http://git-wip-us.apache.org/repos/asf/hive/blob/afa9ffee/ql/src/test/results/clientpositive/vector_windowing_rank.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_windowing_rank.q.out
b/ql/src/test/results/clientpositive/vector_windowing_rank.q.out
deleted file mode 100644
index 5d4ddcd..0000000
--- a/ql/src/test/results/clientpositive/vector_windowing_rank.q.out
+++ /dev/null
@@ -1,1564 +0,0 @@
-PREHOOK: query: drop table over10k
-PREHOOK: type: DROPTABLE
-POSTHOOK: query: drop table over10k
-POSTHOOK: type: DROPTABLE
-PREHOOK: query: create table over10k(
- t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- `dec` decimal(4,2),
- bin binary)
- row format delimited
- fields terminated by '|'
-PREHOOK: type: CREATETABLE
-PREHOOK: Output: database:default
-PREHOOK: Output: default@over10k
-POSTHOOK: query: create table over10k(
- t tinyint,
- si smallint,
- i int,
- b bigint,
- f float,
- d double,
- bo boolean,
- s string,
- ts timestamp,
- `dec` decimal(4,2),
- bin binary)
- row format delimited
- fields terminated by '|'
-POSTHOOK: type: CREATETABLE
-POSTHOOK: Output: database:default
-POSTHOOK: Output: default@over10k
-PREHOOK: query: load data local inpath '../../data/files/over10k' into table
over10k
-PREHOOK: type: LOAD
-#### A masked pattern was here ####
-PREHOOK: Output: default@over10k
-POSTHOOK: query: load data local inpath '../../data/files/over10k' into table
over10k
-POSTHOOK: type: LOAD
-#### A masked pattern was here ####
-POSTHOOK: Output: default@over10k
-PREHOOK: query: explain vectorization detail
-select s, rank() over (partition by f order by t) from over10k limit 100
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select s, rank() over (partition by f order by t) from over10k limit 100
-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
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- projectedColumns: [t:tinyint, si:smallint, i:int, b:bigint,
f:float, d:double, bo:boolean, s:string, ts:timestamp,
dec:decimal(4,2)/DECIMAL_64, bin:binary]
- Reduce Output Operator
- key expressions: f (type: float), t (type: tinyint)
- sort order: ++
- Map-reduce partition columns: f (type: float)
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- value expressions: s (type: string)
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 11
- includeColumns: [0, 4, 7]
- dataColumns: t:tinyint, si:smallint, i:int, b:bigint, f:float,
d:double, bo:boolean, s:string, ts:timestamp, dec:decimal(4,2)/DECIMAL_64,
bin:binary
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0
(type: float), VALUE._col5 (type: string)
- outputColumnNames: _col0, _col4, _col7
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col0: tinyint, _col4: float, _col7: string
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col0 ASC NULLS FIRST
- partition by: _col4
- raw input shape:
- window functions:
- window function definition
- alias: rank_window_0
- arguments: _col0
- name: rank
- window function: GenericUDAFRankEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col7 (type: string), rank_window_0 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Limit
- Number of rows: 100
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1017544 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 100
- Processor Tree:
- ListSink
-
-PREHOOK: query: select s, rank() over (partition by f order by t) from over10k
limit 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select s, rank() over (partition by f order by t) from
over10k limit 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-s rank_window_0
-bob ichabod 1
-yuri thompson 2
-luke steinbeck 1
-fred zipper 2
-luke king 3
-calvin van buren 1
-quinn miller 2
-holly steinbeck 1
-david davidson 1
-calvin quirinius 1
-calvin thompson 2
-david ovid 1
-nick zipper 2
-holly thompson 3
-victor steinbeck 1
-victor robinson 2
-zach ovid 1
-ulysses zipper 1
-irene thompson 1
-luke falkner 2
-yuri johnson 1
-ulysses falkner 1
-gabriella robinson 2
-alice robinson 1
-priscilla xylophone 2
-david laertes 1
-mike underhill 2
-victor van buren 1
-holly falkner 1
-priscilla falkner 1
-luke zipper 1
-ethan ovid 2
-alice quirinius 1
-calvin white 2
-mike steinbeck 3
-nick young 1
-wendy polk 2
-irene miller 3
-ethan ellison 1
-yuri davidson 2
-zach hernandez 1
-wendy miller 1
-katie underhill 1
-irene zipper 1
-holly allen 1
-quinn brown 2
-calvin ovid 1
-zach robinson 1
-nick miller 2
-mike allen 1
-priscilla young 1
-yuri van buren 2
-zach miller 3
-sarah falkner 1
-victor xylophone 2
-rachel ichabod 1
-calvin ovid 1
-alice robinson 2
-calvin ovid 1
-alice ovid 1
-david hernandez 2
-luke laertes 3
-luke quirinius 1
-oscar white 1
-zach falkner 1
-rachel thompson 1
-priscilla king 1
-xavier polk 1
-wendy ichabod 1
-rachel ovid 1
-wendy allen 1
-luke brown 1
-oscar ichabod 2
-mike brown 3
-xavier garcia 1
-bob xylophone 1
-yuri brown 2
-ethan quirinius 1
-luke davidson 2
-zach davidson 1
-irene miller 1
-wendy king 1
-bob zipper 1
-sarah thompson 1
-bob laertes 1
-xavier allen 2
-bob carson 3
-sarah robinson 1
-david king 1
-oscar davidson 1
-wendy polk 1
-victor hernandez 2
-david ellison 1
-ulysses johnson 1
-jessica ovid 1
-bob king 1
-ulysses garcia 1
-irene falkner 1
-holly robinson 1
-yuri white 1
-PREHOOK: query: explain vectorization detail
-select s, dense_rank() over (partition by ts order by i,s desc) from over10k
limit 100
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select s, dense_rank() over (partition by ts order by i,s desc) from over10k
limit 100
-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
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- projectedColumns: [t:tinyint, si:smallint, i:int, b:bigint,
f:float, d:double, bo:boolean, s:string, ts:timestamp,
dec:decimal(4,2)/DECIMAL_64, bin:binary]
- Reduce Output Operator
- key expressions: ts (type: timestamp), i (type: int), s (type:
string)
- sort order: ++-
- Map-reduce partition columns: ts (type: timestamp)
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 11
- includeColumns: [2, 7, 8]
- dataColumns: t:tinyint, si:smallint, i:int, b:bigint, f:float,
d:double, bo:boolean, s:string, ts:timestamp, dec:decimal(4,2)/DECIMAL_64,
bin:binary
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey1 (type: int), KEY.reducesinkkey2
(type: string), KEY.reducesinkkey0 (type: timestamp)
- outputColumnNames: _col2, _col7, _col8
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col2: int, _col7: string, _col8: timestamp
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col2 ASC NULLS FIRST, _col7 DESC NULLS LAST
- partition by: _col8
- raw input shape:
- window functions:
- window function definition
- alias: dense_rank_window_0
- arguments: _col2, _col7
- name: dense_rank
- window function: GenericUDAFDenseRankEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col7 (type: string), dense_rank_window_0 (type:
int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Limit
- Number of rows: 100
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1017544 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 100
- Processor Tree:
- ListSink
-
-PREHOOK: query: select s, dense_rank() over (partition by ts order by i,s
desc) from over10k limit 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select s, dense_rank() over (partition by ts order by i,s
desc) from over10k limit 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-s dense_rank_window_0
-rachel thompson 1
-oscar brown 2
-wendy steinbeck 3
-victor van buren 4
-fred zipper 5
-priscilla zipper 6
-katie white 7
-fred nixon 8
-gabriella van buren 9
-luke zipper 10
-victor ellison 11
-david falkner 12
-nick carson 13
-calvin laertes 14
-yuri allen 15
-calvin brown 16
-tom johnson 17
-jessica laertes 18
-sarah falkner 19
-gabriella xylophone 20
-mike laertes 21
-bob ovid 22
-rachel garcia 23
-katie king 24
-calvin steinbeck 25
-jessica polk 26
-xavier davidson 1
-ethan ovid 2
-calvin white 3
-katie zipper 4
-quinn allen 5
-victor underhill 6
-ulysses xylophone 7
-priscilla zipper 8
-quinn ovid 9
-katie xylophone 10
-rachel ovid 11
-yuri brown 12
-oscar van buren 13
-alice miller 14
-luke thompson 15
-gabriella steinbeck 16
-priscilla brown 17
-gabriella underhill 18
-jessica robinson 19
-luke steinbeck 20
-nick ellison 21
-oscar davidson 22
-wendy johnson 23
-ulysses johnson 24
-jessica nixon 25
-fred king 26
-jessica brown 27
-ethan young 28
-xavier johnson 29
-gabriella johnson 30
-calvin nixon 31
-bob king 32
-calvin carson 33
-zach young 34
-yuri hernandez 35
-sarah van buren 36
-holly falkner 37
-jessica brown 38
-rachel ovid 39
-katie davidson 40
-bob falkner 41
-rachel young 42
-irene brown 43
-fred polk 44
-priscilla hernandez 45
-wendy thompson 46
-rachel robinson 47
-luke xylophone 48
-luke king 49
-holly thompson 50
-yuri garcia 1
-nick king 2
-calvin white 3
-rachel polk 4
-rachel davidson 5
-victor hernandez 6
-wendy miller 7
-wendy brown 8
-priscilla thompson 9
-holly nixon 10
-victor hernandez 11
-priscilla polk 12
-ethan nixon 13
-alice underhill 14
-jessica thompson 15
-tom hernandez 16
-sarah falkner 17
-wendy underhill 18
-rachel ichabod 19
-jessica johnson 20
-rachel ellison 21
-wendy falkner 22
-holly allen 23
-ulysses carson 24
-PREHOOK: query: explain vectorization detail
-select s, cume_dist() over (partition by bo order by b,s) from over10k limit
100
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select s, cume_dist() over (partition by bo order by b,s) from over10k limit
100
-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
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- projectedColumns: [t:tinyint, si:smallint, i:int, b:bigint,
f:float, d:double, bo:boolean, s:string, ts:timestamp,
dec:decimal(4,2)/DECIMAL_64, bin:binary]
- Reduce Output Operator
- key expressions: bo (type: boolean), b (type: bigint), s (type:
string)
- sort order: +++
- Map-reduce partition columns: bo (type: boolean)
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 11
- includeColumns: [3, 6, 7]
- dataColumns: t:tinyint, si:smallint, i:int, b:bigint, f:float,
d:double, bo:boolean, s:string, ts:timestamp, dec:decimal(4,2)/DECIMAL_64,
bin:binary
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey1 (type: bigint), KEY.reducesinkkey0
(type: boolean), KEY.reducesinkkey2 (type: string)
- outputColumnNames: _col3, _col6, _col7
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col3: bigint, _col6: boolean, _col7: string
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col3 ASC NULLS FIRST, _col7 ASC NULLS FIRST
- partition by: _col6
- raw input shape:
- window functions:
- window function definition
- alias: cume_dist_window_0
- arguments: _col3, _col7
- name: cume_dist
- window function: GenericUDAFCumeDistEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col7 (type: string), cume_dist_window_0 (type:
double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Limit
- Number of rows: 100
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1017544 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 100
- Processor Tree:
- ListSink
-
-PREHOOK: query: select s, cume_dist() over (partition by bo order by b,s) from
over10k limit 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select s, cume_dist() over (partition by bo order by b,s)
from over10k limit 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-s cume_dist_window_0
-calvin allen 2.0112630732099757E-4
-david ovid 4.0225261464199515E-4
-david zipper 6.033789219629927E-4
-ethan ellison 8.045052292839903E-4
-holly allen 0.001005631536604988
-irene garcia 0.0012067578439259854
-irene van buren 0.0014078841512469831
-jessica steinbeck 0.0016090104585679806
-katie xylophone 0.0018101367658889783
-mike xylophone 0.002011263073209976
-nick quirinius 0.0022123893805309734
-nick steinbeck 0.002413515687851971
-quinn steinbeck 0.002614641995172969
-rachel thompson 0.0028157683024939663
-sarah miller 0.0030168946098149637
-tom hernandez 0.003218020917135961
-ulysses ichabod 0.003419147224456959
-ulysses nixon 0.0036202735317779565
-ulysses xylophone 0.003821399839098954
-victor garcia 0.004022526146419952
-victor xylophone 0.004223652453740949
-wendy falkner 0.004424778761061947
-yuri nixon 0.004625905068382945
-bob johnson 0.004827031375703942
-bob king 0.00502815768302494
-calvin van buren 0.005229283990345938
-gabriella robinson 0.005430410297666935
-katie xylophone 0.0056315366049879325
-mike steinbeck 0.00583266291230893
-oscar quirinius 0.006033789219629927
-rachel davidson 0.006234915526950925
-sarah van buren 0.006436041834271922
-tom king 0.00663716814159292
-ulysses allen 0.006838294448913918
-wendy ellison 0.007039420756234915
-zach allen 0.007240547063555913
-zach young 0.007441673370876911
-alice falkner 0.007642799678197908
-bob ovid 0.007843925985518906
-bob underhill 0.008045052292839904
-ethan ovid 0.008246178600160902
-gabriella davidson 0.008447304907481898
-gabriella garcia 0.008648431214802896
-irene nixon 0.008849557522123894
-jessica brown 0.009050683829444892
-jessica miller 0.00925181013676589
-jessica quirinius 0.009452936444086887
-luke falkner 0.009654062751407884
-luke robinson 0.009855189058728881
-mike steinbeck 0.01005631536604988
-mike van buren 0.010257441673370877
-priscilla hernandez 0.010458567980691875
-tom polk 0.010659694288012871
-ulysses king 0.01086082059533387
-ulysses robinson 0.011061946902654867
-xavier davidson 0.011263073209975865
-alice hernandez 0.011464199517296863
-bob underhill 0.01166532582461786
-calvin nixon 0.011866452131938857
-david davidson 0.012067578439259855
-holly falkner 0.012268704746580853
-irene laertes 0.01246983105390185
-jessica robinson 0.012670957361222849
-mike falkner 0.012872083668543845
-nick falkner 0.013073209975864843
-oscar laertes 0.01327433628318584
-oscar miller 0.013475462590506838
-oscar thompson 0.013676588897827836
-priscilla nixon 0.013877715205148834
-priscilla xylophone 0.01407884151246983
-quinn miller 0.014279967819790828
-victor robinson 0.014481094127111826
-wendy allen 0.014682220434432824
-wendy nixon 0.014883346741753822
-yuri ellison 0.015084473049074818
-calvin nixon 0.015285599356395816
-fred carson 0.015486725663716814
-holly davidson 0.015687851971037812
-irene king 0.01588897827835881
-jessica davidson 0.016090104585679808
-katie polk 0.016492357200321803
-katie polk 0.016492357200321803
-luke johnson 0.0166934835076428
-nick allen 0.016894609814963796
-nick ellison 0.017095736122284794
-oscar king 0.01729686242960579
-priscilla laertes 0.01749798873692679
-priscilla underhill 0.017699115044247787
-priscilla young 0.017900241351568785
-victor steinbeck 0.018101367658889783
-wendy miller 0.01830249396621078
-calvin carson 0.01850362027353178
-ethan hernandez 0.018704746580852777
-ethan laertes 0.01910699919549477
-ethan laertes 0.01910699919549477
-ethan white 0.019308125502815767
-fred ellison 0.019509251810136765
-gabriella hernandez 0.019710378117457763
-gabriella ovid 0.01991150442477876
-gabriella steinbeck 0.02011263073209976
-PREHOOK: query: explain vectorization detail
-select s, percent_rank() over (partition by `dec` order by f) from over10k
limit 100
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select s, percent_rank() over (partition by `dec` order by f) from over10k
limit 100
-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
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
- projectedColumns: [t:tinyint, si:smallint, i:int, b:bigint,
f:float, d:double, bo:boolean, s:string, ts:timestamp,
dec:decimal(4,2)/DECIMAL_64, bin:binary]
- Reduce Output Operator
- key expressions: dec (type: decimal(4,2)), f (type: float)
- sort order: ++
- Map-reduce partition columns: dec (type: decimal(4,2))
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- value expressions: s (type: string)
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: [DECIMAL_64]
- featureSupportInUse: [DECIMAL_64]
- inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 11
- includeColumns: [4, 7, 9]
- dataColumns: t:tinyint, si:smallint, i:int, b:bigint, f:float,
d:double, bo:boolean, s:string, ts:timestamp, dec:decimal(4,2)/DECIMAL_64,
bin:binary
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey1 (type: float), VALUE._col6 (type:
string), KEY.reducesinkkey0 (type: decimal(4,2))
- outputColumnNames: _col4, _col7, _col9
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col4: float, _col7: string, _col9:
decimal(4,2)
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col4 ASC NULLS FIRST
- partition by: _col9
- raw input shape:
- window functions:
- window function definition
- alias: percent_rank_window_0
- arguments: _col4
- name: percent_rank
- window function: GenericUDAFPercentRankEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col7 (type: string), percent_rank_window_0 (type:
double)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Limit
- Number of rows: 100
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1017544 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 100
- Processor Tree:
- ListSink
-
-PREHOOK: query: select s, percent_rank() over (partition by `dec` order by f)
from over10k limit 100
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select s, percent_rank() over (partition by `dec` order by f)
from over10k limit 100
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-s percent_rank_window_0
-wendy king 0.0
-calvin robinson 1.0
-mike steinbeck 0.0
-calvin hernandez 0.0
-sarah king 1.0
-yuri ellison 0.0
-victor king 0.0
-alice ovid 0.0
-ethan steinbeck 0.5
-mike steinbeck 1.0
-gabriella young 0.0
-jessica johnson 0.0
-holly king 0.5
-tom young 1.0
-victor falkner 0.0
-ethan polk 0.0
-oscar miller 0.0
-ethan quirinius 0.0
-fred hernandez 0.0
-david steinbeck 1.0
-wendy xylophone 0.0
-luke laertes 0.0
-alice quirinius 1.0
-calvin ovid 0.0
-holly allen 0.0
-tom brown 1.0
-wendy ovid 0.0
-mike brown 0.0
-alice polk 0.0
-alice zipper 0.0
-sarah quirinius 1.0
-luke underhill 0.0
-victor white 0.5
-holly xylophone 1.0
-oscar quirinius 0.0
-ethan davidson 0.0
-ethan allen 0.0
-wendy underhill 0.5
-irene xylophone 1.0
-ulysses steinbeck 0.0
-mike hernandez 1.0
-irene brown 0.0
-priscilla brown 0.0
-calvin johnson 1.0
-sarah xylophone 0.0
-yuri underhill 0.5
-ethan nixon 1.0
-calvin hernandez 0.0
-yuri underhill 0.0
-holly allen 1.0
-victor laertes 0.0
-ethan underhill 0.0
-irene steinbeck 1.0
-mike van buren 0.0
-xavier allen 0.5
-sarah xylophone 1.0
-luke van buren 0.0
-gabriella xylophone 0.0
-gabriella ellison 0.0
-luke falkner 0.0
-priscilla garcia 0.0
-ethan quirinius 0.3333333333333333
-alice xylophone 0.6666666666666666
-ethan underhill 1.0
-tom white 0.0
-alice johnson 0.0
-priscilla zipper 0.0
-tom laertes 0.5
-zach laertes 1.0
-xavier miller 0.0
-yuri ovid 0.0
-david steinbeck 0.0
-wendy underhill 0.0
-priscilla xylophone 0.0
-nick hernandez 0.0
-luke steinbeck 0.0
-oscar davidson 0.0
-sarah allen 0.0
-katie steinbeck 0.0
-oscar ovid 1.0
-yuri ellison 0.0
-rachel quirinius 0.0
-irene van buren 0.0
-victor ichabod 0.0
-quinn miller 0.0
-luke allen 0.0
-xavier laertes 0.0
-wendy miller 0.0
-victor brown 0.0
-tom thompson 0.0
-david brown 1.0
-zach quirinius 0.0
-oscar king 1.0
-david nixon 0.0
-ethan white 0.0
-ethan polk 0.0
-ulysses steinbeck 0.0
-victor van buren 0.3333333333333333
-sarah carson 0.6666666666666666
-priscilla nixon 1.0
-PREHOOK: query: explain vectorization detail
-select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where rnk = 1 limit 10
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where rnk = 1 limit 10
-POSTHOOK: type: QUERY
-Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: other
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: b is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: b (type: bigint), ts (type: timestamp), dec
(type: decimal(4,2))
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- value expressions: _col1 (type: timestamp), _col2 (type:
decimal(4,2))
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: b is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: b (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Map Vectorization:
- enabled: false
- enabledConditionsNotMet: Vectorized map work only works with 1
TableScanOperator IS false
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: bigint)
- 1 _col0 (type: bigint)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1]
- projectedColumns: [_col1:timestamp, _col2:decimal(4,2)]
- Reduce Output Operator
- key expressions: _col1 (type: timestamp), _col2 (type:
decimal(4,2))
- sort order: ++
- Map-reduce partition columns: _col1 (type: timestamp)
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: []
- featureSupportInUse: []
- inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- includeColumns: [0, 1]
- dataColumns: _col1:timestamp, _col2:decimal(4,2)
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: timestamp),
KEY.reducesinkkey1 (type: decimal(4,2))
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col1: timestamp, _col2: decimal(4,2)
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col2 ASC NULLS FIRST
- partition by: _col1
- raw input shape:
- window functions:
- window function definition
- alias: rank_window_0
- arguments: _col2
- name: rank
- window function: GenericUDAFRankEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (rank_window_0 = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col1 (type: timestamp), _col2 (type:
decimal(4,2)), 1 (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats:
COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 1119298 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1119298 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where rnk = 1 limit 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where rnk = 1 limit 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-ts dec rnk
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-2013-03-01 09:11:58.70307 0.50 1
-PREHOOK: query: explain vectorization detail
-select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where `dec` = 89.5 limit 10
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where `dec` = 89.5 limit 10
-POSTHOOK: type: QUERY
-Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: other
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: b is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: b (type: bigint), ts (type: timestamp), dec
(type: decimal(4,2))
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- value expressions: _col1 (type: timestamp), _col2 (type:
decimal(4,2))
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: b is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: b (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Map Vectorization:
- enabled: false
- enabledConditionsNotMet: Vectorized map work only works with 1
TableScanOperator IS false
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col0 (type: bigint)
- 1 _col0 (type: bigint)
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1]
- projectedColumns: [_col1:timestamp, _col2:decimal(4,2)]
- Reduce Output Operator
- key expressions: _col1 (type: timestamp)
- sort order: +
- Map-reduce partition columns: _col1 (type: timestamp)
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- value expressions: _col2 (type: decimal(4,2))
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: []
- featureSupportInUse: []
- inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- includeColumns: [0, 1]
- dataColumns: _col1:timestamp, _col2:decimal(4,2)
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: timestamp), VALUE._col1
(type: decimal(4,2))
- outputColumnNames: _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col1: timestamp, _col2: decimal(4,2)
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col1 ASC NULLS FIRST
- partition by: _col1
- raw input shape:
- window functions:
- window function definition
- alias: rank_window_0
- arguments: _col1
- name: rank
- window function: GenericUDAFRankEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (_col2 = 89.5) (type: boolean)
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col1 (type: timestamp), 89.5 (type:
decimal(4,2)), rank_window_0 (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats:
COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 1119298 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1119298 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where `dec` = 89.5 limit 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- ) joined
- ) ranked
-where `dec` = 89.5 limit 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-ts dec rnk
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-2013-03-01 09:11:58.703124 89.50 1
-PREHOOK: query: explain vectorization detail
-select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- where other.t < 10
- ) joined
- ) ranked
-where rnk = 1 limit 10
-PREHOOK: type: QUERY
-POSTHOOK: query: explain vectorization detail
-select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- where other.t < 10
- ) joined
- ) ranked
-where rnk = 1 limit 10
-POSTHOOK: type: QUERY
-Explain
-PLAN VECTORIZATION:
- enabled: true
- enabledConditionsMet: [hive.vectorized.execution.enabled IS true]
-
-STAGE DEPENDENCIES:
- Stage-1 is a root stage
- Stage-2 depends on stages: Stage-1
- Stage-0 depends on stages: Stage-2
-
-STAGE PLANS:
- Stage: Stage-1
- Map Reduce
- Map Operator Tree:
- TableScan
- alias: other
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: ((t < 10) and b is not null) (type: boolean)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: b (type: bigint), ts (type: timestamp), dec
(type: decimal(4,2))
- outputColumnNames: _col1, _col2, _col3
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col1 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col1 (type: bigint)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- value expressions: _col2 (type: timestamp), _col3 (type:
decimal(4,2))
- TableScan
- alias: over10k
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: b is not null (type: boolean)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: b (type: bigint)
- outputColumnNames: _col0
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Reduce Output Operator
- key expressions: _col0 (type: bigint)
- sort order: +
- Map-reduce partition columns: _col0 (type: bigint)
- Statistics: Num rows: 1 Data size: 1017544 Basic stats:
COMPLETE Column stats: NONE
- Map Vectorization:
- enabled: false
- enabledConditionsNotMet: Vectorized map work only works with 1
TableScanOperator IS false
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: bigint)
- 1 _col0 (type: bigint)
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- File Output Operator
- compressed: false
- table:
- input format: org.apache.hadoop.mapred.SequenceFileInputFormat
- output format:
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
- Stage: Stage-2
- Map Reduce
- Map Operator Tree:
- TableScan
- TableScan Vectorization:
- native: true
- projectedColumnNums: [0, 1]
- projectedColumns: [_col2:timestamp, _col3:decimal(4,2)]
- Reduce Output Operator
- key expressions: _col2 (type: timestamp), _col3 (type:
decimal(4,2))
- sort order: ++
- Map-reduce partition columns: _col2 (type: timestamp)
- Reduce Sink Vectorization:
- className: VectorReduceSinkOperator
- native: false
- nativeConditionsMet:
hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true,
No DISTINCT columns IS true, BinarySortableSerDe for keys IS true,
LazyBinarySerDe for values IS true
- nativeConditionsNotMet: hive.execution.engine mr IN [tez,
spark] IS false
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Execution mode: vectorized
- Map Vectorization:
- enabled: true
- enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize
IS true
- inputFormatFeatureSupport: []
- featureSupportInUse: []
- inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat
- allNative: false
- usesVectorUDFAdaptor: false
- vectorized: true
- rowBatchContext:
- dataColumnCount: 2
- includeColumns: [0, 1]
- dataColumns: _col2:timestamp, _col3:decimal(4,2)
- partitionColumnCount: 0
- scratchColumnTypeNames: []
- Reduce Vectorization:
- enabled: false
- enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
- enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS
false
- Reduce Operator Tree:
- Select Operator
- expressions: KEY.reducesinkkey0 (type: timestamp),
KEY.reducesinkkey1 (type: decimal(4,2))
- outputColumnNames: _col2, _col3
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- PTF Operator
- Function definitions:
- Input definition
- input alias: ptf_0
- output shape: _col2: timestamp, _col3: decimal(4,2)
- type: WINDOWING
- Windowing table definition
- input alias: ptf_1
- name: windowingtablefunction
- order by: _col3 ASC NULLS FIRST
- partition by: _col2
- raw input shape:
- window functions:
- window function definition
- alias: rank_window_0
- arguments: _col3
- name: rank
- window function: GenericUDAFRankEvaluator
- window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX)
- isPivotResult: true
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Filter Operator
- predicate: (rank_window_0 = 1) (type: boolean)
- Statistics: Num rows: 1 Data size: 1119298 Basic stats: COMPLETE
Column stats: NONE
- Select Operator
- expressions: _col2 (type: timestamp), _col3 (type:
decimal(4,2)), 1 (type: int)
- outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 1 Data size: 1119298 Basic stats:
COMPLETE Column stats: NONE
- Limit
- Number of rows: 10
- Statistics: Num rows: 1 Data size: 1119298 Basic stats:
COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 1 Data size: 1119298 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
-
- Stage: Stage-0
- Fetch Operator
- limit: 10
- Processor Tree:
- ListSink
-
-PREHOOK: query: select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- where other.t < 10
- ) joined
- ) ranked
-where rnk = 1 limit 10
-PREHOOK: type: QUERY
-PREHOOK: Input: default@over10k
-#### A masked pattern was here ####
-POSTHOOK: query: select ts, `dec`, rnk
-from
- (select ts, `dec`,
- rank() over (partition by ts order by `dec`) as rnk
- from
- (select other.ts, other.`dec`
- from over10k other
- join over10k on (other.b = over10k.b)
- where other.t < 10
- ) joined
- ) ranked
-where rnk = 1 limit 10
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@over10k
-#### A masked pattern was here ####
-ts dec rnk
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1
-2013-03-01 09:11:58.70307 37.30 1