b:string, c:int
- partitionColumnCount: 0
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Map 1 vectorized, llap
+ File Output Operator [FS_4]
+ Select Operator [SEL_3] (rows=5 width=20)
+ Output:["_col0","_col1","_col2"]
+ TableScan [TS_0] (rows=5 width=20)
+ default@table_add_int_permute_select,table_add_int_permute_select,Tbl:COMPLETE,Col:NONE,Output:["insert_num","a","b"]
PREHOOK: query: -- SELECT permutation columns to make sure NULL defaulting works right
select insert_num,a,b from table_add_int_permute_select
@@ -259,72 +212,25 @@ POSTHOOK: Lineage: table_add_int_string_permute_select.c EXPRESSION [(values__tm
POSTHOOK: Lineage: table_add_int_string_permute_select.d SIMPLE [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col5, type:string, comment:), ]
POSTHOOK: Lineage: table_add_int_string_permute_select.insert_num EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4
-PREHOOK: query: explain vectorization detail
+PREHOOK: query: explain
select insert_num,a,b from table_add_int_string_permute_select
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,a,b from table_add_int_string_permute_select
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
+Plan optimized by CBO.
-STAGE PLANS:
- Stage: Stage-1
- Tez
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: table_add_int_string_permute_select
- Statistics: Num rows: 5 Data size: 101 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedOutputColumns: [0, 1, 2, 3, 4]
- Select Operator
- expressions: insert_num (type: int), a (type: int), b (type: string)
- outputColumnNames: _col0, _col1, _col2
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumns: [0, 1, 2]
- Statistics: Num rows: 5 Data size: 101 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 5 Data size: 101 Basic stats: COMPLETE Column stats: NONE
- 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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: 0
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Map 1 vectorized, llap
+ File Output Operator [FS_4]
+ Select Operator [SEL_3] (rows=5 width=20)
+ Output:["_col0","_col1","_col2"]
+ TableScan [TS_0] (rows=5 width=20)
+ default@table_add_int_string_permute_select,table_add_int_string_permute_select,Tbl:COMPLETE,Col:NONE,Output:["insert_num","a","b"]
PREHOOK: query: -- SELECT permutation columns to make sure NULL defaulting works right
select insert_num,a,b from table_add_int_string_permute_select
@@ -501,72 +407,25 @@ POSTHOOK: Lineage: table_change_string_group_double.c2 EXPRESSION [(values__tmp_
POSTHOOK: Lineage: table_change_string_group_double.c3 EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col4, type:string, comment:), ]
POSTHOOK: Lineage: table_change_string_group_double.insert_num EXPRESSION [(values__tmp__table__3)values__tmp__table__3.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
_col0 _col1 _col2 _col3 _col4
-PREHOOK: query: explain vectorization detail
+PREHOOK: query: explain
select insert_num,c1,c2,c3,b from table_change_string_group_double
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,c1,c2,c3,b from table_change_string_group_double
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
+Plan optimized by CBO.
-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: table_change_string_group_double
- Statistics: Num rows: 5 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedOutputColumns: [0, 1, 2, 3, 4]
- Select Operator
- expressions: insert_num (type: int), c1 (type: double), c2 (type: double), c3 (type: double), b (type: string)
- outputColumnNames: _col0, _col1, _col2, _col3, _col4
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumns: [0, 1, 2, 3, 4]
- Statistics: Num rows: 5 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 5 Data size: 264 Basic stats: COMPLETE Column stats: NONE
- 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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: 0
-
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Map 1 vectorized, llap
+ File Output Operator [FS_4]
+ Select Operator [SEL_3] (rows=5 width=52)
+ Output:["_col0","_col1","_col2","_col3","_col4"]
+ TableScan [TS_0] (rows=5 width=52)
+ default@table_change_string_group_double,table_change_string_group_double,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","b"]
PREHOOK: query: select insert_num,c1,c2,c3,b from table_change_string_group_double
PREHOOK: type: QUERY
@@ -836,72 +695,25 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_gro
POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.c9 EXPRESSION [(values__tmp__table__5)values__tmp__table__5.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: table_change_numeric_group_string_group_multi_ints_string_group.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 _col12 _col13 _col14 _col15 _col16 _col17 _col18 _col19 _col20 _col21
-PREHOOK: query: explain vectorization detail
+PREHOOK: query: explain
select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: table_change_numeric_group_string_group_multi_ints_string_group
- Statistics: Num rows: 5 Data size: 755 Basic stats: COMPLETE Column stats: NONE
- 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]
- Select Operator
- expressions: insert_num (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
- Select Vectorization:
- className: VectorSelectOperator
- 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]
- Statistics: Num rows: 5 Data size: 755 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 5 Data size: 755 Basic stats: COMPLETE Column stats: NONE
- 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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: 0
+Plan optimized by CBO.
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Map 1 vectorized, llap
+ File Output Operator [FS_4]
+ Select Operator [SEL_3] (rows=5 width=151)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21"]
+ TableScan [TS_0] (rows=5 width=151)
+ default@table_change_numeric_group_string_group_multi_ints_string_group,table_change_numeric_group_string_group_multi_ints_string_group,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","c16","c17","c18","c19","c20","b"]
PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,c16,c17,c18,c19,c20,b from table_change_numeric_group_string_group_multi_ints_string_group
PREHOOK: type: QUERY
@@ -1056,72 +868,25 @@ POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group
POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.c9 EXPRESSION [(values__tmp__table__6)values__tmp__table__6.FieldSchema(name:tmp_values_col10, type:string, comment:), ]
POSTHOOK: Lineage: table_change_numeric_group_string_group_floating_string_group.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
-PREHOOK: query: explain vectorization detail
+PREHOOK: query: explain
select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
+POSTHOOK: query: explain
select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group
POSTHOOK: type: QUERY
Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-0 depends on stages: Stage-1
-
-STAGE PLANS:
- Stage: Stage-1
- Tez
-#### A masked pattern was here ####
- Vertices:
- Map 1
- Map Operator Tree:
- TableScan
- alias: table_change_numeric_group_string_group_floating_string_group
- Statistics: Num rows: 5 Data size: 1250 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16]
- Select Operator
- expressions: insert_num (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
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16]
- Statistics: Num rows: 5 Data size: 1250 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- File Sink Vectorization:
- className: VectorFileSinkOperator
- native: false
- Statistics: Num rows: 5 Data size: 1250 Basic stats: COMPLETE Column stats: NONE
- 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.row.serde.deserialize IS true
- groupByVectorOutput: true
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- 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: 0
+Plan optimized by CBO.
- Stage: Stage-0
- Fetch Operator
- limit: -1
- Processor Tree:
- ListSink
+Stage-0
+ Fetch Operator
+ limit:-1
+ Stage-1
+ Map 1 vectorized, llap
+ File Output Operator [FS_4]
+ Select Operator [SEL_3] (rows=5 width=250)
+ Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16"]
+ TableScan [TS_0] (rows=5 width=250)
+ default@table_change_numeric_group_string_group_floating_string_group,table_change_numeric_group_string_group_floating_string_group,Tbl:COMPLETE,Col:NONE,Output:["insert_num","c1","c2","c3","c4","c5","c6","c7","c8","c9","c10","c11","c12","c13","c14","c15","b"]
PREHOOK: query: select insert_num,c1,c2,c3,c4,c5,c6,c7,c8,c9,c10,c11,c12,c13,c14,c15,b from table_change_numeric_group_string_group_floating_string_group
PREHOOK: type: QUERY
http://git-wip-us.apache.org/repos/asf/hive/blob/ad6ce078/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
index 653274c..d4a9747 100644
--- a/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_aggregate_9.q.out
@@ -101,16 +101,12 @@ POSTHOOK: Lineage: vectortab2korc.si SIMPLE [(vectortab2k)vectortab2k.FieldSchem
POSTHOOK: Lineage: vectortab2korc.t SIMPLE [(vectortab2k)vectortab2k.FieldSchema(name:t, type:tinyint, comment:null), ]
POSTHOOK: Lineage: vectortab2korc.ts SIMPLE [(vectortab2k)vectortab2k.FieldSchema(name:ts, type:timestamp, comment:null), ]
POSTHOOK: Lineage: vectortab2korc.ts2 SIMPLE [(vectortab2k)vectortab2k.FieldSchema(name:ts2, type:timestamp, comment:null), ]
-PREHOOK: query: explain vectorization expression
+PREHOOK: query: explain
select min(dc), max(dc), sum(dc), avg(dc) from vectortab2korc
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization expression
+POSTHOOK: query: explain
select min(dc), max(dc), sum(dc), avg(dc) from vectortab2korc
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
@@ -128,26 +124,12 @@ STAGE PLANS:
TableScan
alias: vectortab2korc
Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12]
Select Operator
expressions: dc (type: decimal(38,18))
outputColumnNames: dc
- Select Vectorization:
- className: VectorSelectOperator
- native: true
- projectedOutputColumns: [6]
Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE
Group By Operator
aggregations: min(dc), max(dc), sum(dc), avg(dc)
- Group By Vectorization:
- aggregators: VectorUDAFMinDecimal(col 6) -> decimal(38,18), VectorUDAFMaxDecimal(col 6) -> decimal(38,18), VectorUDAFSumDecimal(col 6) -> decimal(38,18), VectorUDAFAvgDecimal(col 6) -> struct<count:bigint,sum:decimal(38,18)>
- className: VectorGroupByOperator
- vectorOutput: false
- native: false
- projectedOutputColumns: [0, 1, 2, 3]
- vectorOutputConditionsNotMet: Vector output of VectorUDAFAvgDecimal(col 6) -> struct<count:bigint,sum:decimal(38,18)> output type STRUCT requires PRIMITIVE IS false
mode: hash
outputColumnNames: _col0, _col1, _col2, _col3
Statistics: Num rows: 1 Data size: 624 Basic stats: COMPLETE Column stats: NONE
@@ -157,21 +139,8 @@ STAGE PLANS:
value expressions: _col0 (type: decimal(38,18)), _col1 (type: decimal(38,18)), _col2 (type: decimal(38,18)), _col3 (type: struct<count:bigint,sum:decimal(38,18),input:decimal(38,18)>)
Execution mode: vectorized, llap
LLAP IO: all inputs
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
- groupByVectorOutput: false
- inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
Reducer 2
Execution mode: llap
- Reduce Vectorization:
- enabled: true
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
- notVectorizedReason: Aggregation Function UDF avg parameter expression for GROUPBY operator: Data type struct<count:bigint,sum:decimal(38,18),input:decimal(38,18)> of Column[VALUE._col3] not supported
- vectorized: false
Reduce Operator Tree:
Group By Operator
aggregations: min(VALUE._col0), max(VALUE._col1), sum(VALUE._col2), avg(VALUE._col3)
http://git-wip-us.apache.org/repos/asf/hive/blob/ad6ce078/ql/src/test/results/clientpositive/llap/vector_aggregate_without_gby.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_aggregate_without_gby.q.out b/ql/src/test/results/clientpositive/llap/vector_aggregate_without_gby.q.out
index 6785248..3d00ade 100644
--- a/ql/src/test/results/clientpositive/llap/vector_aggregate_without_gby.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_aggregate_without_gby.q.out
@@ -33,9 +33,9 @@ POSTHOOK: Output: default@testvec
POSTHOOK: Lineage: testvec.dt EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col2, type:string, comment:), ]
POSTHOOK: Lineage: testvec.greg_dt SIMPLE [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col3, type:string, comment:), ]
POSTHOOK: Lineage: testvec.id EXPRESSION [(values__tmp__table__1)values__tmp__table__1.FieldSchema(name:tmp_values_col1, type:string, comment:), ]
-PREHOOK: query: explain vectorization select max(dt), max(greg_dt) from testvec where id=5
+PREHOOK: query: explain select max(dt), max(greg_dt) from testvec where id=5
PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization select max(dt), max(greg_dt) from testvec where id=5
+POSTHOOK: query: explain select max(dt), max(greg_dt) from testvec where id=5
POSTHOOK: type: QUERY
Plan optimized by CBO.